WorldWideScience

Sample records for neural prosthetic applications

  1. Neural-Network Control Of Prosthetic And Robotic Hands

    Science.gov (United States)

    Buckley, Theresa M.

    1991-01-01

    Electronic neural networks proposed for use in controlling robotic and prosthetic hands and exoskeletal or glovelike electromechanical devices aiding intact but nonfunctional hands. Specific to patient, who activates grasping motion by voice command, by mechanical switch, or by myoelectric impulse. Patient retains higher-level control, while lower-level control provided by neural network analogous to that of miniature brain. During training, patient teaches miniature brain to perform specialized, anthropomorphic movements unique to himself or herself.

  2. Photopolymerized materials and patterning for improved performance of neural prosthetics

    Science.gov (United States)

    Tuft, Bradley William

    Neural prosthetics are used to replace or substantially augment remaining motor and sensory functions of neural pathways that were lost or damaged due to physical trauma, disease, or genetics. However, due to poor spatial signal resolution, neural prostheses fail to recapitulate the intimate, precise interactions inherent to neural networks. Designing materials and interfaces that direct de novo nerve growth to spatially specific stimulating elements is, therefore, a promising method to enhance signal specificity and performance of prostheses such as the successful cochlear implant (CI) and the developing retinal implant. In this work, the spatial and temporal reaction control inherent to photopolymerization was used to develop methods to generate micro and nanopatterned materials that direct neurite growth from prosthesis relevant neurons. In particular, neurite growth and directionality has been investigated in response to physical, mechanical, and chemical cues on photopolymerized surfaces. Spiral ganglion neurons (SGNs) serve as the primary neuronal model as they are the principal target for CI stimulation. The objective of the research is to rationally design materials that spatially direct neurite growth and to translate fundamental understanding of nerve cell-material interactions into methods of nerve regeneration that improve neural prosthetic performance. A rapid, single-step photopolymerization method was developed to fabricate micro and nanopatterned physical cues on methacrylate surfaces by selectively blocking light with photomasks. Feature height is readily tuned by modulating parameters of the photopolymerizaiton including initiator concentration and species, light intensity, separation distance from the photomask, and radiation exposure time. Alignment of neural elements increases significantly with increasing feature amplitude and constant periodicity, as well as with decreasing periodicity and constant amplitude. SGN neurite alignment strongly

  3. Nitinol for Prosthetic and Orthotic Applications

    Science.gov (United States)

    Henderson, Emma; Buis, Arjan

    2011-07-01

    As global populations age, conditions such as stroke and diabetes require individuals to use rehabilitation technology for many years to come due to chronic musculoskeletal, sensory, and other physical impairments. One in four males currently aged 45 will experience a stroke within 40 years and will often require access to prolonged rehabilitation. In addition, worldwide, one individual loses a limb every 30 s due to the complications of diabetes. As a result, innovative ideas are required to devise more effective prosthetic and orthotic devices to enhance quality of life. While Nitinol has already found much favor within the biomedical industry, one area, which has not yet exploited its unique properties, is in the field of physical rehabilitation, ranging from prosthetic and orthotic devices to assistive technology such as wheelchairs. Improved intervention capabilities based on materials such as Nitinol have the potential to vastly improve patients' quality of life and in the case of orthoses, may even reduce the severity of the condition over time. It is hoped that this study will spark discussion and interest for the materials community in a field which has yet to be fully exploited.

  4. Neural Networks: Implementations and Applications

    OpenAIRE

    Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.

    1996-01-01

    Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

  5. Developing a hippocampal neural prosthetic to facilitate human memory encoding and recall

    Science.gov (United States)

    Hampson, Robert E.; Song, Dong; Robinson, Brian S.; Fetterhoff, Dustin; Dakos, Alexander S.; Roeder, Brent M.; She, Xiwei; Wicks, Robert T.; Witcher, Mark R.; Couture, Daniel E.; Laxton, Adrian W.; Munger-Clary, Heidi; Popli, Gautam; Sollman, Myriam J.; Whitlow, Christopher T.; Marmarelis, Vasilis Z.; Berger, Theodore W.; Deadwyler, Sam A.

    2018-06-01

    Objective. We demonstrate here the first successful implementation in humans of a proof-of-concept system for restoring and improving memory function via facilitation of memory encoding using the patient’s own hippocampal spatiotemporal neural codes for memory. Memory in humans is subject to disruption by drugs, disease and brain injury, yet previous attempts to restore or rescue memory function in humans typically involved only nonspecific, modulation of brain areas and neural systems related to memory retrieval. Approach. We have constructed a model of processes by which the hippocampus encodes memory items via spatiotemporal firing of neural ensembles that underlie the successful encoding of short-term memory. A nonlinear multi-input, multi-output (MIMO) model of hippocampal CA3 and CA1 neural firing is computed that predicts activation patterns of CA1 neurons during the encoding (sample) phase of a delayed match-to-sample (DMS) human short-term memory task. Main results. MIMO model-derived electrical stimulation delivered to the same CA1 locations during the sample phase of DMS trials facilitated short-term/working memory by 37% during the task. Longer term memory retention was also tested in the same human subjects with a delayed recognition (DR) task that utilized images from the DMS task, along with images that were not from the task. Across the subjects, the stimulated trials exhibited significant improvement (35%) in both short-term and long-term retention of visual information. Significance. These results demonstrate the facilitation of memory encoding which is an important feature for the construction of an implantable neural prosthetic to improve human memory.

  6. Parietal neural prosthetic control of a computer cursor in a graphical-user-interface task

    Science.gov (United States)

    Revechkis, Boris; Aflalo, Tyson NS; Kellis, Spencer; Pouratian, Nader; Andersen, Richard A.

    2014-12-01

    Objective. To date, the majority of Brain-Machine Interfaces have been used to perform simple tasks with sequences of individual targets in otherwise blank environments. In this study we developed a more practical and clinically relevant task that approximated modern computers and graphical user interfaces (GUIs). This task could be problematic given the known sensitivity of areas typically used for BMIs to visual stimuli, eye movements, decision-making, and attentional control. Consequently, we sought to assess the effect of a complex, GUI-like task on the quality of neural decoding. Approach. A male rhesus macaque monkey was implanted with two 96-channel electrode arrays in area 5d of the superior parietal lobule. The animal was trained to perform a GUI-like ‘Face in a Crowd’ task on a computer screen that required selecting one cued, icon-like, face image from a group of alternatives (the ‘Crowd’) using a neurally controlled cursor. We assessed whether the crowd affected decodes of intended cursor movements by comparing it to a ‘Crowd Off’ condition in which only the matching target appeared without alternatives. We also examined if training a neural decoder with the Crowd On rather than Off had any effect on subsequent decode quality. Main results. Despite the additional demands of working with the Crowd On, the animal was able to robustly perform the task under Brain Control. The presence of the crowd did not itself affect decode quality. Training the decoder with the Crowd On relative to Off had no negative influence on subsequent decoding performance. Additionally, the subject was able to gaze around freely without influencing cursor position. Significance. Our results demonstrate that area 5d recordings can be used for decoding in a complex, GUI-like task with free gaze. Thus, this area is a promising source of signals for neural prosthetics that utilize computing devices with GUI interfaces, e.g. personal computers, mobile devices, and tablet

  7. Parietal neural prosthetic control of a computer cursor in a graphical-user-interface task.

    Science.gov (United States)

    Revechkis, Boris; Aflalo, Tyson N S; Kellis, Spencer; Pouratian, Nader; Andersen, Richard A

    2014-12-01

    To date, the majority of Brain-Machine Interfaces have been used to perform simple tasks with sequences of individual targets in otherwise blank environments. In this study we developed a more practical and clinically relevant task that approximated modern computers and graphical user interfaces (GUIs). This task could be problematic given the known sensitivity of areas typically used for BMIs to visual stimuli, eye movements, decision-making, and attentional control. Consequently, we sought to assess the effect of a complex, GUI-like task on the quality of neural decoding. A male rhesus macaque monkey was implanted with two 96-channel electrode arrays in area 5d of the superior parietal lobule. The animal was trained to perform a GUI-like 'Face in a Crowd' task on a computer screen that required selecting one cued, icon-like, face image from a group of alternatives (the 'Crowd') using a neurally controlled cursor. We assessed whether the crowd affected decodes of intended cursor movements by comparing it to a 'Crowd Off' condition in which only the matching target appeared without alternatives. We also examined if training a neural decoder with the Crowd On rather than Off had any effect on subsequent decode quality. Despite the additional demands of working with the Crowd On, the animal was able to robustly perform the task under Brain Control. The presence of the crowd did not itself affect decode quality. Training the decoder with the Crowd On relative to Off had no negative influence on subsequent decoding performance. Additionally, the subject was able to gaze around freely without influencing cursor position. Our results demonstrate that area 5d recordings can be used for decoding in a complex, GUI-like task with free gaze. Thus, this area is a promising source of signals for neural prosthetics that utilize computing devices with GUI interfaces, e.g. personal computers, mobile devices, and tablet computers.

  8. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

  9. Deep learning with convolutional neural networks: a resource for the control of robotic prosthetic hands via electromyography

    Directory of Open Access Journals (Sweden)

    Manfredo Atzori

    2016-09-01

    Full Text Available Motivation: Natural control methods based on surface electromyography and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications and commercial prostheses are in the best case capable to offer natural control for only a few movements. Objective: In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its capabilities for the natural control of robotic hands via surface electromyography by providing a baseline on a large number of intact and amputated subjects. Methods: We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 hand amputated subjects. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets.Results: The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods but lower than the results obtained with the best reference methods in our tests. Significance: The results show that convolutional neural networks with a very simple architecture can produce accuracy comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters can be fundamental for the analysis of surface electromyography data. Finally, the results suggest that deeper and more complex networks may increase dexterous control robustness, thus contributing to bridge the gap between the market and scientific research

  10. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

  11. Mechanical performance of pyrolytic carbon in prosthetic heart valve applications.

    Science.gov (United States)

    Cao, H

    1996-06-01

    An experimental procedure has been developed for rigorous characterization of the fracture resistance and fatigue crack extension in pyrolytic carbon for prosthetic heart valve application. Experiments were conducted under sustained and cyclic loading in a simulated biological environment using Carbomedics Pyrolite carbon. While the material was shown to have modest fracture toughness, it exhibited excellent resistance to subcritical crack growth. The crack growth kinetics in pyrolytic carbon were formulated using a phenomenological description. A fatigue threshold was observed below which the crack growth rate diminishes. A damage tolerance concept based on fracture mechanics was used to develop an engineering design approach for mechanical heart valve prostheses. In particular, a new quantity, referred to as the safe-life index, was introduced to assess the design adequacy against subcritical crack growth in brittle materials. In addition, a weakest-link statistical description of the fracture strength is provided and used in the design of component proof-tests. It is shown that the structural reliability of mechanical heart valves can be assured by combining effective flaw detection and manufacturing quality control with adequate damage tolerance design.

  12. Determination of relevant neuron-neuron connections for neural prosthetics using time-delayed mutual information: tutorial and preliminary results.

    Science.gov (United States)

    Taghva, Alexander; Song, Dong; Hampson, Robert E; Deadwyler, Sam A; Berger, Theodore W

    2012-12-01

    Identification of functional dependence among neurons is a necessary component in both the rational design of neural prostheses as well as in the characterization of network physiology. The objective of this article is to provide a tutorial for neurosurgeons regarding information theory, specifically time-delayed mutual information, and to compare time-delayed mutual information, an information theoretic quantity based on statistical dependence, with cross-correlation, a commonly used metric for this task in a preliminary analysis of rat hippocampal neurons. Spike trains were recorded from rats performing delayed nonmatch-to-sample task using an array of electrodes surgically implanted into the hippocampus of each hemisphere of the brain. In addition, spike train simulations of positively correlated neurons, negatively correlated neurons, and neurons correlated by nonlinear functions were generated. These were evaluated by time-delayed mutual information (MI) and cross-correlation. Application of time-delayed MI to experimental data indicated the optimal bin size for information capture in the CA3-CA1 system was 40 ms, which may provide some insight into the spatiotemporal nature of encoding in the rat hippocampus. On simulated data, time-delayed MI showed peak values at appropriate time lags in positively correlated, negatively correlated, and complexly correlated data. Cross-correlation showed peak and troughs with positively correlated and negatively correlated data, but failed to capture some higher order correlations. Comparison of time-delayed MI to cross-correlation in identification of functionally dependent neurons indicates that the methods are not equivalent. Time-delayed MI appeared to capture some interactions between CA3-CA1 neurons at physiologically plausible time delays missed by cross-correlation. It should be considered as a method for identification of functional dependence between neurons and may be useful in the development of neural

  13. Swing Phase Control of Semi-Active Prosthetic Knee Using Neural Network Predictive Control With Particle Swarm Optimization.

    Science.gov (United States)

    Ekkachai, Kittipong; Nilkhamhang, Itthisek

    2016-11-01

    In recent years, intelligent prosthetic knees have been developed that enable amputees to walk as normally as possible when compared to healthy subjects. Although semi-active prosthetic knees utilizing magnetorheological (MR) dampers offer several advantages, they lack the ability to generate active force that is required during some states of a normal gait cycle. This prevents semi-active knees from achieving the same level of performance as active devices. In this work, a new control algorithm for a semi-active prosthetic knee during the swing phase is proposed to reduce this gap. The controller uses neural network predictive control and particle swarm optimization to calculate suitable command signals. Simulation results using a double pendulum model show that the generated knee trajectory of the proposed controller is more similar to the normal gait than previous open-loop controllers at various ambulation speeds. Moreover, the investigation shows that the algorithm can be calculated in real time by an embedded system, allowing for easy implementation on real prosthetic knees.

  14. Advances for prosthetic technology from historical perspective to current status to future application

    CERN Document Server

    LeMoyne, Robert

    2016-01-01

    This book focuses on the advances in transtibial prosthetic technology and targets research in the evolution of the powered prosthesis such as the BiOM, which was derived from considerable research and development at the Massachusetts Institute of Technology. The concept of the book spans the historical evolution of prosthetic applications from passive to new and futuristic robotic prosthetic technologies.  The author describes the reasons for amputation, surgical procedures, and an historical perspective of the prosthesis for the lower limb. He also addresses the phases and sub-phases of gait and compensatory mechanisms arising for a transtibial prosthesis and links the compensatory mechanisms to long-term morbidities.  The general technologies for gait analysis central to prosthetic design and the inherent biomechanics foundations for analysis are also explored.  The book reports on recent-past to current-term applications with passive elastic prostheses.  The core of the book deals with futuristic robo...

  15. Neural fields theory and applications

    CERN Document Server

    Graben, Peter; Potthast, Roland; Wright, James

    2014-01-01

    With this book, the editors present the first comprehensive collection in neural field studies, authored by leading scientists in the field - among them are two of the founding-fathers of neural field theory. Up to now, research results in the field have been disseminated across a number of distinct journals from mathematics, computational neuroscience, biophysics, cognitive science and others. Starting with a tutorial for novices in neural field studies, the book comprises chapters on emergent patterns, their phase transitions and evolution, on stochastic approaches, cortical development, cognition, robotics and computation, large-scale numerical simulations, the coupling of neural fields to the electroencephalogram and phase transitions in anesthesia. The intended readership are students and scientists in applied mathematics, theoretical physics, theoretical biology, and computational neuroscience. Neural field theory and its applications have a long-standing tradition in the mathematical and computational ...

  16. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

  17. Selected applications for current polymers in prosthetic dentistry - state of the art.

    Science.gov (United States)

    Kawala, Maciej; Smardz, Joanna; Adamczyk, Lukasz; Grychowska, Natalia; Wieckiewicz, Mieszko

    2018-05-10

    Polymers are widely applied in medicine, including dentistry, i.e. in prosthodontics. The following paper is aimed at demonstrating the applications of selected modern polymers in prosthetic dentistry based on the reported literature. The study was conducted using the PubMed, SCOPUS and CINAHL databases in relation to documents published during 1999-2017. The following keywords were used: polymers with: prosthetic dentistry, impression materials, denture base materials, bite registration materials, denture soft liners, occlusal splint materials and 3D printing. Original papers and reviews which were significant from the modern clinical viewpoint and practical validity in relation to the possibility of using polymeric materials in prosthetic dentistry, were presented. Denture base materials were most commonly modified polymers. Modifications mainly concerned antimicrobial properties and reinforcement of the material structure by introducing additional fibers. Antimicrobial modifications were also common in case of relining materials. Polymeric materials have widely been used in prosthetic dentistry. Modifications of their composition allow achieving new, beneficial properties that affect quality of patients' life. Progress in science allows for a more methodologically-advanced research on the synthesis of new polymeric materials and incorporation of new substances into already known polymeric materials, that will require systematization and appropriate classification. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  18. Neural networks and applications tutorial

    Science.gov (United States)

    Guyon, I.

    1991-09-01

    The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

  19. Neural Networks Methodology and Applications

    CERN Document Server

    Dreyfus, Gérard

    2005-01-01

    Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...

  20. Combining two open source tools for neural computation (BioPatRec and Netlab) improves movement classification for prosthetic control.

    Science.gov (United States)

    Prahm, Cosima; Eckstein, Korbinian; Ortiz-Catalan, Max; Dorffner, Georg; Kaniusas, Eugenijus; Aszmann, Oskar C

    2016-08-31

    Controlling a myoelectric prosthesis for upper limbs is increasingly challenging for the user as more electrodes and joints become available. Motion classification based on pattern recognition with a multi-electrode array allows multiple joints to be controlled simultaneously. Previous pattern recognition studies are difficult to compare, because individual research groups use their own data sets. To resolve this shortcoming and to facilitate comparisons, open access data sets were analysed using components of BioPatRec and Netlab pattern recognition models. Performances of the artificial neural networks, linear models, and training program components were compared. Evaluation took place within the BioPatRec environment, a Matlab-based open source platform that provides feature extraction, processing and motion classification algorithms for prosthetic control. The algorithms were applied to myoelectric signals for individual and simultaneous classification of movements, with the aim of finding the best performing algorithm and network model. Evaluation criteria included classification accuracy and training time. Results in both the linear and the artificial neural network models demonstrated that Netlab's implementation using scaled conjugate training algorithm reached significantly higher accuracies than BioPatRec. It is concluded that the best movement classification performance would be achieved through integrating Netlab training algorithms in the BioPatRec environment so that future prosthesis training can be shortened and control made more reliable. Netlab was therefore included into the newest release of BioPatRec (v4.0).

  1. Automated hexahedral mesh generation from biomedical image data: applications in limb prosthetics.

    Science.gov (United States)

    Zachariah, S G; Sanders, J E; Turkiyyah, G M

    1996-06-01

    A general method to generate hexahedral meshes for finite element analysis of residual limbs and similar biomedical geometries is presented. The method utilizes skeleton-based subdivision of cross-sectional domains to produce simple subdomains in which structured meshes are easily generated. Application to a below-knee residual limb and external prosthetic socket is described. The residual limb was modeled as consisting of bones, soft tissue, and skin. The prosthetic socket model comprised a socket wall with an inner liner. The geometries of these structures were defined using axial cross-sectional contour data from X-ray computed tomography, optical scanning, and mechanical surface digitization. A tubular surface representation, using B-splines to define the directrix and generator, is shown to be convenient for definition of the structure geometries. Conversion of cross-sectional data to the compact tubular surface representation is direct, and the analytical representation simplifies geometric querying and numerical optimization within the mesh generation algorithms. The element meshes remain geometrically accurate since boundary nodes are constrained to lie on the tubular surfaces. Several element meshes of increasing mesh density were generated for two residual limbs and prosthetic sockets. Convergence testing demonstrated that approximately 19 elements are required along a circumference of the residual limb surface for a simple linear elastic model. A model with the fibula absent compared with the same geometry with the fibula present showed differences suggesting higher distal stresses in the absence of the fibula. Automated hexahedral mesh generation algorithms for sliced data represent an advancement in prosthetic stress analysis since they allow rapid modeling of any given residual limb and optimization of mesh parameters.

  2. A modified elastic foundation contact model for application in 3D models of the prosthetic knee.

    Science.gov (United States)

    Pérez-González, Antonio; Fenollosa-Esteve, Carlos; Sancho-Bru, Joaquín L; Sánchez-Marín, Francisco T; Vergara, Margarita; Rodríguez-Cervantes, Pablo J

    2008-04-01

    Different models have been used in the literature for the simulation of surface contact in biomechanical knee models. However, there is a lack of systematic comparisons of these models applied to the simulation of a common case, which will provide relevant information about their accuracy and suitability for application in models of the implanted knee. In this work a comparison of the Hertz model (HM), the elastic foundation model (EFM) and the finite element model (FEM) for the simulation of the elastic contact in a 3D model of the prosthetic knee is presented. From the results of this comparison it is found that although the nature of the EFM offers advantages when compared with that of the HM for its application to realistic prosthetic surfaces, and when compared with the FEM in CPU time, its predictions can differ from FEM in some circumstances. These differences are considerable if the comparison is performed for prescribed displacements, although they are less important for prescribed loads. To solve these problems a new modified elastic foundation model (mEFM) is proposed that maintains basically the simplicity of the original model while producing much more accurate results. In this paper it is shown that this new mEFM calculates pressure distribution and contact area with accuracy and short computation times for toroidal contacting surfaces. Although further work is needed to confirm its validity for more complex geometries the mEFM is envisaged as a good option for application in 3D knee models to predict prosthetic knee performance.

  3. Design for a three-fingered hand. [robotic and prosthetic applications

    Science.gov (United States)

    Crossley, F. R. E.

    1977-01-01

    This paper describes the construction of a prototype mechanical hand or 'end effector' for use on a remotely controlled robot, but with possible application as a prosthetic device. An analysis of hand motions is reported, from which it is concluded that the two most important manipulations (apart from grasps) are to be able to pick up a tool and draw it into a nested grip against the palm, and to be able to hold a pistol-grip tool such as an electric drill and pull the trigger. One of our models was tested and found capable of both these operations.

  4. Fabrication, sensation and control of fluidic elastomer actuators and their application towards hand orthotics and prosthetics

    Science.gov (United States)

    Zhao, Huichan

    Due to their continuous and natural motion, fluidic elastomer actuators (FEAs) have shown potential in a range of robotic applications including prosthetics and orthotics. Despite their advantages and rapid developments, robots using these actuators still have several challenging issues to be addressed. First, the reliable production of low cost and complex actuators that can apply high forces is necessary, yet none of existing fabrication methods are both easy to implement and of high force output. Next, compliant or stretchable sensors that can be embedded into their bodies for sophisticated functions are required, however, many of these sensors suffer from hysteresis, fabrication complexity, chemical safety and environmental instability, and material incompatibility with soft actuators. Finally, feedback control for FEAs is necessary to achieve better performance, but most soft robots are still "open-loop". In this dissertation, I intend to help solve the above issues and drive the applications of soft robotics towards hand orthotics and prosthetics. First, I adapt rotational casting as a new manufacturing method for soft actuators. I present a cuboid soft actuator that can generate a force of >25 N at its tip, a near ten-fold increase over similar actuators previously reported. Next, I propose a soft orthotic finger with position control enabled via embedded optical fiber. I monitor both the static and dynamic states via the optical sensor and achieve the prescribed curvatures accurately and with stability by a gain-scheduled proportional-integral-derivative controller. Then I develop the soft orthotic fingers into a low-cost, closed-loop controlled, soft orthotic glove that can be worn by a typical human hand and helpful for grasping light objects, while also providing finger position control. I achieve motion control with inexpensive, binary pneumatic switches controlled by a simple finite-state-machine. Finally, I report the first use of stretchable optical

  5. Neural Networks in Control Applications

    DEFF Research Database (Denmark)

    Sørensen, O.

    are examined. The models are separated into three groups representing input/output descriptions as well as state space descriptions: - Models, where all in- and outputs are measurable (static networks). - Models, where some inputs are non-measurable (recurrent networks). - Models, where some in- and some...... outputs are non-measurable (recurrent networks with incomplete state information). The three groups are ordered in increasing complexity, and for each group it is shown how to solve the problems concerning training and application of the specific model type. Of particular interest are the model types...... Kalmann filter) representing state space description. The potentials of neural networks for control of non-linear processes are also examined, focusing on three different groups of control concepts, all considered as generalizations of known linear control concepts to handle also non-linear processes...

  6. Psychometric evaluation of self-report outcome measures for prosthetic applications.

    Science.gov (United States)

    Hafner, Brian J; Morgan, Sara J; Askew, Robert L; Salem, Rana

    2016-01-01

    Documentation of clinical outcomes is increasingly expected in delivery of prosthetic services and devices. However, many outcome measures suitable for use in clinical care and research have not been psychometrically tested with prosthesis users. The aim of this study was to determine test-retest reliability, mode-of-administration (MoA) equivalence, standard error of measurement (SEM), and minimal detectable change (MDC) of standardized, self-report instruments that assess constructs of importance to people with lower limb loss. Prosthesis users (n = 201) were randomly assigned to groups based on MoA (i.e., paper, electronic, or mixed-mode). Participants completed two surveys 2 to 3 d apart. Instruments included the Prosthetic Limb Users Survey of Mobility, Prosthesis Evaluation Questionnaire-Mobility Subscale, Activities-Specific Balance Confidence Scale, Quality of Life in Neurological Conditions-Applied Cognition/General Concerns, Patient-Reported Outcomes Measurement Information System Profile, and Socket Comfort Score. Intraclass correlation coefficients indicated all instruments are appropriate for group-level comparisons and select instruments are suitable for individual-level applications. Several instruments showed evidence of possible floor and ceiling effects. All were equivalent across MoAs. SEM and MDC were quantified to facilitate interpretation of outcomes and change scores. These results can enhance clinicians' and researchers' ability to select, apply, and interpret scores from instruments administered to prosthesis users.

  7. An investigation on effects of amputee's physiological parameters on maximum pressure developed at the prosthetic socket interface using artificial neural network.

    Science.gov (United States)

    Nayak, Chitresh; Singh, Amit; Chaudhary, Himanshu; Unune, Deepak Rajendra

    2017-10-23

    Technological advances in prosthetics have attracted the curiosity of researchers in monitoring design and developments of the sockets to sustain maximum pressure without any soft tissue damage, skin breakdown, and painful sores. Numerous studies have been reported in the area of pressure measurement at the limb/socket interface, though, the relation between amputee's physiological parameters and the pressure developed at the limb/socket interface is still not studied. Therefore, the purpose of this work is to investigate the effects of patient-specific physiological parameters viz. height, weight, and stump length on the pressure development at the transtibial prosthetic limb/socket interface. Initially, the pressure values at the limb/socket interface were clinically measured during stance and walking conditions for different patients using strain gauges placed at critical locations of the stump. The measured maximum pressure data related to patient's physiological parameters was used to develop an artificial neural network (ANN) model. The effects of physiological parameters on the pressure development at the limb/socket interface were examined using the ANN model. The analyzed results indicated that the weight and stump length significantly affects the maximum pressure values. The outcomes of this work could be an important platform for the design and development of patient-specific prosthetic socket which can endure the maximum pressure conditions at stance and ambulation conditions.

  8. Fuzzy neural network theory and application

    CERN Document Server

    Liu, Puyin

    2004-01-01

    This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he

  9. [Application and outlook of three-dimensional printing in prosthetic dentistry].

    Science.gov (United States)

    Sun, Y C; Li, R; Zhou, Y S; Wang, Y

    2017-06-09

    At present, three-dimensional (3D) printing has been applied in many aspects in the field of prosthodontics, such as dental models, wax patterns, guide plates, dental restoration and customized implants. The common forming principles include light curing, sintering and melting-condensation, the materials include pure wax, resin, metal and ceramics. However, the printing precision and the strength of multi-material integrated forming, remains to be improved. In addition, as a technology by which the internal structure of a material can be customized manufacturing, further advantage of 3D printing used in the manufacture of dental restoration lies in the customization functional bionic micro-structures, but the related research is still in its infancy. The review briefly summarizes the commonly used 3D printing crafts in prosthetic dentistry, and details clinical applications and evaluations, provides references for clinical decision and further research.

  10. Decentralized neural control application to robotics

    CERN Document Server

    Garcia-Hernandez, Ramon; Sanchez, Edgar N; Alanis, Alma y; Ruz-Hernandez, Jose A

    2017-01-01

    This book provides a decentralized approach for the identification and control of robotics systems. It also presents recent research in decentralized neural control and includes applications to robotics. Decentralized control is free from difficulties due to complexity in design, debugging, data gathering and storage requirements, making it preferable for interconnected systems. Furthermore, as opposed to the centralized approach, it can be implemented with parallel processors. This approach deals with four decentralized control schemes, which are able to identify the robot dynamics. The training of each neural network is performed on-line using an extended Kalman filter (EKF). The first indirect decentralized control scheme applies the discrete-time block control approach, to formulate a nonlinear sliding manifold. The second direct decentralized neural control scheme is based on the backstepping technique, approximated by a high order neural network. The third control scheme applies a decentralized neural i...

  11. Bonding strength of glass-ceramic trabecular-like coatings to ceramic substrates for prosthetic applications.

    Science.gov (United States)

    Chen, Qiang; Baino, Francesco; Pugno, Nicola M; Vitale-Brovarone, Chiara

    2013-04-01

    A new approach based on the concepts of quantized fracture mechanics (QFM) is presented and discussed in this paper to estimate the bonding strength of trabecular-like coatings, i.e. glass-ceramic scaffolds mimicking the architecture of cancellous bone, to ceramic substrates. The innovative application of glass-derived scaffolds as trabecular-like coatings is proposed in order to enhance the osteointegration of prosthetic ceramic devices. The scaffolds, prepared by polymeric sponge replication, are joined to alumina substrates by a dense glass-ceramic coating (interlayer) and the so-obtained 3-layer constructs are investigated from micro-structural, morphological and mechanical viewpoints. In particular, the fracture strengths of three different crack propagation modes, i.e. glass-derived scaffold fracture, interface delamination or mixed fracture, are predicted in agreement with those of experimental mechanical tests. The approach proposed in this work could have interesting applications towards an ever more rational design of bone tissue engineering biomaterials and coatings, in view of the optimization of their mechanical properties for making them actually suitable for clinical applications. Copyright © 2012 Elsevier B.V. All rights reserved.

  12. Applications of neural network to numerical analyses

    International Nuclear Information System (INIS)

    Takeda, Tatsuoki; Fukuhara, Makoto; Ma, Xiao-Feng; Liaqat, Ali

    1999-01-01

    Applications of a multi-layer neural network to numerical analyses are described. We are mainly concerned with the computed tomography and the solution of differential equations. In both cases as the objective functions for the training process of the neural network we employed residuals of the integral equation or the differential equations. This is different from the conventional neural network training where sum of the squared errors of the output values is adopted as the objective function. For model problems both the methods gave satisfactory results and the methods are considered promising for some kind of problems. (author)

  13. Application of neural networks in CRM systems

    Directory of Open Access Journals (Sweden)

    Bojanowska Agnieszka

    2017-01-01

    Full Text Available The central aim of this study is to investigate how to apply artificial neural networks in Customer Relationship Management (CRM. The paper presents several business applications of neural networks in software systems designed to aid CRM, e.g. in deciding on the profitability of building a relationship with a given customer. Furthermore, a framework for a neural-network based CRM software tool is developed. Building beneficial relationships with customers is generating considerable interest among various businesses, and is often mentioned as one of the crucial objectives of enterprises, next to their key aim: to bring satisfactory profit. There is a growing tendency among businesses to invest in CRM systems, which together with an organisational culture of a company aid managing customer relationships. It is the sheer amount of gathered data as well as the need for constant updating and analysis of this breadth of information that may imply the suitability of neural networks for the application in question. Neural networks exhibit considerably higher computational capabilities than sequential calculations because the solution to a problem is obtained without the need for developing a special algorithm. In the majority of presented CRM applications neural networks constitute and are presented as a managerial decision-taking optimisation tool.

  14. Neural networks advances and applications 2

    CERN Document Server

    Gelenbe, E

    1992-01-01

    The present volume is a natural follow-up to Neural Networks: Advances and Applications which appeared one year previously. As the title indicates, it combines the presentation of recent methodological results concerning computational models and results inspired by neural networks, and of well-documented applications which illustrate the use of such models in the solution of difficult problems. The volume is balanced with respect to these two orientations: it contains six papers concerning methodological developments and five papers concerning applications and examples illustrating the theoret

  15. Application of neural network to CT

    International Nuclear Information System (INIS)

    Ma, Xiao-Feng; Takeda, Tatsuoki

    1999-01-01

    This paper presents a new method for two-dimensional image reconstruction by using a multilayer neural network. Multilayer neural networks are extensively investigated and practically applied to solution of various problems such as inverse problems or time series prediction problems. From learning an input-output mapping from a set of examples, neural networks can be regarded as synthesizing an approximation of multidimensional function (that is, solving the problem of hypersurface reconstruction, including smoothing and interpolation). From this viewpoint, neural networks are well suited to the solution of CT image reconstruction. Though a conventionally used object function of a neural network is composed of a sum of squared errors of the output data, we can define an object function composed of a sum of residue of an integral equation. By employing an appropriate line integral for this integral equation, we can construct a neural network that can be used for CT. We applied this method to some model problems and obtained satisfactory results. As it is not necessary to discretized the integral equation using this reconstruction method, therefore it is application to the problem of complicated geometrical shapes is also feasible. Moreover, in neural networks, interpolation is performed quite smoothly, as a result, inverse mapping can be achieved smoothly even in case of including experimental and numerical errors, However, use of conventional back propagation technique for optimization leads to an expensive computation cost. To overcome this drawback, 2nd order optimization methods or parallel computing will be applied in future. (J.P.N.)

  16. Development and validation of a 3D-printed interfacial stress sensor for prosthetic applications.

    Science.gov (United States)

    Laszczak, P; Jiang, L; Bader, D L; Moser, D; Zahedi, S

    2015-01-01

    A novel capacitance-based sensor designed for monitoring mechanical stresses at the stump-socket interface of lower-limb amputees is described. It provides practical means of measuring pressure and shear stresses simultaneously. In particular, it comprises of a flexible frame (20 mm × 20 mm), with thickness of 4mm. By employing rapid prototyping technology in its fabrication, it offers a low-cost and versatile solution, with capability of adopting bespoke shapes of lower-limb residua. The sensor was first analysed using finite element analysis (FEA) and then evaluated using lab-based electromechanical tests. The results validate that the sensor is capable of monitoring both pressure and shear at stresses up to 350 kPa and 80 kPa, respectively. A post-signal processing model is developed to induce pressure and shear stresses, respectively. The effective separation of pressure and shear signals can be potentially advantageous for sensor calibration in clinical applications. The sensor also demonstrates high linearity (approx. 5-8%) and high pressure (approx. 1.3 kPa) and shear (approx. 0.6 kPa) stress resolution performance. Accordingly, the sensor offers the potential for exploitation as an assistive tool to both evaluate prosthetic socket fitting in clinical settings and alert amputees in home settings of excessive loading at the stump-socket interface, effectively preventing stump tissue breakdown at an early stage. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

  17. Application of neural networks in experimental physics

    International Nuclear Information System (INIS)

    Kisel', I.V.; Neskromnyj, V.N.; Ososkov, G.A.

    1993-01-01

    The theoretical foundations of numerous models of artificial neural networks (ANN) and their applications to the actual problems of associative memory, optimization and pattern recognition are given. This review contains also numerous using of ANN in the experimental physics both as the hardware realization of fast triggering systems for even selection and for the following software implementation of the trajectory data recognition

  18. Recurrent pannus formation causing prosthetic aortic valve dysfunction: Is excision without valve re-replacement applicable?

    Directory of Open Access Journals (Sweden)

    Darwazah Ahmad K

    2012-06-01

    Full Text Available Abstract Prosthetic valve dysfunction at aortic position is commonly caused by pannus formation. The exact etiology is not known. It arises from ventricular aspect of the prosthesis encroaching its leaflets causing stenosis or it may remain localized causing left ventricular outflow tract obstruction without affecting valve function. The difference in location entails different approaches in management. Such a pathology requires surgical excision of the pannus with or without valve re-replacement. A recurrent pannus was observed in a female patient who needed repeated surgical intervention to excise a localized pannus without re-replacement of a well functioning prosthetic valve. Management of our case presents several questions, whether recurrence of pannus is caused by sparing the prosthetic valve, is it simply an exaggeration of an inflammatory healing process in certain individuals or is it ideal to re-replace the valve despite a well preserved function.

  19. Recurrent pannus formation causing prosthetic aortic valve dysfunction: is excision without valve re-replacement applicable?

    Science.gov (United States)

    Darwazah, Ahmad K

    2012-06-29

    Prosthetic valve dysfunction at aortic position is commonly caused by pannus formation. The exact etiology is not known. It arises from ventricular aspect of the prosthesis encroaching its leaflets causing stenosis or it may remain localized causing left ventricular outflow tract obstruction without affecting valve function.The difference in location entails different approaches in management. Such a pathology requires surgical excision of the pannus with or without valve re-replacement.A recurrent pannus was observed in a female patient who needed repeated surgical intervention to excise a localized pannus without re-replacement of a well functioning prosthetic valve.Management of our case presents several questions, whether recurrence of pannus is caused by sparing the prosthetic valve, is it simply an exaggeration of an inflammatory healing process in certain individuals or is it ideal to re-replace the valve despite a well preserved function.

  20. Application of radial basis neural network for state estimation of ...

    African Journals Online (AJOL)

    An original application of radial basis function (RBF) neural network for power system state estimation is proposed in this paper. The property of massive parallelism of neural networks is employed for this. The application of RBF neural network for state estimation is investigated by testing its applicability on a IEEE 14 bus ...

  1. Effects of sterilization and storage on the properties of ALP-grafted biomaterials for prosthetic and bone tissue engineering applications

    International Nuclear Information System (INIS)

    Ferraris, S; Pan, G; Vernè, E; Spriano, S; Cassinelli, C; Mazzucco, L

    2012-01-01

    Grafting of the biomaterial surfaces with biomolecules is nowadays a challenging research field for prosthetic and bone tissue engineering applications. On the other hand, very few research works investigate the effect of the sterilization processes on the properties of functionalized biomaterials. In this study, the effects of different sterilization techniques (e.g. gamma and electron beam irradiation, ethylene oxide) on the enzymatic activity of bioactive glasses and Ti6Al4V grafted with alkaline phosphatase (ALP) have been analyzed. Sterility maintenance and in vitro bioactivity of the sterilized surfaces have also been investigated. Finally the effect of packaging and storage conditions has been considered. (paper)

  2. Recurrent pannus formation causing prosthetic aortic valve dysfunction: Is excision without valve re-replacement applicable?

    OpenAIRE

    Darwazah Ahmad K

    2012-01-01

    Abstract Prosthetic valve dysfunction at aortic position is commonly caused by pannus formation. The exact etiology is not known. It arises from ventricular aspect of the prosthesis encroaching its leaflets causing stenosis or it may remain localized causing left ventricular outflow tract obstruction without affecting valve function. The difference in location entails different approaches in management. Such a pathology requires surgical excision of the pannus with or without valve re-replace...

  3. Psychometric evaluation of self-report outcome measures for prosthetic applications

    OpenAIRE

    Hafner, Brian J.; Morgan, Sara J.; Askew, Robert L.; Salem, Rana

    2016-01-01

    Documentation of clinical outcomes is increasingly expected in delivery of prosthetic services and devices. However, many outcome measures suitable for use in clinical care and research have not been psychometrically tested with prosthesis users. The aim of this study was to determine test-retest reliability, mode-of-administration (MoA) equivalence, standard error of measurement (SEM), and minimal detectable change (MDC) of standardized, self-report instruments that assess constructs of impo...

  4. Prosthetic Engineering

    Science.gov (United States)

    ... the household and community environments may lead to falls and injuries. This research aims to develop an ankle that can invert and evert and thereby control the center of pressure under the prosthetic foot; enhancing balance and stability of lower limb amputees. Foot-Ankle ...

  5. Application of neural networks to group technology

    Science.gov (United States)

    Caudell, Thomas P.; Smith, Scott D. G.; Johnson, G. C.; Wunsch, Donald C., II

    1991-08-01

    Adaptive resonance theory (ART) neural networks are being developed for application to the industrial engineering problem of group technology--the reuse of engineering designs. Two- and three-dimensional representations of engineering designs are input to ART-1 neural networks to produce groups or families of similar parts. These representations, in their basic form, amount to bit maps of the part, and can become very large when the part is represented in high resolution. This paper describes an enhancement to an algorithmic form of ART-1 that allows it to operate directly on compressed input representations and to generate compressed memory templates. The performance of this compressed algorithm is compared to that of the regular algorithm on real engineering designs and a significant savings in memory storage as well as a speed up in execution is observed. In additions, a `neural database'' system under development is described. This system demonstrates the feasibility of training an ART-1 network to first cluster designs into families, and then to recall the family when presented a similar design. This application is of large practical value to industry, making it possible to avoid duplication of design efforts.

  6. Improved Extension Neural Network and Its Applications

    Directory of Open Access Journals (Sweden)

    Yu Zhou

    2014-01-01

    Full Text Available Extension neural network (ENN is a new neural network that is a combination of extension theory and artificial neural network (ANN. The learning algorithm of ENN is based on supervised learning algorithm. One of important issues in the field of classification and recognition of ENN is how to achieve the best possible classifier with a small number of labeled training data. Training data selection is an effective approach to solve this issue. In this work, in order to improve the supervised learning performance and expand the engineering application range of ENN, we use a novel data selection method based on shadowed sets to refine the training data set of ENN. Firstly, we use clustering algorithm to label the data and induce shadowed sets. Then, in the framework of shadowed sets, the samples located around each cluster centers (core data and the borders between clusters (boundary data are selected as training data. Lastly, we use selected data to train ENN. Compared with traditional ENN, the proposed improved ENN (IENN has a better performance. Moreover, IENN is independent of the supervised learning algorithms and initial labeled data. Experimental results verify the effectiveness and applicability of our proposed work.

  7. Neural network application to diesel generator diagnostics

    International Nuclear Information System (INIS)

    Logan, K.P.

    1990-01-01

    Diagnostic problems typically begin with the observation of some system behavior which is recognized as a deviation from the expected. The fundamental underlying process is one involving pattern matching cf observed symptoms to a set of compiled symptoms belonging to a fault-symptom mapping. Pattern recognition is often relied upon for initial fault detection and diagnosis. Parallel distributed processing (PDP) models employing neural network paradigms are known to be good pattern recognition devices. This paper describes the application of neural network processing techniques to the malfunction diagnosis of subsystems within a typical diesel generator configuration. Neural network models employing backpropagation learning were developed to correctly recognize fault conditions from the input diagnostic symptom patterns pertaining to various engine subsystems. The resulting network models proved to be excellent pattern recognizers for malfunction examples within the training set. The motivation for employing network models in lieu of a rule-based expert system, however, is related to the network's potential for generalizing malfunctions outside of the training set, as in the case of noisy or partial symptom patterns

  8. Artificial neural network applications in ionospheric studies

    Directory of Open Access Journals (Sweden)

    L. R. Cander

    1998-06-01

    Full Text Available The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC. Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.

  9. Application of multi-modality image coregistration in paediatric prosthetic endocarditis

    International Nuclear Information System (INIS)

    Kitsos, T.; Chung, D.K.; Howman-Giles, R.; Lau, Y.H.; University of Technology, Sydney, NSW

    2003-01-01

    This is a case where coregistration of Gallium and chest CT scans provided important clinical information which had a significant impact on management decisions. A 13-year-old girl from Noumea was transferred to our hospital for further management of S.haemolyticus bacteraemia. She had a history of complex congenital heart disease, requiring several cardiac surgical procedures. Seven months earlier she had a patch repair of the ventricular septum and formation of a right ventricle to pulmonary artery conduit. On admission she was generally unwell and had hemoptysis. She had fever to 39.9 deg C, oximetry of 83 per cent on room air, finger clubbing and a cardiac murmur. Chest X-ray and CT scans showed widespread pulmonary consolidation with bilateral pleural effusions. An echocardiogram showed no evidence of endocarditis. The crucial diagnostic dilemma was whether she had pneumonia or prosthetic endocarditis: the latter was more ominous and entailed high risk surgery. A Gallium whole body scan with chest SPECT showed focal localisation in the right mid chest. However, its location could not be confidently defined. A specifically developed computer program was used to co-register the Gallium SPECT and chest CT scans. The co-registered images conclusively localised the Gallium scan lesion to the prosthetic pulmonary outflow conduit, consistent with endocarditis. This triggered referral for cardiac MRI, which confirmed the diagnosis. In summary co-registration allowed precise structural localisation of focal Gallium uptake in the prosthetic pulmonary outflow conduit, with profound impact on the patient's diagnosis and subsequent management. This is an example of the potential benefits of co-registering structural and functional imaging modalities. Copyright (2002) The Australian and New Zealand Society of Nuclear Medicine Inc

  10. Possibility of magnetic resonance imaging application in teaching preclinical dentistry - endodontic and prosthetic treatment prognosis

    International Nuclear Information System (INIS)

    Tanasiewicz, T.

    2010-01-01

    Background. The necessary condition for successful both endodontic and prosthetic reconstruction treatment is the precise mapping of the shape of dental cavities. The aim of this work is an elaboration and verification of the possibility of using 3D Spin Echo MRI techniques in teaching preclinical dentistry both in endodontic and prosthetics specialty. Objectives. Author' aim was to obtain an elaboration and a verification, whether there exists a possibility to use, at the level of in vitro analysis, techniques of the Magnetic Resonance Imaging, which are based on the 3D sequence of the Spin Echo that may in the future find employment in the teaching of preclinical dentistry, clinical dental therapy and diagnostics within the scope of: a dimensional imaging of the inner topography of teeth and spatial structure of a chamber and root canals of teeth for the therapeutic and didactic aims; introduction of a nondestructive and a non-impressional method of reconstruction of the topography of the inner spaces of the human teeth for the purposes of the reconstructive dentistry. Material and Methods. 6 extracted molar teeth were used for measurements without additional preparation, after endodontic and prosthetic preparation. MR measurements were carried out on a 4.7 T research MRI system equipped with Maran DRX console. Results. Figures show 3D images of outer surface, inner space of the teeth before and after endodontic preparation and internal tooth fixation constructed using both classical methods (polymer mass impression) and non-impressional methods (MRI representation). The sizes of the presented volumes were calculated. Internal tooth volumes were determined before and after endodontic treatment; total tooth volumes were also measured. Research proceedings made it possible to compare the quality of internal tooth space after preparation for inner root canals fixations constructed using both classical methods and non-impressional MRI method. Conclusions. The results

  11. Advanced Applications of Neural Networks and Artificial Intelligence: A Review

    OpenAIRE

    Koushal Kumar; Gour Sundar Mitra Thakur

    2012-01-01

    Artificial Neural Network is a branch of Artificial intelligence and has been accepted as a new computing technology in computer science fields. This paper reviews the field of Artificial intelligence and focusing on recent applications which uses Artificial Neural Networks (ANN’s) and Artificial Intelligence (AI). It also considers the integration of neural networks with other computing methods Such as fuzzy logic to enhance the interpretation ability of data. Artificial Neural Networks is c...

  12. Robotic hand with locking mechanism using TCP muscles for applications in prosthetic hand and humanoids

    Science.gov (United States)

    Saharan, Lokesh; Tadesse, Yonas

    2016-04-01

    This paper presents a biomimetic, lightweight, 3D printed and customizable robotic hand with locking mechanism consisting of Twisted and Coiled Polymer (TCP) muscles based on nylon precursor fibers as artificial muscles. Previously, we have presented a small-sized biomimetic hand using nylon based artificial muscles and fishing line muscles as actuators. The current study focuses on an adult-sized prosthetic hand with improved design and a position/force locking system. Energy efficiency is always a matter of concern to make compact, lightweight, durable and cost effective devices. In natural human hand, if we keep holding objects for long time, we get tired because of continuous use of energy for keeping the fingers in certain positions. Similarly, in prosthetic hands we also need to provide energy continuously to artificial muscles to hold the object for a certain period of time, which is certainly not energy efficient. In this work we, describe the design of the robotic hand and locking mechanism along with the experimental results on the performance of the locking mechanism.

  13. Skin-Inspired Hydrogel-Elastomer Composite with Application in a Moisture Permeable Prosthetic Limb Liner

    Science.gov (United States)

    Ruiz, Esteban

    Recent advances in fields such as 3D printing, and biomaterials, have enabled the development of a moisture permeable prosthetic liner. This project demonstrates the feasibility of the invention by addressing the three primary areas of risk including the mechanical strength, the permeability, and the ability to manufacture. The key enabling technology which allows the liner to operate is the skin inspired hydrogel elastomer composite. The skin inspiration is reflected in the molecular arrangement of the double network of polymers which mimics collagen-elastin toughening in the natural epidermis. A custom formulation for a novel tough double network nanocomposite reinforced hydrogel was developed to improve manufacturability of the liner. The liner features this double network nanocomposite reinforced hydrogel as a permeable membrane which is reinforced on either side by perforated silicone layers manufactured by 3d printing assisted casting. Uniaxial compression tests were conducted on the individual hydrogels, as well as a representative sample of off the shelf prosthetic liners for comparison. Permeability testing was also done on the same set of materials and compared to literature values for traditional hydrogels. This work led to the manufacture of three generations of liner prototypes, with the second and third liner prototype being tested with human participants.

  14. Neural network application for illicit substances identification

    International Nuclear Information System (INIS)

    Nunes, Wallace V.; Silva, Ademir X. da; Crispim, Verginia R.; Schirru, Roberto

    2000-01-01

    Thermal neutron activation analysis is based on neutron capture prompt gamma-ray analysis and has been used in wide variety of fields, for examples, for inspection of checked airline baggage and for detection of buried land mines. In all of these applications, the detected γ-ray intensities from the elements present are used to estimate their concentrations. A study about application using a trained neutral network is presented to determine the presence of illicit substances, such as explosives and drugs, carried out in the luggages. The illicit substances emit characteristic detected γ-ray which are the fingerprint of each isotope. The fingerprint data-base of the gamma-ray spectrum of substances is obtained via Monte Carlo N-Particle Transport code, MCNP, version 4B. It was possible to train the neural network to determine the presence of explosives and narcotics even hidden by several materials. (author)

  15. Applications of neural networks to mechanics

    International Nuclear Information System (INIS)

    1997-01-01

    Neural networks have become powerful tools in engineer's techniques. The aim of this conference was to present their application to concrete cases in the domain of mechanics, including the preparation and use of materials. Artificial neurons are non-linear organs which provide an output signal that depends on several differently weighted input signals. Their connection into networks allows to solve problems for which the driving laws are not well known. The applications discussed during this conference deal with: the driving of machines or processes, the control of machines, materials or products, the simulation and forecasting, and the optimization. Three papers dealing with the control of spark ignition engines, the regulation of heating floors and the optimization of energy consumptions in industrial buildings were selected for ETDE and one paper dealing with the optimization of the management of a reprocessed plutonium stock was selected for INIS. (J.S.)

  16. Development and Evaluation of Micro-Electrocorticography Arrays for Neural Interfacing Applications

    Science.gov (United States)

    Schendel, Amelia Ann

    Neural interfaces have great promise for both electrophysiological research and therapeutic applications. Whether for the study of neural circuitry or for neural prosthetic or other therapeutic applications, micro-electrocorticography (micro-ECoG) arrays have proven extremely useful as neural interfacing devices. These devices strike a balance between invasiveness and signal resolution, an important step towards eventual human application. The objective of this research was to make design improvements to micro-ECoG devices to enhance both biocompatibility and device functionality. To best evaluate the effectiveness of these improvements, a cranial window imaging method for in vivo monitoring of the longitudinal tissue response post device implant was developed. Employment of this method provided valuable insight into the way tissue grows around micro-ECoG arrays after epidural implantation, spurring a study of the effects of substrate geometry on the meningeal tissue response. The results of the substrate footprint comparison suggest that a more open substrate geometry provides an easy path for the tissue to grow around to the top side of the device, whereas a solid device substrate encourages the tissue to thicken beneath the device, between the electrode sites and the brain. The formation of thick scar tissue between the recording electrode sites and the neural tissue is disadvantageous for long-term recorded signal quality, and thus future micro-ECoG device designs should incorporate open-architecture substrates for enhanced longitudinal in vivo function. In addition to investigating improvements for long-term device reliability, it was also desired to enhance the functionality of micro-ECoG devices for neural electrophysiology research applications. To achieve this goal, a completely transparent graphene-based device was fabricated for use with the cranial window imaging method and optogenetic techniques. The use of graphene as the conductive material provided

  17. Application of neural networks in coastal engineering

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    the neural network attractive. A neural network is an information processing system modeled on the structure of the dynamic process. It can solve the complex/nonlinear problems quickly once trained by operating on problems using an interconnected number...

  18. Fuzzy logic and neural networks basic concepts & application

    CERN Document Server

    Alavala, Chennakesava R

    2008-01-01

    About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank

  19. Introduction to spiking neural networks: Information processing, learning and applications.

    Science.gov (United States)

    Ponulak, Filip; Kasinski, Andrzej

    2011-01-01

    The concept that neural information is encoded in the firing rate of neurons has been the dominant paradigm in neurobiology for many years. This paradigm has also been adopted by the theory of artificial neural networks. Recent physiological experiments demonstrate, however, that in many parts of the nervous system, neural code is founded on the timing of individual action potentials. This finding has given rise to the emergence of a new class of neural models, called spiking neural networks. In this paper we summarize basic properties of spiking neurons and spiking networks. Our focus is, specifically, on models of spike-based information coding, synaptic plasticity and learning. We also survey real-life applications of spiking models. The paper is meant to be an introduction to spiking neural networks for scientists from various disciplines interested in spike-based neural processing.

  20. Introduction to neural networks with electric power applications

    International Nuclear Information System (INIS)

    Wildberger, A.M.; Hickok, K.A.

    1990-01-01

    This is an introduction to the general field of neural networks with emphasis on prospects for their application in the power industry. It is intended to provide enough background information for its audience to begin to follow technical developments in neural networks and to recognize those which might impact on electric power engineering. Beginning with a brief discussion of natural and artificial neurons, the characteristics of neural networks in general and how they learn, neural networks are compared with other modeling tools such as simulation and expert systems in order to provide guidance in selecting appropriate applications. In the power industry, possible applications include plant control, dispatching, and maintenance scheduling. In particular, neural networks are currently being investigated for enhancements to the Thermal Performance Advisor (TPA) which General Physics Corporation (GP) has developed to improve the efficiency of electric power generation

  1. Hidden neural networks: application to speech recognition

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1998-01-01

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...

  2. Neural networks and their application to nuclear power plant diagnosis

    International Nuclear Information System (INIS)

    Reifman, J.

    1997-01-01

    The authors present a survey of artificial neural network-based computer systems that have been proposed over the last decade for the detection and identification of component faults in thermal-hydraulic systems of nuclear power plants. The capabilities and advantages of applying neural networks as decision support systems for nuclear power plant operators and their inherent characteristics are discussed along with their limitations and drawbacks. The types of neural network structures used and their applications are described and the issues of process diagnosis and neural network-based diagnostic systems are identified. A total of thirty-four publications are reviewed

  3. Neural Network Based Models for Fusion Applications

    Science.gov (United States)

    Meneghini, Orso; Tema Biwole, Arsene; Luda, Teobaldo; Zywicki, Bailey; Rea, Cristina; Smith, Sterling; Snyder, Phil; Belli, Emily; Staebler, Gary; Canty, Jeff

    2017-10-01

    Whole device modeling, engineering design, experimental planning and control applications demand models that are simultaneously physically accurate and fast. This poster reports on the ongoing effort towards the development and validation of a series of models that leverage neural-­network (NN) multidimensional regression techniques to accelerate some of the most mission critical first principle models for the fusion community, such as: the EPED workflow for prediction of the H-Mode and Super H-Mode pedestal structure the TGLF and NEO models for the prediction of the turbulent and neoclassical particle, energy and momentum fluxes; and the NEO model for the drift-kinetic solution of the bootstrap current. We also applied NNs on DIII-D experimental data for disruption prediction and quantifying the effect of RMPs on the pedestal and ELMs. All of these projects were supported by the infrastructure provided by the OMFIT integrated modeling framework. Work supported by US DOE under DE-SC0012656, DE-FG02-95ER54309, DE-FC02-04ER54698.

  4. Neural networks and their potential application in nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1991-01-01

    A neural network is a data processing system consisting of a number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. Neural networks have emerged in the past few years as an area of unusual opportunity for research, development and application to a variety of real world problems. Indeed, neural networks exhibit characteristics and capabilities not provided by any other technology. Examples include reading Japanese Kanji characters and human handwriting, reading a typewritten manuscript aloud, compensating for alignment errors in robots, interpreting very noise signals (e.g., electroencephalograms), modeling complex systems that cannot be modeled mathematically, and predicting whether proposed loans will be good or fail. This paper presents a brief tutorial on neural networks and describes research on the potential applications to nuclear power plants

  5. Additive Manufacturing Technologies Used for Processing Polymers: Current Status and Potential Application in Prosthetic Dentistry.

    Science.gov (United States)

    Revilla-León, Marta; Özcan, Mutlu

    2018-04-22

    There are 7 categories of additive manufacturing (AM) technologies, and a wide variety of materials can be used to build a CAD 3D object. The present article reviews the main AM processes for polymers for dental applications: stereolithography (SLA), digital light processing (DLP), material jetting (MJ), and material extrusion (ME). The manufacturing process, accuracy, and precision of these methods will be reviewed, as well as their prosthodontic applications. © 2018 by the American College of Prosthodontists.

  6. Neural networks and their potential application to nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1991-01-01

    A network of artificial neurons, usually called an artificial neural network is a data processing system consisting of a number of highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. Neural networks exhibit characteristics and capabilities not provided by any other technology. Neural networks may be designed so as to classify an input pattern as one of several predefined types or to create, as needed, categories or classes of system states which can be interpreted by a human operator. Neural networks have the ability to recognize patterns, even when the information comprising these patterns is noisy, sparse, or incomplete. Thus, systems of artificial neural networks show great promise for use in environments in which robust, fault-tolerant pattern recognition is necessary in a real-time mode, and in which the incoming data may be distorted or noisy. The application of neural networks, a rapidly evolving technology used extensively in defense applications, alone or in conjunction with other advanced technologies, to some of the problems of operating nuclear power plants has the potential to enhance the safety, reliability and operability of nuclear power plants. The potential applications of neural networking include, but are not limited to diagnosing specific abnormal conditions, identification of nonlinear dynamics and transients, detection of the change of mode of operation, control of temperature and pressure during start-up, signal validation, plant-wide monitoring using autoassociative neural networks, monitoring of check valves, modeling of the plant thermodynamics, emulation of core reload calculations, analysis of temporal sequences in NRC's ''licensee event reports,'' and monitoring of plant parameters

  7. Advances in Artificial Neural Networks – Methodological Development and Application

    Directory of Open Access Journals (Sweden)

    Yanbo Huang

    2009-08-01

    Full Text Available Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological

  8. The application of artificial neural networks to TLD dose algorithm

    International Nuclear Information System (INIS)

    Moscovitch, M.

    1997-01-01

    We review the application of feed forward neural networks to multi element thermoluminescence dosimetry (TLD) dose algorithm development. A Neural Network is an information processing method inspired by the biological nervous system. A dose algorithm based on a neural network is a fundamentally different approach from conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with a given response of a multi-element dosimeter (input) many times.The algorithm, being trained that way, eventually is able to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personnel dosimetry, the output consists of the desired dose components: deep dose, shallow dose, and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. For this application, a neural network architecture was developed based on the concept of functional links network (FLN). The FLN concept allowed an increase in the dimensionality of the input space and construction of a neural network without any hidden layers. This simplifies the problem and results in a relatively simple and reliable dose calculation algorithm. Overall, the neural network dose algorithm approach has been shown to significantly improve the precision and accuracy of dose calculations. (authors)

  9. Robust neural network with applications to credit portfolio data analysis.

    Science.gov (United States)

    Feng, Yijia; Li, Runze; Sudjianto, Agus; Zhang, Yiyun

    2010-01-01

    In this article, we study nonparametric conditional quantile estimation via neural network structure. We proposed an estimation method that combines quantile regression and neural network (robust neural network, RNN). It provides good smoothing performance in the presence of outliers and can be used to construct prediction bands. A Majorization-Minimization (MM) algorithm was developed for optimization. Monte Carlo simulation study is conducted to assess the performance of RNN. Comparison with other nonparametric regression methods (e.g., local linear regression and regression splines) in real data application demonstrate the advantage of the newly proposed procedure.

  10. Complex-valued neural networks advances and applications

    CERN Document Server

    Hirose, Akira

    2013-01-01

    Presents the latest advances in complex-valued neural networks by demonstrating the theory in a wide range of applications Complex-valued neural networks is a rapidly developing neural network framework that utilizes complex arithmetic, exhibiting specific characteristics in its learning, self-organizing, and processing dynamics. They are highly suitable for processing complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems to deal with electromagnetic, light, sonic/ultrasonic waves as well as quantum waves, namely, electron and

  11. Physico-chemical characterization of functionalized polypropylenic fibers for prosthetic applications

    Science.gov (United States)

    Nisticò, Roberto; Faga, Maria Giulia; Gautier, Giovanna; Magnacca, Giuliana; D'Angelo, Domenico; Ciancio, Emanuele; Piacenza, Giacomo; Lamberti, Roberta; Martorana, Selanna

    2012-08-01

    Polypropylene (PP) fibers can be manufactured to form nets which can find application as prosthesis in hernioplasty. One of the most important problem to deal with when nets are applied in vivo consists in the reproduction of bacteria within the net fibers intersections. This occurs right after the application of the prosthesis, and causes infections, thus it is fundamental to remove bacteria in the very early stage of the nets application. This paper deals with the physico-chemical characterization of such nets, pre-treated by atmospheric pressure plasma dielectric barrier discharge apparatus (APP-DBD) and functionalized with an antibiotic drug such as chitosan. The physico-chemical characterization of sterilized nets, before and after the functionalization with chitosan, was carried out by means of scanning electron microscopy (SEM) coupled with EDS spectroscopy, FTIR spectroscopy, drop shape analysis (DSA), X-ray diffraction and thermal analyses (TGA and DSC). The aim of the work is to individuate a good strategy to characterize this kind of materials, to understand the effects of polypropylene pre-treatment on functionalization efficiency, to follow the materials ageing in order to study the effects of the surface treatment for in vivo applications.

  12. Physico-chemical characterization of functionalized polypropylenic fibers for prosthetic applications

    International Nuclear Information System (INIS)

    Nisticò, Roberto; Faga, Maria Giulia; Gautier, Giovanna; Magnacca, Giuliana; D’Angelo, Domenico; Ciancio, Emanuele; Piacenza, Giacomo; Lamberti, Roberta; Martorana, Selanna

    2012-01-01

    Polypropylene (PP) fibers can be manufactured to form nets which can find application as prosthesis in hernioplasty. One of the most important problem to deal with when nets are applied in vivo consists in the reproduction of bacteria within the net fibers intersections. This occurs right after the application of the prosthesis, and causes infections, thus it is fundamental to remove bacteria in the very early stage of the nets application. This paper deals with the physico-chemical characterization of such nets, pre-treated by atmospheric pressure plasma dielectric barrier discharge apparatus (APP-DBD) and functionalized with an antibiotic drug such as chitosan. The physico-chemical characterization of sterilized nets, before and after the functionalization with chitosan, was carried out by means of scanning electron microscopy (SEM) coupled with EDS spectroscopy, FTIR spectroscopy, drop shape analysis (DSA), X-ray diffraction and thermal analyses (TGA and DSC). The aim of the work is to individuate a good strategy to characterize this kind of materials, to understand the effects of polypropylene pre-treatment on functionalization efficiency, to follow the materials ageing in order to study the effects of the surface treatment for in vivo applications.

  13. Hybrid digital signal processing and neural networks applications in PWRs

    International Nuclear Information System (INIS)

    Eryurek, E.; Upadhyaya, B.R.; Kavaklioglu, K.

    1991-01-01

    Signal validation and plant subsystem tracking in power and process industries require the prediction of one or more state variables. Both heteroassociative and auotassociative neural networks were applied for characterizing relationships among sets of signals. A multi-layer neural network paradigm was applied for sensor and process monitoring in a Pressurized Water Reactor (PWR). This nonlinear interpolation technique was found to be very effective for these applications

  14. Type-2 fuzzy neural networks and their applications

    CERN Document Server

    Aliev, Rafik Aziz

    2014-01-01

    This book deals with the theory, design principles, and application of hybrid intelligent systems using type-2 fuzzy sets in combination with other paradigms of Soft Computing technology such as Neuro-Computing and Evolutionary Computing. It provides a self-contained exposition of the foundation of type-2 fuzzy neural networks and presents a vast compendium of its applications to control, forecasting, decision making, system identification and other real problems. Type-2 Fuzzy Neural Networks and Their Applications is helpful for teachers and students of universities and colleges, for scientis

  15. Neural networks: Application to medical imaging

    Science.gov (United States)

    Clarke, Laurence P.

    1994-01-01

    The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

  16. Applications of neural networks in training science.

    Science.gov (United States)

    Pfeiffer, Mark; Hohmann, Andreas

    2012-04-01

    Training science views itself as an integrated and applied science, developing practical measures founded on scientific method. Therefore, it demands consideration of a wide spectrum of approaches and methods. Especially in the field of competitive sports, research questions are usually located in complex environments, so that mainly field studies are drawn upon to obtain broad external validity. Here, the interrelations between different variables or variable sets are mostly of a nonlinear character. In these cases, methods like neural networks, e.g., the pattern recognizing methods of Self-Organizing Kohonen Feature Maps or similar instruments to identify interactions might be successfully applied to analyze data. Following on from a classification of data analysis methods in training-science research, the aim of the contribution is to give examples of varied sports in which network approaches can be effectually used in training science. First, two examples are given in which neural networks are employed for pattern recognition. While one investigation deals with the detection of sporting talent in swimming, the other is located in game sports research, identifying tactical patterns in team handball. The third and last example shows how an artificial neural network can be used to predict competitive performance in swimming. Copyright © 2011 Elsevier B.V. All rights reserved.

  17. Potential applications of neural networks to nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1991-01-01

    Application of neural networks to the operation of nuclear power plants is being investigated under a US Department of Energy sponsored program at the University of Tennessee. Projects include the feasibility of using neural networks for the following tasks: diagnosing specific abnormal conditions, detection of the change of mode of operation, signal validation, monitoring of check valves, plant-wide monitoring using autoassociative neural networks, modeling of the plant thermodynamics, emulation of core reload calculations, monitoring of plant parameters, and analysis of plant vibrations. Each of these projects and its status are described briefly in this article. The objective of each of these projects is to enhance the safety and performance of nuclear plants through the use of neural networks

  18. Neural networks. A new analytical tool, applicable also in nuclear technology

    International Nuclear Information System (INIS)

    Stritar, A.

    1992-01-01

    The basic concept of neural networks and back propagation learning algorithm are described. The behaviour of typical neural network is demonstrated on a simple graphical case. A short literature survey about the application of neural networks in nuclear science and engineering is made. The application of the neural network to the probability density calculation is shown. (author) [sl

  19. Echocardiographic Evaluation of Tricuspid Prosthetic Valves: An Update

    Directory of Open Access Journals (Sweden)

    Dimitrios Maragiannis, MD, FASE, FACC

    2016-05-01

    Full Text Available This review focuses on the diagnostic value of novel echocardiographic techniques and the clinical application of recently described algorithms to assess tricuspid prosthetic valve function.

  20. Biomaterial applications in neural therapy and repair

    Institute of Scientific and Technical Information of China (English)

    Harmanvir Ghuman; Michel Modo

    2017-01-01

    The use of biomaterials,such as hydrogels,as a scaffold to deliver cells and drugs is becoming increasingly common to treat neurological conditions,including stroke.With a limited intrinsic ability to regenerate after injury,innovative tissue engineering strategies have shown the potential of biomaterials in facilitating neural tissue regeneration and functional recovery.Using biomaterials can not only promote the survival and integration of transplanted cells in the existing circuitry,but also support controlled site specific delivery of therapeutic drugs.This review aims to provide the reader an understanding of the brain tissue microenvironment after injury,biomaterial criteria that support tissue repair,commonly used natural and synthetic biomaterials,benefits of incorporating cells and neurotrophic factors,as well as the potential of endogenous neurogenesis in repairing the injured brain.

  1. Prevention of Prosthetic Dentistry

    Directory of Open Access Journals (Sweden)

    Eremin O.V.

    2011-03-01

    Full Text Available Prevention in prosthetic dentistry is not just a regular oral hygiene and the prevention of caries in the early stages of its development. The initial goal of orthopedic and dental should be the ability to convey to the patient's sense of pros-thetics that proteziruya one saved more. An example is included prosthetic dental arch defects with bridges or single artificial crowns on implants that will prevent movement of teeth and the continuity of the dentition

  2. Applications of neural networks in high energy physics

    International Nuclear Information System (INIS)

    Cutts, D.; Hoftun, J.S.; Nesic, D.; Sornborger, A.; Johnson, C.R.; Zeller, R.T.

    1990-01-01

    Neural network techniques provide promising solutions to pattern recognition problems in high energy physics. We discuss several applications of back propagation networks, and in particular describe the operation of an electron algorithm based on calorimeter energies. 5 refs., 5 figs., 1 tab

  3. Application of artificial neural networks to improve power transfer ...

    African Journals Online (AJOL)

    Application of artificial neural networks to improve power transfer capability through OLTC. ... International Journal of Engineering, Science and Technology ... Numerical results show that the setting of OLTC transformer in terms of the load model has a major effect on the maximum power transfer in power systems and the ...

  4. Non-linear feedback neural networks VLSI implementations and applications

    CERN Document Server

    Ansari, Mohd Samar

    2014-01-01

    This book aims to present a viable alternative to the Hopfield Neural Network (HNN) model for analog computation. It is well known that the standard HNN suffers from problems of convergence to local minima, and requirement of a large number of neurons and synaptic weights. Therefore, improved solutions are needed. The non-linear synapse neural network (NoSyNN) is one such possibility and is discussed in detail in this book. This book also discusses the applications in computationally intensive tasks like graph coloring, ranking, and linear as well as quadratic programming. The material in the book is useful to students, researchers and academician working in the area of analog computation.

  5. Real-time applications of neural nets

    International Nuclear Information System (INIS)

    Spencer, J.E.

    1989-05-01

    Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs

  6. Real-time applications of neural nets

    Energy Technology Data Exchange (ETDEWEB)

    Spencer, J.E.

    1989-05-01

    Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs.

  7. Real-time applications of neural nets

    International Nuclear Information System (INIS)

    Spencer, J.E.

    1989-01-01

    Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas e.g. improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. In this paper, such issues are considered, examples given and possibilities discussed

  8. SU-8-based microneedles for in vitro neural applications

    International Nuclear Information System (INIS)

    Altuna, Ane; Tijero, María; Berganzo, Javier; Salido, Rafa; Fernández, Luis J; Gabriel, Gemma; Guimerá, Anton; Villa, Rosa; Menéndez de la Prida, Liset

    2010-01-01

    This paper presents novel design, fabrication, packaging and the first in vitro neural activity recordings of SU-8-based microneedles. The polymer SU-8 was chosen because it provides excellent features for the fabrication of flexible and thin probes. A microprobe was designed in order to allow a clean insertion and to minimize the damage caused to neural tissue during in vitro applications. In addition, a tetrode is patterned at the tip of the needle to obtain fine-scale measurements of small neuronal populations within a radius of 100 µm. Impedance characterization of the electrodes has been carried out to demonstrate their viability for neural recording. Finally, probes are inserted into 400 µm thick hippocampal slices, and simultaneous action potentials with peak-to-peak amplitudes of 200–250 µV are detected.

  9. Assessment of Myoelectric Controller Performance and Kinematic Behavior of a Novel Soft Synergy-Inspired Robotic Hand for Prosthetic Applications.

    Science.gov (United States)

    Fani, Simone; Bianchi, Matteo; Jain, Sonal; Pimenta Neto, José Simões; Boege, Scott; Grioli, Giorgio; Bicchi, Antonio; Santello, Marco

    2016-01-01

    Myoelectric artificial limbs can significantly advance the state of the art in prosthetics, since they can be used to control mechatronic devices through muscular activity in a way that mimics how the subjects used to activate their muscles before limb loss. However, surveys indicate that dissatisfaction with the functionality of terminal devices underlies the widespread abandonment of prostheses. We believe that one key factor to improve acceptability of prosthetic devices is to attain human likeness of prosthesis movements, a goal which is being pursued by research on social and human-robot interactions. Therefore, to reduce early abandonment of terminal devices, we propose that controllers should be designed so as to ensure effective task accomplishment in a natural fashion. In this work, we have analyzed and compared the performance of three types of myoelectric controller algorithms based on surface electromyography to control an underactuated and multi-degrees of freedom prosthetic hand, the SoftHand Pro. The goal of the present study was to identify the myoelectric algorithm that best mimics the native hand movements. As a preliminary step, we first quantified the repeatability of the SoftHand Pro finger movements and identified the electromyographic recording sites for able-bodied individuals with the highest signal-to-noise ratio from two pairs of muscles, i.e., flexor digitorum superficialis/extensor digitorum communis, and flexor carpi radialis/extensor carpi ulnaris. Able-bodied volunteers were then asked to execute reach-to-grasp movements, while electromyography signals were recorded from flexor digitorum superficialis/extensor digitorum communis as this was identified as the muscle pair characterized by high signal-to-noise ratio and intuitive control. Subsequently, we tested three myoelectric controllers that mapped electromyography signals to position of the SoftHand Pro. We found that a differential electromyography-to-position mapping ensured the

  10. Application of Artificial Neural Networks for estimating index floods

    Science.gov (United States)

    Šimor, Viliam; Hlavčová, Kamila; Kohnová, Silvia; Szolgay, Ján

    2012-12-01

    This article presents an application of Artificial Neural Networks (ANNs) and multiple regression models for estimating mean annual maximum discharge (index flood) at ungauged sites. Both approaches were tested for 145 small basins in Slovakia in areas ranging from 20 to 300 km2. Using the objective clustering method, the catchments were divided into ten homogeneous pooling groups; for each pooling group, mutually independent predictors (catchment characteristics) were selected for both models. The neural network was applied as a simple multilayer perceptron with one hidden layer and with a back propagation learning algorithm. Hyperbolic tangents were used as an activation function in the hidden layer. Estimating index floods by the multiple regression models were based on deriving relationships between the index floods and catchment predictors. The efficiencies of both approaches were tested by the Nash-Sutcliffe and a correlation coefficients. The results showed the comparative applicability of both models with slightly better results for the index floods achieved using the ANNs methodology.

  11. Application of neural networks and cellular automata to calorimetric problems

    Energy Technology Data Exchange (ETDEWEB)

    Brenton, V; Fonvieille, H; Guicheney, C; Jousset, J; Roblin, Y; Tamin, F; Grenier, P

    1994-09-01

    Computing techniques based on parallel processing have been used to treat the information from the electromagnetic calorimeters in SLAC experiments E142/E143. Cluster finding and separation of overlapping showers are performed by a cellular automaton, pion and electron identification is done by using a multilayered neural network. Both applications are presented and their resulting performances are shown to be improved compared to more standard approaches. (author). 9 refs.; Submitted to Nuclear Instruments and Methods (NL).

  12. Application of neural networks and cellular automata to calorimetric problems

    International Nuclear Information System (INIS)

    Brenton, V.; Fonvieille, H.; Guicheney, C.; Jousset, J.; Roblin, Y.; Tamin, F.; Grenier, P.

    1994-09-01

    Computing techniques based on parallel processing have been used to treat the information from the electromagnetic calorimeters in SLAC experiments E142/E143. Cluster finding and separation of overlapping showers are performed by a cellular automaton, pion and electron identification is done by using a multilayered neural network. Both applications are presented and their resulting performances are shown to be improved compared to more standard approaches. (author)

  13. Application of artificial neural networks in particle physics

    International Nuclear Information System (INIS)

    Kolanoski, H.

    1995-04-01

    The application of Artificial Neural Networks in Particle Physics is reviewed. Most common is the use of feed-forward nets for event classification and function approximation. This network type is best suited for a hardware implementation and special VLSI chips are available which are used in fast trigger processors. Also discussed are fully connected networks of the Hopfield type for pattern recognition in tracking detectors. (orig.)

  14. Workshop on environmental and energy applications of neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hashem, S.

    1995-03-01

    This report consists of the abstracts for the papers given at the conference. Applications of neural networks in the environmental, energy and biomedical fields are discussed. Some of the topics covered are: predicting atmospheric pollutant concentrations due to fossil-fired electric power generation; hazardous waste characterization; nondestructive TRU (transuranic) waste assay; risk analysis; load forecasting for electric utilities; design of a wind power storage and generation system; nuclear fuel management; etc.

  15. Workshop on environmental and energy applications of neural networks

    International Nuclear Information System (INIS)

    Hashem, S.

    1995-03-01

    This report consists of the abstracts for the papers given at the conference. Applications of neural networks in the environmental, energy and biomedical fields are discussed. Some of the topics covered are: predicting atmospheric pollutant concentrations due to fossil-fired electric power generation; hazardous waste characterization; nondestructive TRU (transuranic) waste assay; risk analysis; load forecasting for electric utilities; design of a wind power storage and generation system; nuclear fuel management; etc

  16. Review On Applications Of Neural Network To Computer Vision

    Science.gov (United States)

    Li, Wei; Nasrabadi, Nasser M.

    1989-03-01

    Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.

  17. Application of neural networks to waste site screening

    International Nuclear Information System (INIS)

    Dabiri, A.E.; Garrett, M.; Kraft, T.; Hilton, J.; VanHammersveld, M.

    1993-02-01

    Waste site screening requires knowledge of the actual concentrations of hazardous materials and rates of flow around and below the site with time. The present approach consists primarily of drilling boreholes near contaminated sites and chemically analyzing the extracted physical samples and processing the data. This is expensive and time consuming. The feasibility of using neural network techniques to reduce the cost of waste site screening was investigated. Two neural network techniques, gradient descent back propagation and fully recurrent back propagation were utilized. The networks were trained with data received from Westinghouse Hanford Corporation. The results indicate that the network trained with the fully recurrent technique shows satisfactory generalization capability. The predicted results are close to the results obtained from a mathematical flow prediction model. It is possible to develop a new tool to predict the waste plume, thus substantially reducing the number of the bore sites and samplings. There are a variety of applications for this technique in environmental site screening and remediation. One of the obvious applications would be for optimum well siting. A neural network trained from the existing sampling data could be utilized to decide where would be the best position for the next bore site. Other applications are discussed in the report

  18. Methodology for neural networks prototyping. Application to traffic control

    Energy Technology Data Exchange (ETDEWEB)

    Belegan, I.C.

    1998-07-01

    The work described in this report was carried out in the context of the European project ASTORIA (Advanced Simulation Toolbox for Real-World Industrial Application in Passenger Management and Adaptive Control), and concerns the development of an advanced toolbox for complex transportation systems. Our work was focused on the methodology for prototyping a set of neural networks corresponding to specific strategies for traffic control and congestion management. The tool used for prototyping is SNNS (Stuggart Neural Network Simulator), developed at the University of Stuggart, Institute for Parallel and Distributed High Performance Systems, and the real data from the field were provided by ZELT. This report is structured into six parts. The introduction gives some insights about traffic control and its approaches. The second chapter discusses the various control strategies existing. The third chapter is an introduction to the field of neural networks. The data analysis and pre-processing is described in the fourth chapter. In the fifth chapter, the methodology for prototyping the neural networks is presented. Finally, conclusions and further work are presented. (author) 14 refs.

  19. Tutorial on neural network applications in high energy physics: A 1992 perspective

    International Nuclear Information System (INIS)

    Denby, B.

    1992-04-01

    Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given

  20. GIANT PROSTHETIC VALVE THROMBUS

    Directory of Open Access Journals (Sweden)

    Prashanth Kumar

    2015-04-01

    Full Text Available Mechanical prosthetic valves are predisposed to bleeding, thrombosis & thromboembolic complications. Overall incidence of thromboembolic complications is 1% per year who are on oral anticoagulants, whereas bleeding complications incidence is 0.5% to 6.6% per year. 1, 2 Minimization of Scylla of thromboembolic & Charybdis of bleeding complication needs a balancing act of optimal antithrombotic therapy. We are reporting a case of middle aged male patient with prosthetic mitral valve presenting in heart failure. Patient had discontinued anticoagulants, as he had subdural hematoma in the past. He presented to our institute with a giant prosthetic valve thrombus.

  1. The Component Timed-Up-and-Go test: the utility and psychometric properties of using a mobile application to determine prosthetic mobility in people with lower limb amputations.

    Science.gov (United States)

    Clemens, Sheila M; Gailey, Robert S; Bennett, Christopher L; Pasquina, Paul F; Kirk-Sanchez, Neva J; Gaunaurd, Ignacio A

    2018-03-01

    Using a custom mobile application to evaluate the reliability and validity of the Component Timed-Up-and-Go test to assess prosthetic mobility in people with lower limb amputation. Cross-sectional design. National conference for people with limb loss. A total of 118 people with non-vascular cause of lower limb amputation participated. Subjects had a mean age of 48 (±13.7) years and were an average of 10 years post amputation. Of them, 54% ( n = 64) of subjects were male. None. The Component Timed-Up-and-Go was administered using a mobile iPad application, generating a total time to complete the test and five component times capturing each subtask (sit to stand transitions, linear gait, turning) of the standard timed-up-and-go test. The outcome underwent test-retest reliability using intraclass correlation coefficients (ICCs) and convergent validity analyses through correlation with self-report measures of balance and mobility. The Component Timed-Up-and-Go exhibited excellent test-retest reliability with ICCs ranging from .98 to .86 for total and component times. Evidence of discriminative validity resulted from significant differences in mean total times between people with transtibial (10.1 (SD: ±2.3)) and transfemoral (12.76 (SD: ±5.1) amputation, as well as significant differences in all five component times ( P < .05). Convergent validity of the Component Timed-Up-and-Go was demonstrated through moderate correlations with the PLUS-M ( r s  = -.56). The Component Timed-Up-and-Go is a reliable and valid clinical tool for detailed assessment of prosthetic mobility in people with non-vascular lower limb amputation. The iPad application provided a means to easily record data, contributing to clinical utility.

  2. Assessment of Myoelectric Controller Performance and Kinematic Behavior of a Novel Soft Synergy-inspired Robotic Hand for Prosthetic Applications

    Directory of Open Access Journals (Sweden)

    Simone Fani

    2016-10-01

    Full Text Available Myoelectric-artificial limbs can significantly advance the state of the art in prosthetics, since they can be used to control mechatronic devices through muscular activity in a way that mimics how the subjects used to activate their muscles before limb loss. However, surveys indicate that dissatisfaction with the functionality of terminal devices underlies the widespread abandonment of prostheses. We believe that one key factor to improve acceptability of prosthetic devices is to attain human-likeness of prosthesis movements, a goal which is being pursued by research on social and human-robot interactions. Therefore, to reduce early abandonment of terminal devices, we propose that controllers should be designed such as to ensure effective task accomplishment in a natural fashion. In this work, we have analyzed and compared the performance of three types of myoelectric controller algorithms based on surface electromyography to control an under-actuated and multi-degrees of freedom prosthetic hand, the SoftHand Pro. The goal of the present study was to identify the myoelectric algorithm that best mimics the native hand movements. As a preliminary step, we first quantified the repeatability of the SoftHand Pro finger movements and identified the electromyographic recording sites for able-bodied individuals with the highest signal-to-noise ratio from two pairs of muscles, i.e. flexor digitorum superficialis/extensor digitorum communis, and flexor carpi radialis/extensor carpi ulnaris. Able-bodied volunteers were then asked to execute reach-to-grasp movements, while electromyography signals were recorded from flexor digitorum superficialis/extensor digitorum communis as this was identified as the muscle pair characterized by high signal-to-noise ratio and intuitive control. Subsequently, we tested three myoelectric controllers that mapped electromyography signals to position of the SoftHand Pro. We found that a differential electromyography

  3. Rehabilitation and Prosthetic Services

    Science.gov (United States)

    ... Review Resources AT Education Blind Rehab Chiropractic Service Polytrauma/TBI Prosthetics & Sensory Aids Recreation Therapy More Health ... Military Sexual Trauma PTSD Research (MIRECC) Military Exposures Polytrauma Rehabilitation Spinal Cord Injury Telehealth Womens Health Issues ...

  4. Prosthetics / Limb Loss

    Science.gov (United States)

    ... implant to encourage the sealing process. Implanting titanium prosthetic components avoids the need for a socket. But preventing bacterial invasion and infection is a key challenge, one that this research ...

  5. Prosthetic Joint Infections

    Science.gov (United States)

    Aslam, Saima; Darouiche, Rabih O.

    2012-01-01

    Prosthetic joint infections represent a major therapeutic challenge for both healthcare providers and patients. This paper reviews the predisposing factors, pathogenesis, microbiology, diagnosis, treatment and prophylaxis of prosthetic joint infection. The most optimal management strategy should be identified based on a number of considerations including type and duration of infection, antimicrobial susceptibility of the infecting pathogen, condition of infected tissues and bone stock, patient wishes and functional status. PMID:22847032

  6. Neural chips, neural computers and application in high and superhigh energy physics experiments

    International Nuclear Information System (INIS)

    Nikityuk, N.M.; )

    2001-01-01

    Architecture peculiarity and characteristics of series of neural chips and neural computes used in scientific instruments are considered. Tendency of development and use of them in high energy and superhigh energy physics experiments are described. Comparative data which characterize the efficient use of neural chips for useful event selection, classification elementary particles, reconstruction of tracks of charged particles and for search of hypothesis Higgs particles are given. The characteristics of native neural chips and accelerated neural boards are considered [ru

  7. Neural network application to aircraft control system design

    Science.gov (United States)

    Troudet, Terry; Garg, Sanjay; Merrill, Walter C.

    1991-01-01

    The feasibility of using artificial neural network as control systems for modern, complex aerospace vehicles is investigated via an example aircraft control design study. The problem considered is that of designing a controller for an integrated airframe/propulsion longitudinal dynamics model of a modern fighter aircraft to provide independent control of pitch rate and airspeed responses to pilot command inputs. An explicit model following controller using H infinity control design techniques is first designed to gain insight into the control problem as well as to provide a baseline for evaluation of the neurocontroller. Using the model of the desired dynamics as a command generator, a multilayer feedforward neural network is trained to control the vehicle model within the physical limitations of the actuator dynamics. This is achieved by minimizing an objective function which is a weighted sum of tracking errors and control input commands and rates. To gain insight in the neurocontrol, linearized representations of the nonlinear neurocontroller are analyzed along a commanded trajectory. Linear robustness analysis tools are then applied to the linearized neurocontroller models and to the baseline H infinity based controller. Future areas of research identified to enhance the practical applicability of neural networks to flight control design.

  8. Neural network application to aircraft control system design

    Science.gov (United States)

    Troudet, Terry; Garg, Sanjay; Merrill, Walter C.

    1991-01-01

    The feasibility of using artificial neural networks as control systems for modern, complex aerospace vehicles is investigated via an example aircraft control design study. The problem considered is that of designing a controller for an integrated airframe/propulsion longitudinal dynamics model of a modern fighter aircraft to provide independent control of pitch rate and airspeed responses to pilot command inputs. An explicit model following controller using H infinity control design techniques is first designed to gain insight into the control problem as well as to provide a baseline for evaluation of the neurocontroller. Using the model of the desired dynamics as a command generator, a multilayer feedforward neural network is trained to control the vehicle model within the physical limitations of the actuator dynamics. This is achieved by minimizing an objective function which is a weighted sum of tracking errors and control input commands and rates. To gain insight in the neurocontrol, linearized representations of the nonlinear neurocontroller are analyzed along a commanded trajectory. Linear robustness analysis tools are then applied to the linearized neurocontroller models and to the baseline H infinity based controller. Future areas of research are identified to enhance the practical applicability of neural networks to flight control design.

  9. Evolutionary Computation and Its Applications in Neural and Fuzzy Systems

    Directory of Open Access Journals (Sweden)

    Biaobiao Zhang

    2011-01-01

    Full Text Available Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neo-Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.

  10. Artificial neural nets application in the cotton yarn industry

    Directory of Open Access Journals (Sweden)

    Gilberto Clóvis Antoneli

    2016-06-01

    Full Text Available The competitiveness in the yarn production sector has led companies to search for solutions to attain quality yarn at a low cost. Today, the difference between them, and thus the sector, is in the raw material, meaning processed cotton and its characteristics. There are many types of cotton with different characteristics due to its production region, harvest, storage and transportation. Yarn industries work with cotton mixtures, which makes it difficult to determine the quality of the yarn produced from the characteristics of the processed fibers. This study uses data from a conventional spinning, from a raw material made of 100% cotton, and presents a solution with artificial neural nets that determine the thread quality information, using the fibers’ characteristics values and settings of some process adjustments. In this solution a neural net of the type MultiLayer Perceptron with 11 entry neurons (8 characteristics of the fiber and 3 process adjustments, 7 output neurons (yarn quality and two types of training, Back propagation and Conjugate gradient descent. The selection and organization of the production data of the yarn industry of the cocamar® indústria de fios company are described, to apply the artificial neural nets developed. In the application of neural nets to determine yarn quality, one concludes that, although the ideal precision of absolute values is lacking, the presented solution represents an excellent tool to define yarn quality variations when modifying the raw material composition. The developed system enables a simulation to define the raw material percentage mixture to be processed in the plant using the information from the stocked cotton packs, thus obtaining a mixture that maintains the stability of the entire productive process.

  11. Applications of artificial neural networks in medical science.

    Science.gov (United States)

    Patel, Jigneshkumar L; Goyal, Ramesh K

    2007-09-01

    Computer technology has been advanced tremendously and the interest has been increased for the potential use of 'Artificial Intelligence (AI)' in medicine and biological research. One of the most interesting and extensively studied branches of AI is the 'Artificial Neural Networks (ANNs)'. Basically, ANNs are the mathematical algorithms, generated by computers. ANNs learn from standard data and capture the knowledge contained in the data. Trained ANNs approach the functionality of small biological neural cluster in a very fundamental manner. They are the digitized model of biological brain and can detect complex nonlinear relationships between dependent as well as independent variables in a data where human brain may fail to detect. Nowadays, ANNs are widely used for medical applications in various disciplines of medicine especially in cardiology. ANNs have been extensively applied in diagnosis, electronic signal analysis, medical image analysis and radiology. ANNs have been used by many authors for modeling in medicine and clinical research. Applications of ANNs are increasing in pharmacoepidemiology and medical data mining. In this paper, authors have summarized various applications of ANNs in medical science.

  12. Application of artificial neural nets to Shashlik calorimetry

    International Nuclear Information System (INIS)

    Bonesini, M.; Paganoni, M.; Terranova, F.

    1997-01-01

    Artificial neural networks (ANN) are powerful tools widely used in high-energy physics to solve track finding and particle identification problems. An entirely new class of application is related to the problem of recovering the information lost during data taking or signal transmission. Good performances can be reached by ANN when the events are described by quite regular patterns. Such a method was used for the DELPHI luminosity monitor (STIC) to recover calorimeter dead channels. A comparison with more traditional techniques is also given. (orig.)

  13. Application of the minimum fuel neural network to music signals

    DEFF Research Database (Denmark)

    Harbo, Anders La-Cour

    2004-01-01

    ) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up......Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN...

  14. Neural computation and particle accelerators research, technology and applications

    CERN Document Server

    D'Arras, Horace

    2010-01-01

    This book discusses neural computation, a network or circuit of biological neurons and relatedly, particle accelerators, a scientific instrument which accelerates charged particles such as protons, electrons and deuterons. Accelerators have a very broad range of applications in many industrial fields, from high energy physics to medical isotope production. Nuclear technology is one of the fields discussed in this book. The development that has been reached by particle accelerators in energy and particle intensity has opened the possibility to a wide number of new applications in nuclear technology. This book reviews the applications in the nuclear energy field and the design features of high power neutron sources are explained. Surface treatments of niobium flat samples and superconducting radio frequency cavities by a new technique called gas cluster ion beam are also studied in detail, as well as the process of electropolishing. Furthermore, magnetic devises such as solenoids, dipoles and undulators, which ...

  15. Recurrent Neural Network Based Boolean Factor Analysis and its Application to Word Clustering

    Czech Academy of Sciences Publication Activity Database

    Frolov, A. A.; Húsek, Dušan; Polyakov, P.Y.

    2009-01-01

    Roč. 20, č. 7 (2009), s. 1073-1086 ISSN 1045-9227 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.889, year: 2009

  16. Ultra-nanocrystalline diamond electrodes: optimization towards neural stimulation applications.

    Science.gov (United States)

    Garrett, David J; Ganesan, Kumaravelu; Stacey, Alastair; Fox, Kate; Meffin, Hamish; Prawer, Steven

    2012-02-01

    Diamond is well known to possess many favourable qualities for implantation into living tissue including biocompatibility, biostability, and for some applications hardness. However, conducting diamond has not, to date, been exploited in neural stimulation electrodes due to very low electrochemical double layer capacitance values that have been previously reported. Here we present electrochemical characterization of ultra-nanocrystalline diamond electrodes grown in the presence of nitrogen (N-UNCD) that exhibit charge injection capacity values as high as 163 µC cm(-2) indicating that N-UNCD is a viable material for microelectrode fabrication. Furthermore, we show that the maximum charge injection of N-UNCD can be increased by tailoring growth conditions and by subsequent electrochemical activation. For applications requiring yet higher charge injection, we show that N-UNCD electrodes can be readily metalized with platinum or iridium, further increasing charge injection capacity. Using such materials an implantable neural stimulation device fabricated from a single piece of bio-permanent material becomes feasible. This has significant advantages in terms of the physical stability and hermeticity of a long-term bionic implant.

  17. Research on artificial neural network applications for nuclear power plants

    International Nuclear Information System (INIS)

    Chang, Soon-Heung; Cheon, Se-Woo

    1992-01-01

    Artificial neural networks (ANNs) are an emerging computational technology which can significantly enhance a number of applications. These consist of many interconnected processing elements that exhibit human-like performance, i.e., learning, pattern recognition and associative memory skills. Several application studies on ANNs devoted to nuclear power plants have been carried out at the Korea Advanced Institute of Science and Technology since 1989. These studies include the feasibility of using ANNs for the following tasks: (1) thermal power prediction, (2) transient identification, (3) multiple alarm processing and diagnosis, (4) core thermal margin prediction, and (5) prediction of core parameters for fuel reloading. This paper introduces the back-propagation network (BPN) model which is the most commonly used algorithm, and summarizes each of the studies briefly. (author)

  18. Application of neural networks and its prospect. 1. General comment on application to nuclear fusion and plasma researches

    International Nuclear Information System (INIS)

    Takeda, Tatsuoki

    2006-01-01

    The back ground of application of neutral networks to R and D of scientific field and increasing of application fields are stated. A definition of neural networks, the kinds of neural networks and functions, error back propagation, and generalization are explained. An application of multi-layer neural networks to nuclear fusion and plasma researches are described by inverse problem, interpolation, time series prediction, and computerized tomography. Some examples of researches such as MHD of plasma from magnetic probe data of fusion reactor systems, parameter prediction of distribution of the impurity spectra and the charge exchange neutral particle energy spectra, disruption prediction, and residual minimization training neural network are commented. (S.Y.)

  19. An application of neural networks to process and materials control

    International Nuclear Information System (INIS)

    Howell, J.A.; Whiteson, R.

    1991-01-01

    Process control consists of two basic elements: a model of the process and knowledge of the desired control algorithm. In some cases the level of the control algorithm is merely supervisory, as in an alarm-reporting or anomaly-detection system. If the model of the process is known, then a set of equations may often be solved explicitly to provide the control algorithm. Otherwise, the model has to be discovered through empirical studies. Neural networks have properties that make them useful in this application. They can learn (make internal models from experience or observations). The problem of anomaly detection in materials control systems fits well into this general control framework. To successfully model a process with a neutral network, a good set of observables must be chosen. These observables must in some sense adequately span the space of representable events, so that a signature metric can be built for normal operation. In this way, a non-normal event, one that does not fit within the signature, can be detected. In this paper, we discuss the issues involved in applying a neural network model to anomaly detection in materials control systems. These issues include data selection and representation, network architecture, prediction of events, the use of simulated data, and software tools. 10 refs., 4 figs., 1 tab

  20. Recurrent Neural Network Applications for Astronomical Time Series

    Science.gov (United States)

    Protopapas, Pavlos

    2017-06-01

    The benefits of good predictive models in astronomy lie in early event prediction systems and effective resource allocation. Current time series methods applicable to regular time series have not evolved to generalize for irregular time series. In this talk, I will describe two Recurrent Neural Network methods, Long Short-Term Memory (LSTM) and Echo State Networks (ESNs) for predicting irregular time series. Feature engineering along with a non-linear modeling proved to be an effective predictor. For noisy time series, the prediction is improved by training the network on error realizations using the error estimates from astronomical light curves. In addition to this, we propose a new neural network architecture to remove correlation from the residuals in order to improve prediction and compensate for the noisy data. Finally, I show how to set hyperparameters for a stable and performant solution correctly. In this work, we circumvent this obstacle by optimizing ESN hyperparameters using Bayesian optimization with Gaussian Process priors. This automates the tuning procedure, enabling users to employ the power of RNN without needing an in-depth understanding of the tuning procedure.

  1. Gonococcal Prosthetic Joint Infection.

    Science.gov (United States)

    Gassiep, Ian; Gilpin, Bradley; Douglas, Joel; Siebert, David

    2017-01-01

    Neisseria gonorrhoea is a common sexually transmitted infection worldwide. Disseminated gonococcal infection is an infrequent presentation and rarely can be associated with septic arthritis. Incidence of this infection is rising, both internationally and in older age groups. We present the first documented case of N. gonorrhoea prosthetic joint infection which was successfully treated with laparoscopic debridement and antimicrobial therapy.

  2. Amputation and Prosthetics

    Science.gov (United States)

    ... All Topics A-Z Videos Infographics Symptom Picker Anatomy Bones Joints Muscles Nerves Vessels Tendons About Hand Surgery What is a Hand Surgeon? What is a Hand Therapist? Media Find a Hand Surgeon Home Anatomy Amputation and Prosthetics Email to a friend * required ...

  3. An Artificial Neural Network Controller for Intelligent Transportation Systems Applications

    Science.gov (United States)

    1996-01-01

    An Autonomous Intelligent Cruise Control (AICC) has been designed using a feedforward artificial neural network, as an example for utilizing artificial neural networks for nonlinear control problems arising in intelligent transportation systems appli...

  4. Investigation of the medical applications of the unique biocarbons developed by NASA. [compatibility of percutaneous prosthetic carbon devices

    Science.gov (United States)

    Mooney, V.

    1973-01-01

    The biocompatibility of percutaneous endoskeletal fixation devices made from carbon compounds, and their applications are considered. The clinical application of these carbons to solve human problems is demonstrated and the nature of myoelectric simulation by carbon implants is studied.

  5. APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION

    Energy Technology Data Exchange (ETDEWEB)

    Musson, John C. [JLAB; Seaton, Chad [JLAB; Spata, Mike F. [JLAB; Yan, Jianxun [JLAB

    2012-11-01

    Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.

  6. Neural networks. A new analytical tool, applicable also in nuclear technology

    Energy Technology Data Exchange (ETDEWEB)

    Stritar, A [Inst. Jozef Stefan, Ljubljana (Slovenia)

    1992-07-01

    The basic concept of neural networks and back propagation learning algorithm are described. The behaviour of typical neural network is demonstrated on a simple graphical case. A short literature survey about the application of neural networks in nuclear science and engineering is made. The application of the neural network to the probability density calculation is shown. (author) [Slovenian] Opisana je osnova nevronskih mrez in back propagation nacina njihovega ucenja. Obnasanje enostavne nevronske mreze je prikazano na graficnem primeru. Podan je kratek pregled literaure o uporabi nevronskih mrez v jedrski znanosti in tehnologiji. Prikazana je tudi uporaba nevronske mreze pri izracunu verjetnostne porazdelitve. (author)

  7. Prosthetics in Paediatric Dentistry

    Directory of Open Access Journals (Sweden)

    Vulićević Zoran

    2017-07-01

    Full Text Available Premature loss of teeth in children may lead to both functional and esthetic problems. Missing teeth in both anterior and posterior regions may cause malfunctions in mastication and proper pronunciation. If the missing teeth are not replaced, further complications may occur, including adjacent tooth migration, loss of alveolar bone, and irregular occlusion. Considering the sensitive nature of children, loss of teeth may cause the development of insecurities and low self esteem problems. Due to dynamic nature of growth in children and adolescents, prosthetic appliances must not hinder development of orofacial system, and must meet adequate esthetic and functional standards. Dental prosthetic appliances in paediatrics must be planned with respect to the special conditions that led to tooth loss or damage. Multi-disciplinary approach is needed, under constant supervision of paediatric dentist and orthodontist, as well as regular checkups with clinical and radiographical examinations.

  8. Welding of Prosthetic Alloys

    Directory of Open Access Journals (Sweden)

    Wojciechowska M.

    2015-04-01

    Full Text Available This paper presents the techniques of joining metal denture elements, used in prosthetic dentistry: the traditional soldering technique with a gas burner and a new technique of welding with a laser beam; the aim of the study was to make a comparative assessment of the quality of the joints in view of the possibility of applying them in prosthetic structures. Fractographic examinations were conducted along with tensile strength and impact strength tests, and the quality of the joints was assessed compared to the solid metal. The experiments have shown that the metal elements used to make dentures, joined by the technique which employs a laser beam, have better strength properties than those achieved with a gas burner.

  9. Human-Machine Interface for the Control of Multi-Function Systems Based on Electrocutaneous Menu: Application to Multi-Grasp Prosthetic Hands.

    Directory of Open Access Journals (Sweden)

    Jose Gonzalez-Vargas

    Full Text Available Modern assistive devices are very sophisticated systems with multiple degrees of freedom. However, an effective and user-friendly control of these systems is still an open problem since conventional human-machine interfaces (HMI cannot easily accommodate the system's complexity. In HMIs, the user is responsible for generating unique patterns of command signals directly triggering the device functions. This approach can be difficult to implement when there are many functions (necessitating many command patterns and/or the user has a considerable impairment (limited number of available signal sources. In this study, we propose a novel concept for a general-purpose HMI where the controller and the user communicate bidirectionally to select the desired function. The system first presents possible choices to the user via electro-tactile stimulation; the user then acknowledges the desired choice by generating a single command signal. Therefore, the proposed approach simplifies the user communication interface (one signal to generate, decoding (one signal to recognize, and allows selecting from a number of options. To demonstrate the new concept the method was used in one particular application, namely, to implement the control of all the relevant functions in a state of the art commercial prosthetic hand without using any myoelectric channels. We performed experiments in healthy subjects and with one amputee to test the feasibility of the novel approach. The results showed that the performance of the novel HMI concept was comparable or, for some outcome measures, better than the classic myoelectric interfaces. The presented approach has a general applicability and the obtained results point out that it could be used to operate various assistive systems (e.g., prosthesis vs. wheelchair, or it could be integrated into other control schemes (e.g., myoelectric control, brain-machine interfaces in order to improve the usability of existing low

  10. Human-Machine Interface for the Control of Multi-Function Systems Based on Electrocutaneous Menu: Application to Multi-Grasp Prosthetic Hands.

    Science.gov (United States)

    Gonzalez-Vargas, Jose; Dosen, Strahinja; Amsuess, Sebastian; Yu, Wenwei; Farina, Dario

    2015-01-01

    Modern assistive devices are very sophisticated systems with multiple degrees of freedom. However, an effective and user-friendly control of these systems is still an open problem since conventional human-machine interfaces (HMI) cannot easily accommodate the system's complexity. In HMIs, the user is responsible for generating unique patterns of command signals directly triggering the device functions. This approach can be difficult to implement when there are many functions (necessitating many command patterns) and/or the user has a considerable impairment (limited number of available signal sources). In this study, we propose a novel concept for a general-purpose HMI where the controller and the user communicate bidirectionally to select the desired function. The system first presents possible choices to the user via electro-tactile stimulation; the user then acknowledges the desired choice by generating a single command signal. Therefore, the proposed approach simplifies the user communication interface (one signal to generate), decoding (one signal to recognize), and allows selecting from a number of options. To demonstrate the new concept the method was used in one particular application, namely, to implement the control of all the relevant functions in a state of the art commercial prosthetic hand without using any myoelectric channels. We performed experiments in healthy subjects and with one amputee to test the feasibility of the novel approach. The results showed that the performance of the novel HMI concept was comparable or, for some outcome measures, better than the classic myoelectric interfaces. The presented approach has a general applicability and the obtained results point out that it could be used to operate various assistive systems (e.g., prosthesis vs. wheelchair), or it could be integrated into other control schemes (e.g., myoelectric control, brain-machine interfaces) in order to improve the usability of existing low-bandwidth HMIs.

  11. Methodology of Neural Design: Applications in Microwave Engineering

    Directory of Open Access Journals (Sweden)

    Z. Raida

    2006-06-01

    Full Text Available In the paper, an original methodology for the automatic creation of neural models of microwave structures is proposed and verified. Following the methodology, neural models of the prescribed accuracy are built within the minimum CPU time. Validity of the proposed methodology is verified by developing neural models of selected microwave structures. Functionality of neural models is verified in a design - a neural model is joined with a genetic algorithm to find a global minimum of a formulated objective function. The objective function is minimized using different versions of genetic algorithms, and their mutual combinations. The verified methodology of the automated creation of accurate neural models of microwave structures, and their association with global optimization routines are the most important original features of the paper.

  12. Application of a Shallow Neural Network to Short-Term Stock Trading

    OpenAIRE

    Madahar, Abhinav; Ma, Yuze; Patel, Kunal

    2017-01-01

    Machine learning is increasingly prevalent in stock market trading. Though neural networks have seen success in computer vision and natural language processing, they have not been as useful in stock market trading. To demonstrate the applicability of a neural network in stock trading, we made a single-layer neural network that recommends buying or selling shares of a stock by comparing the highest high of 10 consecutive days with that of the next 10 days, a process repeated for the stock's ye...

  13. The application of neural networks with artificial intelligence technique in the modeling of industrial processes

    International Nuclear Information System (INIS)

    Saini, K. K.; Saini, Sanju

    2008-01-01

    Neural networks are a relatively new artificial intelligence technique that emulates the behavior of biological neural systems in digital software or hardware. These networks can 'learn', automatically, complex relationships among data. This feature makes the technique very useful in modeling processes for which mathematical modeling is difficult or impossible. The work described here outlines some examples of the application of neural networks with artificial intelligence technique in the modeling of industrial processes.

  14. Neural network and its application to CT imaging

    Energy Technology Data Exchange (ETDEWEB)

    Nikravesh, M.; Kovscek, A.R.; Patzek, T.W. [Lawrence Berkeley National Lab., CA (United States)] [and others

    1997-02-01

    We present an integrated approach to imaging the progress of air displacement by spontaneous imbibition of oil into sandstone. We combine Computerized Tomography (CT) scanning and neural network image processing. The main aspects of our approach are (I) visualization of the distribution of oil and air saturation by CT, (II) interpretation of CT scans using neural networks, and (III) reconstruction of 3-D images of oil saturation from the CT scans with a neural network model. Excellent agreement between the actual images and the neural network predictions is found.

  15. The application of artificial neural networks in astronomy

    Science.gov (United States)

    Li, Li-Li; Zhang, Yan-Xia; Zhao, Yong-Heng; Yang, Da-Wei

    2006-12-01

    Artificial Neural Networks (ANNs) are computer algorithms inspired from simple models of human central nervous system activity. They can be roughly divided into two main kinds: supervised and unsupervised. The supervised approach lays the stress on "teaching" a machine to do the work of a mention human expert, usually by showing examples for which the true answer is supplied by the expert. The unsupervised one is aimed at learning new things from the data, and most useful when the data cannot easily be plotted in a two or three dimensional space. ANNs have been used widely and successfully in various fields, for instance, pattern recognition, financial analysis, biology, engineering and so on, because they have many merits such as self-learning, self-adapting, good robustness and dynamically rapid response as well as strong capability of dealing with non-linear problems. In the last few years there has been an increasing interest toward the astronomical applications of ANNs. In this paper, the authors firstly introduce the fundamental principle of ANNs together with the architecture of the network and outline various kinds of learning algorithms and network toplogies. The specific aspects of the applications of ANNs in astronomical problems are also listed, which contain the strong capabilities of approximating to arbitrary accuracy, any nonlinear functional mapping, parallel and distributed storage, tolerance of faulty and generalization of results. They summarize the advantages and disadvantages of main ANN models available to the astronomical community. Furthermore, the application cases of ANNs in astronomy are mainly described in detail. Here, the focus is on some of the most interesting fields of its application, for example: object detection, star/galaxy classification, spectral classification, galaxy morphology classification, the estimation of photometric redshifts of galaxies and time series analysis. In addition, other kinds of applications have been

  16. Application of genetic neural network in steam generator fault diagnosing

    International Nuclear Information System (INIS)

    Lin Xiaogong; Jiang Xingwei; Liu Tao; Shi Xiaocheng

    2005-01-01

    In the paper, a new algorithm which neural network and genetic algorithm are mixed is adopted, aiming at the problems of slow convergence rate and easily falling into part minimums in network studying of traditional BP neural network, and used in the fault diagnosis of steam generator. The result shows that this algorithm can solve the convergence problem in the network trains effectively. (author)

  17. Advances in Artificial Neural Networks - Methodological Development and Application

    Science.gov (United States)

    Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...

  18. Application of a neural network for reflectance spectrum classification

    Science.gov (United States)

    Yang, Gefei; Gartley, Michael

    2017-05-01

    Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

  19. Application of neural networks to connectional expert system for identification of transients in nuclear power plants

    International Nuclear Information System (INIS)

    Cheon, Se Woo; Kim, Wan Joo; Chang, Soon Heung; Roh, Myung Sub

    1991-01-01

    The Back-propagation Neural Network (BPN) algorithm is applied to connectionist expert system for the identification of BWR transients. Several powerful features of neural network-based expert systems over traditional rule-based expert systems are described. The general mapping capability of the neural networks enables to identify transients easily. A number of case studies were performed with emphasis on the applicability of the neural networks to the diagnostic domain. It is revealed that the BPN algorithm can identify transients properly, even when incomplete or untrained symptoms are given. It is also shown that multiple transients are easily identified

  20. Applications of neural networks in environmental and energy sciences and engineering. Proceedings of the 1995 workshop on environmental and energy applications of neural networks

    Energy Technology Data Exchange (ETDEWEB)

    Hashem, S.; Keller, P.E.; Kouzes, R.T.; Kangas, L.J.

    1995-12-31

    These proceedings contain edited versions of the technical presentations of the Workshop on Environmental and Energy Applications of Neural Networks, held on March 30--31, 1995, in Richland, Washington. The purpose of the workshop was to provide a forum for discussing environmental, energy, and biomedical applications of neural networks. Panels were held to discuss various research and development issues relating to real-world applications in each of the three areas. The applications covered in the workshop were: Environmental applications -- modeling and predicting soil, air and water pollution, environmental sensing, spectroscopy, hazardous waste handling and cleanup; Energy applications -- process monitoring and optimization of power systems, modeling and control of power plants, environmental monitoring for power systems, power load forecasting, fault location and diagnosis of power systems; and Biomedical applications -- medical image and signal analysis, medical diagnosis, analysis of environmental health effects, and modeling biological systems. Selected papers are indexed separately for inclusion in the Energy Science and Technology Database.

  1. Viability of Controlling Prosthetic Hand Utilizing Electroencephalograph (EEG) Dataset Signal

    Science.gov (United States)

    Miskon, Azizi; A/L Thanakodi, Suresh; Raihan Mazlan, Mohd; Mohd Haziq Azhar, Satria; Nooraya Mohd Tawil, Siti

    2016-11-01

    This project presents the development of an artificial hand controlled by Electroencephalograph (EEG) signal datasets for the prosthetic application. The EEG signal datasets were used as to improvise the way to control the prosthetic hand compared to the Electromyograph (EMG). The EMG has disadvantages to a person, who has not used the muscle for a long time and also to person with degenerative issues due to age factor. Thus, the EEG datasets found to be an alternative for EMG. The datasets used in this work were taken from Brain Computer Interface (BCI) Project. The datasets were already classified for open, close and combined movement operations. It served the purpose as an input to control the prosthetic hand by using an Interface system between Microsoft Visual Studio and Arduino. The obtained results reveal the prosthetic hand to be more efficient and faster in response to the EEG datasets with an additional LiPo (Lithium Polymer) battery attached to the prosthetic. Some limitations were also identified in terms of the hand movements, weight of the prosthetic, and the suggestions to improve were concluded in this paper. Overall, the objective of this paper were achieved when the prosthetic hand found to be feasible in operation utilizing the EEG datasets.

  2. An Evaluation of Dental Prosthetic Status and Prosthetic Needs ...

    African Journals Online (AJOL)

    present cross‑sectional study aimed to evaluate the dental prosthetic status and prosthetic needs among eunuchs .... who consented to become part of the study guided us to the .... to the reason that our study population comprised of adults with low SES. ... Arora M, Schwarz E, Sivaneswaran S, Banks E. Cigarette smoking.

  3. Corrosion of tungsten microelectrodes used in neural recording applications.

    Science.gov (United States)

    Patrick, Erin; Orazem, Mark E; Sanchez, Justin C; Nishida, Toshikazu

    2011-06-15

    In neuroprosthetic applications, long-term electrode viability is necessary for robust recording of the activity of neural populations used for generating communication and control signals. The corrosion of tungsten microwire electrodes used for intracortical recording applications was analyzed in a controlled bench-top study and compared to the corrosion of tungsten microwires used in an in vivo study. Two electrolytes were investigated for the bench-top electrochemical analysis: 0.9% phosphate buffered saline (PBS) and 0.9% PBS containing 30 mM of hydrogen peroxide. The oxidation and reduction reactions responsible for corrosion were found by measurement of the open circuit potential and analysis of Pourbaix diagrams. Dissolution of tungsten to form the tungstic ion was found to be the corrosion mechanism. The corrosion rate was estimated from the polarization resistance, which was extrapolated from the electrochemical impedance spectroscopy data. The results show that tungsten microwires in an electrolyte of PBS have a corrosion rate of 300-700 μm/yr. The corrosion rate for tungsten microwires in an electrolyte containing PBS and 30 mM H₂O₂ is accelerated to 10,000-20,000 μm/yr. The corrosion rate was found to be controlled by the concentration of the reacting species in the cathodic reaction (e.g. O₂ and H₂O₂). The in vivo corrosion rate, averaged over the duration of implantation, was estimated to be 100 μm/yr. The reduced in vivo corrosion rate as compared to the bench-top rate is attributed to decreased rate of oxygen diffusion caused by the presence of a biological film and a reduced concentration of available oxygen in the brain. Copyright © 2011 Elsevier B.V. All rights reserved.

  4. Proceedings of the workshop cum symposium on applications of neural networks in nuclear science and industry

    International Nuclear Information System (INIS)

    1993-01-01

    The Workshop cum Symposium on Application of Neural Networks in Nuclear Science and Industry was held at Bombay during November 24-26. 1993. The past decade has seen many important advances in the design and technology of artificial neural networks in research and industry. Neural networks is an interdisciplinary field covering a broad spectrum of applications in surveillance, diagnosis of nuclear power plants, nuclear spectroscopy, speech and written text recognition, robotic control, signal processing etc. The objective of the symposium was to promote awareness of advances in neural network research and applications. It was also aimed at conducting the review of the present status and giving direction for future technological developments. Contributed papers have been organized into the following groups: a) neural network architectures, learning algorithms and modelling, b) computer vision and image processing, c) signal processing, d) neural networks and fuzzy systems, e) nuclear applications and f) neural networks and allied applications. Papers relevant to INIS are indexed separately. (M.K.V.)

  5. Anaerobic prosthetic joint infection.

    Science.gov (United States)

    Shah, Neel B; Tande, Aaron J; Patel, Robin; Berbari, Elie F

    2015-12-01

    In an effort to improve mobility and alleviate pain from degenerative and connective tissue joint disease, an increasing number of individuals are undergoing prosthetic joint replacement in the United States. Joint replacement is a highly effective intervention, resulting in improved quality of life and increased independence [1]. By 2030, it is predicted that approximately 4 million total hip and knee arthroplasties will be performed yearly in the United States [2]. One of the major complications associated with this procedure is prosthetic joint infection (PJI), occurring at a rate of 1-2% [3-7]. In 2011, the Musculoskeletal Infectious Society created a unifying definition for prosthetic joint infection [8]. The following year, the Infectious Disease Society of America published practice guidelines that focused on the diagnosis and management of PJI. These guidelines focused on the management of commonly encountered organisms associated with PJI, including staphylococci, streptococci and select aerobic Gram-negative bacteria. However, with the exception of Propionibacterium acnes, management of other anaerobic organisms was not addressed in these guidelines [1]. Although making up approximately 3-6% of PJI [9,10], anaerobic microorganisms cause devastating complications, and similar to the more common organisms associated with PJI, these bacteria also result in significant morbidity, poor outcomes and increased health-care costs. Data on diagnosis and management of anaerobic PJI is mostly derived from case reports, along with a few cohort studies [3]. There is a paucity of published data outlining factors associated with risks, diagnosis and management of anaerobic PJI. We therefore reviewed available literature on anaerobic PJI by systematically searching the PubMed database, and collected data from secondary searches to determine information on pathogenesis, demographic data, clinical features, diagnosis and management. We focused our search on five commonly

  6. Chaotic Hopfield Neural Network Swarm Optimization and Its Application

    Directory of Open Access Journals (Sweden)

    Yanxia Sun

    2013-01-01

    Full Text Available A new neural network based optimization algorithm is proposed. The presented model is a discrete-time, continuous-state Hopfield neural network and the states of the model are updated synchronously. The proposed algorithm combines the advantages of traditional PSO, chaos and Hopfield neural networks: particles learn from their own experience and the experiences of surrounding particles, their search behavior is ergodic, and convergence of the swarm is guaranteed. The effectiveness of the proposed approach is demonstrated using simulations and typical optimization problems.

  7. Application of artificial neural network in radiographic diagnosis

    International Nuclear Information System (INIS)

    Piraino, D.; Amartur, S.; Richmond, B.; Schils, J.; Belhobek, G.

    1990-01-01

    This paper reports on an artificial neural network trained to rate the likelihood of different bone neoplasms when given a standard description of a radiograph. A three-layer back propagation algorithm was trained with descriptions of examples of bone neoplasms obtained from standard radiographic textbooks. Fifteen bone neoplasms obtained from clinical material were used as unknowns to test the trained artificial neural network. The artificial neural network correctly rated the pathologic diagnosis as the most likely diagnosis in 10 of the 15 unknown cases

  8. Prosthetic Joint Infection

    Science.gov (United States)

    Tande, Aaron J.

    2014-01-01

    SUMMARY Prosthetic joint infection (PJI) is a tremendous burden for individual patients as well as the global health care industry. While a small minority of joint arthroplasties will become infected, appropriate recognition and management are critical to preserve or restore adequate function and prevent excess morbidity. In this review, we describe the reported risk factors for and clinical manifestations of PJI. We discuss the pathogenesis of PJI and the numerous microorganisms that can cause this devastating infection. The recently proposed consensus definitions of PJI and approaches to accurate diagnosis are reviewed in detail. An overview of the treatment and prevention of this challenging condition is provided. PMID:24696437

  9. Biomaterial Characterization of Off-the-Shelf Decellularized Porcine Pericardial Tissue for use in Prosthetic Valvular Applications.

    Science.gov (United States)

    Choe, Joshua A; Jana, Soumen; Tefft, Brandon J; Hennessy, Ryan S; Go, Jason; Morse, David; Lerman, Amir; Young, Melissa D

    2018-05-10

    Fixed pericardial tissue is commonly used for commercially available xenograft valve implants, and has proven durability, but lacks the capability to remodel and grow. Decellularized porcine pericardial tissue has the promise to outperform fixed tissue and remodel, but the decellularization process has been shown to damage the collagen structure and reduce mechanical integrity of the tissue. Therefore, a comparison of uniaxial tensile properties was performed on decellularized, decellularized-sterilized, fixed, and native porcine pericardial tissue, versus native valve leaflet cusps. The results of non-parametric analysis showed statistically significant differences (ptesting of the tissues showed no statistical difference between decellularized or decell-sterilized tissue compared to native cusps (p>0.05). SEM confirmed that valvular endothelial and interstitial cells colonized the decellularized pericardial surface when seeded and grown for 30 days in static culture. Collagen assays and TEM analysis showed limited reductions in collagen with processing; yet, GAG assays showed great reductions in the processed pericardium relative to native cusps. Decellularized pericardium had comparatively lower mechanical properties amongst the groups studied; yet, the stiffness was comparatively similar to the native cusps and demonstrated a lack of cytotoxicity. Suture retention, accelerated wear, and hydrodynamic testing of prototype decellularized and decell-sterilized valves showed positive functionality. Sterilized tissue could mimic valvular mechanical environment in vitro, therefore making it a viable potential candidate for off-the-shelf tissue engineered valvular applications. KEYTERMS Decellularization, Sterilization, Pericardial Tissue, Heart Valves, Tissue Engineering, Biomechanics. This article is protected by copyright. All rights reserved.

  10. Guide to prosthetic cardiac valves

    International Nuclear Information System (INIS)

    Morse, D.; Steiner, R.M.; Fernandez, J.

    1985-01-01

    This book contains 10 chapters. Some of the chapter titles are: The development of artificial heart valves: Introduction and historical perspective; The radiology of prosthetic heart valves; The evaluation of patients for prosthetic valve implantation; Pathology of cardiac valve replacement; and Bioengineering of mechanical and biological heart valve substitutes

  11. Controlled neural network application in track-match problem

    International Nuclear Information System (INIS)

    Baginyan, S.A.; Ososkov, G.A.

    1993-01-01

    Track-match problem of high energy physics (HEP) data handling is formulated in terms of incidence matrices. The corresponding Hopfield neural network is developed to solve this type of constraint satisfaction problems (CSP). A special concept of the controlled neural network is proposed as a basis of an algorithm for the effective CSP solution. Results of comparable calculations show the very high performance of this algorithm against conventional search procedures. 8 refs.; 1 fig.; 1 tab

  12. A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing

    Directory of Open Access Journals (Sweden)

    Yi-Qing Wang

    2015-09-01

    Full Text Available Recent years have seen a surge of interest in multilayer neural networks fueled by their successful applications in numerous image processing and computer vision tasks. In this article, we describe a C++ implementation of the stochastic gradient descent to train a multilayer neural network, where a fast and accurate acceleration of tanh(· is achieved with linear interpolation. As an example of application, we present a neural network able to deliver state-of-the-art performance in image demosaicing.

  13. Applications of artificial neural networks in Nuclear Medicine

    International Nuclear Information System (INIS)

    Maddalena, D.J.

    1993-01-01

    Artificial neural networks (ANNs) are computer-based mathematical models developed to have analogous functions to idealized simple biological nervous systems. They consist of layers of processing elements, which are considered to be analogous to the nerve cells (neurons) and these are interconnected to form a network which is in essence a parallel computer even though they are most likely to be run on non-parallel computers such as personal computers or workstations. The parallel processing nature of the ANNs gives them the characteristics of speed, reliability and generalisation. The speed occurs because many bits of information can be input and analysed simultaneously. Reliability occurs because the networks can produce reasonable results even when some input data are missing or inaccurate. Generalisation is the ability of the network to estimate reasonable results when faced with new data outside its normal range of experience. There are two main classes of ANN - supervised and un-supervised. Supervised ANNs are trained to build internal algorithms relating patterns of inputs to outputs. After learning the relationship between the inputs and outputs they are able to classify patterns and make decisions of predictions based upon new patterns of inputs. The most frequently used ANN for biomedical applications is a supervised type called the back propagation ANN which has an excellent ability to predict and classify data and is becoming commonly used throughout the biomedical field. This article will discuss back propagation ANN structure. Its use for image analysis and diagnostic classification in various imaging modalities including Single Photon Emission Computed Tomography and Positron Emission Tomography 17 refs., 2 figs

  14. Application of Artificial Neural Networks to Complex Groundwater Management Problems

    International Nuclear Information System (INIS)

    Coppola, Emery; Poulton, Mary; Charles, Emmanuel; Dustman, John; Szidarovszky, Ferenc

    2003-01-01

    As water quantity and quality problems become increasingly severe, accurate prediction and effective management of scarcer water resources will become critical. In this paper, the successful application of artificial neural network (ANN) technology is described for three types of groundwater prediction and management problems. In the first example, an ANN was trained with simulation data from a physically based numerical model to predict head (groundwater elevation) at locations of interest under variable pumping and climate conditions. The ANN achieved a high degree of predictive accuracy, and its derived state-transition equations were embedded into a multiobjective optimization formulation and solved to generate a trade-off curve depicting water supply in relation to contamination risk. In the second and third examples, ANNs were developed with real-world hydrologic and climate data for different hydrogeologic environments. For the second problem, an ANN was developed using data collected for a 5-year, 8-month period to predict heads in a multilayered surficial and limestone aquifer system under variable pumping, state, and climate conditions. Using weekly stress periods, the ANN substantially outperformed a well-calibrated numerical flow model for the 71-day validation period, and provided insights into the effects of climate and pumping on water levels. For the third problem, an ANN was developed with data collected automatically over a 6-week period to predict hourly heads in 11 high-capacity public supply wells tapping a semiconfined bedrock aquifer and subject to large well-interference effects. Using hourly stress periods, the ANN accurately predicted heads for 24-hour periods in all public supply wells. These test cases demonstrate that the ANN technology can solve a variety of complex groundwater management problems and overcome many of the problems and limitations associated with traditional physically based flow models

  15. State-of-the-art of applications of neural networks in the nuclear industry

    International Nuclear Information System (INIS)

    Zwingelstein, G.; Masson, M.H.

    1990-01-01

    Artificial neural net models have been extensively studied for many years in various laboratories to try to simulate with computer programs the human brain performances. The first applications were developed in the fields of speech and image recognition. The aims of these studies were mainly to classify rapidly patterns corrupted by noises or partly missing. Neural networks with the development of new net topologies and algorithms and parallel computing hardwares and softwares are to-day very promising for applications in many industries. In the introduction, this paper presents the anticipated benefits of the uses of neural networks for industrial applications. Then a brief overview of the main neural networks is provided. Finally a short review of neural networks applications in the nuclear industry is given. It covers domains such as: predictive maintenance for vibratory surveillance of rotating machinery, signal processing, operator guidance and eddy current inspection. In conclusion recommendations are made to use with efficiency neural networks for practical applications. In particular the need for supercomputing will be pinpointed. (author)

  16. Application of artificial neural network for medical image recognition and diagnostic decision making

    International Nuclear Information System (INIS)

    Asada, N.; Eiho, S.; Doi, K.; MacMahon, H.; Montner, S.M.; Giger, M.L.

    1989-01-01

    An artificial neural network has been applied for pattern recognition and used as a tool in an expert system. The purpose of this study is to examine the potential usefulness of the neural network approach in medical applications for image recognition and decision making. The authors designed multilayer feedforward neural networks with a back-propagation algorithm for our study. Using first-pass radionuclide ventriculograms, we attempted to identify the right and left ventricles of the heart and the lungs by training the neural network from patterns of time-activity curves. In a preliminary study, the neural network enabled identification of the lungs and heart chambers once the network was trained sufficiently by means of repeated entries of data from the same case

  17. Application of neural networks to multiple alarm processing and diagnosis in nuclear power plants

    International Nuclear Information System (INIS)

    Cheon, Se Woo; Chang Soon Heung; Chung, Hak Yeong

    1992-01-01

    This paper presents feasibility studies of multiple alarm processing and diagnosis using neural networks. The back-propagation neural network model is applied to the training of multiple alarm patterns for the identification of failure in a reactor coolant pump (RCP) system. The general mapping capability of the neural network enables to identify a fault easily. The case studies are performed with emphasis on the applicability of the neural network to pattern recognition problems. It is revealed that the neural network model can identify the cause of multiple alarms properly, even when untrained or sensor-failed alarm symptoms are given. It is also shown that multiple failures are easily identified using the symptoms of multiple alarms

  18. Application of neural network technology to setpoint control of a simulated reactor experiment loop

    International Nuclear Information System (INIS)

    Cordes, G.A.; Bryan, S.R.; Powell, R.H.; Chick, D.R.

    1991-01-01

    This paper describes the design, implementation, and application of artificial neural networks to achieve temperature and flow rate control for a simulation of a typical experiment loop in the Advanced Test Reactor (ATR) located at the Idaho National Engineering Laboratory (INEL). The goal of the project was to research multivariate, nonlinear control using neural networks. A loop simulation code was adapted for the project and used to create a training set and test the neural network controller for comparison with the existing loop controllers. The results for the best neural network design are documented and compared with existing loop controller action. The neural network was shown to be as accurate at loop control as the classical controllers in the operating region represented by the training set. 5 refs., 8 figs., 3 tabs

  19. Statistical modelling of neural networks in γ-spectrometry applications

    International Nuclear Information System (INIS)

    Vigneron, V.; Martinez, J.M.; Morel, J.; Lepy, M.C.

    1995-01-01

    Layered Neural Networks, which are a class of models based on neural computation, are applied to the measurement of uranium enrichment, i.e. the isotope ratio 235 U/( 235 U + 236 U + 238 U). The usual method consider a limited number of Γ-ray and X-ray peaks, and require previously calibrated instrumentation for each sample. But, in practice, the source-detector ensemble geometry conditions are critically different, thus a means of improving the above convention methods is to reduce the region of interest: this is possible by focusing on the K α X region where the three elementary components are present. Real data are used to study the performance of neural networks. Training is done with a Maximum Likelihood method to measure uranium 235 U and 238 U quantities in infinitely thick samples. (authors). 18 refs., 6 figs., 3 tabs

  20. Disorder generated by interacting neural networks: application to econophysics and cryptography

    International Nuclear Information System (INIS)

    Kinzel, Wolfgang; Kanter, Ido

    2003-01-01

    When neural networks are trained on their own output signals they generate disordered time series. In particular, when two neural networks are trained on their mutual output they can synchronize; they relax to a time-dependent state with identical synaptic weights. Two applications of this phenomenon are discussed for (a) econophysics and (b) cryptography. (a) When agents competing in a closed market (minority game) are using neural networks to make their decisions, the total system relaxes to a state of good performance. (b) Two partners communicating over a public channel can find a common secret key

  1. The application of neural networks for fault diagnosis in nuclear reactors

    International Nuclear Information System (INIS)

    Jalel, N.A.; Nicholson, H.

    1990-11-01

    In recent years considerable work have been done in the field of neural networks due to the recent development of effective learning algorithms, and the results of their applications have suggested that they can provide useful tools for solving practical problems. Artificial neural networks are mathematical models of theorized mind and brain activity. They are aimed to explore and reproduce human information processing tasks such as speech, vision, knowledge processing and control. The possibility of using artificial neural networks for fault and accident diagnosis in the Loss Of Fluid Test (LOFT) reactor, a small scale pressurised water reactor, is examined and explained in the paper. (author)

  2. Development and application of deep convolutional neural network in target detection

    Science.gov (United States)

    Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

    2018-04-01

    With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

  3. Neural networks and its application in biomedical engineering

    International Nuclear Information System (INIS)

    Husnain, S.K.; Bhatti, M.I.

    2002-01-01

    Artificial network (ANNs) is an information processing system that has certain performance characteristics in common with biological neural networks. A neural network is characterized by connections between the neurons, method of determining the weights on the connections and its activation functions while a biological neuron has three types of components that are of particular interest in understanding an artificial neuron: its dendrites, soma, and axon. The actin of the chemical transmitter modifies the incoming signal. The study of neural networks is an extremely interdisciplinary field. Computer-based diagnosis is an increasingly used method that tries to improve the quality of health care. Systems on Neural Networks have been developed extensively in the last ten years with the hope that medical diagnosis and therefore medical care would improve dramatically. The addition of a symbolic processing layer enhances the ANNs in a number of ways. It is, for instance, possible to supplement a network that is purely diagnostic with a level that recommends or nodes in order to more closely simulate the nervous system. (author)

  4. Application of neural networks in coastal engineering - An overview

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Patil, S.G.; Manjunatha, Y.R.; Hegde, A.V.

    Artificial Neural Network (ANN) is being applied to solve a wide variety of coastal/ocean engineering problems. In practical terms ANNs are non-linear modeling tools and they can be used to model complex relationship between the input and output...

  5. Application of Neural Networks to Higgs Boson Search

    Czech Academy of Sciences Publication Activity Database

    Hakl, František; Hlaváček, M.; Kalous, R.

    2003-01-01

    Roč. 502, - (2003), s. 489-491 ISSN 0168-9002 R&D Projects: GA MPO RP-4210/69/97 Institutional research plan: AV0Z1030915 Keywords : neural network s * Higgs search * genetic optimization Subject RIV: BA - General Mathematics Impact factor: 1.166, year: 2003

  6. Neural network application to the neutral meson recognition

    International Nuclear Information System (INIS)

    Lefevre, F.; Delagrange, H.; Merrouch, R.; Ostendorf, R.; Schutz, Y.; Matulewicz, T.

    1991-01-01

    The combinatorial background produced by high photon multiplicities expected in TAPS experiments causes problems in precise meson recognition. We use neural networks to reduce this background. First we give a description of this technique, hereafter the first results obtained by applying this method to simulated events and future perspective will be discussed [fr

  7. Neural network based satellite tracking for deep space applications

    Science.gov (United States)

    Amoozegar, F.; Ruggier, C.

    2003-01-01

    The objective of this paper is to provide a survey of neural network trends as applied to the tracking of spacecrafts in deep space at Ka-band under various weather conditions and examine the trade-off between tracing accuracy and communication link performance.

  8. Application of design of experiments and artificial neural networks ...

    African Journals Online (AJOL)

    This paper discusses the use of Distance based optimal designs in the design of experiments (DOE) and artificial neural networks (ANN) in optimizing the stacking sequence for simply supported laminated composite plate under uniformly distributed load (UDL) for minimizing the deflections and stresses. A number of finite ...

  9. Application of neural networks to seismic active control

    International Nuclear Information System (INIS)

    Tang, Yu.

    1995-01-01

    An exploratory study on seismic active control using an artificial neural network (ANN) is presented in which a singledegree-of-freedom (SDF) structural system is controlled by a trained neural network. A feed-forward neural network and the backpropagation training method are used in the study. In backpropagation training, the learning rate is determined by ensuring the decrease of the error function at each training cycle. The training patterns for the neural net are generated randomly. Then, the trained ANN is used to compute the control force according to the control algorithm. The control strategy proposed herein is to apply the control force at every time step to destroy the build-up of the system response. The ground motions considered in the simulations are the N21E and N69W components of the Lake Hughes No. 12 record that occurred in the San Fernando Valley in California on February 9, 1971. Significant reduction of the structural response by one order of magnitude is observed. Also, it is shown that the proposed control strategy has the ability to reduce the peak that occurs during the first few cycles of the time history. These promising results assert the potential of applying ANNs to active structural control under seismic loads

  10. A Bootstrap Neural Network Based Heterogeneous Panel Unit Root Test: Application to Exchange Rates

    OpenAIRE

    Christian de Peretti; Carole Siani; Mario Cerrato

    2010-01-01

    This paper proposes a bootstrap artificial neural network based panel unit root test in a dynamic heterogeneous panel context. An application to a panel of bilateral real exchange rate series with the US Dollar from the 20 major OECD countries is provided to investigate the Purchase Power Parity (PPP). The combination of neural network and bootstrapping significantly changes the findings of the economic study in favour of PPP.

  11. Management of Prosthetic Joint Infection.

    Science.gov (United States)

    Tande, Aaron J; Gomez-Urena, Eric O; Berbari, Elie F; Osmon, Douglas R

    2017-06-01

    Although uncommon, prosthetic joint infection is a devastating complication. This challenging condition requires a coordinated management approach to achieve good patient outcomes. This review details the general principles to consider when managing patients with prosthetic joint infection. The different medical/surgical treatment strategies and how to appropriately select a strategy are discussed. The data to support each strategy are presented, along with discussion of antimicrobial strategies in specific situations. Copyright © 2017 Elsevier Inc. All rights reserved.

  12. Advanced Prosthetic Gait Training Tool

    Science.gov (United States)

    2015-12-01

    modules to train individuals to distinguish gait deviations (trunk motion and lower-limb motion). Each of these modules help trainers improve their...AWARD NUMBER: W81XWH-10-1-0870 TITLE: Advanced Prosthetic Gait Training Tool PRINCIPAL INVESTIGATOR: Dr. Karim Abdel-Malek CONTRACTING...study is to produce a computer-based Advanced Prosthetic Gait Training Tool to aid in the training of clinicians at military treatment facilities

  13. Which prosthetic foot to prescribe?

    OpenAIRE

    De Asha, AR; Barnett, CT; Struchkov, V; Buckley, JG

    2017-01-01

    Introduction: \\ud Clinicians typically use findings from cohort studies to objectively inform judgements regarding the potential (dis)advantages of prescribing a new prosthetic device. However, before finalising prescription a clinician will typically ask a patient to 'try out' a change of prosthetic device while the patient is at the clinic. Observed differences in gait when using the new device should be the result of the device’s mechanical function, but could also conceivably be due to pa...

  14. Pre-prosthetic surgery: Mandible

    Directory of Open Access Journals (Sweden)

    Veeramalai Naidu Devaki

    2012-01-01

    Full Text Available Pre-prosthetic surgery is that part of oral and maxillofacial surgery which restores oral function and facial form. This is concerned with surgical modification of the alveolar process and its surrounding structures to enable the fabrication of a well-fitting, comfortable, and esthetic dental prosthesis. The ultimate goal of pre-prosthetic surgery is to prepare a mouth to receive a dental prosthesis by redesigning and smoothening bony edges.

  15. Practical Application of Neural Networks in State Space Control

    DEFF Research Database (Denmark)

    Bendtsen, Jan Dimon

    the networks, although some modifications are needed for the method to apply to the multilayer perceptron network. In connection with the multilayer perceptron networks it is also pointed out how instantaneous, sample-by-sample linearized state space models can be extracted from a trained network, thus opening......In the present thesis we address some problems in discrete-time state space control of nonlinear dynamical systems and attempt to solve them using generic nonlinear models based on artificial neural networks. The main aim of the work is to examine how well such control algorithms perform when...... theoretic notions followed by a detailed description of the topology, neuron functions and learning rules of the two types of neural networks treated in the thesis, the multilayer perceptron and the neurofuzzy networks. In both cases, a Least Squares second-order gradient method is used to train...

  16. Inner and Outer Recursive Neural Networks for Chemoinformatics Applications.

    Science.gov (United States)

    Urban, Gregor; Subrahmanya, Niranjan; Baldi, Pierre

    2018-02-26

    Deep learning methods applied to problems in chemoinformatics often require the use of recursive neural networks to handle data with graphical structure and variable size. We present a useful classification of recursive neural network approaches into two classes, the inner and outer approach. The inner approach uses recursion inside the underlying graph, to essentially "crawl" the edges of the graph, while the outer approach uses recursion outside the underlying graph, to aggregate information over progressively longer distances in an orthogonal direction. We illustrate the inner and outer approaches on several examples. More importantly, we provide open-source implementations [available at www.github.com/Chemoinformatics/InnerOuterRNN and cdb.ics.uci.edu ] for both approaches in Tensorflow which can be used in combination with training data to produce efficient models for predicting the physical, chemical, and biological properties of small molecules.

  17. Application of artificial neural network for NHR fault diagnosis

    International Nuclear Information System (INIS)

    Yu Haitao; Zhang Liangju; Xu Xiangdong

    1999-01-01

    The author makes researches on 200 MW nuclear heating reactor (NHR) fault diagnosis system using artificial neural network, and use the tendency value and real value of the data under the accidents to train and test two BP networks respectively. The final diagnostic result is the combination of the results of the two networks. The compound system can enhance the accuracy and adaptability of the diagnosis comparing to the single network system

  18. An analog integrated front-end amplifier for neural applications

    OpenAIRE

    Zhou, Zhijun; Warr, Paul

    2017-01-01

    The front-end amplifier forms the critical element for signal detection and pre-processing within neural monitoring systems. It determines not only the fidelity of the biosignal, but also impacts power consumption and detector size. In this paper, a combined feedback loop-controlled approach is proposed to neutralize for the input leakage currents generated by low noise amplifiers when in integrated circuit form, alongside signal leakage into the input bias network. Significantly, this loop t...

  19. Artificial neural networks application for solid fuel slagging intensity predictions

    Directory of Open Access Journals (Sweden)

    Kakietek Sławomir

    2017-01-01

    Full Text Available Slagging issues present in pulverized steam boilers very often lead to heat transfer problems, corrosion and not planned outages of boilers which increase the cost of energy production and decrease the efficiency of energy production. Slagging especially occurs in regions with reductive atmospheres which nowadays are very common due to very strict limitations in NOx emissions. Moreover alternative fuels like biomass which are also used in combustion systems from two decades in order to decrease CO2 emissions also usually increase the risk of slagging. Thus the prediction of slagging properties of fuels is not the minor issue which can be neglected before purchasing or mixing of fuels. This however is rather difficult to estimate and even commonly known standard laboratory methods like fusion temperature determination or special indexers calculated on the basis of proximate and ultimate analyses, very often have no reasonable correlation to real boiler fuel behaviour. In this paper the method of determination of slagging properties of solid fuels based on laboratory investigation and artificial neural networks were presented. A fuel data base with over 40 fuels was created. Neural networks simulations were carried out in order to predict the beginning temperature and intensity of slagging. Reasonable results were obtained for some of tested neural networks, especially for hybrid feedforward networks with PCA technique. Consequently neural network model will be used in Common Intelligent Boiler Operation Platform (CIBOP being elaborated within CERUBIS research project for two BP-1150 and BB-1150 steam boilers. The model among others enables proper fuel selection in order to minimize slagging risk.

  20. Application of neural networks to waste site screening

    Energy Technology Data Exchange (ETDEWEB)

    Dabiri, A.E.; Kraft, T.; Hilton, J.M. [Science Applications International Corp., San Diego, CA (United States)

    1993-03-01

    Waste site screening requires knowledge of the actual concentrations of hazardous materials and rates of flow around and below the site with time. The present approach to site screening consists primarily of drilling, boreholes near contaminated site and chemically analyzing the extracted physical samples and processing the data. In addition, hydraulic and geochemical soil properties are obtained so that numerical simulation models can be used to interpret and extrapolate the field data. The objective of this work is to investigate the feasibility of using neural network techniques to reduce the cost of waste site screening. A successful technique may lead to an ability to reduce the number of boreholes and the number of samples analyzed from each borehole to properly screen the waste site. The analytic tool development described here is inexpensive because it makes use of neural network techniques that can interpolate rapidly and which can learn how to analyze data rather than having to be explicitly programmed. In the following sections, data collection and data analyses will be described, followed by a section on different neural network techniques used. The results will be presented and compared with mathematical model. Finally, the last section will summarize the research work performed and make several recommendations for future work.

  1. Sensory feedback in upper limb prosthetics.

    Science.gov (United States)

    Antfolk, Christian; D'Alonzo, Marco; Rosén, Birgitta; Lundborg, Göran; Sebelius, Fredrik; Cipriani, Christian

    2013-01-01

    One of the challenges facing prosthetic designers and engineers is to restore the missing sensory function inherit to hand amputation. Several different techniques can be employed to provide amputees with sensory feedback: sensory substitution methods where the recorded stimulus is not only transferred to the amputee, but also translated to a different modality (modality-matched feedback), which transfers the stimulus without translation and direct neural stimulation, which interacts directly with peripheral afferent nerves. This paper presents an overview of the principal works and devices employed to provide upper limb amputees with sensory feedback. The focus is on sensory substitution and modality matched feedback; the principal features, advantages and disadvantages of the different methods are presented.

  2. Automated implementation of rule-based expert systems with neural networks for time-critical applications

    Science.gov (United States)

    Ramamoorthy, P. A.; Huang, Song; Govind, Girish

    1991-01-01

    In fault diagnosis, control and real-time monitoring, both timing and accuracy are critical for operators or machines to reach proper solutions or appropriate actions. Expert systems are becoming more popular in the manufacturing community for dealing with such problems. In recent years, neural networks have revived and their applications have spread to many areas of science and engineering. A method of using neural networks to implement rule-based expert systems for time-critical applications is discussed here. This method can convert a given rule-based system into a neural network with fixed weights and thresholds. The rules governing the translation are presented along with some examples. We also present the results of automated machine implementation of such networks from the given rule-base. This significantly simplifies the translation process to neural network expert systems from conventional rule-based systems. Results comparing the performance of the proposed approach based on neural networks vs. the classical approach are given. The possibility of very large scale integration (VLSI) realization of such neural network expert systems is also discussed.

  3. Neural attractor network for application in visual field data classification

    International Nuclear Information System (INIS)

    Fink, Wolfgang

    2004-01-01

    The purpose was to introduce a novel method for computer-based classification of visual field data derived from perimetric examination, that may act as a ' counsellor', providing an independent 'second opinion' to the diagnosing physician. The classification system consists of a Hopfield-type neural attractor network that obtains its input data from perimetric examination results. An iterative relaxation process determines the states of the neurons dynamically. Therefore, even 'noisy' perimetric output, e.g., early stages of a disease, may eventually be classified correctly according to the predefined idealized visual field defect (scotoma) patterns, stored as attractors of the network, that are found with diseases of the eye, optic nerve and the central nervous system. Preliminary tests of the classification system on real visual field data derived from perimetric examinations have shown a classification success of over 80%. Some of the main advantages of the Hopfield-attractor-network-based approach over feed-forward type neural networks are: (1) network architecture is defined by the classification problem; (2) no training is required to determine the neural coupling strengths; (3) assignment of an auto-diagnosis confidence level is possible by means of an overlap parameter and the Hamming distance. In conclusion, the novel method for computer-based classification of visual field data, presented here, furnishes a valuable first overview and an independent 'second opinion' in judging perimetric examination results, pointing towards a final diagnosis by a physician. It should not be considered a substitute for the diagnosing physician. Thanks to the worldwide accessibility of the Internet, the classification system offers a promising perspective towards modern computer-assisted diagnosis in both medicine and tele-medicine, for example and in particular, with respect to non-ophthalmic clinics or in communities where perimetric expertise is not readily available

  4. Artificial intelligence. Application of the Statistical Neural Networks computer program in nuclear medicine

    International Nuclear Information System (INIS)

    Stefaniak, B.; Cholewinski, W.; Tarkowska, A.

    2005-01-01

    Artificial Neural Networks (ANN) may be a tool alternative and complementary to typical statistical analysis. However, in spite of many computer application of various ANN algorithms ready for use, artificial intelligence is relatively rarely applied to data processing. In this paper practical aspects of scientific application of ANN in medicine using the Statistical Neural Networks Computer program, were presented. Several steps of data analysis with the above ANN software package were discussed shortly, from material selection and its dividing into groups to the types of obtained results. The typical problems connected with assessing scintigrams by ANN were also described. (author)

  5. Application of neural computing paradigms for signal validation

    International Nuclear Information System (INIS)

    Upadhyaya, B.R.; Eryurek, E.; Mathai, G.

    1989-01-01

    Signal validation and process monitoring problems often require the prediction of one or more process variables in a system. The feasibility of applying neural network paradigms to relate one variable with a set of other related variables is studied. The backpropagation network (BPN) is applied to develop models of signals from both a commercial power plant and the EBR-II. Modification of the BPN algorithm is studied with emphasis on the speed of network training and the accuracy of prediction. The prediction of process variables in a Westinghouse PWR is presented in this paper

  6. Application of neural networks for the prediction of multidirectional magnetostriction

    CERN Document Server

    Baumgartinger, N; Pfützner, H; Krismanic, G

    2000-01-01

    This paper describes attempts to use artificial neural networks (ANNs) for the prediction of magnetostriction (MS) characteristics of transformer core materials. In this first approach, the ANNs were trained with data from a rotational single-sheet tester to predict MS in rolling direction (r.d.) as a function of material grade, amplitude and shape of multidirectional magnetisation as well as the level of additional mechanical stress. It is shown that ANNs are able to forecast the corresponding relative MS changes in an approximate way.

  7. Artificial neural network applications in the calibration of spark-ignition engines: An overview

    Directory of Open Access Journals (Sweden)

    Richard Fiifi Turkson

    2016-09-01

    Full Text Available Emission legislation has become progressively tighter, making the development of new internal combustion engines very challenging. New engine technologies for complying with these regulations introduce an exponential dependency between the number of test combinations required for obtaining optimum results and the time and cost outlays. This makes the calibration task very expensive and virtually impossible to carry out. The potential use of trained neural networks in combination with Design of Experiments (DoE methods for engine calibration has been a subject of research activities in recent times. This is because artificial neural networks, compared with other data-driven modeling techniques, perform better in satisfying a majority of the modeling requirements for engine calibration including the curse of dimensionality; the use of DoE for obtaining few measurements as practicable, with the aim of reducing engine calibration costs; the required flexibility that allows model parameters to be optimized to avoid overfitting; and the facilitation of automated online optimization during the engine calibration process that eliminates the need for user intervention. The purpose of this review is to give an overview of the various applications of neural networks in the calibration of spark-ignition engines. The identified and discussed applications include system identification for rapid prototyping, virtual sensing, use of neural networks as look-up table surrogates, emerging control strategies and On-Board Diagnostic (OBD applications. The demerits of neural networks, future possibilities and alternatives were also discussed.

  8. Image Finder Mobile Application Based on Neural Networks

    Directory of Open Access Journals (Sweden)

    Nabil M. Hewahi

    2017-04-01

    Full Text Available Nowadays taking photos via mobile phone has become a very important part of everyone’s life. Almost each and every person who has a smart phone also has thousands of photos in their mobile device. At times it becomes very difficult to find a particular photo from thousands of photos, and it takes time. This research was done to come up with an innovative solution that could solve this problem. The solution will allow the user to find the required photo by simply drawing a sketch on the objects in the required picture, for example a tree or car, etc. Two types of supervised Artificial Neural Networks are used for this purpose; one is trained to identify the handmade sketches and other is trained to identify the images. The proposed approach introduces a mechanism to relate the sketches with the images by matching them after training. The experimentation results for testing the trained neural networks reached 100% for the sketches, and 84% for the images of two objects as a case study.

  9. The application of particle swarm optimization to identify gamma spectrum with neural network

    International Nuclear Information System (INIS)

    Shi Dongsheng; Di Yuming; Zhou Chunlin

    2006-01-01

    Aiming at the shortcomings that BP algorithm is usually trapped to a local optimum and it has a low speed of convergence in the application of neural network to identify gamma spectrum, according to the advantage of the globe optimal searching of particle swarm optimization, this paper put forward a new algorithm for neural network training by combining BP algorithm and Particle Swarm Optimization-mixed PSO-BP algorithm. In the application to identify gamma spectrum, the new algorithm overcomes the shortcoming that BP algorithm is usually trapped to a local optimum and the neural network trained by it has a high ability of generalization with identification result of one hundred percent correct. Practical example shows that the mixed PSO-BP algorithm can effectively and reliably be used to identify gamma spectrum. (authors)

  10. Application of artificial neural networks to evaluate weld defects of nuclear components

    International Nuclear Information System (INIS)

    Amin, E.S.

    2007-01-01

    Artificial neural networks (ANNs) are computational representations based on the biological neural architecture of the brain. ANNs have been successfully applied to a wide range of engineering and scientific applications, such as signal, image processing and data analysis. Although Radiographic testing is widely used for welding defects, it is unsuccessful in identifying some welding defects because of the nature of image formation and quality. Neoteric algorithms have been used for the purpose of weld defects identifications in radiographic images to replace the expert knowledge. The application of artificial neural networks in noise detection of radiographic films is used. Radial Basis (RB) and learning vector quantization (LVQ) were applied. The method shows good performance in weld defects recognition and classification problems.

  11. ARM-based visual processing system for prosthetic vision.

    Science.gov (United States)

    Matteucci, Paul B; Byrnes-Preston, Philip; Chen, Spencer C; Lovell, Nigel H; Suaning, Gregg J

    2011-01-01

    A growing number of prosthetic devices have been shown to provide visual perception to the profoundly blind through electrical neural stimulation. These first-generation devices offer promising outcomes to those affected by degenerative disorders such as retinitis pigmentosa. Although prosthetic approaches vary in their placement of the stimulating array (visual cortex, optic-nerve, epi-retinal surface, sub-retinal surface, supra-choroidal space, etc.), most of the solutions incorporate an externally-worn device to acquire and process video to provide the implant with instructions on how to deliver electrical stimulation to the patient, in order to elicit phosphenized vision. With the significant increase in availability and performance of low power-consumption smart phone and personal device processors, the authors investigated the use of a commercially available ARM (Advanced RISC Machine) device as an externally-worn processing unit for a prosthetic neural stimulator for the retina. A 400 MHz Samsung S3C2440A ARM920T single-board computer was programmed to extract 98 values from a 1.3 Megapixel OV9650 CMOS camera using impulse, regional averaging and Gaussian sampling algorithms. Power consumption and speed of video processing were compared to results obtained to similar reported devices. The results show that by using code optimization, the system is capable of driving a 98 channel implantable device for the restoration of visual percepts to the blind.

  12. Architecture and biological applications of artificial neural networks: a tuberculosis perspective.

    Science.gov (United States)

    Darsey, Jerry A; Griffin, William O; Joginipelli, Sravanthi; Melapu, Venkata Kiran

    2015-01-01

    Advancement of science and technology has prompted researchers to develop new intelligent systems that can solve a variety of problems such as pattern recognition, prediction, and optimization. The ability of the human brain to learn in a fashion that tolerates noise and error has attracted many researchers and provided the starting point for the development of artificial neural networks: the intelligent systems. Intelligent systems can acclimatize to the environment or data and can maximize the chances of success or improve the efficiency of a search. Due to massive parallelism with large numbers of interconnected processers and their ability to learn from the data, neural networks can solve a variety of challenging computational problems. Neural networks have the ability to derive meaning from complicated and imprecise data; they are used in detecting patterns, and trends that are too complex for humans, or other computer systems. Solutions to the toughest problems will not be found through one narrow specialization; therefore we need to combine interdisciplinary approaches to discover the solutions to a variety of problems. Many researchers in different disciplines such as medicine, bioinformatics, molecular biology, and pharmacology have successfully applied artificial neural networks. This chapter helps the reader in understanding the basics of artificial neural networks, their applications, and methodology; it also outlines the network learning process and architecture. We present a brief outline of the application of neural networks to medical diagnosis, drug discovery, gene identification, and protein structure prediction. We conclude with a summary of the results from our study on tuberculosis data using neural networks, in diagnosing active tuberculosis, and predicting chronic vs. infiltrative forms of tuberculosis.

  13. Candida infection of a prosthetic shoulder joint

    Energy Technology Data Exchange (ETDEWEB)

    Lichtman, E.A.

    1983-09-01

    A heroin addict developed a Candida parapsilosis infection in a prosthetic shoulder joint. Radiographs showed loose fragments of cement with prosthetic loosening. The patient was treated with removal of the prosthesis and intravenous amphotericin B followed by oral ketoconazole.

  14. Candida infection of a prosthetic shoulder joint

    International Nuclear Information System (INIS)

    Lichtman, E.A.; Veterans Administration Medical Center, New York

    1983-01-01

    A heroin addict developed a Candida parapsilosis infection in a prosthetic shoulder joint. Radiographs showed loose fragments of cement with prosthetic loosening. The patient was treated with removal of the prosthesis and intravenous amphotericin B followed by oral ketoconazole. (orig.)

  15. Absolute stability of nonlinear systems with time delays and applications to neural networks

    Directory of Open Access Journals (Sweden)

    Xinzhi Liu

    2001-01-01

    Full Text Available In this paper, absolute stability of nonlinear systems with time delays is investigated. Sufficient conditions on absolute stability are derived by using the comparison principle and differential inequalities. These conditions are simple and easy to check. In addition, exponential stability conditions for some special cases of nonlinear delay systems are discussed. Applications of those results to cellular neural networks are presented.

  16. Artificial Neural Networks: A New Approach for Predicting Application Behavior. AIR 2001 Annual Forum Paper.

    Science.gov (United States)

    Gonzalez, Julie M. Byers; DesJardins, Stephen L.

    This paper examines how predictive modeling can be used to study application behavior. A relatively new technique, artificial neural networks (ANNs), was applied to help predict which students were likely to get into a large Research I university. Data were obtained from a university in Iowa. Two cohorts were used, each containing approximately…

  17. Development & automation of a novel ["1"8F]F prosthetic group, 2-["1"8F]-fluoro-3-pyridinecarboxaldehyde, and its application to an amino(oxy)-functionalised Aβ peptide

    International Nuclear Information System (INIS)

    Morris, Olivia; Gregory, J.; Kadirvel, M.; Henderson, Fiona; Blykers, A.; McMahon, Adam; Taylor, Mark; Allsop, David; Allan, Stuart; Grigg, J.; Boutin, Herve; Prenant, Christian

    2016-01-01

    2-["1"8F]-Fluoro-3-pyridinecarboxaldehyde (["1"8F]FPCA) is a novel, water-soluble prosthetic group. It's radiochemistry has been developed and fully-automated for application in chemoselective radiolabelling of amino(oxy)-derivatised RI-OR2-TAT peptide, (Aoa-k)-RI-OR2-TAT, using a GE TRACERlab FX-FN. RI-OR2-TAT is a brain-penetrant, retro-inverso peptide that binds to amyloid species associated with Alzheimer's Disease. Radiolabelled (Aoa-k)-RI-OR2-TAT was reproducibly synthesised and the product of the reaction with FPCA has been fully characterised. In-vivo biodistribution of ["1"8F]RI-OR2-TAT has been measured in Wistar rats.

  18. Prosthetic management of deciduous teeth

    OpenAIRE

    Bassil, Jean

    2015-01-01

    Projeto de Pós-Graduação/Dissertação apresentado à Universidade Fernando Pessoa como parte dos requisitos para obtenção do grau de Mestre em Medicina Dentária Introduction: Situations of single or multiple edentulous are not an exception during childhood. Prosthetic management is necessary in case of absence of replacing tooth or when its eruption is planned too far in time. Indications of prosthetic rehabilitation for children are multiple and rise from the etiologic factors caus...

  19. Development of a 3D-Printed Robotic Prosthetic Arm

    Energy Technology Data Exchange (ETDEWEB)

    Gomez Martinez, M.; Garcia-Miquel, A.; Vidal Martinez, N.

    2016-07-01

    Current prostheses are not affordable to the general public. 3D printing technology may allow low-cost production of such devices, making them more readily accessible to people in need. This contribution presents the set-up and the considerations that have to be taken into account to develop a functional artificial upper limb prototype. The robotic prosthetic arm reported herein was produced entirely using 3D printing technology to demonstrate its feasibility on a limited budget. The project was developed to integrate two different functional modes: a prosthetic application and a remote application. The prosthetic application is intended to emulate existing prosthetic devices using myoelectric sensors. The remote application is conceived as a tool for prevention, by providing the general public with a device that could carry out activities that entail a risk of severe physical injury. This is achieved using a hand-tracking system that allows the robotic arm to copy the user’s movements remotely and in real time. The outcome of the validation tests has been considerably successful for both applications and the total costs are on target. (Author)

  20. Illusory movement perception improves motor control for prosthetic hands

    Science.gov (United States)

    Marasco, Paul D.; Hebert, Jacqueline S.; Sensinger, Jon W.; Shell, Courtney E.; Schofield, Jonathon S.; Thumser, Zachary C.; Nataraj, Raviraj; Beckler, Dylan T.; Dawson, Michael R.; Blustein, Dan H.; Gill, Satinder; Mensh, Brett D.; Granja-Vazquez, Rafael; Newcomb, Madeline D.; Carey, Jason P.; Orzell, Beth M.

    2018-01-01

    To effortlessly complete an intentional movement, the brain needs feedback from the body regarding the movement’s progress. This largely non-conscious kinesthetic sense helps the brain to learn relationships between motor commands and outcomes to correct movement errors. Prosthetic systems for restoring function have predominantly focused on controlling motorized joint movement. Without the kinesthetic sense, however, these devices do not become intuitively controllable. Here we report a method for endowing human amputees with a kinesthetic perception of dexterous robotic hands. Vibrating the muscles used for prosthetic control via a neural-machine interface produced the illusory perception of complex grip movements. Within minutes, three amputees integrated this kinesthetic feedback and improved movement control. Combining intent, kinesthesia, and vision instilled participants with a sense of agency over the robotic movements. This feedback approach for closed-loop control opens a pathway to seamless integration of minds and machines. PMID:29540617

  1. Aerogel Use as a Skin Protective Liner In Space Suits and Prosthetic Limbs Project

    Science.gov (United States)

    Roberson, Luke Bennett

    2014-01-01

    Existing materials for prosthetic liners tend to be thick and airtight, causing perspiration to accumulate inside the liner and potentially causing infection and injury. The purpose of this project was to examine the suitability of aerogel for prosthetic liner applications for use in space suits and orthopedics. Three tests were performed on several types of aerogel to assess the properties of each material, and our initial findings demonstrated that these materrials would be excellent candidates for liner applications for prosthetics and space suits. The project is currently on hold until additional funding is obtained for application testing at the VH Hospitals in Tampa

  2. Stability Analysis and Application for Delayed Neural Networks Driven by Fractional Brownian Noise.

    Science.gov (United States)

    Zhou, Wuneng; Zhou, Xianghui; Yang, Jun; Zhou, Jun; Tong, Dongbing

    2018-05-01

    This paper deals with two types of the stability problem for the delayed neural networks driven by fractional Brownian noise (FBN). The existence and the uniqueness of the solution to the main system with respect to FBN are proved via fixed point theory. Based on Hilbert-Schmidt operator theory and analytic semigroup principle, the mild solution of the stochastic neural networks is obtained. By applying the stochastic analytic technique and some well-known inequalities, the asymptotic stability criteria and the exponential stability condition are established. Both numerical example and practical application for synchronization control of multiagent system are provided to illustrate the effectiveness and potential of the proposed techniques.

  3. Application of neural network in τ→ρυτ polarization analysis

    International Nuclear Information System (INIS)

    Zhang Ziping; Wang Yifang; Innocente, V.

    1994-01-01

    An artificial neutral network was built to select events in the τ→ρυ τ polarization analysis at LEP/L3, much better selection efficiency has been achieved. Detailed studies show that no systematic errors or bias have been introduced by the application of neural network. A polarization of P τ = -0.129 +- 0.050 +- 0.050 for this channel was obtained by using a sample of 8977 τ + τ - pairs collected near the peak of Z 0 resonance. The neural network training method and some details are described

  4. Application of recurrent neural networks for drought projections in California

    Science.gov (United States)

    Le, J. A.; El-Askary, H. M.; Allali, M.; Struppa, D. C.

    2017-05-01

    We use recurrent neural networks (RNNs) to investigate the complex interactions between the long-term trend in dryness and a projected, short but intense, period of wetness due to the 2015-2016 El Niño. Although it was forecasted that this El Niño season would bring significant rainfall to the region, our long-term projections of the Palmer Z Index (PZI) showed a continuing drought trend, contrasting with the 1998-1999 El Niño event. RNN training considered PZI data during 1896-2006 that was validated against the 2006-2015 period to evaluate the potential of extreme precipitation forecast. We achieved a statistically significant correlation of 0.610 between forecasted and observed PZI on the validation set for a lead time of 1 month. This gives strong confidence to the forecasted precipitation indicator. The 2015-2016 El Niño season proved to be relatively weak as compared with the 1997-1998, with a peak PZI anomaly of 0.242 standard deviations below historical averages, continuing drought conditions.

  5. Application of Artificial Neural Networks in Canola Crop Yield Prediction

    Directory of Open Access Journals (Sweden)

    S. J. Sajadi

    2014-02-01

    Full Text Available Crop yield prediction has an important role in agricultural policies such as specification of the crop price. Crop yield prediction researches have been based on regression analysis. In this research canola yield was predicted using Artificial Neural Networks (ANN using 11 crop year climate data (1998-2009 in Gonbad-e-Kavoos region of Golestan province. ANN inputs were mean weekly rainfall, mean weekly temperature, mean weekly relative humidity and mean weekly sun shine hours and ANN output was canola yield (kg/ha. Multi-Layer Perceptron networks (MLP with Levenberg-Marquardt backpropagation learning algorithm was used for crop yield prediction and Root Mean Square Error (RMSE and square of the Correlation Coefficient (R2 criterions were used to evaluate the performance of the ANN. The obtained results show that the 13-20-1 network has the lowest RMSE equal to 101.235 and maximum value of R2 equal to 0.997 and is suitable for predicting canola yield with climate factors.

  6. Application of neural networks to quantitative spectrometry analysis

    International Nuclear Information System (INIS)

    Pilato, V.; Tola, F.; Martinez, J.M.; Huver, M.

    1999-01-01

    Accurate quantitative analysis of complex spectra (fission and activation products), relies upon experts' knowledge. In some cases several hours, even days of tedious calculations are needed. This is because current software is unable to solve deconvolution problems when several rays overlap. We have shown that such analysis can be correctly handled by a neural network, and the procedure can be automated with minimum laboratory measurements for networks training, as long as all the elements of the analysed solution figure in the training set and provided that adequate scaling of input data is performed. Once the network has been trained, analysis is carried out in a few seconds. On submitting to a test between several well-known laboratories, where unknown quantities of 57 Co, 58 Co, 85 Sr, 88 Y, 131 I, 139 Ce, 141 Ce present in a sample had to be determined, the results yielded by our network classed it amongst the best. The method is described, including experimental device and measures, training set designing, relevant input parameters definition, input data scaling and networks training. Main results are presented together with a statistical model allowing networks error prediction

  7. Early prosthetic valve endocarditis caused by Corynebacterium kroppenstedtii.

    Science.gov (United States)

    Hagemann, Jürgen Benjamin; Essig, Andreas; Herrmann, Manuel; Liebold, Andreas; Quader, Mohamed Abo

    2015-12-01

    Corynebacterium (C.) kroppenstedtii is a rarely detected agent of bacterial infections in humans. Here, we describe the first case of prosthetic valve endocarditis caused by C. kroppenstedtii. Application of molecular methods using surgically excised valve tissue was a cornerstone for the establishment of the microbiological diagnosis, which is crucial for targeted antimicrobial treatment. Copyright © 2015 Elsevier GmbH. All rights reserved.

  8. Applications of neural networks to monitoring and decision making in the operation of nuclear power plants

    International Nuclear Information System (INIS)

    Uhrig, R.E.

    1990-01-01

    Application of neural networks to monitoring and decision making in the operation of nuclear power plants is being investigated under a US Department of Energy sponsored program at the University of Tennessee. Projects include the feasibility of using neural networks for the following tasks: (1) diagnosing specific abnormal conditions or problems in nuclear power plants, (2) detection of the change of mode of operation of the plant, (3) validating signals coming from detectors, (4) review of ''noise'' data from TVA's Sequoyah Nuclear Power Plant, and (5) examination of the NRC's database of ''Letter Event Reports'' for correlation of sequences of events in the reported incidents. Each of these projects and its status are described briefly in this paper. This broad based program has as its objective the definition of the state-of-the-art in using neural networks to enhance the performance of commercial nuclear power plants

  9. Application of clustering analysis in the prediction of photovoltaic power generation based on neural network

    Science.gov (United States)

    Cheng, K.; Guo, L. M.; Wang, Y. K.; Zafar, M. T.

    2017-11-01

    In order to select effective samples in the large number of data of PV power generation years and improve the accuracy of PV power generation forecasting model, this paper studies the application of clustering analysis in this field and establishes forecasting model based on neural network. Based on three different types of weather on sunny, cloudy and rainy days, this research screens samples of historical data by the clustering analysis method. After screening, it establishes BP neural network prediction models using screened data as training data. Then, compare the six types of photovoltaic power generation prediction models before and after the data screening. Results show that the prediction model combining with clustering analysis and BP neural networks is an effective method to improve the precision of photovoltaic power generation.

  10. Application of Artificial Neural Network to Predict the use of Runway at Juanda International Airport

    Science.gov (United States)

    Putra, J. C. P.; Safrilah

    2017-06-01

    Artificial neural network approaches are useful to solve many complicated problems. It solves a number of problems in various areas such as engineering, medicine, business, manufacturing, etc. This paper presents an application of artificial neural network to predict a runway capacity at Juanda International Airport. An artificial neural network model of backpropagation and multi-layer perceptron is adopted to this research to learning process of runway capacity at Juanda International Airport. The results indicate that the training data is successfully recognizing the certain pattern of runway use at Juanda International Airport. Whereas, testing data indicate vice versa. Finally, it can be concluded that the approach of uniformity data and network architecture is the critical part to determine the accuracy of prediction results.

  11. Application of General Regression Neural Network to the Prediction of LOD Change

    Science.gov (United States)

    Zhang, Xiao-Hong; Wang, Qi-Jie; Zhu, Jian-Jun; Zhang, Hao

    2012-01-01

    Traditional methods for predicting the change in length of day (LOD change) are mainly based on some linear models, such as the least square model and autoregression model, etc. However, the LOD change comprises complicated non-linear factors and the prediction effect of the linear models is always not so ideal. Thus, a kind of non-linear neural network — general regression neural network (GRNN) model is tried to make the prediction of the LOD change and the result is compared with the predicted results obtained by taking advantage of the BP (back propagation) neural network model and other models. The comparison result shows that the application of the GRNN to the prediction of the LOD change is highly effective and feasible.

  12. Applications of self-organizing neural networks in virtual screening and diversity selection.

    Science.gov (United States)

    Selzer, Paul; Ertl, Peter

    2006-01-01

    Artificial neural networks provide a powerful technique for the analysis and modeling of nonlinear relationships between molecular structures and pharmacological activity. Many network types, including Kohonen and counterpropagation, also provide an intuitive method for the visual assessment of correspondence between the input and output data. This work shows how a combination of neural networks and radial distribution function molecular descriptors can be applied in various areas of industrial pharmaceutical research. These applications include the prediction of biological activity, the selection of screening candidates (cherry picking), and the extraction of representative subsets from large compound collections such as combinatorial libraries. The methods described have also been implemented as an easy-to-use Web tool, allowing chemists to perform interactive neural network experiments on the Novartis intranet.

  13. Control method for prosthetic devices

    Science.gov (United States)

    Bozeman, Richard J., Jr. (Inventor)

    1995-01-01

    A control system and method for prosthetic devices is provided. The control system comprises a transducer for receiving movement from a body part for generating a sensing signal associated with that movement. The sensing signal is processed by a linearizer for linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part. The linearized sensing signal is normalized to be a function of the entire range of body part movement from the no-shrug position of the moveable body part. The normalized signal is divided into a plurality of discrete command signals. The discrete command signals are used by typical converter devices which are in operational association with the prosthetic device. The converter device uses the discrete command signals for driving the moveable portions of the prosthetic device and its sub-prosthesis. The method for controlling a prosthetic device associated with the present invention comprises the steps of receiving the movement from the body part, generating a sensing signal in association with the movement of the body part, linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part, normalizing the linear signal to be a function of the entire range of the body part movement, dividing the normalized signal into a plurality of discrete command signals, and implementing the plurality of discrete command signals for driving the respective moveable prosthesis device and its sub-prosthesis.

  14. A mechatronics platform to study prosthetic hand control using EMG signals.

    Science.gov (United States)

    Geethanjali, P

    2016-09-01

    In this paper, a low-cost mechatronics platform for the design and development of robotic hands as well as a surface electromyogram (EMG) pattern recognition system is proposed. This paper also explores various EMG classification techniques using a low-cost electronics system in prosthetic hand applications. The proposed platform involves the development of a four channel EMG signal acquisition system; pattern recognition of acquired EMG signals; and development of a digital controller for a robotic hand. Four-channel surface EMG signals, acquired from ten healthy subjects for six different movements of the hand, were used to analyse pattern recognition in prosthetic hand control. Various time domain features were extracted and grouped into five ensembles to compare the influence of features in feature-selective classifiers (SLR) with widely considered non-feature-selective classifiers, such as neural networks (NN), linear discriminant analysis (LDA) and support vector machines (SVM) applied with different kernels. The results divulged that the average classification accuracy of the SVM, with a linear kernel function, outperforms other classifiers with feature ensembles, Hudgin's feature set and auto regression (AR) coefficients. However, the slight improvement in classification accuracy of SVM incurs more processing time and memory space in the low-level controller. The Kruskal-Wallis (KW) test also shows that there is no significant difference in the classification performance of SLR with Hudgin's feature set to that of SVM with Hudgin's features along with AR coefficients. In addition, the KW test shows that SLR was found to be better in respect to computation time and memory space, which is vital in a low-level controller. Similar to SVM, with a linear kernel function, other non-feature selective LDA and NN classifiers also show a slight improvement in performance using twice the features but with the drawback of increased memory space requirement and time

  15. Application of neural network to multi-dimensional design window search in reactor core design

    International Nuclear Information System (INIS)

    Kugo, Teruhiko; Nakagawa, Masayuki

    1999-01-01

    In the reactor core design, many parametric survey calculations should be carried out to decide an optimal set of basic design parameter values. They consume a large amount of computation time and labor in the conventional way. To support design work, we investigate a procedure to search efficiently a design window, which is defined as feasible design parameter ranges satisfying design criteria and requirements, in a multi-dimensional space composed of several basic design parameters. The present method is applied to the neutronics and thermal hydraulics fields. The principle of the present method is to construct the multilayer neural network to simulate quickly a response of an analysis code through a training process, and to reduce computation time using the neural network without parametric study using analysis codes. To verify the applicability of the present method to the neutronics and the thermal hydraulics design, we have applied it to high conversion water reactors and examined effects of the structure of the neural network and the number of teaching patterns on the accuracy of the design window estimated by the neural network. From the results of the applications, a guideline to apply the present method is proposed and the present method can predict an appropriate design window in a reasonable computation time by following the guideline. (author)

  16. Neural Spike Train Synchronisation Indices: Definitions, Interpretations and Applications.

    Science.gov (United States)

    Halliday, D M; Rosenberg, J R

    2017-04-24

    A comparison of previously defined spike train syncrhonization indices is undertaken within a stochastic point process framework. The second order cumulant density (covariance density) is shown to be common to all the indices. Simulation studies were used to investigate the sampling variability of a single index based on the second order cumulant. The simulations used a paired motoneurone model and a paired regular spiking cortical neurone model. The sampling variability of spike trains generated under identical conditions from the paired motoneurone model varied from 50% { 160% of the estimated value. On theoretical grounds, and on the basis of simulated data a rate dependence is present in all synchronization indices. The application of coherence and pooled coherence estimates to the issue of synchronization indices is considered. This alternative frequency domain approach allows an arbitrary number of spike train pairs to be evaluated for statistically significant differences, and combined into a single population measure. The pooled coherence framework allows pooled time domain measures to be derived, application of this to the simulated data is illustrated. Data from the cortical neurone model is generated over a wide range of firing rates (1 - 250 spikes/sec). The pooled coherence framework correctly characterizes the sampling variability as not significant over this wide operating range. The broader applicability of this approach to multi electrode array data is briefly discussed.

  17. Use of neural networks in process engineering. Thermodynamics, diffusion, and process control and simulation applications

    International Nuclear Information System (INIS)

    Otero, F

    1998-01-01

    This article presents the current status of the use of Artificial Neural Networks (ANNs) in process engineering applications where common mathematical methods do not completely represent the behavior shown by experimental observations, results, and plant operating data. Three examples of the use of ANNs in typical process engineering applications such as prediction of activity in solvent-polymer binary systems, prediction of a surfactant self-diffusion coefficient of micellar systems, and process control and simulation are shown. These examples are important for polymerization applications, enhanced-oil recovery, and automatic process control

  18. Image processing using pulse-coupled neural networks applications in Python

    CERN Document Server

    Lindblad, Thomas

    2013-01-01

    Image processing algorithms based on the mammalian visual cortex are powerful tools for extraction information and manipulating images. This book reviews the neural theory and translates them into digital models. Applications are given in areas of image recognition, foveation, image fusion and information extraction. The third edition reflects renewed international interest in pulse image processing with updated sections presenting several newly developed applications. This edition also introduces a suite of Python scripts that assist readers in replicating results presented in the text and to further develop their own applications.

  19. Application of artificial neural network model combined with four biomarkers in auxiliary diagnosis of lung cancer.

    Science.gov (United States)

    Duan, Xiaoran; Yang, Yongli; Tan, Shanjuan; Wang, Sihua; Feng, Xiaolei; Cui, Liuxin; Feng, Feifei; Yu, Songcheng; Wang, Wei; Wu, Yongjun

    2017-08-01

    The purpose of the study was to explore the application of artificial neural network model in the auxiliary diagnosis of lung cancer and compare the effects of back-propagation (BP) neural network with Fisher discrimination model for lung cancer screening by the combined detections of four biomarkers of p16, RASSF1A and FHIT gene promoter methylation levels and the relative telomere length. Real-time quantitative methylation-specific PCR was used to detect the levels of three-gene promoter methylation, and real-time PCR method was applied to determine the relative telomere length. BP neural network and Fisher discrimination analysis were used to establish the discrimination diagnosis model. The levels of three-gene promoter methylation in patients with lung cancer were significantly higher than those of the normal controls. The values of Z(P) in two groups were 2.641 (0.008), 2.075 (0.038) and 3.044 (0.002), respectively. The relative telomere lengths of patients with lung cancer (0.93 ± 0.32) were significantly lower than those of the normal controls (1.16 ± 0.57), t = 4.072, P < 0.001. The areas under the ROC curve (AUC) and 95 % CI of prediction set from Fisher discrimination analysis and BP neural network were 0.670 (0.569-0.761) and 0.760 (0.664-0.840). The AUC of BP neural network was higher than that of Fisher discrimination analysis, and Z(P) was 0.76. Four biomarkers are associated with lung cancer. BP neural network model for the prediction of lung cancer is better than Fisher discrimination analysis, and it can provide an excellent and intelligent diagnosis tool for lung cancer.

  20. Neural network retrieval of soil moisture: application to SMOS

    Science.gov (United States)

    Rodriguez-Fernandez, Nemesio; Richaume, Philippe; Aires, Filipe; Prigent, Catherine; Kerr, Yann; Kolasssa, Jana; Jimenez, Carlos; Cabot, Francois; Mahmoodi, Ali

    2014-05-01

    We present an efficient statistical soil moisture (SM) retrieval method using SMOS brightness temperatures (BTs) complemented with MODIS NDVI and ASCAT backscattering data. The method is based on a feed-forward neural network (hereafter NN) trained with SM from ECMWF model predictions or from the SMOS operational algorithm. The best compromise to retrieve SM with NNs from SMOS brightness temperatures in a large fraction of the swath (~ 670 km) is to use incidence angles from 25 to 60 degrees (in 7 bins of 5 deg width) for both H and V polarizations. The correlation coefficient (R) of the SM retrieved by the NN and the reference SM dataset (ECMWF or SMOS L3) is 0.8. The correlation coefficient increases to 0.91 when adding as input MODIS NDVI, ECOCLIMAP sand and clay fractions and one of the following data: (i) active microwaves observations (ASCAT backscattering coefficient at 40 deg incidence angle), (ii) ECMWF soil temperature. Finally, the correlation coefficient increases to R=0.94 when using a normalization index computed locally for each latitude-longitude point with the maximum and minimum BTs and the associated SM values from the local time series. Global maps of SM obtained with NNs reproduce well the spatial structures present in the reference SM datasets, implying that the NN works well for a wide range of ecosystems and physical conditions. In addition, the results of the NNs have been evaluated at selected locations for which in situ measurements are available such as the USDA-ARS watersheds (USA), the OzNet network (AUS) and USDA-NRCS SCAN network (USA). The time series of SM obtained with NNs reproduce the temporal behavior measured with in situ sensors. For well known sites where the in situ measurement is representative of a 40 km scale like the Little Washita watershed, the NN models show a very high correlation of (R = 0.8-0.9) and a low standard deviation of 0.02-0.04 m3/m3 with respect to the in situ measurements. When comparing with all the in

  1. Fiber-array based optogenetic prosthetic system for stimulation therapy

    Science.gov (United States)

    Gu, Ling; Cote, Chris; Tejeda, Hector; Mohanty, Samarendra

    2012-02-01

    Recent advent of optogenetics has enabled activation of genetically-targeted neuronal cells using low intensity blue light with high temporal precision. Since blue light is attenuated rapidly due to scattering and absorption in neural tissue, optogenetic treatment of neurological disorders may require stimulation of specific cell types in multiple regions of the brain. Further, restoration of certain neural functions (vision, and auditory etc) requires accurate spatio-temporal stimulation patterns rather than just precise temporal stimulation. In order to activate multiple regions of the central nervous system in 3D, here, we report development of an optogenetic prosthetic comprising of array of fibers coupled to independently-controllable LEDs. This design avoids direct contact of LEDs with the brain tissue and thus does not require electrical and heat isolation, which can non-specifically stimulate and damage the local brain regions. The intensity, frequency, and duty cycle of light pulses from each fiber in the array was controlled independently using an inhouse developed LabView based program interfaced with a microcontroller driving the individual LEDs. While the temporal profile of the light pulses was controlled by varying the current driving the LED, the beam profile emanating from each fiber tip could be sculpted by microfabrication of the fiber tip. The fiber array was used to stimulate neurons, expressing channelrhodopsin-2, in different locations within the brain or retina. Control of neural activity in the mice cortex, using the fiber-array based prosthetic, is evaluated from recordings made with multi-electrode array (MEA). We also report construction of a μLED array based prosthetic for spatio-temporal stimulation of cortex.

  2. A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization.

    Science.gov (United States)

    Liu, Qingshan; Guo, Zhishan; Wang, Jun

    2012-02-01

    In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed. Copyright © 2011 Elsevier Ltd. All rights reserved.

  3. An Improved Recurrent Neural Network for Complex-Valued Systems of Linear Equation and Its Application to Robotic Motion Tracking.

    Science.gov (United States)

    Ding, Lei; Xiao, Lin; Liao, Bolin; Lu, Rongbo; Peng, Hua

    2017-01-01

    To obtain the online solution of complex-valued systems of linear equation in complex domain with higher precision and higher convergence rate, a new neural network based on Zhang neural network (ZNN) is investigated in this paper. First, this new neural network for complex-valued systems of linear equation in complex domain is proposed and theoretically proved to be convergent within finite time. Then, the illustrative results show that the new neural network model has the higher precision and the higher convergence rate, as compared with the gradient neural network (GNN) model and the ZNN model. Finally, the application for controlling the robot using the proposed method for the complex-valued systems of linear equation is realized, and the simulation results verify the effectiveness and superiorness of the new neural network for the complex-valued systems of linear equation.

  4. NEURAL NETWORKS, FUZZY LOGIC AND GENETIC ALGORITHMS: APPLICATIONS AND POSSIBILITIES IN FINANCE AND ACCOUNTING

    Directory of Open Access Journals (Sweden)

    José Alonso Borba

    2010-04-01

    Full Text Available There are problems in Finance and Accounting that can not be easily solved by means of traditional techniques (e.g. bankruptcy prediction and strategies for investing in common stock. In these situations, it is possible to use methods of Artificial Intelligence. This paper analyzes empirical works published in international journals between 2000 and 2007 that present studies about the application of Neural Networks, Fuzzy Logic and Genetic Algorithms to problems in Finance and Accounting. The objective is to identify and quantify the relationships established between the available techniques and the problems studied by the researchers. Analyzing 258 papers, it was noticed that the most used technique is the Artificial Neural Network. The most researched applications are from the field of Finance, especially those related to stock exchanges (forecasting of common stock and indices prices.

  5. Application of neural networks for finding the relation between stress and operational parameters of NPP Temelin

    International Nuclear Information System (INIS)

    Ruzek, L.

    2003-01-01

    Quick and sufficiently precise determination of stresses and strains measured by I and C, TMDS a CHEMIS is very important for on-line assessment of continuous damage of material under operating conditions. The application of some of the artificial intelligence methods, viz. neural network, is convenient in this context. A practical example of the application of this method is presented and the advantages in comparison with the finite element method (FEM) are discussed. The approach to the selection of characteristic loading used for the preparation of training data is also shown. The paper presents the results of actual calculation and analyses the merits of the attained coincidence for the determination of the tensor of stresses by FEM and neural networks

  6. Wavelet neural networks with applications in financial engineering, chaos, and classification

    CERN Document Server

    Alexandridis, Antonios K

    2014-01-01

    Through extensive examples and case studies, Wavelet Neural Networks provides a step-by-step introduction to modeling, training, and forecasting using wavelet networks. The acclaimed authors present a statistical model identification framework to successfully apply wavelet networks in various applications, specifically, providing the mathematical and statistical framework needed for model selection, variable selection, wavelet network construction, initialization, training, forecasting and prediction, confidence intervals, prediction intervals, and model adequacy testing. The text is ideal for

  7. Artificial neural networks application for analysis of gamma ray spectrum obtained from the scintillation detectors

    International Nuclear Information System (INIS)

    Stegowski, Z.

    2002-01-01

    Scintillation detectors are commonly used for the gamma ray detection. Actually the small peak resolution and the significant Compton effect fraction limit their utilization in the gamma ray spectrometry analysis. This article presents the artificial neural networks (ANN) application to the analysis of the gamma ray spectra acquired from scintillation detectors. The obtained results validate the effectiveness of the ANN method to spectrometry analysis. (author)

  8. Simulation Techniques and Prosthetic Approach Towards Biologically Efficient Artificial Sense Organs- An Overview

    OpenAIRE

    Neogi, Biswarup; Ghosal, Soumya; Mukherjee, Soumyajit; Das, Achintya; Tibarewala, D. N.

    2011-01-01

    An overview of the applications of control theory to prosthetic sense organs including the senses of vision, taste and odor is being presented in this paper. Simulation aspect nowadays has been the centre of research in the field of prosthesis. There have been various successful applications of prosthetic organs, in case of natural biological organs dis-functioning patients. Simulation aspects and control modeling are indispensible for knowing system performance, and to generate an original a...

  9. Cyclic fatigue-crack propagation, stress-corrosion, and fracture-toughness behavior in pyrolytic carbon-coated graphite for prosthetic heart valve applications.

    Science.gov (United States)

    Ritchie, R O; Dauskardt, R H; Yu, W K; Brendzel, A M

    1990-02-01

    Fracture-mechanics tests were performed to characterize the cyclic fatigue, stress-corrosion cracking, and fracture-toughness behavior of a pyrolytic carbon-coated graphite composite material used in the manufacture of cardiac valve prostheses. Testing was carried out using compact tension C(T) samples containing "atomically" sharp precracks, both in room-temperature air and principally in a simulated physiological environment of 37 degrees C Ringer's lactate solution. Under sustained (monotonic) loads, the composite exhibited resistance-curve behavior, with a fracture toughness (KIc) between 1.1 and 1.9 MPa square root of m, and subcritical stress-corrosion crack velocities (da/dt) which were a function of the stress intensity K raised to the 74th power (over the range approximately 10(-9) to over 10(-5) m/s). More importantly, contrary to common perception, under cyclic loading conditions the composite was found to display true (cyclic) fatigue failure in both environments; fatigue-crack growth rates (da/dN) were seen to be a function of the 19th power of the stress-intensity range delta K (over the range approximately 10(-11) to over 10(-8) m/cycle). As subcritical crack velocities under cyclic loading were found to be many orders of magnitude faster than those measured under equivalent monotonic loads and to occur at typically 45% lower stress-intensity levels, cyclic fatigue in pyrolytic carbon-coated graphite is reasoned to be a vital consideration in the design and life-prediction procedures of prosthetic devices manufactured from this material.

  10. Validation and Application of a Dried Blood Spot Assay for Biofilm-Active Antibiotics Commonly Used for Treatment of Prosthetic Implant Infections

    Science.gov (United States)

    Knippenberg, Ben; Page-Sharp, Madhu; Clark, Ben; Dyer, John; Batty, Kevin T.; Davis, Timothy M. E.

    2016-01-01

    Dried blood spot (DBS) antibiotic assays can facilitate pharmacokinetic (PK)/pharmacodynamic (PD) studies in situations where venous blood sampling is logistically difficult. We sought to develop, validate, and apply a DBS assay for rifampin (RIF), fusidic acid (FUS), and ciprofloxacin (CIP). These antibiotics are considered active against organisms in biofilms and are therefore commonly used for the treatment of infections associated with prosthetic implants. A liquid chromatography-mass spectroscopy DBS assay was developed and validated, including red cell partitioning and thermal stability for each drug and the rifampin metabolite desacetyl rifampin (Des-RIF). Plasma and DBS concentrations in 10 healthy adults were compared, and the concentration-time profiles were incorporated into population PK models. The limits of quantification for RIF, Des-RIF, CIP, and FUS in DBS were 15 μg/liter, 14 μg/liter, 25 μg/liter, and 153 μg/liter, respectively. Adjusting for hematocrit, red cell partitioning, and relative recovery, DBS-predicted plasma concentrations were comparable to measured plasma concentrations for each antibiotic (r > 0.95; P < 0.0001), and Bland-Altman plots showed no significant bias. The final population PK estimates of clearance, volume of distribution, and time above threshold MICs for measured and DBS-predicted plasma concentrations were comparable. These drugs were stable in DBSs for at least 10 days at room temperature and 1 month at 4°C. The present DBS antibiotic assays are robust and can be used as surrogates for plasma concentrations to provide valid PK and PK/PD data in a variety of clinical situations, including therapeutic drug monitoring or studies of implant infections. PMID:27270283

  11. Prosthetic Mitral Valve Leaflet Escape

    Science.gov (United States)

    Kim, Darae; Hun, Sin Sang; Cho, In-Jeong; Shim, Chi-Young; Ha, Jong-Won; Chung, Namsik; Ju, Hyun Chul; Sohn, Jang Won

    2013-01-01

    Leaflet escape of prosthetic valve is rare but potentially life threatening. It is essential to make timely diagnosis in order to avoid mortality. Transesophageal echocardiography and cinefluoroscopy is usually diagnostic and the location of the missing leaflet can be identified by computed tomography (CT). Emergent surgical correction is mandatory. We report a case of fractured escape of Edward-Duromedics mitral valve 27 years after the surgery. The patient presented with symptoms of acute decompensated heart failure and cardiogenic shock. She was instantly intubated and mechanically ventilated. After prompt evaluation including transthoracic echocardiography and CT, the escape of the leaflet was confirmed. The patient underwent emergent surgery for replacement of the damaged prosthetic valves immediately. Eleven days after the surgery, the dislodged leaflet in iliac artery was removed safely and the patient recovered well. PMID:23837121

  12. Investigation and modeling on protective textiles using artificial neural networks for defense applications

    International Nuclear Information System (INIS)

    Ramaiah, Gurumurthy B.; Chennaiah, Radhalakshmi Y.; Satyanarayanarao, Gurumurthy K.

    2010-01-01

    Kevlar 29 is a class of Kevlar fiber used for protective applications primarily by the military and law enforcement agencies for bullet resistant vests, hence for these reasons military has found that armors reinforced with Kevlar 29 multilayer fabrics which offer 25-40% better fragmentation resistance and provide better fit with greater comfort. The objective of this study is to investigate and develop an artificial neural network model for analyzing the performance of ballistic fabrics made from Kevlar 29 single layer fabrics using their material properties as inputs. Data from fragment simulation projectile (FSP) ballistic penetration measurements at 244 m/s has been used to demonstrate the modeling aspects of artificial neural networks. The neural network models demonstrated in this paper is based on back propagation (BP) algorithm which is inbuilt in MATLAB 7.1 software and is used for studies in science, technology and engineering. In the present research, comparisons are also made between the measured values of samples selected for building the neural network model and network predicted results. The analysis of the results for network predicted and experimental samples used in this study showed similarity.

  13. Applications of Mesenchymal Stem Cells and Neural Crest Cells in Craniofacial Skeletal Research

    Directory of Open Access Journals (Sweden)

    Satoru Morikawa

    2016-01-01

    Full Text Available Craniofacial skeletal tissues are composed of tooth and bone, together with nerves and blood vessels. This composite material is mainly derived from neural crest cells (NCCs. The neural crest is transient embryonic tissue present during neural tube formation whose cells have high potential for migration and differentiation. Thus, NCCs are promising candidates for craniofacial tissue regeneration; however, the clinical application of NCCs is hindered by their limited accessibility. In contrast, mesenchymal stem cells (MSCs are easily accessible in adults, have similar potential for self-renewal, and can differentiate into skeletal tissues, including bones and cartilage. Therefore, MSCs may represent good sources of stem cells for clinical use. MSCs are classically identified under adherent culture conditions, leading to contamination with other cell lineages. Previous studies have identified mouse- and human-specific MSC subsets using cell surface markers. Additionally, some studies have shown that a subset of MSCs is closely related to neural crest derivatives and endothelial cells. These MSCs may be promising candidates for regeneration of craniofacial tissues from the perspective of developmental fate. Here, we review the fundamental biology of MSCs in craniofacial research.

  14. Control System for Prosthetic Devices

    Science.gov (United States)

    Bozeman, Richard J. (Inventor)

    1996-01-01

    A control system and method for prosthetic devices is provided. The control system comprises a transducer for receiving movement from a body part for generating a sensing signal associated with that of movement. The sensing signal is processed by a linearizer for linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part. The linearized sensing signal is normalized to be a function of the entire range of body part movement from the no-shrug position of the moveable body part through the full-shrg position of the moveable body part. The normalized signal is divided into a plurality of discrete command signals. The discrete command signals are used by typical converter devices which are in operational association with the prosthetic device. The converter device uses the discrete command signals for driving the moveable portions of the prosthetic device and its sub-prosthesis. The method for controlling a prosthetic device associated with the present invention comprises the steps of receiving the movement from the body part, generating a sensing signal in association with the movement of the body part, linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part, normalizing the linear signal to be a function of the entire range of the body part movement, dividing the normalized signal into a plurality of discrete command signals, and implementing the plurality of discrete command signals for driving the respective moveable prosthesis device and its sub-prosthesis.

  15. Prosthetics & Orthotics Manufacturing Initiative (POMI)

    Science.gov (United States)

    2012-12-21

    suspension system, socket- ankle /knee interface, etc.) associated with a complete prosthetic system. More specific, the purpose of these deliverables was...strap. The waist belt consists of an adjustable belt utilizing polypropylene buckles and a 2‖ elastic suspension strap which descends to the anchor ...Superior View. Step 8: The suspension component consists of a 1’ anchor strap with a buckle and a 5’ – 6’ long shoulder strap with hook and

  16. The application of neural networks to flow regime identification

    International Nuclear Information System (INIS)

    Embrechts, M.; Yapo, T.C.; Lahey, R.T. Jr.

    1993-01-01

    This paper deals with the application of a Kohonen map for the identification of two-phase flow regimes where a mixture of gas and fluid flows through a horizontal tube. Depending on the relative flow velocities of the gas and the liquid phase, four distinct flow regimes can be identified: Wavy flow, plug flow, slug flow and annular flow. A schematic of these flow regimes is presented. The objective identification of two-phase flow regimes constitutes an important and challenging problem for the design of safe and reliable nuclear power plants. Previous attempts to classify these flow regimes are reviewed by Franca and Lahey. The authors describe how a Kohonen map can be applied to distinguish between flow regimes based on the Fourier power spectra and wavelet transforms of pressure drop fluctuations. The Fourier power spectra allowed the Kohonen map to identify the flow regimes successfully. In contrast, the Kohonen maps based on a wavelet transform could only distinguish between wavy and annular flows. An analysis of typical two-phase pressure drop data for an air/water mixture in a horizontal pipe is presented. Use of the wavelet transform and the Kohonen feature map are discussed

  17. Application of artificial neural networks for decision support in medicine.

    Science.gov (United States)

    Larder, Brendan; Wang, Dechao; Revell, Andy

    2008-01-01

    The emergence of drug resistant pathogens can reduce the efficacy of drugs commonly used to treat infectious diseases. Human immunodeficiency virus (HIV) is particularly sensitive to drug selection pressure, rapidly evolving into drug resistant variants on exposure to anti-HIV drugs. Over 200 mutations within the genetic material of HIV have been shown to be associated with drug resistance to date, and complex mutational patterns have been found in HIV isolates from infected patients exposed to multiple antiretroviral drugs. Genotyping is commonly used in clinical practice as a tool to identify drug resistance mutations in HIV from individual patients. This information is then used to help guide the choice of future therapy for patients whose drug regimen is failing because of the development of drug resistant HIV. Many sets of rules and algorithms are available to predict loss of susceptibility to individual antiretroviral drugs from genotypic data. Although this approach has been helpful, the interpretation of genotypic data remains challenging. We describe here the development and application of ANN models as alternative tools for the interpretation of HIV genotypic drug resistance data. A large amount of clinical and virological data, from around 30,000 patients treated with antiretroviral drugs, has been collected by the HIV Resistance Response Database Initiative (RDI, www.hivrdi.org) in a centralized database. Treatment change episodes (TCEs) have been extracted from these data and used along with HIV drug resistance mutations as the basic input variables to train ANN models. We performed a series of analyses that have helped define the following: (1) the reliability of ANN predictions for HIV patients receiving routine clinical care; (2) the utility of ANN models to identify effective treatments for patients failing therapy; (3) strategies to increase the accuracy of ANN predictions; and (4) performance of ANN models in comparison to the rules-based methods

  18. An Examination of Application of Artificial Neural Network in Cognitive Radios

    Science.gov (United States)

    Bello Salau, H.; Onwuka, E. N.; Aibinu, A. M.

    2013-12-01

    Recent advancement in software radio technology has led to the development of smart device known as cognitive radio. This type of radio fuses powerful techniques taken from artificial intelligence, game theory, wideband/multiple antenna techniques, information theory and statistical signal processing to create an outstanding dynamic behavior. This cognitive radio is utilized in achieving diverse set of applications such as spectrum sensing, radio parameter adaptation and signal classification. This paper contributes by reviewing different cognitive radio implementation that uses artificial intelligence such as the hidden markov models, metaheuristic algorithm and artificial neural networks (ANNs). Furthermore, different areas of application of ANNs and their performance metrics based approach are also examined.

  19. [Algorithms of artificial neural networks--practical application in medical science].

    Science.gov (United States)

    Stefaniak, Bogusław; Cholewiński, Witold; Tarkowska, Anna

    2005-12-01

    Artificial Neural Networks (ANN) may be a tool alternative and complementary to typical statistical analysis. However, in spite of many computer applications of various ANN algorithms ready for use, artificial intelligence is relatively rarely applied to data processing. This paper presents practical aspects of scientific application of ANN in medicine using widely available algorithms. Several main steps of analysis with ANN were discussed starting from material selection and dividing it into groups, to the quality assessment of obtained results at the end. The most frequent, typical reasons for errors as well as the comparison of ANN method to the modeling by regression analysis were also described.

  20. An Examination of Application of Artificial Neural Network in Cognitive Radios

    International Nuclear Information System (INIS)

    Salau, H Bello; Onwuka, E N; Aibinu, A M

    2013-01-01

    Recent advancement in software radio technology has led to the development of smart device known as cognitive radio. This type of radio fuses powerful techniques taken from artificial intelligence, game theory, wideband/multiple antenna techniques, information theory and statistical signal processing to create an outstanding dynamic behavior. This cognitive radio is utilized in achieving diverse set of applications such as spectrum sensing, radio parameter adaptation and signal classification. This paper contributes by reviewing different cognitive radio implementation that uses artificial intelligence such as the hidden markov models, metaheuristic algorithm and artificial neural networks (ANNs). Furthermore, different areas of application of ANNs and their performance metrics based approach are also examined

  1. Neural Network Based Recognition of Signal Patterns in Application to Automatic Testing of Rails

    Directory of Open Access Journals (Sweden)

    Tomasz Ciszewski

    2006-01-01

    Full Text Available The paper describes the application of neural network for recognition of signal patterns in measuring data gathered by the railroad ultrasound testing car. Digital conversion of the measuring signal allows to store and process large quantities of data. The elaboration of smart, effective and automatic procedures recognizing the obtained patterns on the basisof measured signal amplitude has been presented. The test shows only two classes of pattern recognition. In authors’ opinion if we deliver big enough quantity of training data, presented method is applicable to a system that recognizes many classes.

  2. "Geo-statistics methods and neural networks in geophysical applications: A case study"

    Science.gov (United States)

    Rodriguez Sandoval, R.; Urrutia Fucugauchi, J.; Ramirez Cruz, L. C.

    2008-12-01

    The study is focus in the Ebano-Panuco basin of northeastern Mexico, which is being explored for hydrocarbon reservoirs. These reservoirs are in limestones and there is interest in determining porosity and permeability in the carbonate sequences. The porosity maps presented in this study are estimated from application of multiattribute and neural networks techniques, which combine geophysics logs and 3-D seismic data by means of statistical relationships. The multiattribute analysis is a process to predict a volume of any underground petrophysical measurement from well-log and seismic data. The data consist of a series of target logs from wells which tie a 3-D seismic volume. The target logs are neutron porosity logs. From the 3-D seismic volume a series of sample attributes is calculated. The objective of this study is to derive a set of attributes and the target log values. The selected set is determined by a process of forward stepwise regression. The analysis can be linear or nonlinear. In the linear mode the method consists of a series of weights derived by least-square minimization. In the nonlinear mode, a neural network is trained using the select attributes as inputs. In this case we used a probabilistic neural network PNN. The method is applied to a real data set from PEMEX. For better reservoir characterization the porosity distribution was estimated using both techniques. The case shown a continues improvement in the prediction of the porosity from the multiattribute to the neural network analysis. The improvement is in the training and the validation, which are important indicators of the reliability of the results. The neural network showed an improvement in resolution over the multiattribute analysis. The final maps provide more realistic results of the porosity distribution.

  3. Identification of complex systems by artificial neural networks. Applications to mechanical frictions

    International Nuclear Information System (INIS)

    Dominguez, Manuel

    1998-01-01

    In the frame of complex systems modelization, we describe in this report the contribution of neural networks to mechanical friction modelization. This thesis is divided in three parts, each one corresponding to every stage of the realized work. The first part takes stock of the properties of neural networks by replacing them in the statistic frame of learning theory (particularly: non-linear and non-parametric regression models) and by showing the existing links with other more 'classic' techniques from automatics. We show then how identification models can be integrated in the neural networks description as a larger nonlinear model class. A methodology of neural networks use have been developed. We focused on validation techniques using correlation functions for non-linear systems, and on the use of regularization methods. The second part deals with the problematic of friction in mechanical systems. Particularly, we present the main current identified physical phenomena, which are integrated in advanced friction modelization. Characterization of these phenomena allows us to state a priori knowledge to be used in the identification stage. We expose some of the most well-known friction models: Dahl's model, Reset Integrator and Canuda's dynamical model, which are then used in simulation studies. The last part links the former one by illustrating a real-world application: an electric jack from SFIM-Industries, used in the Very Large Telescope (VLT) control scheme. This part begins with physical system presentation. The results are compared with more 'classic' methods. We finish using neural networks compensation scheme in closed-loop control. (author) [fr

  4. An Approach for Pattern Recognition of EEG Applied in Prosthetic Hand Drive

    Directory of Open Access Journals (Sweden)

    Xiao-Dong Zhang

    2011-12-01

    Full Text Available For controlling the prosthetic hand by only electroencephalogram (EEG, it has become the hot spot in robotics research to set up a direct communication and control channel between human brain and prosthetic hand. In this paper, the EEG signal is analyzed based on multi-complicated hand activities. And then, two methods of EEG pattern recognition are investigated, a neural prosthesis hand system driven by BCI is set up, which can complete four kinds of actions (arm’s free state, arm movement, hand crawl, hand open. Through several times of off-line and on-line experiments, the result shows that the neural prosthesis hand system driven by BCI is reasonable and feasible, the C-support vector classifiers-based method is better than BP neural network on the EEG pattern recognition for multi-complicated hand activities.

  5. 38 CFR 17.149 - Sensori-neural aids.

    Science.gov (United States)

    2010-07-01

    ... 38 Pensions, Bonuses, and Veterans' Relief 1 2010-07-01 2010-07-01 false Sensori-neural aids. 17... Prosthetic, Sensory, and Rehabilitative Aids § 17.149 Sensori-neural aids. (a) Notwithstanding any other provision of this part, VA will furnish needed sensori-neural aids (i.e., eyeglasses, contact lenses...

  6. Study of functional viability of SU-8-based microneedles for neural applications

    International Nuclear Information System (INIS)

    Fernández, Luis J; Altuna, Ane; Tijero, Maria; Vilares, Roman; Berganzo, Javier; Blanco, F J; Gabriel, Gemma; Villa, Rosa; Rodríguez, Manuel J; Batlle, Montse

    2009-01-01

    This paper presents the design, fabrication, packaging and first test results of SU-8-based microneedles for neural applications. By the use of photolithography, sputtering and bonding techniques, polymer needles with integrated microchannels and electrodes have been successfully fabricated. The use of photolithography for the patterning of the fluidic channel integrated in the needle allows the design of multiple outlet ports at the needle tip, minimizing the possibility of being blocked by the tissue. Furthermore, the flexibility of the polymer reduces the risk of fracture and tissue damage once the needle is inserted, while it is still rigid enough to allow a perfect insertion into the neural tissue. Fluidic and electric characterization of the microneedles has shown their viability for drug delivery and monitoring in neural applications. First drug delivery tests in ex vivo tissue demonstrated the functional viability of the needle to deliver drugs to precise points. Furthermore, in vivo experiments have demonstrated lower associated damages during insertion than those by stereotaxic standard needles

  7. Application of neural network in market segmentation: A review on recent trends

    Directory of Open Access Journals (Sweden)

    Manojit Chattopadhyay

    2012-04-01

    Full Text Available Despite the significance of Artificial Neural Network (ANN algorithm to market segmentation, there is a need of a comprehensive literature review and a classification system for it towards identification of future trend of market segmentation research. The present work is the first identifiable academic literature review of the application of neural network based techniques to segmentation. Our study has provided an academic database of literature between the periods of 2000–2010 and proposed a classification scheme for the articles. One thousands (1000 articles have been identified, and around 100 relevant selected articles have been subsequently reviewed and classified based on the major focus of each paper. Findings of this study indicated that the research area of ANN based applications are receiving most research attention and self organizing map based applications are second in position to be used in segmentation. The commonly used models for market segmentation are data mining, intelligent system etc. Our analysis furnishes a roadmap to guide future research and aid knowledge accretion and establishment pertaining to the application of ANN based techniques in market segmentation. Thus the present work will significantly contribute to both the industry and academic research in business and marketing as a sustainable valuable knowledge source of market segmentation with the future trend of ANN application in segmentation.

  8. Computer Aided Facial Prosthetics Manufacturing System

    Directory of Open Access Journals (Sweden)

    Peng H.K.

    2016-01-01

    Full Text Available Facial deformities can impose burden to the patient. There are many solutions for facial deformities such as plastic surgery and facial prosthetics. However, current fabrication method of facial prosthetics is high-cost and time consuming. This study aimed to identify a new method to construct a customized facial prosthetic. A 3D scanner, computer software and 3D printer were used in this study. Results showed that the new developed method can be used to produce a customized facial prosthetics. The advantages of the developed method over the conventional process are low cost, reduce waste of material and pollution in order to meet the green concept.

  9. Circuit For Control Of Electromechanical Prosthetic Hand

    Science.gov (United States)

    Bozeman, Richard J., Jr.

    1995-01-01

    Proposed circuit for control of electromechanical prosthetic hand derives electrical control signals from shoulder movements. Updated, electronic version of prosthesis, that includes two hooklike fingers actuated via cables from shoulder harness. Circuit built around favored shoulder harness, provides more dexterous movement, without incurring complexity of computer-controlled "bionic" or hydraulically actuated devices. Additional harness and potentiometer connected to similar control circuit mounted on other shoulder. Used to control stepping motor rotating hand about prosthetic wrist to one of number of angles consistent with number of digital outputs. Finger-control signals developed by circuit connected to first shoulder harness transmitted to prosthetic hand via sliprings at prosthetic wrist joint.

  10. Study on application of adaptive fuzzy control and neural network in the automatic leveling system

    Science.gov (United States)

    Xu, Xiping; Zhao, Zizhao; Lan, Weiyong; Sha, Lei; Qian, Cheng

    2015-04-01

    This paper discusses the adaptive fuzzy control and neural network BP algorithm in large flat automatic leveling control system application. The purpose is to develop a measurement system with a flat quick leveling, Make the installation on the leveling system of measurement with tablet, to be able to achieve a level in precision measurement work quickly, improve the efficiency of the precision measurement. This paper focuses on the automatic leveling system analysis based on fuzzy controller, Use of the method of combining fuzzy controller and BP neural network, using BP algorithm improve the experience rules .Construct an adaptive fuzzy control system. Meanwhile the learning rate of the BP algorithm has also been run-rate adjusted to accelerate convergence. The simulation results show that the proposed control method can effectively improve the leveling precision of automatic leveling system and shorten the time of leveling.

  11. Parzen neural networks: Fundamentals, properties, and an application to forensic anthropology.

    Science.gov (United States)

    Trentin, Edmondo; Lusnig, Luca; Cavalli, Fabio

    2018-01-01

    A novel, unsupervised nonparametric model of multivariate probability density functions (pdf) is introduced, namely the Parzen neural network (PNN). The PNN is intended to overcome the major limitations of traditional (either statistical or neural) pdf estimation techniques. Besides being profitably simple, the PNN turns out to have nice properties in terms of unbiased modeling capability, asymptotic convergence, and efficiency at test time. Several matters pertaining the practical application of the PNN are faced in the paper, too. Experiments are reported, involving (i) synthetic datasets, and (ii) a challenging sex determination task from 1400 scout-view CT-scan images of human crania. Incidentally, the empirical evidence entails also some conclusions of high anthropological relevance. Copyright © 2017 Elsevier Ltd. All rights reserved.

  12. Application of fuzzy neural network technologies in management of transport and logistics processes in Arctic

    Science.gov (United States)

    Levchenko, N. G.; Glushkov, S. V.; Sobolevskaya, E. Yu; Orlov, A. P.

    2018-05-01

    The method of modeling the transport and logistics process using fuzzy neural network technologies has been considered. The analysis of the implemented fuzzy neural network model of the information management system of transnational multimodal transportation of the process showed the expediency of applying this method to the management of transport and logistics processes in the Arctic and Subarctic conditions. The modular architecture of this model can be expanded by incorporating additional modules, since the working conditions in the Arctic and the subarctic themselves will present more and more realistic tasks. The architecture allows increasing the information management system, without affecting the system or the method itself. The model has a wide range of application possibilities, including: analysis of the situation and behavior of interacting elements; dynamic monitoring and diagnostics of management processes; simulation of real events and processes; prediction and prevention of critical situations.

  13. The applications of deep neural networks to sdBV classification

    Science.gov (United States)

    Boudreaux, Thomas M.

    2017-12-01

    With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in industry for years now, allows for advanced feature detection in minimally prepared datasets at very high speeds; however, despite the advantages of this method, its application to astrophysics has not yet been extensively explored. This dearth may be due to a lack of training data available to researchers. Here we generate synthetic data loosely mimicking the properties of acoustic mode pulsating stars and we show that two separate paradigms of deep learning - the Artificial Neural Network And the Convolutional Neural Network - can both be used to classify this synthetic data effectively. And that additionally this classification can be performed at relatively high levels of accuracy with minimal time spent adjusting network hyperparameters.

  14. Multiple Linear Regression Model Based on Neural Network and Its Application in the MBR Simulation

    Directory of Open Access Journals (Sweden)

    Chunqing Li

    2012-01-01

    Full Text Available The computer simulation of the membrane bioreactor MBR has become the research focus of the MBR simulation. In order to compensate for the defects, for example, long test period, high cost, invisible equipment seal, and so forth, on the basis of conducting in-depth study of the mathematical model of the MBR, combining with neural network theory, this paper proposed a three-dimensional simulation system for MBR wastewater treatment, with fast speed, high efficiency, and good visualization. The system is researched and developed with the hybrid programming of VC++ programming language and OpenGL, with a multifactor linear regression model of affecting MBR membrane fluxes based on neural network, applying modeling method of integer instead of float and quad tree recursion. The experiments show that the three-dimensional simulation system, using the above models and methods, has the inspiration and reference for the future research and application of the MBR simulation technology.

  15. Comments on "The multisynapse neural network and its application to fuzzy clustering".

    Science.gov (United States)

    Yu, Jian; Hao, Pengwei

    2005-05-01

    In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

  16. Carbon based prosthetic devices

    Energy Technology Data Exchange (ETDEWEB)

    Devlin, D.J.; Carroll, D.W.; Barbero, R.S.; Archuleta, T. [Los Alamos National Lab., NM (US); Klawitter, J.J.; Ogilvie, W.; Strzepa, P. [Ascension Orthopedics (US); Cook, S.D. [Tulane Univ., New Orleans, LA (US). School of Medicine

    1998-12-31

    This is the final report of a one-year, Laboratory Directed Research and Development (LDRD) project at the Los Alamos National Laboratory (LANL). The project objective was to evaluate the use of carbon/carbon-fiber-reinforced composites for use in endoprosthetic devices. The application of these materials for the metacarpophalangeal (MP) joints of the hand was investigated. Issues concerning mechanical properties, bone fixation, biocompatibility, and wear are discussed. A system consisting of fiber reinforced materials with a pyrolytic carbon matrix and diamond-like, carbon-coated wear surfaces was developed. Processes were developed for the chemical vapor infiltration (CVI) of pyrolytic carbon into porous fiber preforms with the ability to tailor the outer porosity of the device to provide a surface for bone in-growth. A method for coating diamond-like carbon (DLC) on the articulating surface by plasma-assisted chemical vapor deposition (CVD) was developed. Preliminary results on mechanical properties of the composite system are discussed and initial biocompatibility studies were performed.

  17. Broadband Prosthetic Interfaces: Combining Nerve Transfers and Implantable Multichannel EMG Technology to Decode Spinal Motor Neuron Activity

    Directory of Open Access Journals (Sweden)

    Konstantin D. Bergmeister

    2017-07-01

    Full Text Available Modern robotic hands/upper limbs may replace multiple degrees of freedom of extremity function. However, their intuitive use requires a high number of control signals, which current man-machine interfaces do not provide. Here, we discuss a broadband control interface that combines targeted muscle reinnervation, implantable multichannel electromyographic sensors, and advanced decoding to address the increasing capabilities of modern robotic limbs. With targeted muscle reinnervation, nerves that have lost their targets due to an amputation are surgically transferred to residual stump muscles to increase the number of intuitive prosthetic control signals. This surgery re-establishes a nerve-muscle connection that is used for sensing nerve activity with myoelectric interfaces. Moreover, the nerve transfer determines neurophysiological effects, such as muscular hyper-reinnervation and cortical reafferentation that can be exploited by the myoelectric interface. Modern implantable multichannel EMG sensors provide signals from which it is possible to disentangle the behavior of single motor neurons. Recent studies have shown that the neural drive to muscles can be decoded from these signals and thereby the user's intention can be reliably estimated. By combining these concepts in chronic implants and embedded electronics, we believe that it is in principle possible to establish a broadband man-machine interface, with specific applications in prosthesis control. This perspective illustrates this concept, based on combining advanced surgical techniques with recording hardware and processing algorithms. Here we describe the scientific evidence for this concept, current state of investigations, challenges, and alternative approaches to improve current prosthetic interfaces.

  18. Application of neural network technology to nuclear plant thermal efficiency improvement

    International Nuclear Information System (INIS)

    Doremus, Rick; Allen Ho, S.; Bailey, James V.; Roman, Harry

    2004-01-01

    to determine which plant systems and components should be manipulated to increase electric output. Each parameter from the current data is replaced, one at a time, with an optimum value found among all the data used to train the neural networks. Each new data record, with one altered parameter, is then processed through the neural network, which calculates a predicted electric output These predictions are then ranked by order of increased electric output. Thermal Performance Engineers then review and perform selected recommendations An initial feasibility study was recently completed. The next phase of the project is the creation of a demonstration application to be tested at Salem Nuclear Generating Station. (author)

  19. Modeling Markov Switching ARMA-GARCH Neural Networks Models and an Application to Forecasting Stock Returns

    Directory of Open Access Journals (Sweden)

    Melike Bildirici

    2014-01-01

    Full Text Available The study has two aims. The first aim is to propose a family of nonlinear GARCH models that incorporate fractional integration and asymmetric power properties to MS-GARCH processes. The second purpose of the study is to augment the MS-GARCH type models with artificial neural networks to benefit from the universal approximation properties to achieve improved forecasting accuracy. Therefore, the proposed Markov-switching MS-ARMA-FIGARCH, APGARCH, and FIAPGARCH processes are further augmented with MLP, Recurrent NN, and Hybrid NN type neural networks. The MS-ARMA-GARCH family and MS-ARMA-GARCH-NN family are utilized for modeling the daily stock returns in an emerging market, the Istanbul Stock Index (ISE100. Forecast accuracy is evaluated in terms of MAE, MSE, and RMSE error criteria and Diebold-Mariano equal forecast accuracy tests. The results suggest that the fractionally integrated and asymmetric power counterparts of Gray’s MS-GARCH model provided promising results, while the best results are obtained for their neural network based counterparts. Further, among the models analyzed, the models based on the Hybrid-MLP and Recurrent-NN, the MS-ARMA-FIAPGARCH-HybridMLP, and MS-ARMA-FIAPGARCH-RNN provided the best forecast performances over the baseline single regime GARCH models and further, over the Gray’s MS-GARCH model. Therefore, the models are promising for various economic applications.

  20. Gait Phases Recognition from Accelerations and Ground Reaction Forces: Application of Neural Networks

    Directory of Open Access Journals (Sweden)

    S. Rafajlović

    2009-06-01

    Full Text Available The goal of this study was to test the applicability of accelerometer as the sensor for assessment of the walking. We present here the comparison of gait phases detected from the data recorded by force sensing resistors mounted in the shoe insoles, non-processed acceleration and processed acceleration perpendicular to the direction of the foot. The gait phases in all three cases were detected by means of a neural network. The output from the neural network was the gait phase, while the inputs were data from the sensors. The results show that the errors were in the ranges: 30 ms (2.7% – force sensors; 150 ms (13.6% – nonprocessed acceleration, and 120 ms (11% – processed acceleration data. This result suggests that it is possible to use the accelerometer as the gait phase detector, however, with the knowledge that the gait phases are time shifted for about 100 ms with respect the neural network predicted times.

  1. Simulation Study on the Application of the Generalized Entropy Concept in Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Krzysztof Gajowniczek

    2018-04-01

    Full Text Available Artificial neural networks are currently one of the most commonly used classifiers and over the recent years they have been successfully used in many practical applications, including banking and finance, health and medicine, engineering and manufacturing. A large number of error functions have been proposed in the literature to achieve a better predictive power. However, only a few works employ Tsallis statistics, although the method itself has been successfully applied in other machine learning techniques. This paper undertakes the effort to examine the q -generalized function based on Tsallis statistics as an alternative error measure in neural networks. In order to validate different performance aspects of the proposed function and to enable identification of its strengths and weaknesses the extensive simulation was prepared based on the artificial benchmarking dataset. The results indicate that Tsallis entropy error function can be successfully introduced in the neural networks yielding satisfactory results and handling with class imbalance, noise in data or use of non-informative predictors.

  2. Large-scale multielectrode recording and stimulation of neural activity

    International Nuclear Information System (INIS)

    Sher, A.; Chichilnisky, E.J.; Dabrowski, W.; Grillo, A.A.; Grivich, M.; Gunning, D.; Hottowy, P.; Kachiguine, S.; Litke, A.M.; Mathieson, K.; Petrusca, D.

    2007-01-01

    Large circuits of neurons are employed by the brain to encode and process information. How this encoding and processing is carried out is one of the central questions in neuroscience. Since individual neurons communicate with each other through electrical signals (action potentials), the recording of neural activity with arrays of extracellular electrodes is uniquely suited for the investigation of this question. Such recordings provide the combination of the best spatial (individual neurons) and temporal (individual action-potentials) resolutions compared to other large-scale imaging methods. Electrical stimulation of neural activity in turn has two very important applications: it enhances our understanding of neural circuits by allowing active interactions with them, and it is a basis for a large variety of neural prosthetic devices. Until recently, the state-of-the-art in neural activity recording systems consisted of several dozen electrodes with inter-electrode spacing ranging from tens to hundreds of microns. Using silicon microstrip detector expertise acquired in the field of high-energy physics, we created a unique neural activity readout and stimulation framework that consists of high-density electrode arrays, multi-channel custom-designed integrated circuits, a data acquisition system, and data-processing software. Using this framework we developed a number of neural readout and stimulation systems: (1) a 512-electrode system for recording the simultaneous activity of as many as hundreds of neurons, (2) a 61-electrode system for electrical stimulation and readout of neural activity in retinas and brain-tissue slices, and (3) a system with telemetry capabilities for recording neural activity in the intact brain of awake, naturally behaving animals. We will report on these systems, their various applications to the field of neurobiology, and novel scientific results obtained with some of them. We will also outline future directions

  3. Undergraduate prosthetics and orthotics teaching methods: A baseline for international comparison.

    Science.gov (United States)

    Aminian, Gholamreza; O'Toole, John M; Mehraban, Afsoon Hassani

    2015-08-01

    Education of Prosthetics and Orthotics is a relatively recent professional program. While there has been some work on various teaching methods and strategies in international medical education, limited publication exists within prosthetics and orthotics. To identify the teaching and learning methods that are used in Bachelor-level prosthetics and orthotics programs that are given highest priority by expert prosthetics and orthotics instructors from regions enjoying a range of economic development. Mixed method. The study partly documented by this article utilized a mixed method approach (qualitative and quantitative methods) within which each phase provided data for other phases. It began with analysis of prosthetics and orthotics curricula documents, which was followed by a broad survey of instructors in this field and then a modified Delphi process. The expert instructors who participated in this study gave high priority to student-centered, small group methods that encourage critical thinking and may lead to lifelong learning. Instructors from more developed nations placed higher priority on student's independent acquisition of prosthetics and orthotics knowledge, particularly in clinical training. Application of student-centered approaches to prosthetics and orthotics programs may be preferred by many experts, but there appeared to be regional differences in the priority given to different teaching methods. The results of this study identify the methods of teaching that are preferred by expert prosthetics and orthotics instructors from a variety of regions. This treatment of current instructional techniques may inform instructor choice of teaching methods that impact the quality of education and improve the professional skills of students. © The International Society for Prosthetics and Orthotics 2014.

  4. A design philosophy for multi-layer neural networks with applications to robot control

    Science.gov (United States)

    Vadiee, Nader; Jamshidi, MO

    1989-01-01

    A system is proposed which receives input information from many sensors that may have diverse scaling, dimension, and data representations. The proposed system tolerates sensory information with faults. The proposed self-adaptive processing technique has great promise in integrating the techniques of artificial intelligence and neural networks in an attempt to build a more intelligent computing environment. The proposed architecture can provide a detailed decision tree based on the input information, information stored in a long-term memory, and the adapted rule-based knowledge. A mathematical model for analysis will be obtained to validate the cited hypotheses. An extensive software program will be developed to simulate a typical example of pattern recognition problem. It is shown that the proposed model displays attention, expectation, spatio-temporal, and predictory behavior which are specific to the human brain. The anticipated results of this research project are: (1) creation of a new dynamic neural network structure, and (2) applications to and comparison with conventional multi-layer neural network structures. The anticipated benefits from this research are vast. The model can be used in a neuro-computer architecture as a building block which can perform complicated, nonlinear, time-varying mapping from a multitude of input excitory classes to an output or decision environment. It can be used for coordinating different sensory inputs and past experience of a dynamic system and actuating signals. The commercial applications of this project can be the creation of a special-purpose neuro-computer hardware which can be used in spatio-temporal pattern recognitions in such areas as air defense systems, e.g., target tracking, and recognition. Potential robotics-related applications are trajectory planning, inverse dynamics computations, hierarchical control, task-oriented control, and collision avoidance.

  5. Parallelization of learning problems by artificial neural networks. Application in external radiotherapy

    International Nuclear Information System (INIS)

    Sauget, M.

    2007-12-01

    This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

  6. The application of neural network techniques to magnetic and optical inverse problems

    International Nuclear Information System (INIS)

    Jones, H.V.

    2000-12-01

    The processing power of the computer has increased at unimaginable rates over the last few decades. However, even today's fastest computer can take several hours to find solutions to some mathematical problems; and there are instances where a high powered supercomputer may be impractical, with the need for near instant solutions just as important (such as in an on-line testing system). This led us to believe that such complex problems could be solved using a novel approach, whereby the system would have prior knowledge about the expected solutions through a process of learning. One method of approaching this kind of problem is through the use of machine learning. Just as a human can be trained and is able to learn from past experiences, a machine is can do just the same. This is the concept of neural networks. The research which was conducted involves the investigation of various neural network techniques, and their applicability to solve some known complex inverse problems in the field of magnetic and optical recording. In some cases a comparison is also made to more conventional methods of solving the problems, from which it was possible to outline some key advantages of using a neural network approach. We initially investigated the application of neural networks to transverse susceptibility data in order to determine anisotropy distributions. This area of research is proving to be very important, as it gives us information about the switching field distribution, which then determines the minimum transition width achievable in a medium, and affects the overwrite characteristics of the media. Secondly, we investigated a similar situation, but applied to an optical problem. This involved the determination of important compact disc parameters from the diffraction pattern of a laser from a disc. This technique was then intended for use in an on-line testing system. Finally we investigated another area of neural networks with the analysis of magnetisation maps and

  7. Application of artificial neural network with extreme learning machine for economic growth estimation

    Science.gov (United States)

    Milačić, Ljubiša; Jović, Srđan; Vujović, Tanja; Miljković, Jovica

    2017-01-01

    The purpose of this research is to develop and apply the artificial neural network (ANN) with extreme learning machine (ELM) to forecast gross domestic product (GDP) growth rate. The economic growth forecasting was analyzed based on agriculture, manufacturing, industry and services value added in GDP. The results were compared with ANN with back propagation (BP) learning approach since BP could be considered as conventional learning methodology. The reliability of the computational models was accessed based on simulation results and using several statistical indicators. Based on results, it was shown that ANN with ELM learning methodology can be applied effectively in applications of GDP forecasting.

  8. Radial basis function neural networks with sequential learning MRAN and its applications

    CERN Document Server

    Sundararajan, N; Wei Lu Ying

    1999-01-01

    This book presents in detail the newly developed sequential learning algorithm for radial basis function neural networks, which realizes a minimal network. This algorithm, created by the authors, is referred to as Minimal Resource Allocation Networks (MRAN). The book describes the application of MRAN in different areas, including pattern recognition, time series prediction, system identification, control, communication and signal processing. Benchmark problems from these areas have been studied, and MRAN is compared with other algorithms. In order to make the book self-contained, a review of t

  9. The application of neural networks for optimization of the configuration of fuel assemblies in PWR reactors

    International Nuclear Information System (INIS)

    Sadighi, M.; Setayeshi, S.; Salehi, A.A.

    2002-01-01

    This paper presents a new method to solve the problem of finding the best configuration of fuel assemblies in a PWR (Pressurized Water Reactor) core. Finding an optimum solution requires a huge amount of calculations in classical methods. It has been shown that the application of continuous Hop field neural network accompanied by the Simulated Annealing method to this problem not only reduces the volume of the calculations, but also guarantees finding the best solution. In this study flattening of neutron flux inside the reactor core of Brusher NPP is considered as an objective function. The result shows the optimum core configuration which is in agreement with the pattern proposed by the designer

  10. Fuzzy logic and artificial neural networks for nuclear power plant applications

    International Nuclear Information System (INIS)

    Berkan, R.C.; Eryurek, E.; Upadhyaya, B.R.

    1992-01-01

    This paper discusses the feasibility of applying fuzzy logic and neural networks to plant-wide monitoring, diagnostics, and control problems. Different data sets are gathered from several sources including two commercial Pressurized Water Reactors (PWR), the Experimental Breeder Reactor-II (EBR-II), and the conceptual design of Modular Liquid-Metal Reactor (PRISM). These data sets are used to illustrate applications to operating processes, and to PRISM design. The results show that the artificial intelligence approach to a number of operational tasks can considerably improve the safety and availability of nuclear power generation

  11. Prosthetic

    Directory of Open Access Journals (Sweden)

    Pokpong Amornvit

    2014-01-01

    Full Text Available Ocular trauma can be caused by road traffic accidents, falls, assaults, or work-related accidents. Enucleation is often indicated after ocular injury or for the treatment of intraocular tumors, severe ocular infections, and painful blind eyes. Rehabilitation of an enucleated socket without an intraocular implant or with an inappropriately sized implant can result in superior sulcus deepening, enophthalmos, ptosis, ectropion, and lower lid laxity, which are collectively known as post-enucleation socket syndrome. This clinical report describes the rehabilitation of post-enucleation socket syndrome with a modified ocular prosthesis. Modifications to the ocular prosthesis were performed to correct the ptosis, superior sulcus deepening, and enophthalmos. The rehabilitation procedure produced satisfactory results.

  12. Application of a hybrid model of neural networks and genetic algorithms to evaluate landslide susceptibility

    Science.gov (United States)

    Wang, H. B.; Li, J. W.; Zhou, B.; Yuan, Z. Q.; Chen, Y. P.

    2013-03-01

    is 93.02%, whereas units without landslide occurrence are predicted with an accuracy of 81.13%. To sum up, the verification shows satisfactory agreement with an accuracy of 86.46% between the susceptibility map and the landslide locations. In the landslide susceptibility assessment, ten new slopes were predicted to show potential for failure, which can be confirmed by the engineering geological conditions of these slopes. It was also observed that some disadvantages could be overcome in the application of the neural networks with back propagation, for example, the low convergence rate and local minimum, after the network was optimized using genetic algorithms. To conclude, neural networks with back propagation that are optimized by genetic algorithms are an effective method to predict landslide susceptibility with high accuracy.

  13. Improving Pattern Recognition and Neural Network Algorithms with Applications to Solar Panel Energy Optimization

    Science.gov (United States)

    Zamora Ramos, Ernesto

    Artificial Intelligence is a big part of automation and with today's technological advances, artificial intelligence has taken great strides towards positioning itself as the technology of the future to control, enhance and perfect automation. Computer vision includes pattern recognition and classification and machine learning. Computer vision is at the core of decision making and it is a vast and fruitful branch of artificial intelligence. In this work, we expose novel algorithms and techniques built upon existing technologies to improve pattern recognition and neural network training, initially motivated by a multidisciplinary effort to build a robot that helps maintain and optimize solar panel energy production. Our contributions detail an improved non-linear pre-processing technique to enhance poorly illuminated images based on modifications to the standard histogram equalization for an image. While the original motivation was to improve nocturnal navigation, the results have applications in surveillance, search and rescue, medical imaging enhancing, and many others. We created a vision system for precise camera distance positioning motivated to correctly locate the robot for capture of solar panel images for classification. The classification algorithm marks solar panels as clean or dirty for later processing. Our algorithm extends past image classification and, based on historical and experimental data, it identifies the optimal moment in which to perform maintenance on marked solar panels as to minimize the energy and profit loss. In order to improve upon the classification algorithm, we delved into feedforward neural networks because of their recent advancements, proven universal approximation and classification capabilities, and excellent recognition rates. We explore state-of-the-art neural network training techniques offering pointers and insights, culminating on the implementation of a complete library with support for modern deep learning architectures

  14. Application of Artificial Neural Networks to Rainfall Forecasting in Queensland, Australia

    Institute of Scientific and Technical Information of China (English)

    John ABBOT; Jennifer MAROHASY

    2012-01-01

    In this study,the application of artificial intelligence to monthly and seasonal rainfall forecasting in Queensland,Australia,was assessed by inputting recognized climate indices,monthly historical rainfall data,and atmospheric temperatures into a prototype stand-alone,dynamic,recurrent,time-delay,artificial neural network.Outputs,as monthly rainfall forecasts 3 months in advance for the period 1993 to 2009,were compared with observed rainfall data using time-series plots,root mean squared error (RMSE),and Pearson correlation coefficients.A comparison of RMSE values with forecasts generated by the Australian Bureau of Meteorology's Predictive Ocean Atmosphere Model for Australia (POAMA)-1.5 general circulation model (GCM) indicated that the prototype achieved a lower RMSE for 16 of the 17 sites compared.The application of artificial neural networks to rainfall forecasting was reviewed.The prototype design is considered preliminary,with potential for significant improvement such as inclusion of output from GCMs and experimentation with other input attributes.

  15. Neural prostheses in clinical applications--trends from precision mechanics towards biomedical microsystems in neurological rehabilitation.

    Science.gov (United States)

    Stieglitz, T; Schuettler, M; Koch, K P

    2004-04-01

    Neural prostheses partially restore body functions by technical nerve excitation after trauma or neurological diseases. External devices and implants have been developed since the early 1960s for many applications. Several systems have reached nowadays clinical practice: Cochlea implants help the deaf to hear, micturition is induced by bladder stimulators in paralyzed persons and deep brain stimulation helps patients with Parkinson's disease to participate in daily life again. So far, clinical neural prostheses are fabricated with means of precision mechanics. Since microsystem technology opens the opportunity to design and develop complex systems with a high number of electrodes to interface with the nervous systems, the opportunity for selective stimulation and complex implant scenarios seems to be feasible in the near future. The potentials and limitations with regard to biomedical microdevices are introduced and discussed in this paper. Target specifications are derived from existing implants and are discussed on selected applications that has been investigated in experimental research: a micromachined implant to interface a nerve stump with a sieve electrode, cuff electrodes with integrated electronics, and an epiretinal vision prosthesis.

  16. Application of RBF neural network improved by peak density function in intelligent color matching of wood dyeing

    International Nuclear Information System (INIS)

    Guan, Xuemei; Zhu, Yuren; Song, Wenlong

    2016-01-01

    According to the characteristics of wood dyeing, we propose a predictive model of pigment formula for wood dyeing based on Radial Basis Function (RBF) neural network. In practical application, however, it is found that the number of neurons in the hidden layer of RBF neural network is difficult to determine. In general, we need to test several times according to experience and prior knowledge, which is lack of a strict design procedure on theoretical basis. And we also don’t know whether the RBF neural network is convergent. This paper proposes a peak density function to determine the number of neurons in the hidden layer. In contrast to existing approaches, the centers and the widths of the radial basis function are initialized by extracting the features of samples. So the uncertainty caused by random number when initializing the training parameters and the topology of RBF neural network is eliminated. The average relative error of the original RBF neural network is 1.55% in 158 epochs. However, the average relative error of the RBF neural network which is improved by peak density function is only 0.62% in 50 epochs. Therefore, the convergence rate and approximation precision of the RBF neural network are improved significantly.

  17. Prospects of application of artificial neural networks for forecasting of cargo transportation volume in transport systems

    Directory of Open Access Journals (Sweden)

    D. T. Yakupov

    2017-01-01

    Full Text Available The purpose of research – to identify the prospects for the use of neural network approach in relation to the tasks of economic forecasting of logistics performance, in particular of volume freight traffic in the transport system promiscuous regional freight traffic, as well as to substantiate the effectiveness of the use of artificial neural networks (ANN, as compared with the efficiency of traditional extrapolative methods of forecasting. The authors consider the possibility of forecasting to use ANN for these economic indicators not as an alternative to the traditional methods of statistical forecasting, but as one of the available simple means for solving complex problems.Materials and methods. When predicting the ANN, three methods of learning were used: 1 the Levenberg-Marquardt algorithm-network training stops when the generalization ceases to improve, which is shown by the increase in the mean square error of the output value; 2 Bayes regularization method - network training is stopped in accordance with the minimization of adaptive weights; 3 the method of scaled conjugate gradients, which is used to find the local extremum of a function on the basis of information about its values and gradient. The Neural Network Toolbox package is used for forecasting. The neural network model consists of a hidden layer of neurons with a sigmoidal activation function and an output neuron with a linear activation function, the input values of the dynamic time series, and the predicted value is removed from the output. For a more objective assessment of the prospects of the ANN application, the results of the forecast are presented in comparison with the results obtained in predicting the method of exponential smoothing.Results. When predicting the volumes of freight transportation by rail, satisfactory indicators of the verification of forecasting by both the method of exponential smoothing and ANN had been obtained, although the neural network

  18. Synchronization of Markovian jumping inertial neural networks and its applications in image encryption.

    Science.gov (United States)

    Prakash, M; Balasubramaniam, P; Lakshmanan, S

    2016-11-01

    This study is mainly concerned with the problem on synchronization criteria for Markovian jumping time delayed bidirectional associative memory neural networks and their applications in secure image communications. Based on the variable transformation method, the addressed second order differential equations are transformed into first order differential equations. Then, by constructing a suitable Lyapunov-Krasovskii functional and based on integral inequalities, the criteria which ensure the synchronization between the uncontrolled system and controlled system are established through designed feedback controllers and linear matrix inequalities. Further, the proposed results proved that the error system is globally asymptotically stable in the mean square. Moreover, numerical illustrations are provided to validate the effectiveness of the derived analytical results. Finally, the application of addressed system is explored via image encryption/decryption process. Copyright © 2016 Elsevier Ltd. All rights reserved.

  19. Applications of artificial neural networks for thermal analysis of heat exchangers - A review

    International Nuclear Information System (INIS)

    Mohanraj, M.; Jayaraj, S.; Muraleedharan, C.

    2015-01-01

    Artificial neural networks (ANN) have been widely used for thermal analysis of heat exchangers during the last two decades. In this paper, the applications of ANN for thermal analysis of heat exchangers are reviewed. The reported investigations on thermal analysis of heat exchangers are categorized into four major groups, namely (i) modeling of heat exchangers, (ii) estimation of heat exchanger parameters, (iii) estimation of phase change characteristics in heat exchangers and (iv) control of heat exchangers. Most of the papers related to the applications of ANN for thermal analysis of heat exchangers are discussed. The limitations of ANN for thermal analysis of heat exchangers and its further research needs in this field are highlighted. ANN is gaining popularity as a tool, which can be successfully used for the thermal analysis of heat exchangers with acceptable accuracy. (authors)

  20. Engineering applications of fpgas chaotic systems, artificial neural networks, random number generators, and secure communication systems

    CERN Document Server

    Tlelo-Cuautle, Esteban; de la Fraga, Luis Gerardo

    2016-01-01

    This book offers readers a clear guide to implementing engineering applications with FPGAs, from the mathematical description to the hardware synthesis, including discussion of VHDL programming and co-simulation issues. Coverage includes FPGA realizations such as: chaos generators that are described from their mathematical models; artificial neural networks (ANNs) to predict chaotic time series, for which a discussion of different ANN topologies is included, with different learning techniques and activation functions; random number generators (RNGs) that are realized using different chaos generators, and discussions of their maximum Lyapunov exponent values and entropies. Finally, optimized chaotic oscillators are synchronized and realized to implement a secure communication system that processes black and white and grey-scale images. In each application, readers will find VHDL programming guidelines and computer arithmetic issues, along with co-simulation examples with Active-HDL and Simulink. Readers will b...

  1. Application of neural networks to the petroleum refining industry; Aplicando redes neurais a industria de refino de petroleo

    Energy Technology Data Exchange (ETDEWEB)

    Silva, R M.C.F. da [PETROBRAS, Rio de Janeiro, RJ (Brazil); Chaves, C. [Fundacao Gorceix, Belo Horizonte, MG (Brazil)

    2000-07-01

    Neural Network technology is an approach for describing behavior from process data, using mathematical algorithms and statistical techniques. The use of Neural Network in industrial process modeling and property estimation of feedstocks or products, is increasing in several kinds of chemical industries. This paper comments about critical successful factors, advantages and disadvantages of this methodology. Moreover, it presents some applications in Hydrotreating Process of the petroleum refining industry. In Hydrotreating of feedstocks, knowledge about characteristics of process regarding product property estimation, hydrogen consumption and removal of contaminants (sulfur, nitrogen, aromatics), are very important to process optimization, product specification and environment protection. The Neural Network technique has been used to model the behaviour of the chemical hydrogen consumption, the conversions of the hydrogenation of aromatic hydrocarbons, hydrodesulfurization and hydro denitrogenation reactions and the physical properties of product with operational conditions and feedstock properties. In addition, Neural Networks have been built to predict the cetane number of feedstocks. (author)

  2. Embedded System for Prosthetic Control Using Implanted Neuromuscular Interfaces Accessed Via an Osseointegrated Implant.

    Science.gov (United States)

    Mastinu, Enzo; Doguet, Pascal; Botquin, Yohan; Hakansson, Bo; Ortiz-Catalan, Max

    2017-08-01

    Despite the technological progress in robotics achieved in the last decades, prosthetic limbs still lack functionality, reliability, and comfort. Recently, an implanted neuromusculoskeletal interface built upon osseointegration was developed and tested in humans, namely the Osseointegrated Human-Machine Gateway. Here, we present an embedded system to exploit the advantages of this technology. Our artificial limb controller allows for bioelectric signals acquisition, processing, decoding of motor intent, prosthetic control, and sensory feedback. It includes a neurostimulator to provide direct neural feedback based on sensory information. The system was validated using real-time tasks characterization, power consumption evaluation, and myoelectric pattern recognition performance. Functionality was proven in a first pilot patient from whom results of daily usage were obtained. The system was designed to be reliably used in activities of daily living, as well as a research platform to monitor prosthesis usage and training, machine-learning-based control algorithms, and neural stimulation paradigms.

  3. Magnetic Oculomotor Prosthetics for Acquired Nystagmus.

    Science.gov (United States)

    Nachev, Parashkev; Rose, Geoff E; Verity, David H; Manohar, Sanjay G; MacKenzie, Kelly; Adams, Gill; Theodorou, Maria; Pankhurst, Quentin A; Kennard, Christopher

    2017-10-01

    Acquired nystagmus, a highly symptomatic consequence of damage to the substrates of oculomotor control, often is resistant to pharmacotherapy. Although heterogeneous in its neural cause, its expression is unified at the effector-the eye muscles themselves-where physical damping of the oscillation offers an alternative approach. Because direct surgical fixation would immobilize the globe, action at a distance is required to damp the oscillation at the point of fixation, allowing unhindered gaze shifts at other times. Implementing this idea magnetically, herein we describe the successful implantation of a novel magnetic oculomotor prosthesis in a patient. Case report of a pilot, experimental intervention. A 49-year-old man with longstanding, medication-resistant, upbeat nystagmus resulting from a paraneoplastic syndrome caused by stage 2A, grade I, nodular sclerosing Hodgkin's lymphoma. We designed a 2-part, titanium-encased, rare-earth magnet oculomotor prosthesis, powered to damp nystagmus without interfering with the larger forces involved in saccades. Its damping effects were confirmed when applied externally. We proceeded to implant the device in the patient, comparing visual functions and high-resolution oculography before and after implantation and monitoring the patient for more than 4 years after surgery. We recorded Snellen visual acuity before and after intervention, as well as the amplitude, drift velocity, frequency, and intensity of the nystagmus in each eye. The patient reported a clinically significant improvement of 1 line of Snellen acuity (from 6/9 bilaterally to 6/6 on the left and 6/5-2 on the right), reflecting an objectively measured reduction in the amplitude, drift velocity, frequency, and intensity of the nystagmus. These improvements were maintained throughout a follow-up of 4 years and enabled him to return to paid employment. This work opens a new field of implantable therapeutic devices-oculomotor prosthetics-designed to modify eye

  4. An improved superconducting neural circuit and its application for a neural network solving a combinatorial optimization problem

    International Nuclear Information System (INIS)

    Onomi, T; Nakajima, K

    2014-01-01

    We have proposed a superconducting Hopfield-type neural network for solving the N-Queens problem which is one of combinatorial optimization problems. The sigmoid-shape function of a neuron output is represented by the output of coupled SQUIDs gate consisting of a single-junction and a double-junction SQUIDs. One of the important factors for an improvement of the network performance is an improvement of a threshold characteristic of a neuron circuit. In this paper, we report an improved design of coupled SQUID gates for a superconducting neural network. A step-like function with a steep threshold at a rising edge is desirable for a neuron circuit to solve a combinatorial optimization problem. A neuron circuit is composed of two coupled SQUIDs gates with a cascade connection in order to obtain such characteristics. The designed neuron circuit is fabricated by a 2.5 kA/cm 2 Nb/AlOx/Nb process. The operation of a fabricated neuron circuit is experimentally demonstrated. Moreover, we discuss about the performance of the neural network using the improved neuron circuits and delayed negative self-connections.

  5. Refining mass formulas for astrophysical applications: A Bayesian neural network approach

    Science.gov (United States)

    Utama, R.; Piekarewicz, J.

    2017-10-01

    Background: Exotic nuclei, particularly those near the drip lines, are at the core of one of the fundamental questions driving nuclear structure and astrophysics today: What are the limits of nuclear binding? Exotic nuclei play a critical role in both informing theoretical models as well as in our understanding of the origin of the heavy elements. Purpose: Our aim is to refine existing mass models through the training of an artificial neural network that will mitigate the large model discrepancies far away from stability. Methods: The basic paradigm of our two-pronged approach is an existing mass model that captures as much as possible of the underlying physics followed by the implementation of a Bayesian neural network (BNN) refinement to account for the missing physics. Bayesian inference is employed to determine the parameters of the neural network so that model predictions may be accompanied by theoretical uncertainties. Results: Despite the undeniable quality of the mass models adopted in this work, we observe a significant improvement (of about 40%) after the BNN refinement is implemented. Indeed, in the specific case of the Duflo-Zuker mass formula, we find that the rms deviation relative to experiment is reduced from σrms=0.503 MeV to σrms=0.286 MeV. These newly refined mass tables are used to map the neutron drip lines (or rather "drip bands") and to study a few critical r -process nuclei. Conclusions: The BNN approach is highly successful in refining the predictions of existing mass models. In particular, the large discrepancy displayed by the original "bare" models in regions where experimental data are unavailable is considerably quenched after the BNN refinement. This lends credence to our approach and has motivated us to publish refined mass tables that we trust will be helpful for future astrophysical applications.

  6. Design and evaluation of carbon nanofiber and silicon materials for neural implant applications

    Science.gov (United States)

    McKenzie, Janice L.

    Reduction of glial scar tissue around central nervous system implants is necessary for improved efficacy in chronic applications. Design of materials that possess tunable properties inspired by native biological tissue and elucidation of pertinent cellular interactions with these materials was the motivation for this study. Since nanoscale carbon fibers possess the fundamental dimensional similarities to biological tissue and have attractive material properties needed for neural biomaterial implants, this present study explored cytocompatibility of these materials as well as modifications to traditionally used silicon. On silicon materials, results indicated that nanoscale surface features reduced astrocyte functions, and could be used to guide neurite extension from PC12 cells. Similarly, it was determined that astrocyte functions (key cells in glial scar tissue formation) were reduced on smaller diameter carbon fibers (125 nm or less) while PC12 neurite extension was enhanced on smaller diameter carbon fibers (100 nm or less). Further studies implicated laminin adsorption as a key mechanism in enhancing astrocyte adhesion to larger diameter fibers and at the same time encouraging neurite extension on smaller diameter fibers. Polycarbonate urethane (PCU) was then used as a matrix material for the smaller diameter carbon fibers (100 and 60 nm). These composites proved very versatile since electrical and mechanical properties as well as cell functions and directionality could be influenced by changing bulk and surface composition and features of these matrices. When these composites were modified to be smooth at the micronscale and only rough at the nanoscale, P19 cells actually submerged philopodia, extensions, or whole cells bodies beneath the PCU in order to interact with the carbon nanofibers. These carbon nanofiber composites that have been formulated are a promising material to coat neural probes and thereby enhance functionality at the tissue interface. This

  7. Regenerative medicine using adult neural stem cells: the potential for diabetes therapy and other pharmaceutical applications

    Institute of Scientific and Technical Information of China (English)

    Tomoko Kuwabara; Makoto Asashima

    2012-01-01

    Neural stem cells (NSCs),which are responsible for continuous neurogenesis during the adult stage,are present in human adults.The typical neurogenic regions are the hippocampus and the subventricular zone; recent studies have revealed that NSCs also exist in the olfactory bulb.Olfactory bulb-derived neural stem cells (OB NSCs) have the potential to be used in therapeutic applications and can be easily harvested without harm to the patient.Through the combined influence of extrinsic cues and innate programming,adult neurogenesis is a finely regulated process occurring in a specialized cellular environment,a niche.Understanding the regulatory mechanisms of adult NSCs and their cellular niche is not only important to understand the physiological roles of neurogenesis in adulthood,but also to provide the knowledge necessary for developing new therapeutic applications using adult NSCs in other organs with similar regulatory environments.Diabetes is a devastating disease affecting more than 200 million people worldwide.Numerous diabetic patients suffer increased symptom severity after the onset,involving complications such as retinopathy and nephropathy.Therefore,the development of treatments for fundamental diabetes is important.The utilization of autologous cells from patients with diabetes may address challenges regarding the compatibility of donor tissues as well as provide the means to naturally and safely restore function,reducing future risks while also providing a long-term cure.Here,we review recent findings regarding the use of adult OB NSCs as a potential diabetes cure,and discuss the potential of OB NSC-based pharmaceutical applications for neuronal diseases and mental disorders.

  8. Advanced upper limb prosthetic devices: implications for upper limb prosthetic rehabilitation.

    Science.gov (United States)

    Resnik, Linda; Meucci, Marissa R; Lieberman-Klinger, Shana; Fantini, Christopher; Kelty, Debra L; Disla, Roxanne; Sasson, Nicole

    2012-04-01

    The number of catastrophic injuries caused by improvised explosive devices in the Afghanistan and Iraq Wars has increased public, legislative, and research attention to upper limb amputation. The Department of Veterans Affairs (VA) has partnered with the Defense Advanced Research Projects Agency and DEKA Integrated Solutions to optimize the function of an advanced prosthetic arm system that will enable greater independence and function. In this special communication, we examine current practices in prosthetic rehabilitation including trends in adoption and use of prosthetic devices, financial considerations, and the role of rehabilitation team members in light of our experiences with a prototype advanced upper limb prosthesis during a VA study to optimize the device. We discuss key challenges in the adoption of advanced prosthetic technology and make recommendations for service provision and use of advanced upper limb prosthetics. Rates of prosthetic rejection are high among upper limb amputees. However, these rates may be reduced with sufficient training by a highly specialized, multidisciplinary team of clinicians, and a focus on patient education and empowerment throughout the rehabilitation process. There are significant challenges emerging that are unique to implementing the use of advanced upper limb prosthetic technology, and a lack of evidence to establish clinical guidelines regarding prosthetic prescription and treatment. Finally, we make recommendations for future research to aid in the identification of best practices and development of policy decisions regarding insurance coverage of prosthetic rehabilitation. Copyright © 2012 American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.

  9. Applications of autoassociative neural networks for signal validation in accident management

    International Nuclear Information System (INIS)

    Fantoni, P.; Mazzola, A.

    1994-01-01

    The OECD Halden Reactor Project has been working for several years with computer based systems for determination on plant status including early fault detection and signal validation. The method here presented explores the possibility to use a neural network approach to validate important process signals during normal and abnormal plant conditions. In BWR plants, signal validation has two important applications: reliable thermal limits calculation and reliable inputs to other computerized systems that support the operator during accident scenarious. This work shows how a properly trained autoassociative neural network can promptly detect faulty process signal measurements and produce a best estimate of the actual process value. Noise has been artificially added to the input to evaluate the network ability to respond in a very low signal to noise ratio environment. Training and test datasets have been simulated by the real time transient simulator code APROS. Future development addresses the validation of the model through the use of real data from the plant. (author). 5 refs, 17 figs

  10. Quality-on-Demand Compression of EEG Signals for Telemedicine Applications Using Neural Network Predictors

    Directory of Open Access Journals (Sweden)

    N. Sriraam

    2011-01-01

    Full Text Available A telemedicine system using communication and information technology to deliver medical signals such as ECG, EEG for long distance medical services has become reality. In either the urgent treatment or ordinary healthcare, it is necessary to compress these signals for the efficient use of bandwidth. This paper discusses a quality on demand compression of EEG signals using neural network predictors for telemedicine applications. The objective is to obtain a greater compression gains at a low bit rate while preserving the clinical information content. A two-stage compression scheme with a predictor and an entropy encoder is used. The residue signals obtained after prediction is first thresholded using various levels of thresholds and are further quantized and then encoded using an arithmetic encoder. Three neural network models, single-layer and multi-layer perceptrons and Elman network are used and the results are compared with linear predictors such as FIR filters and AR modeling. The fidelity of the reconstructed EEG signal is assessed quantitatively using parameters such as PRD, SNR, cross correlation and power spectral density. It is found from the results that the quality of the reconstructed signal is preserved at a low PRD thereby yielding better compression results compared to results obtained using lossless scheme.

  11. The application of expert systems and neural networks to gas turbine prognostics and diagnostics

    Energy Technology Data Exchange (ETDEWEB)

    DePold, H.R.; Gass, F.D.

    1999-10-01

    Condition monitoring of engine gas generators plays an essential role in airline fleet management. Adaptive diagnostic systems are becoming available that interpret measured data, furnish diagnosis of problems, provide a prognosis of engine health for planning purposes, and rank engines for scheduled maintenance. More than four hundred operations worldwide currently use versions of the first or second generation diagnostic tools. Development of a third generation system is underway which will provide additional system enhancements and combine the functions of the existing tools. Proposed enhancements include the use of artificial intelligence to automate, improve the quality of the analysis, provide timely alerts, and the use of an Internet link for collaboration. One objective of these enhancements is to have the intelligent system do more of the analysis and decision making, while continuing to support the depth of analysis currently available at experienced operations. This paper presents recent developments in technology and strategies in engine condition monitoring including: (1) application of statistical analysis and artificial neural network filters to improve data quality, (2) neural networks for trend change detection, and classification to diagnose performance change, and (3) expert systems to diagnose, provide alerts and to rank maintenance action recommendations.

  12. Evaluation of the maximum-likelihood adaptive neural system (MLANS) applications to noncooperative IFF

    Science.gov (United States)

    Chernick, Julian A.; Perlovsky, Leonid I.; Tye, David M.

    1994-06-01

    This paper describes applications of maximum likelihood adaptive neural system (MLANS) to the characterization of clutter in IR images and to the identification of targets. The characterization of image clutter is needed to improve target detection and to enhance the ability to compare performance of different algorithms using diverse imagery data. Enhanced unambiguous IFF is important for fratricide reduction while automatic cueing and targeting is becoming an ever increasing part of operations. We utilized MLANS which is a parametric neural network that combines optimal statistical techniques with a model-based approach. This paper shows that MLANS outperforms classical classifiers, the quadratic classifier and the nearest neighbor classifier, because on the one hand it is not limited to the usual Gaussian distribution assumption and can adapt in real time to the image clutter distribution; on the other hand MLANS learns from fewer samples and is more robust than the nearest neighbor classifiers. Future research will address uncooperative IFF using fused IR and MMW data.

  13. An Inverse Neural Controller Based on the Applicability Domain of RBF Network Models

    Directory of Open Access Journals (Sweden)

    Alex Alexandridis

    2018-01-01

    Full Text Available This paper presents a novel methodology of generic nature for controlling nonlinear systems, using inverse radial basis function neural network models, which may combine diverse data originating from various sources. The algorithm starts by applying the particle swarm optimization-based non-symmetric variant of the fuzzy means (PSO-NSFM algorithm so that an approximation of the inverse system dynamics is obtained. PSO-NSFM offers models of high accuracy combined with small network structures. Next, the applicability domain concept is suitably tailored and embedded into the proposed control structure in order to ensure that extrapolation is avoided in the controller predictions. Finally, an error correction term, estimating the error produced by the unmodeled dynamics and/or unmeasured external disturbances, is included to the control scheme to increase robustness. The resulting controller guarantees bounded input-bounded state (BIBS stability for the closed loop system when the open loop system is BIBS stable. The proposed methodology is evaluated on two different control problems, namely, the control of an experimental armature-controlled direct current (DC motor and the stabilization of a highly nonlinear simulated inverted pendulum. For each one of these problems, appropriate case studies are tested, in which a conventional neural controller employing inverse models and a PID controller are also applied. The results reveal the ability of the proposed control scheme to handle and manipulate diverse data through a data fusion approach and illustrate the superiority of the method in terms of faster and less oscillatory responses.

  14. Extruded Bread Classification on the Basis of Acoustic Emission Signal With Application of Artificial Neural Networks

    Science.gov (United States)

    Świetlicka, Izabela; Muszyński, Siemowit; Marzec, Agata

    2015-04-01

    The presented work covers the problem of developing a method of extruded bread classification with the application of artificial neural networks. Extruded flat graham, corn, and rye breads differening in water activity were used. The breads were subjected to the compression test with simultaneous registration of acoustic signal. The amplitude-time records were analyzed both in time and frequency domains. Acoustic emission signal parameters: single energy, counts, amplitude, and duration acoustic emission were determined for the breads in four water activities: initial (0.362 for rye, 0.377 for corn, and 0.371 for graham bread), 0.432, 0.529, and 0.648. For classification and the clustering process, radial basis function, and self-organizing maps (Kohonen network) were used. Artificial neural networks were examined with respect to their ability to classify or to cluster samples according to the bread type, water activity value, and both of them. The best examination results were achieved by the radial basis function network in classification according to water activity (88%), while the self-organizing maps network yielded 81% during bread type clustering.

  15. Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures

    Directory of Open Access Journals (Sweden)

    Hossein Foroozand

    2018-03-01

    Full Text Available Recently, the Entropy Ensemble Filter (EEF method was proposed to mitigate the computational cost of the Bootstrap AGGregatING (bagging method. This method uses the most informative training data sets in the model ensemble rather than all ensemble members created by the conventional bagging. In this study, we evaluate, for the first time, the application of the EEF method in Neural Network (NN modeling of El Nino-southern oscillation. Specifically, we forecast the first five principal components (PCs of sea surface temperature monthly anomaly fields over tropical Pacific, at different lead times (from 3 to 15 months, with a three-month increment for the period 1979–2017. We apply the EEF method in a multiple-linear regression (MLR model and two NN models, one using Bayesian regularization and one Levenberg-Marquardt algorithm for training, and evaluate their performance and computational efficiency relative to the same models with conventional bagging. All models perform equally well at the lead time of 3 and 6 months, while at higher lead times, the MLR model’s skill deteriorates faster than the nonlinear models. The neural network models with both bagging methods produce equally successful forecasts with the same computational efficiency. It remains to be shown whether this finding is sensitive to the dataset size.

  16. Artificial neural network application for predicting soil distribution coefficient of nickel

    International Nuclear Information System (INIS)

    Falamaki, Amin

    2013-01-01

    The distribution (or partition) coefficient (K d ) is an applicable parameter for modeling contaminant and radionuclide transport as well as risk analysis. Selection of this parameter may cause significant error in predicting the impacts of contaminant migration or site-remediation options. In this regards, various models were presented to predict K d values for different contaminants specially heavy metals and radionuclides. In this study, artificial neural network (ANN) is used to present simplified model for predicting K d of nickel. The main objective is to develop a more accurate model with a minimal number of parameters, which can be determined experimentally or select by review of different studies. In addition, the effects of training as well as the type of the network are considered. The K d values of Ni is strongly dependent on pH of the soil and mathematical relationships were presented between pH and K d of nickel recently. In this study, the same database of these presented models was used to verify that neural network may be more useful tools for predicting of K d . Two different types of ANN, multilayer perceptron and redial basis function, were used to investigate the effect of the network geometry on the results. In addition, each network was trained by 80 and 90% of the data and tested for 20 and 10% of the rest data. Then the results of the networks compared with the results of the mathematical models. Although the networks trained by 80 and 90% of the data the results show that all the networks predict with higher accuracy relative to mathematical models which were derived by 100% of data. More training of a network increases the accuracy of the network. Multilayer perceptron network used in this study predicts better than redial basis function network. - Highlights: ► Simplified models for predicting K d of nickel presented using artificial neural networks. ► Multilayer perceptron and redial basis function used to predict K d of nickel in

  17. Real-time animation software for customized training to use motor prosthetic systems.

    Science.gov (United States)

    Davoodi, Rahman; Loeb, Gerald E

    2012-03-01

    Research on control of human movement and development of tools for restoration and rehabilitation of movement after spinal cord injury and amputation can benefit greatly from software tools for creating precisely timed animation sequences of human movement. Despite their ability to create sophisticated animation and high quality rendering, existing animation software are not adapted for application to neural prostheses and rehabilitation of human movement. We have developed a software tool known as MSMS (MusculoSkeletal Modeling Software) that can be used to develop models of human or prosthetic limbs and the objects with which they interact and to animate their movement using motion data from a variety of offline and online sources. The motion data can be read from a motion file containing synthesized motion data or recordings from a motion capture system. Alternatively, motion data can be streamed online from a real-time motion capture system, a physics-based simulation program, or any program that can produce real-time motion data. Further, animation sequences of daily life activities can be constructed using the intuitive user interface of Microsoft's PowerPoint software. The latter allows expert and nonexpert users alike to assemble primitive movements into a complex motion sequence with precise timing by simply arranging the order of the slides and editing their properties in PowerPoint. The resulting motion sequence can be played back in an open-loop manner for demonstration and training or in closed-loop virtual reality environments where the timing and speed of animation depends on user inputs. These versatile animation utilities can be used in any application that requires precisely timed animations but they are particularly suited for research and rehabilitation of movement disorders. MSMS's modeling and animation tools are routinely used in a number of research laboratories around the country to study the control of movement and to develop and test

  18. Artificial neural networks application for horizontal and vertical forecasting radionuclides transport

    International Nuclear Information System (INIS)

    Khil'ko, O.S.; Kovalenko, V.I.; Kundas, S.P.

    2010-01-01

    Artificial neural networks approach for horizontal and vertical radionuclide transport forecasting was proposed. Runoff factors analysis was considered. Additional artificial neural network structures for physical-chemical properties recognition were used. (authors)

  19. Echocardiographic evaluation of heart valve prosthetic dysfunction

    Directory of Open Access Journals (Sweden)

    Yuriy Ivaniv

    2018-02-01

    Full Text Available Patients with replaced heart valve submitted to echocardiographic examination may have symptoms related either to valvular malfunction or ventricular dysfunction from different causes. Clinical examination is not reliable in a prosthetic valve evaluation and the main information regarding its function could be obtained using different cardiac ultrasound modalities. This review provides a description of echocardiographic and Doppler techniques useful in evaluation of prosthetic heart valves. For the interpretation of echocardiography there is a need in special knowledge of prosthesis types and possible reasons of prosthetic function deterioration. Echocardiography allows to reveal valve thrombosis, pannus formation, vegetation and such complications of infective endocarditis as valve ring abscess or dehiscence. Transthoracic echocardiography requires different section plane angles and unconventional views. Transesophageal echocardiography is more often used than in native valve examination due to better visualization of prosthetic valve structure and function. Three-dimensional echocardiography could provide more detailed visual information especially in the assessment of paravalvular regurgitation or valve obstruction.

  20. DME Prosthetics Orthotics, and Supplies Fee Schedule

    Data.gov (United States)

    U.S. Department of Health & Human Services — Durable Medical Equipment, Prosthetics-Orthotics, and Supplies Fee Schedule. The list contains the fee schedule amounts, floors, and ceilings for all procedure codes...

  1. Computed Tomography of Prosthetic Heart Valves

    NARCIS (Netherlands)

    Habets, J.

    2012-01-01

    Prosthetic heart valve (PHV) dysfunction is an infrequent but potentially life-threatening disease with a heterogeneous clinical presentation. Patients with PHV dysfunction clinically can present with symptoms of congestive heart failure (dyspnea, fatigue, edema), fever, angina pectoris, dizziness

  2. Illusory movement perception improves motor control for prosthetic hands.

    Science.gov (United States)

    Marasco, Paul D; Hebert, Jacqueline S; Sensinger, Jon W; Shell, Courtney E; Schofield, Jonathon S; Thumser, Zachary C; Nataraj, Raviraj; Beckler, Dylan T; Dawson, Michael R; Blustein, Dan H; Gill, Satinder; Mensh, Brett D; Granja-Vazquez, Rafael; Newcomb, Madeline D; Carey, Jason P; Orzell, Beth M

    2018-03-14

    To effortlessly complete an intentional movement, the brain needs feedback from the body regarding the movement's progress. This largely nonconscious kinesthetic sense helps the brain to learn relationships between motor commands and outcomes to correct movement errors. Prosthetic systems for restoring function have predominantly focused on controlling motorized joint movement. Without the kinesthetic sense, however, these devices do not become intuitively controllable. We report a method for endowing human amputees with a kinesthetic perception of dexterous robotic hands. Vibrating the muscles used for prosthetic control via a neural-machine interface produced the illusory perception of complex grip movements. Within minutes, three amputees integrated this kinesthetic feedback and improved movement control. Combining intent, kinesthesia, and vision instilled participants with a sense of agency over the robotic movements. This feedback approach for closed-loop control opens a pathway to seamless integration of minds and machines. Copyright © 2018 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.

  3. Prosthetic vision: devices, patient outcomes and retinal research.

    Science.gov (United States)

    Hadjinicolaou, Alex E; Meffin, Hamish; Maturana, Matias I; Cloherty, Shaun L; Ibbotson, Michael R

    2015-09-01

    Retinal disease and its associated retinal degeneration can lead to the loss of photoreceptors and therefore, profound blindness. While retinal degeneration destroys the photoreceptors, the neural circuits that convey information from the eye to the brain are sufficiently preserved to make it possible to restore sight using prosthetic devices. Typically, these devices consist of a digital camera and an implantable neurostimulator. The image sensor in a digital camera has the same spatiotopic arrangement as the photoreceptors of the retina. Therefore, it is possible to extract meaningful spatial information from an image and deliver it via an array of stimulating electrodes directly to the surviving retinal circuits. Here, we review the structure and function of normal and degenerate retina. The different approaches to prosthetic implant design are described in the context of human and preclinical trials. In the last section, we review studies of electrical properties of the retina and its response to electrical stimulation. These types of investigation are currently assessing a number of key challenges identified in human trials, including stimulation efficacy, spatial localisation, desensitisation to repetitive stimulation and selective activation of retinal cell populations. © 2015 The Authors. Clinical and Experimental Optometry © 2015 Optometry Australia.

  4. Overview: Mechanism and Control of a Prosthetic Arm.

    Science.gov (United States)

    Kulkarni, Tushar; Uddanwadiker, Rashmi

    2015-09-01

    Continuous growth in industrialization and lack of awareness in safety parameters the cases of amputations are growing. The search of safer, simpler and automated prosthetic arms for managing upper limbs is expected. Continuous efforts have been made to design and develop prosthetic arms ranging from simple harness actuated to automated mechanisms with various control options. However due the cost constraints, the automated prosthetic arms are still out of the reach of needy people. Recent data have shown that there is a wide scope to develop a low cost and light weight upper limb prosthesis. This review summarizes the various designs methodologies, mechanisms and control system developed by the researchers and the advances therein. Educating the patient to develop acceptability to prosthesis and using the same for the most basic desired functions of human hand, post amputation care and to improve patient's independent life is equally important. In conclusion it can be interpreted that there is a wide scope in design in an adaptive mechanism for opening and closing of the fingers using other methods of path and position synthesis. Simple mechanisms and less parts may optimize the cost factor. Reduction in the weight of the prosthesis may be achieved using polymers used for engineering applications. Control system will remain never ending challenge for the researchers, but it is essential to maintain the simplicity from the patients perspective.

  5. Application of Artificial Neural Networks to the Analysis of NORM Samples

    International Nuclear Information System (INIS)

    Moser, H.; Peyrés, V.; Mejuto, M.; García-Toraño, E.

    2015-01-01

    This work describes the application of artificial neural networks (ANNs) to analyze the raw data of gamma-ray spectra of NORM samples and decide if the activity content of a certain nuclide is above or below the exemption limit of 1 Bq/g. The main advantage of using an ANN for this purpose is that for the user no specialized knowledge in the field of gamma-ray spectrometry is necessary. In total a number of 635 spectra consisting of varying activity concentrations, seven different materials and three densities each have been generated by Monte Carlo simulation to provide training material to the ANN. These spectra have been created using the simulation code PENELOPE. Validation was carried out with a number of NORM samples previously characterized by conventional gamma-ray spectrometry with peak fitting

  6. Natural gas demand forecast system based on the application of artificial neural networks

    International Nuclear Information System (INIS)

    Sanfeliu, J.M.; Doumanian, J.E.

    1997-01-01

    Gas Natural BAN, as a distribution gas company since 1993 in the north and west area of Buenos Aires Argentina, with 1,000,000 customers, had to develop a gas demand forecast system which should comply with the following basic requirements: Be able to do reliable forecasts with short historical information (2 years); Distinguish demands in areas of different characteristics, i.e. mainly residential, mainly industrial; Self-learning capability. To accomplish above goals, Gas Natural BAN chose in view of its own necessities, an artificial intelligence application (neural networks). 'SANDRA', the gas demand forecast system for gas distribution used by Gas Natural BAN, has the following features: Daily gas demand forecast, Hourly gas demand forecast and Breakdown of both forecast for each of the 3 basic zones in which the distribution area of Gas Natural BAN is divided. (au)

  7. Fault tolerance of artificial neural networks with applications in critical systems

    Science.gov (United States)

    Protzel, Peter W.; Palumbo, Daniel L.; Arras, Michael K.

    1992-01-01

    This paper investigates the fault tolerance characteristics of time continuous recurrent artificial neural networks (ANN) that can be used to solve optimization problems. The principle of operations and performance of these networks are first illustrated by using well-known model problems like the traveling salesman problem and the assignment problem. The ANNs are then subjected to 13 simultaneous 'stuck at 1' or 'stuck at 0' faults for network sizes of up to 900 'neurons'. The effects of these faults is demonstrated and the cause for the observed fault tolerance is discussed. An application is presented in which a network performs a critical task for a real-time distributed processing system by generating new task allocations during the reconfiguration of the system. The performance degradation of the ANN under the presence of faults is investigated by large-scale simulations, and the potential benefits of delegating a critical task to a fault tolerant network are discussed.

  8. Application of artificial neural network to predict the optimal start time for heating system in building

    International Nuclear Information System (INIS)

    Yang, In-Ho; Yeo, Myoung-Souk; Kim, Kwang-Woo

    2003-01-01

    The artificial neural network (ANN) approach is a generic technique for mapping non-linear relationships between inputs and outputs without knowing the details of these relationships. This paper presents an application of the ANN in a building control system. The objective of this study is to develop an optimized ANN model to determine the optimal start time for a heating system in a building. For this, programs for predicting the room air temperature and the learning of the ANN model based on back propagation learning were developed, and learning data for various building conditions were collected through program simulation for predicting the room air temperature using systems of experimental design. Then, the optimized ANN model was presented through learning of the ANN, and its performance to determine the optimal start time was evaluated

  9. Synchronization of Switched Interval Networks and Applications to Chaotic Neural Networks

    Directory of Open Access Journals (Sweden)

    Jinde Cao

    2013-01-01

    Full Text Available This paper investigates synchronization problem of switched delay networks with interval parameters uncertainty, based on the theories of the switched systems and drive-response technique, a mathematical model of the switched interval drive-response error system is established. Without constructing Lyapunov-Krasovskii functions, introducing matrix measure method for the first time to switched time-varying delay networks, combining Halanay inequality technique, synchronization criteria are derived for switched interval networks under the arbitrary switching rule, which are easy to verify in practice. Moreover, as an application, the proposed scheme is then applied to chaotic neural networks. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.

  10. Artificial Neural Networks to reconstruct incomplete satellite data: application to the Mediterranean Sea Surface Temperature

    Directory of Open Access Journals (Sweden)

    E. Pisoni

    2008-02-01

    Full Text Available Satellite data can be very useful in applications where extensive spatial information is needed, but sometimes missing data due to presence of clouds can affect data quality. In this study a methodology for pre-processing sea surface temperature (SST data is proposed. The methodology, that processes measures in the visible wavelength, is based on an Artificial Neural Network (ANN system. The effectiveness of the procedure has been also evaluated comparing results obtained using an interpolation method. After the methodology has been identified, a validation is performed on 3 different episodes representative of SST variability in the Mediterranean sea. The proposed technique can process SST NOAA/AVHRR data to simulate severe storm episodes by means of prognostic meteorological models.

  11. A systematic FPGA acceleration design for applications based on convolutional neural networks

    Science.gov (United States)

    Dong, Hao; Jiang, Li; Li, Tianjian; Liang, Xiaoyao

    2018-04-01

    Most FPGA accelerators for convolutional neural network are designed to optimize the inner acceleration and are ignored of the optimization for the data path between the inner accelerator and the outer system. This could lead to poor performance in applications like real time video object detection. We propose a brand new systematic FPFA acceleration design to solve this problem. This design takes the data path optimization between the inner accelerator and the outer system into consideration and optimizes the data path using techniques like hardware format transformation, frame compression. It also takes fixed-point, new pipeline technique to optimize the inner accelerator. All these make the final system's performance very good, reaching about 10 times the performance comparing with the original system.

  12. Applications of neural networks to the studies of phase transitions of two-dimensional Potts models

    Science.gov (United States)

    Li, C.-D.; Tan, D.-R.; Jiang, F.-J.

    2018-04-01

    We study the phase transitions of two-dimensional (2D) Q-states Potts models on the square lattice, using the first principles Monte Carlo (MC) simulations as well as the techniques of neural networks (NN). We demonstrate that the ideas from NN can be adopted to study these considered phase transitions efficiently. In particular, even with a simple NN constructed in this investigation, we are able to obtain the relevant information of the nature of these phase transitions, namely whether they are first order or second order. Our results strengthen the potential applicability of machine learning in studying various states of matters. Subtlety of applying NN techniques to investigate many-body systems is briefly discussed as well.

  13. Neural Network for Principal Component Analysis with Applications in Image Compression

    Directory of Open Access Journals (Sweden)

    Luminita State

    2007-04-01

    Full Text Available Classical feature extraction and data projection methods have been extensively investigated in the pattern recognition and exploratory data analysis literature. Feature extraction and multivariate data projection allow avoiding the "curse of dimensionality", improve the generalization ability of classifiers and significantly reduce the computational requirements of pattern classifiers. During the past decade a large number of artificial neural networks and learning algorithms have been proposed for solving feature extraction problems, most of them being adaptive in nature and well-suited for many real environments where adaptive approach is required. Principal Component Analysis, also called Karhunen-Loeve transform is a well-known statistical method for feature extraction, data compression and multivariate data projection and so far it has been broadly used in a large series of signal and image processing, pattern recognition and data analysis applications.

  14. Application of Artificial Neural Network into the Water Level Modeling and Forecast

    Directory of Open Access Journals (Sweden)

    Marzenna Sztobryn

    2013-06-01

    Full Text Available The dangerous sea and river water level increase does not only destroy the human lives, but also generate the severe flooding in coastal areas. The rapidly changes in the direction and velocity of wind and associated with them sea level changes could be the severe threat for navigation, especially on the fairways of small fishery harbors located in the river mouth. There is the area of activity of two external forcing: storm surges and flood wave. The aim of the work was the description of an application of Artificial Neural Network (ANN methodology into the water level forecast in the case study field in Swibno harbor located is located at 938.7 km of the Wisla River and at a distance of about 3 km up the mouth (Gulf of Gdansk - Baltic Sea.

  15. Application of cellular neural network (CNN) method to the nuclear reactor dynamics equations

    International Nuclear Information System (INIS)

    Hadad, K.; Piroozmand, A.

    2007-01-01

    This paper describes the application of a multilayer cellular neural network (CNN) to model and solve the nuclear reactor dynamic equations. An equivalent electrical circuit is analyzed and the governing equations of a bare, homogeneous reactor core are modeled via CNN. The validity of the CNN result is compared with numerical solution of the system of nonlinear governing partial differential equations (PDE) using MATLAB. Steady state as well as transient simulations, show very good comparison between the two methods. We used our CNN model to simulate space-time response of different reactivity excursions in a typical nuclear reactor. On line solution of reactor dynamic equations is used as an aid to reactor operation decision making. The complete algorithm could also be implemented using very large scale integrated circuit (VLSI) circuitry. The efficiency of the calculation method makes it useful for small size nuclear reactors such as the ones used in space missions

  16. Isolated Lactobacillus chronic prosthetic knee infection.

    Science.gov (United States)

    Bennett, David M; Shekhel, Tatyana; Radelet, Matt; Miller, Michael D

    2014-01-01

    Lactobacillus is a gram-positive rod bacteria found primarily in the gastrointestinal and female genital tracts. Prosthetic infections in implants are being increasingly reported. The authors present a case of a 58-year-old patient with Lactobacillus septic prosthetic knee joint infection. To the authors’ knowledge, this is the first reported case of chronic prosthetic knee infection with isolated Lactobacillus species. Lactobacillus has been most commonly implicated with bacteremia and endocarditis and rarely with pneumonia, meningitis, and endovascular infection, and a vast majority of the cases are reported in immunocompromised patients. In the current case, diabetes mellitus, hepatitis, malnutrition, anemia, and liver failure were comorbid conditions, placing the patient at increased risk of infection. The findings suggest that further case series are necessary to establish the significance of Lactobacillus as an etiologic agent in chronic low-virulence, and potentially vancomycin-resistant, prosthetic joint infection. The need also exists for further research aimed at the risk of prosthetic joint infection with oral intake of certain probiotic foods and supplements. The goal of this case report is to bring to light the potential of this organism to be a cause of subtle chronic prosthetic joint infection.

  17. Application and assessment of multiscale bending energy for morphometric characterization of neural cells

    Science.gov (United States)

    Cesar, Roberto Marcondes; Costa, Luciano da Fontoura

    1997-05-01

    The estimation of the curvature of experimentally obtained curves is an important issue in many applications of image analysis including biophysics, biology, particle physics, and high energy physics. However, the accurate calculation of the curvature of digital contours has proven to be a difficult endeavor, mainly because of the noise and distortions that are always present in sampled signals. Errors ranging from 1% to 1000% have been reported with respect to the application of standard techniques in the estimation of the curvature of circular contours [M. Worring and A. W. M. Smeulders, CVGIP: Im. Understanding, 58, 366 (1993)]. This article explains how diagrams of multiscale bending energy can be easily obtained from curvegrams and used as a robust general feature for morphometric characterization of neural cells. The bending energy is an interesting global feature for shape characterization that expresses the amount of energy needed to transform the specific shape under analysis into its lowest energy state (i.e., a circle). The curvegram, which can be accurately obtained by using digital signal processing techniques (more specifically through the Fourier transform and its inverse, as described in this work), provides multiscale representation of the curvature of digital contours. The estimation of the bending energy from the curvegram is introduced and exemplified with respect to a series of neural cells. The masked high curvature effect is reported and its implications to shape analysis are discussed. It is also discussed and illustrated that, by normalizing the multiscale bending energy with respect to a standard circle of unitary perimeter, this feature becomes an effective means for expressing shape complexity in a way that is invariant to rotation, translation, and scaling, and that is robust to noise and other artifacts implied by image acquisition.

  18. Efficient second order Algorithms for Function Approximation with Neural Networks. Application to Sextic Potentials

    International Nuclear Information System (INIS)

    Gougam, L.A.; Taibi, H.; Chikhi, A.; Mekideche-Chafa, F.

    2009-01-01

    The problem of determining the analytical description for a set of data arises in numerous sciences and applications and can be referred to as data modeling or system identification. Neural networks are a convenient means of representation because they are known to be universal approximates that can learn data. The desired task is usually obtained by a learning procedure which consists in adjusting the s ynaptic weights . For this purpose, many learning algorithms have been proposed to update these weights. The convergence for these learning algorithms is a crucial criterion for neural networks to be useful in different applications. The aim of the present contribution is to use a training algorithm for feed forward wavelet networks used for function approximation. The training is based on the minimization of the least-square cost function. The minimization is performed by iterative second order gradient-based methods. We make use of the Levenberg-Marquardt algorithm to train the architecture of the chosen network and, then, the training procedure starts with a simple gradient method which is followed by a BFGS (Broyden, Fletcher, Glodfarb et Shanno) algorithm. The performances of the two algorithms are then compared. Our method is then applied to determine the energy of the ground state associated to a sextic potential. In fact, the Schrodinger equation does not always admit an exact solution and one has, generally, to solve it numerically. To this end, the sextic potential is, firstly, approximated with the above outlined wavelet network and, secondly, implemented into a numerical scheme. Our results are in good agreement with the ones found in the literature.

  19. Application of an artificial neural network in the enumeration of yeasts and bacteria adhering to solid substrata

    NARCIS (Netherlands)

    Wit, P; Busscher, HJ

    Artificial neural networks (ANNs) combined with automated image processing are bring used in a growing number of applications, ranging from car license plate identification to speech recognition. ANN analysis is capable of handling complicated images that cannot be dealt with using conventional

  20. Myoelectric control of prosthetic hands: state-of-the-art review

    Directory of Open Access Journals (Sweden)

    Geethanjali P

    2016-07-01

    Full Text Available Purushothaman Geethanjali School of Electrical Engineering Department of Control and Automation VIT University, Vellore, Tamil Nadu, India Abstract: Myoelectric signals (MES have been used in various applications, in particular, for identification of user intention to potentially control assistive devices for amputees, orthotic devices, and exoskeleton in order to augment capability of the user. MES are also used to estimate force and, hence, torque to actuate the assistive device. The application of MES is not limited to assistive devices, and they also find potential applications in teleoperation of robots, haptic devices, virtual reality, and so on. The myoelectric control-based prosthetic hand aids to restore activities of daily living of amputees in order to improve the self-esteem of the user. All myoelectric control-based prosthetic hands may not have similar operations and exhibit variation in sensing input, deciphering the signals, and actuating prosthetic hand. Researchers are focusing on improving the functionality of prosthetic hand in order to suit the user requirement with the different operating features. The myoelectric control differs in operation to accommodate various external factors. This article reviews the state of the art of myoelectric prosthetic hand, giving description of each control strategy. Keywords: EMG, assistive device, amputee, myoelectric control, electric powered, body ­powered, bioelectric signal control

  1. Neural PID Control of Robot Manipulators With Application to an Upper Limb Exoskeleton.

    Science.gov (United States)

    Yu, Wen; Rosen, Jacob

    2013-04-01

    In order to minimize steady-state error with respect to uncertainties in robot control, proportional-integral-derivative (PID) control needs a big integral gain, or a neural compensator is added to the classical proportional-derivative (PD) control with a large derivative gain. Both of them deteriorate transient performances of the robot control. In this paper, we extend the popular neural PD control into neural PID control. This novel control is a natural combination of industrial linear PID control and neural compensation. The main contributions of this paper are semiglobal asymptotic stability of the neural PID control and local asymptotic stability of the neural PID control with a velocity observer which are proved with standard weight training algorithms. These conditions give explicit selection methods for the gains of the linear PID control. An experimental study on an upper limb exoskeleton with this neural PID control is addressed.

  2. Cetacean Swimming with Prosthetic Limbs

    Science.gov (United States)

    Bode-Oke, Ayodeji; Ren, Yan; Dong, Haibo; Fish, Frank

    2016-11-01

    During entanglement in fishing gear, dolphins can suffer abrasions and amputations of flukes and fins. As a result, if the dolphin survives the ordeal, swimming performance is altered. Current rehabilitation technques is the use of prosthesis to regain swimming ability. In this work, analyses are focused on two dolphins with locomotive impairment; Winter (currently living in Clearwater Marine Aquarium in Florida) and Fuji (lived in Okinawa Churaumi Aquarium in Japan). Fuji lost about 75% of its fluke surface to necrosis (death of cells) and Winter lost its tail due to amputation. Both dolphins are aided by prosthetic tails that mimic the shape of a real dolphin tail. Using 3D surface reconstruction techniques and a high fidelity Computational Fluid Dynamics (CFD) flow solver, we were able to elucidate the kinematics and hydrodynamics and fluke deformation of these swimmers to clarify the effectiveness of prostheses in helping the dolphins regain their swimming ability. Associated with the performance, we identified distinct features in the wake structures that can explain this gap in the performance compared to a healthy dolphin. This work was supported by ONR MURI Grant Number N00014-14-1-0533.

  3. Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm. (On-Line Harmonics Estimation Application

    Directory of Open Access Journals (Sweden)

    Eyad K Almaita

    2017-03-01

    Keywords: Energy efficiency, Power quality, Radial basis function, neural networks, adaptive, harmonic. Article History: Received Dec 15, 2016; Received in revised form Feb 2nd 2017; Accepted 13rd 2017; Available online How to Cite This Article: Almaita, E.K and Shawawreh J.Al (2017 Improving Stability and Convergence for Adaptive Radial Basis Function Neural Networks Algorithm (On-Line Harmonics Estimation Application.  International Journal of Renewable Energy Develeopment, 6(1, 9-17. http://dx.doi.org/10.14710/ijred.6.1.9-17

  4. The cochlear implant and possibilities for narrowing the remaining gaps between prosthetic and normal hearing

    Directory of Open Access Journals (Sweden)

    Blake S. Wilson

    2017-12-01

    Full Text Available Background: The cochlear implant has become the standard of care for severe or worse losses in hearing and indeed has produced the first substantial restoration of a lost or absent human sense using a medical intervention. However, the devices are not perfect and many efforts to narrow the remaining gaps between prosthetic and normal hearing are underway. Objective: To assess the present status of cochlear implants and to describe possibilities for improving them. Results: The present-day devices work well in quiet conditions for the great majority of users. However, not all users have high levels of speech reception in quiet and nearly all users struggle with speech reception in typically noisy acoustic environments. In addition, perception of sounds more complex than speech, such as most music, is generally poor unless residual hearing at low frequencies can be stimulated acoustically in conjunction with the electrical stimuli provided by the implant. Possibilities for improving the present devices include increasing the spatial specificity of neural excitation by reducing masking effects or with new stimulus modes; prudent pruning of interfering or otherwise detrimental electrodes from the stimulation map; a further relaxation in the criteria for implant candidacy, based on recent evidence from persons with high levels of residual hearing and to allow many more people to benefit from cochlear implants; and “top down” or “brain centric” approaches to implant designs and applications. Conclusions: Progress in the development of the cochlear implant and related treatments has been remarkable but room remains for improvements. The future looks bright as there are multiple promising possibilities for improvements and many talented teams are pursuing them. Keywords: Auditory prosthesis, Cochlear implant, Cochlear prosthesis, Deafness, Neural prosthesis

  5. Development of a signal-analysis algorithm for the ZEUS transition-radiation detector under application of a neural network

    International Nuclear Information System (INIS)

    Wollschlaeger, U.

    1992-07-01

    The aim of this thesis consisted in the development of a procedure for the analysis of the data of the transition-radiation detector at ZEUS. For this a neural network was applied and first studied, which results concerning the separation power between electron an pions can be reached by this procedure. It was shown that neural nets yield within the error limits as well results as standard algorithms (total charge, cluster analysis). At an electron efficiency of 90% pion contaminations in the range 1%-2% were reached. Furthermore it could be confirmed that neural networks can be considered for the here present application field as robust in relatively insensitive against external perturbations. For the application in the experiment beside the separation power also the time-behaviour is of importance. The requirement to keep dead-times small didn't allow the application of standard method. By a simulation the time availabel for the signal analysis was estimated. For the testing of the processing time in a neural network subsequently the corresponding algorithm was implemented into an assembler code for the digital signal processor DSP56001. (orig./HSI) [de

  6. A facile route to the synthesis of anilinic electroactive colloidal hydrogels for neural tissue engineering applications.

    Science.gov (United States)

    Zarrintaj, Payam; Urbanska, Aleksandra M; Gholizadeh, Saman Seyed; Goodarzi, Vahabodin; Saeb, Mohammad Reza; Mozafari, Masoud

    2018-04-15

    An innovative drug-loaded colloidal hydrogel was synthesized for applications in neural interfaces in tissue engineering by reacting carboxyl capped aniline dimer and gelatin molecules. Dexamethasone was loaded into the gelatin-aniline dimer solution as a model drug to form an in situ drug-loaded colloidal hydrogel. The conductivity of the hydrogel samples fluctuated around 10 -5  S/cm which appeared suitable for cellular activities. Cyclic voltammetry was used for electroactivity determination, in which 2 redox states were observed, suggesting that the short chain length and steric hindrance prevented the gel from achieving a fully oxidized state. Rheological data depicted the modulus decreasing with aniline dimer increment due to limited hydrogen bonds accessibility. Though the swelling ratio of pristine gelatin (600%) decreased by the introduction and increasing the concentration of aniline dimer because of its hydrophobic nature, it took the value of 300% at worst, which still seems promising for drug delivery uses. Degradation rate of hydrogel was similarly decreased by adding aniline dimer. Drug release was evaluated in passive and stimulated patterns demonstrating tendency of aniline dimer to form a vesicle that controls the drug release behavior. The optimal cell viability, proper cell attachment and neurite extension was achieved in the case of hydrogel containing 10 wt% aniline dimer. Based on tissue/organ behavior, it was promisingly possible to adjust the characteristics of the hydrogels for an optimal drug release. The outcome of this simple and effective approach can potentially offer additional tunable characteristics for recording and stimulating purposes in neural interfaces. Copyright © 2018 Elsevier Inc. All rights reserved.

  7. Application of deep learning in determining IR precipitation occurrence: a Convolutional Neural Network model

    Science.gov (United States)

    Wang, C.; Hong, Y.

    2017-12-01

    Infrared (IR) information from Geostationary satellites can be used to retrieve precipitation at pretty high spatiotemporal resolutions. Traditional artificial intelligence (AI) methodologies, such as artificial neural networks (ANN), have been designed to build the relationship between near-surface precipitation and manually derived IR features in products including PERSIANN and PERSIANN-CCS. This study builds an automatic precipitation detection model based on IR data using Convolutional Neural Network (CNN) which is implemented by the newly developed deep learning framework, Caffe. The model judges whether there is rain or no rain at pixel level. Compared with traditional ANN methods, CNN can extract features inside the raw data automatically and thoroughly. In this study, IR data from GOES satellites and precipitation estimates from the next generation QPE (Q2) over the central United States are used as inputs and labels, respectively. The whole datasets during the study period (June to August in 2012) are randomly partitioned to three sub datasets (train, validation and test) to establish the model at the spatial resolution of 0.08°×0.08° and the temporal resolution of 1 hour. The experiments show great improvements of CNN in rain identification compared to the widely used IR-based precipitation product, i.e., PERSIANN-CCS. The overall gain in performance is about 30% for critical success index (CSI), 32% for probability of detection (POD) and 12% for false alarm ratio (FAR). Compared to other recent IR-based precipitation retrieval methods (e.g., PERSIANN-DL developed by University of California Irvine), our model is simpler with less parameters, but achieves equally or even better results. CNN has been applied in computer vision domain successfully, and our results prove the method is suitable for IR precipitation detection. Future studies can expand the application of CNN from precipitation occurrence decision to precipitation amount retrieval.

  8. The Application of Artificial Neural Networks to Ore Reserve Estimation at Choghart Iron Ore Deposit

    Directory of Open Access Journals (Sweden)

    Seyyed Ali Nezamolhosseini

    2017-01-01

    Full Text Available Geo-statistical methods for reserve estimation are difficult to use when stationary conditions are not satisfied. Artificial Neural Networks (ANNs provide an alternative to geo-statistical techniques while considerably reducing the processing time required for development and application. In this paper the ANNs was applied to the Choghart iron ore deposit in Yazd province of Iran. Initially, an optimum Multi Layer Perceptron (MLP was constructed to estimate the Fe grade within orebody using the whole ore data of the deposit. Sensitivity analysis was applied for a number of hidden layers and neurons, different types of activation functions and learning rules. Optimal architectures for iron grade estimation were 3-20-10-1. In order to improve the network performance, the deposit was divided into four homogenous zones. Subsequently, all sensitivity analyses were carried out on each zone.  Finally, a different optimum network was trained and Fe was estimated separately for each zone. Comparison of correlation coefficient (R and least mean squared error (MSE showed that the ANNs performed on four homogenous zones were far better than the nets applied to the overall ore body. Therefore, these optimized neural networks were used to estimate the distribution of iron grades and the iron resource in Choghart deposit. As a result of applying ANNs, the tonnage of ore for Choghart deposit is approximately estimated at 135.8 million tones with average grade of Fe at 56.14 percent. Results of reserve estimation using ANNs showed a good agreement with the geo-statistical methods applied to this ore body in another work.

  9. Synchronization of an Inertial Neural Network With Time-Varying Delays and Its Application to Secure Communication.

    Science.gov (United States)

    Lakshmanan, Shanmugam; Prakash, Mani; Lim, Chee Peng; Rakkiyappan, Rajan; Balasubramaniam, Pagavathigounder; Nahavandi, Saeid

    2018-01-01

    In this paper, synchronization of an inertial neural network with time-varying delays is investigated. Based on the variable transformation method, we transform the second-order differential equations into the first-order differential equations. Then, using suitable Lyapunov-Krasovskii functionals and Jensen's inequality, the synchronization criteria are established in terms of linear matrix inequalities. Moreover, a feedback controller is designed to attain synchronization between the master and slave models, and to ensure that the error model is globally asymptotically stable. Numerical examples and simulations are presented to indicate the effectiveness of the proposed method. Besides that, an image encryption algorithm is proposed based on the piecewise linear chaotic map and the chaotic inertial neural network. The chaotic signals obtained from the inertial neural network are utilized for the encryption process. Statistical analyses are provided to evaluate the effectiveness of the proposed encryption algorithm. The results ascertain that the proposed encryption algorithm is efficient and reliable for secure communication applications.

  10. A neural networks application for the study of the influence of transport conditions on the working performance

    Science.gov (United States)

    Anghel, D.-C.; Ene, A.; Ştirbu, C.; Sicoe, G.

    2017-10-01

    This paper presents a study about the factors that influence the working performances of workers in the automotive industry. These factors regard mainly the transportations conditions, taking into account the fact that a large number of workers live in places that are far away of the enterprise. The quantitative data obtained from this study will be generalized by using a neural network, software simulated. The neural network is able to estimate the performance of workers even for the combinations of input factors that had been not recorded by the study. The experimental data obtained from the study will be divided in two classes. The first class that contains approximately 80% of data will be used by the Java software for the training of the neural network. The weights resulted from the training process will be saved in a text file. The other class that contains the rest of the 20% of experimental data will be used to validate the neural network. The training and the validation of the networks are performed in a Java software (TrainAndValidate java class). We designed another java class, Test.java that will be used with new input data, for new situations. The experimental data collected from the study. The software that simulated the neural network. The software that estimates the working performance, when new situations are met. This application is useful for human resources department of an enterprise. The output results are not quantitative. They are qualitative (from low performance to high performance, divided in five classes).

  11. Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms.

    Science.gov (United States)

    Ferentinos, Konstantinos P

    2005-09-01

    Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms. The developed systems are a fault detection NN model and a predictive modeling NN system. An indirect or 'weak specification' representation was used for the encoding of NN topologies and training parameters into genes of the genetic algorithm (GA). Some a priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to some reasonable degree. Both one-hidden-layer and two-hidden-layer network architectures were explored by the GA. Except for the network architecture, each gene of the GA also encoded the type of activation functions in both hidden and output nodes of the NN and the type of minimization algorithm that was used by the backpropagation algorithm for the training of the NN. Both models achieved satisfactory performance, while the GA system proved to be a powerful tool that can successfully replace the problematic trial-and-error approach that is usually used for these tasks.

  12. Combined application of mixture experimental design and artificial neural networks in the solid dispersion development.

    Science.gov (United States)

    Medarević, Djordje P; Kleinebudde, Peter; Djuriš, Jelena; Djurić, Zorica; Ibrić, Svetlana

    2016-01-01

    This study for the first time demonstrates combined application of mixture experimental design and artificial neural networks (ANNs) in the solid dispersions (SDs) development. Ternary carbamazepine-Soluplus®-poloxamer 188 SDs were prepared by solvent casting method to improve carbamazepine dissolution rate. The influence of the composition of prepared SDs on carbamazepine dissolution rate was evaluated using d-optimal mixture experimental design and multilayer perceptron ANNs. Physicochemical characterization proved the presence of the most stable carbamazepine polymorph III within the SD matrix. Ternary carbamazepine-Soluplus®-poloxamer 188 SDs significantly improved carbamazepine dissolution rate compared to pure drug. Models developed by ANNs and mixture experimental design well described the relationship between proportions of SD components and percentage of carbamazepine released after 10 (Q10) and 20 (Q20) min, wherein ANN model exhibit better predictability on test data set. Proportions of carbamazepine and poloxamer 188 exhibited the highest influence on carbamazepine release rate. The highest carbamazepine release rate was observed for SDs with the lowest proportions of carbamazepine and the highest proportions of poloxamer 188. ANNs and mixture experimental design can be used as powerful data modeling tools in the systematic development of SDs. Taking into account advantages and disadvantages of both techniques, their combined application should be encouraged.

  13. Application of Artificial Neural Networks in the Heart Electrical Axis Position Conclusion Modeling

    Science.gov (United States)

    Bakanovskaya, L. N.

    2016-08-01

    The article touches upon building of a heart electrical axis position conclusion model using an artificial neural network. The input signals of the neural network are the values of deflections Q, R and S; and the output signal is the value of the heart electrical axis position. Training of the network is carried out by the error propagation method. The test results allow concluding that the created neural network makes a conclusion with a high degree of accuracy.

  14. Application and Simulation of Fuzzy Neural Network PID Controller in the Aircraft Cabin Temperature

    Directory of Open Access Journals (Sweden)

    Ding Fang

    2013-06-01

    Full Text Available Considering complex factors of affecting ambient temperature in Aircraft cabin, and some shortages of traditional PID control like the parameters difficult to be tuned and control ineffective, this paper puts forward the intelligent PID algorithm that makes fuzzy logic method and neural network together, scheming out the fuzzy neural net PID controller. After the correction of the fuzzy inference and dynamic learning of neural network, PID parameters of the controller get the optimal parameters. MATLAB simulation results of the cabin temperature control model show that the performance of the fuzzy neural network PID controller has been greatly improved, with faster response, smaller overshoot and better adaptability.

  15. The Role of Virtual Articulator in Prosthetic and Restorative Dentistry

    Science.gov (United States)

    Aljanakh, Mohammad

    2014-01-01

    Virtual reality is a computer based technology linked with the future of dentistry and dental practice. The virtual articulator is one such application in prosthetic and restorative dentistry based on virtual reality that will significantly reduce the limitations of the mechanical articulator, and by simulation of real patient data, allow analyses with regard to static and dynamic occlusion as well as to jaw relation. It is the purpose of this article to present the concepts and strategies for a future replacement of the mechanical articulator by a virtual one. Also, a brief note on virtual reality haptic system has been highlighted along with newly developed touch enabled virtual articulator. PMID:25177664

  16. Handling limited datasets with neural networks in medical applications: A small-data approach.

    Science.gov (United States)

    Shaikhina, Torgyn; Khovanova, Natalia A

    2017-01-01

    Single-centre studies in medical domain are often characterised by limited samples due to the complexity and high costs of patient data collection. Machine learning methods for regression modelling of small datasets (less than 10 observations per predictor variable) remain scarce. Our work bridges this gap by developing a novel framework for application of artificial neural networks (NNs) for regression tasks involving small medical datasets. In order to address the sporadic fluctuations and validation issues that appear in regression NNs trained on small datasets, the method of multiple runs and surrogate data analysis were proposed in this work. The approach was compared to the state-of-the-art ensemble NNs; the effect of dataset size on NN performance was also investigated. The proposed framework was applied for the prediction of compressive strength (CS) of femoral trabecular bone in patients suffering from severe osteoarthritis. The NN model was able to estimate the CS of osteoarthritic trabecular bone from its structural and biological properties with a standard error of 0.85MPa. When evaluated on independent test samples, the NN achieved accuracy of 98.3%, outperforming an ensemble NN model by 11%. We reproduce this result on CS data of another porous solid (concrete) and demonstrate that the proposed framework allows for an NN modelled with as few as 56 samples to generalise on 300 independent test samples with 86.5% accuracy, which is comparable to the performance of an NN developed with 18 times larger dataset (1030 samples). The significance of this work is two-fold: the practical application allows for non-destructive prediction of bone fracture risk, while the novel methodology extends beyond the task considered in this study and provides a general framework for application of regression NNs to medical problems characterised by limited dataset sizes. Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

  17. [Localized purpura revealing vascular prosthetic graft infection].

    Science.gov (United States)

    Boureau, A S; Lescalie, F; Cassagnau, E; Clairand, R; Connault, J

    2013-07-01

    Prosthetic graft infection after vascular reconstruction is a rare but serious complication. We report a case of infection occurring late after implantation of an iliofemoral prosthetic vascular graft. The Staphylococcus aureus infection was revealed by vascular purpura localized on the right leg 7 years after implantation of a vascular prosthesis. This case illustrates an uncommonly late clinical manifestation presenting as an acute infection 7 years after the primary operation. In this situation, the presentation differs from early infection, which generally occurs within the first four postoperative months. Diagnosis and treatment remain a difficult challenge because prosthetic graft infection is a potentially life-threatening complication. Morbidity and mortality rates are high. Here we detail specific aspects of the clinical and radiological presentation. Copyright © 2013 Elsevier Masson SAS. All rights reserved.

  18. Validation of the prosthetic esthetic index

    DEFF Research Database (Denmark)

    Özhayat, Esben B; Dannemand, Katrine

    2014-01-01

    OBJECTIVES: In order to diagnose impaired esthetics and evaluate treatments for these, it is crucial to evaluate all aspects of oral and prosthetic esthetics. No professionally administered index currently exists that sufficiently encompasses comprehensive prosthetic esthetics. This study aimed...... to validate a new comprehensive index, the Prosthetic Esthetic Index (PEI), for professional evaluation of esthetics in prosthodontic patients. MATERIAL AND METHODS: The content, criterion, and construct validity; the test-retest, inter-rater, and internal consistency reliability; and the sensitivity...... furthermore distinguish between participants and controls, indicating sufficient sensitivity. CONCLUSION: The PEI is considered a valid and reliable instrument involving sufficient aspects for assessment of the professionally evaluated esthetics in prosthodontic patients. CLINICAL RELEVANCE...

  19. Responsiveness of the Prosthetic Esthetic Scale

    DEFF Research Database (Denmark)

    Øzhayat, Esben Boeskov

    2017-01-01

    Objectives The aim of the study was to evaluate the responsiveness of the Prosthetic Esthetic Index (PEI) in a population who received prosthetic replacements. Materials and methods Fifty-seven patients who received prosthetic replacement of at least one tooth by means of fixed or removable...... prosthesis were professionally esthetically evaluated using the PEI and the Dental Aesthetic Index (DAI) before and after treatment. The participants further evaluated their oral esthetics using the Oral Health Impact Profile Aesthetic (OHIP-Aes) and Orofacial Esthetic Index (OES). Responsiveness......-Aes and OES scores. The PEI was more consistent in responsiveness than the DAI. Conclusions The PEI shows sufficient responsiveness for use in longitudinal studies and for use as a follow-up measure in clinical practice. Clinical relevance The PEI can in a standardized manner monitor and document esthetic...

  20. Ten questions on prosthetic shoulder infection.

    Science.gov (United States)

    Pinder, Elizabeth M; Ong, Joshua Cy; Bale, R Stephen; Trail, Ian A

    2016-07-01

    Prosthetic shoulder infection can cause significant morbidity secondary to pain and stiffness. Symptoms may be present for years before diagnosis because clinical signs are often absent and inflammatory markers may be normal. An emerging common culprit, Propionibacterium acnes, is hard to culture and so prolonged incubation is necessary. A negative culture result does not always exclude infection and new synovial fluid biochemical markers such as α defensin are less sensitive than for lower limb arthroplasty. A structured approach is necessary when assessing patients for prosthetic shoulder joint infection. This includes history, examination, serum inflammatory markers, plain radiology and aspiration and/or biopsy. A classification for the likelihood of prosthetic shoulder infection has been described based on culture, pre-operative and intra-operative findings. Treatment options include antibiotic suppression, debridement with component retention, one-stage revision, two-stage revision and excision arthroplasty. Revision arthroplasty is associated with the best outcomes.

  1. Bruxism and prosthetic treatment: a critical review.

    Science.gov (United States)

    Johansson, Anders; Omar, Ridwaan; Carlsson, Gunnar E

    2011-07-01

    Based on the findings from available research on bruxism and prosthetic treatment published in the dental literature, an attempt was made to draw conclusions about the existence of a possible relationship between the two, and its clinical relevance. MEDLINE/PubMed searches were conducted using the terms 'bruxism' and 'prosthetic treatment', as well as combinations of these and related terms. The few studies judged to be relevant were critically reviewed, in addition to papers found during an additional manual search of reference lists within selected articles. Bruxism is a common parafunctional habit, occurring both during sleep and wakefulness. Usually it causes few serious effects, but can do so in some patients. The etiology is multifactorial. There is no known treatment to stop bruxism, including prosthetic treatment. The role of bruxism in the process of tooth wear is unclear, but it is not considered a major cause. As informed by the present critical review, the relationship between bruxism and prosthetic treatment is one that relates mainly to the effect of the former on the latter. Bruxism may be included among the risk factors, and is associated with increased mechanical and/or technical complications in prosthodontic rehabilitation, although it seems not to affect implant survival. When prosthetic intervention is indicated in a patient with bruxism, efforts should be made to reduce the effects of likely heavy occlusal loading on all the components that contribute to prosthetic structural integrity. Failure to do so may indicate earlier failure than is the norm. Copyright © 2011 Japan Prosthodontic Society. Published by Elsevier Ltd. All rights reserved.

  2. An application of neural networks in microeconomics: input-output mapping in a power generation subsector of the US electricity industry

    NARCIS (Netherlands)

    Erbas, B.C.; Stefanou, S.E.

    2009-01-01

    The use of the artificial neural networks in economics and business goes back to 1950s, while the major bulk of the applications have been developed in more recent years. Reviewing this literature indicates that the field of business benefits from the neural networks in a wide spectrum from

  3. Gene regulation in adult neural stem cells : Current challenges and possible applications

    NARCIS (Netherlands)

    Encinas, J.M.; Fitzsimons, C.P.

    2017-01-01

    Adult neural stem and progenitor cells (NSPCs) offer a unique opportunity for neural regeneration and niche modification in physiopathological conditions, harnessing the capability to modify from neuronal circuits to glial scar. Findings exposing the vast plasticity and potential of NSPCs have

  4. Applicability of neural networks to etalon fringe filtering in laser spectrometers

    Science.gov (United States)

    Nicely, J. M.; Hanisco, T. F.; Riris, H.

    2018-05-01

    We present a neural network algorithm for spectroscopic retrievals of concentrations of trace gases. Using synthetic data we demonstrate that a neural network is well suited for filtering etalon fringes and provides superior performance to conventional least squares minimization techniques. This novel method can improve the accuracy of atmospheric retrievals and minimize biases.

  5. Application of Integrated Neural Network Method to Fault Diagnosis of Nuclear Steam Generator

    International Nuclear Information System (INIS)

    Zhou Gang; Yang Li

    2009-01-01

    A new fault diagnosis method based on integrated neural networks for nuclear steam generator (SG) was proposed in view of the shortcoming of the conventional fault monitoring and diagnosis method. In the method, two neural networks (ANNs) were employed for the fault diagnosis of steam generator. A neural network, which was used for predicting the values of steam generator operation parameters, was taken as the dynamics model of steam generator. The principle of fault monitoring method using the neural network model is to detect the deviations between process signals measured from an operating steam generator and corresponding output signals from the neural network model of steam generator. When the deviation exceeds the limit set in advance, the abnormal event is thought to occur. The other neural network as a fault classifier conducts the fault classification of steam generator. So, the fault types of steam generator are given by the fault classifier. The clear information on steam generator faults was obtained by fusing the monitoring and diagnosis results of two neural networks. The simulation results indicate that employing integrated neural networks can improve the capacity of fault monitoring and diagnosis for the steam generator. (authors)

  6. Application of artificial neural networks in the analysis of multi-particle data

    International Nuclear Information System (INIS)

    Kunze, M.

    1995-01-01

    During the past years artificial neural networks (ANN) have gained increasing interest not only in the regime of financial forecast and data mining, but also in the field of particle physics. Up to now artificial neural networks have mostly been applied in high energy physics trigger studies. The use of ANNs in medium energy physics data analysis is summarized. (author). 21 refs., 9 figs

  7. Applicability of Neural Networks to Etalon Fringe Filtering in Laser Spectrometers

    Science.gov (United States)

    Nicely, J. M.; Hanisco, T. F.; Riris, H.

    2018-01-01

    We present a neural network algorithm for spectroscopic retrievals of concentrations of trace gases. Using synthetic data we demonstrate that a neural network is well suited for filtering etalon fringes and provides superior performance to conventional least squares minimization techniques. This novel method can improve the accuracy of atmospheric retrievals and minimize biases.

  8. Optimising the prescription of prosthetic technologies (opptec): Outcome measures for evidence based prosthetic practice and use

    LENUS (Irish Health Repository)

    Ryall, Dr Nicola

    2010-01-01

    This study provided a forum for patients and service providers to voice their opinions in what they believe to be the important predictors and outcomes involved in successful rehabilitation following limb loss. To develop a consensus on the most important outcomes and factors to address for both the lower limb and upper limb prosthetic prescription process, the above data relating to lower limb and upper prosthetics were subsequently used in the next phase of the research involving two Delphi surveys of 23 and 53 experts within the lower limb and upper limb amputation and prosthetic field respectively, including users, service providers and researchers.\\r\

  9. [Multiple agenesis and prosthetic restoration].

    Science.gov (United States)

    Renault, P

    1990-03-01

    Cases of multiple agenesia present some difficulties in the treatment planing. Three situations may be encountered: limited agenesia, restored by a fixed, bonded or cemented prosthesis, multiple uni- or bimaxillary agenesia without remaining of deciduous teeth, restored by a fixed, bonded or cemented prosthesis or the partial adjacent prosthesis, multiple uni- or bimaxillary agenesia with remaining of deciduous teeth, restored by means of a supra-dental prosthesis. The first two situations have been described in dental literature and are relatively easy to treat. The same is not true for the third situation, where the decision to keep the temporary teeth considerably increases the difficulty of prosthetic restoration. This subject will be illustrated by the presentation of a clinical case of multiple bi-maxillary agenesia. The patient has: on the maxilla: an absence of 9 permanent teeth (18, 15, 14, 12, 22, 23, 24, 25, 28) and the presence of 4 deciduous teeth (62, 63, 64, 65), on the mandible: an absence of all permanent teeth, with the exception of 36 and 46, and the remaining of 4 deciduous teeth (75, 73, 83, 84). The remaining of deciduous teeth and the presence of a very high inter-arch space led to opting for dental coverage so as to keep the deciduous teeth and a proper vertical dimension. The patient wished to solve his "problem" in the maxilla first, and is not wanting to undergo the extraction of his deciduous teeth. The following therapeutic proposal was adapted: On the maxilla, a three-step procedure: first step: building of metal copings on 13, 16 and 26 and metal-ceramic crowns on 11 and 21, second step: building of telescop crowns on 16 and 26 and clasps on 13, 11 and 21, third step: casting of the removable partial denture framework and soldering to the telescop crowns and clasps. On the mandible, a provisional restoration using a supra-dental resin removable partial denture with ceramic occlusal surfaces was adopted. The aesthetic and functional

  10. Mesofluidic controlled robotic or prosthetic finger

    Science.gov (United States)

    Lind, Randall F; Jansen, John F; Love, Lonnie J

    2013-11-19

    A mesofluidic powered robotic and/or prosthetic finger joint includes a first finger section having at least one mesofluidic actuator in fluid communication with a first actuator, a second mesofluidic actuator in fluid communication with a second actuator and a second prosthetic finger section pivotally connected to the first finger section by a joint pivot, wherein the first actuator pivotally cooperates with the second finger to provide a first mechanical advantage relative to the joint point and wherein the second actuator pivotally cooperates with the second finger section to provide a second mechanical advantage relative to the joint point.

  11. Application of two neural network paradigms to the study of voluntary employee turnover.

    Science.gov (United States)

    Somers, M J

    1999-04-01

    Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

  12. Nuclear power plant monitoring method by neural network and its application to actual nuclear reactor

    International Nuclear Information System (INIS)

    Nabeshima, Kunihiko; Suzuki, Katsuo; Shinohara, Yoshikuni; Tuerkcan, E.

    1995-11-01

    In this paper, the anomaly detection method for nuclear power plant monitoring and its program are described by using a neural network approach, which is based on the deviation between measured signals and output signals of neural network model. The neural network used in this study has three layered auto-associative network with 12 input/output, and backpropagation algorithm is adopted for learning. Furthermore, to obtain better dynamical model of the reactor plant, a new learning technique was developed in which the learning process of the present neural network is divided into initial and adaptive learning modes. The test results at the actual nuclear reactor shows that the neural network plant monitoring system is successfull in detecting in real-time the symptom of small anomaly over a wide power range including reactor start-up, shut-down and stationary operation. (author)

  13. An application of neural networks and artificial intelligence for in-core fuel management

    International Nuclear Information System (INIS)

    Miller, L.F.; Algutifan, F.; Uhrig, R.E.

    1992-01-01

    This paper reports the feasibility of using expert systems in combination with neural networks and neutronics calculations to improve the efficiency for obtaining optimal candidate reload core designs. The general objectives of this research are as follows: (1) generate a suitable data base and ancillary software for training neural networks that duplicate neutronics calculations. (2) develop a graphical interface with neutronics software and neural networks for manual shuffling of reload cores. (3) construct an expert system for shuffling reload cores with specified rules. (4) develp neural networks that capture the nonlinear behavior of fuel depletion. (5) integrate the neural networks and neutronics software with an expert system to specify reload cores that obtain appropriate figure of merit

  14. APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN CLASSIFICATION OF HIGH RESOLUTION AGRICULTURAL REMOTE SENSING IMAGES

    Directory of Open Access Journals (Sweden)

    C. Yao

    2017-09-01

    Full Text Available With the rapid development of Precision Agriculture (PA promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN. For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

  15. Expandable and Rapidly Differentiating Human Induced Neural Stem Cell Lines for Multiple Tissue Engineering Applications

    Directory of Open Access Journals (Sweden)

    Dana M. Cairns

    2016-09-01

    Full Text Available Limited availability of human neurons poses a significant barrier to progress in biological and preclinical studies of the human nervous system. Current stem cell-based approaches of neuron generation are still hindered by prolonged culture requirements, protocol complexity, and variability in neuronal differentiation. Here we establish stable human induced neural stem cell (hiNSC lines through the direct reprogramming of neonatal fibroblasts and adult adipose-derived stem cells. These hiNSCs can be passaged indefinitely and cryopreserved as colonies. Independently of media composition, hiNSCs robustly differentiate into TUJ1-positive neurons within 4 days, making them ideal for innervated co-cultures. In vivo, hiNSCs migrate, engraft, and contribute to both central and peripheral nervous systems. Lastly, we demonstrate utility of hiNSCs in a 3D human brain model. This method provides a valuable interdisciplinary tool that could be used to develop drug screening applications as well as patient-specific disease models related to disorders of innervation and the brain.

  16. PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications.

    Science.gov (United States)

    Pasquier, C; Promponas, V J; Hamodrakas, S J

    2001-08-15

    A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the avoidance of data overfitting. Capturing information from as few as 50 protein sequences spread among the four target classes (6 transmembrane, 10 fibrous, 13 globular, and 17 mixed), PRED-CLASS was able to obtain 371 correct predictions out of a set of 387 proteins (success rate approximately 96%) unambiguously assigned into one of the target classes. The application of PRED-CLASS to several test sets and complete proteomes of several organisms demonstrates that such a method could serve as a valuable tool in the annotation of genomic open reading frames with no functional assignment or as a preliminary step in fold recognition and ab initio structure prediction methods. Detailed results obtained for various data sets and completed genomes, along with a web sever running the PRED-CLASS algorithm, can be accessed over the World Wide Web at http://o2.biol.uoa.gr/PRED-CLASS.

  17. High purity of human oligodendrocyte progenitor cells obtained from neural stem cells: suitable for clinical application.

    Science.gov (United States)

    Wang, Caiying; Luan, Zuo; Yang, Yinxiang; Wang, Zhaoyan; Wang, Qian; Lu, Yabin; Du, Qingan

    2015-01-30

    Recent studies have suggested that the transplantation of oligodendrocyte progenitor cells (OPCs) may be a promising potential therapeutic strategy for a broad range of diseases affecting myelin, such as multiple sclerosis, periventricular leukomalacia, and spinal cord injury. Clinical interest arose from the potential of human stem cells to be directed to OPCs for the clinical application of treating these diseases since large quantities of high quality OPCs are needed. However, to date, there have been precious few studies about OPC induction from human neural stem cells (NSCs). Here we successfully directed human fetal NSCs into highly pure OPCs using a cocktail of basic fibroblast growth factor, platelet-derived growth factor, and neurotrophic factor-3. These cells had typical morphology of OPCs, and 80-90% of them expressed specific OPC markers such as A2B5, O4, Sox10 and PDGF-αR. When exposed to differentiation medium, 90% of the cells differentiated into oligodendrocytes. The OPCs could be amplified in our culture medium and passaged at least 10 times. Compared to a recent published method, this protocol had much higher stability and repeatability, and OPCs could be obtained from NSCs from passage 5 to 38. It also obtained more highly pure OPCs (80-90%) via simpler and more convenient manipulation. This study provided an easy and efficient method to obtain large quantities of high-quality human OPCs to meet clinical demand. Copyright © 2014 Elsevier B.V. All rights reserved.

  18. Optimization of a hardware implementation for pulse coupled neural networks for image applications

    Science.gov (United States)

    Gimeno Sarciada, Jesús; Lamela Rivera, Horacio; Warde, Cardinal

    2010-04-01

    Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.

  19. Application of Recurrent Neural Networks on El Nino Impact on California Climate

    Science.gov (United States)

    Le, J.; El-Askary, H. M.; Allai, M.

    2017-12-01

    Following our successful paper on the application for the El Nino season of 2015-2016 over Southern California, we use recurrent neural networks (RNNs) to investigate the complex interactions between the long-term trend in dryness and a projected, short but intense, period of wetness due to the 2015-2016 El Niño. Although it was forecasted that this El Niño season would bring significant rainfall to the region, our long-term projections of the Palmer Z Index (PZI) showed a continuing drought trend. We achieved a statistically significant correlation of 0.610 between forecasted and observed PZI on the validation set for a lead time of 1 month. This gives strong confidence to the forecasted precipitation indicator. These predictions were bourne out in the resulting data. This paper details the expansion of our system to the climate of the entire California climate as a whole, dealing with inter-relationships and spatial variations within the state.

  20. Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications

    Science.gov (United States)

    Pastur-Romay, Lucas Antón; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana Belén

    2016-01-01

    Over the past decade, Deep Artificial Neural Networks (DNNs) have become the state-of-the-art algorithms in Machine Learning (ML), speech recognition, computer vision, natural language processing and many other tasks. This was made possible by the advancement in Big Data, Deep Learning (DL) and drastically increased chip processing abilities, especially general-purpose graphical processing units (GPGPUs). All this has created a growing interest in making the most of the potential offered by DNNs in almost every field. An overview of the main architectures of DNNs, and their usefulness in Pharmacology and Bioinformatics are presented in this work. The featured applications are: drug design, virtual screening (VS), Quantitative Structure–Activity Relationship (QSAR) research, protein structure prediction and genomics (and other omics) data mining. The future need of neuromorphic hardware for DNNs is also discussed, and the two most advanced chips are reviewed: IBM TrueNorth and SpiNNaker. In addition, this review points out the importance of considering not only neurons, as DNNs and neuromorphic chips should also include glial cells, given the proven importance of astrocytes, a type of glial cell which contributes to information processing in the brain. The Deep Artificial Neuron–Astrocyte Networks (DANAN) could overcome the difficulties in architecture design, learning process and scalability of the current ML methods. PMID:27529225

  1. Artificial neural network application in isotopic characterization of radioactive waste drums

    International Nuclear Information System (INIS)

    Potiens Junior, Ademar Jose

    2005-01-01

    One of the most important aspects to the development of the nuclear technology is the safe management of the radioactive waste arising from several stages of the nuclear fuel cycles, as well as from production and use of radioisotope in the medicine, industry and research centers. The accurate characterization of this waste is not a simple task, given to its diversity in isotopic composition and non homogeneity in the space distribution and mass density. In this work it was developed a methodology for quantification and localization of radionuclides not non homogeneously distributed in a 200 liters drum based in the Monte Carlo Method and Artificial Neural Network (RNA), for application in the isotopic characterization of the stored radioactive waste at IPEN. Theoretical arrangements had been constructed involving the division of the radioactive waste drum in some units or cells and some possible configurations of source intensities. Beyond the determination of the detection positions, the respective detection efficiencies for each position in function of each cell of the drum had been obtained. After the construction and the training of the RNA's for each developed theoretical arrangement, the validation of the method were carried out for the two arrangements that had presented the best performance. The results obtained show that the methodology developed in this study could be an effective tool for isotopic characterization of radioactive wastes contained in many kind of packages. (author)

  2. Aspects of artificial neural networks - with applications in high energy physics

    International Nuclear Information System (INIS)

    Roegnvaldsson, T.S.

    1994-02-01

    Different aspects of artificial neural networks are studied and discussed. They are demonstrated to be powerful general purpose algorithms, applicable to many different problem areas like pattern recognition, function fitting and prediction. Multi-layer perceptron (MPL) models are shown to out perform previous standard approaches on both off-line and on-line analysis tasks in high energy physics, like quark flavour tagging and mass reconstruction, as well as being powerful tools for prediction tasks. It is also demonstrated how a self-organizing network can be employed to extract information from data, for instance to track down origins of unexpected model discrepancies. Furthermore, it is proved that the MPL is more efficient than the learning vector quantization technique on classification problems, by producing smoother discrimination surfaces, and that an MPL network should be trained with a noisy updating schedule if the Hessian is ill-conditioned - A result that is especially important for MPL network with more than just one hidden layer. 81 refs, 6 figs

  3. Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications.

    Science.gov (United States)

    Pastur-Romay, Lucas Antón; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana Belén

    2016-08-11

    Over the past decade, Deep Artificial Neural Networks (DNNs) have become the state-of-the-art algorithms in Machine Learning (ML), speech recognition, computer vision, natural language processing and many other tasks. This was made possible by the advancement in Big Data, Deep Learning (DL) and drastically increased chip processing abilities, especially general-purpose graphical processing units (GPGPUs). All this has created a growing interest in making the most of the potential offered by DNNs in almost every field. An overview of the main architectures of DNNs, and their usefulness in Pharmacology and Bioinformatics are presented in this work. The featured applications are: drug design, virtual screening (VS), Quantitative Structure-Activity Relationship (QSAR) research, protein structure prediction and genomics (and other omics) data mining. The future need of neuromorphic hardware for DNNs is also discussed, and the two most advanced chips are reviewed: IBM TrueNorth and SpiNNaker. In addition, this review points out the importance of considering not only neurons, as DNNs and neuromorphic chips should also include glial cells, given the proven importance of astrocytes, a type of glial cell which contributes to information processing in the brain. The Deep Artificial Neuron-Astrocyte Networks (DANAN) could overcome the difficulties in architecture design, learning process and scalability of the current ML methods.

  4. Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications

    Directory of Open Access Journals (Sweden)

    Lucas Antón Pastur-Romay

    2016-08-01

    Full Text Available Over the past decade, Deep Artificial Neural Networks (DNNs have become the state-of-the-art algorithms in Machine Learning (ML, speech recognition, computer vision, natural language processing and many other tasks. This was made possible by the advancement in Big Data, Deep Learning (DL and drastically increased chip processing abilities, especially general-purpose graphical processing units (GPGPUs. All this has created a growing interest in making the most of the potential offered by DNNs in almost every field. An overview of the main architectures of DNNs, and their usefulness in Pharmacology and Bioinformatics are presented in this work. The featured applications are: drug design, virtual screening (VS, Quantitative Structure–Activity Relationship (QSAR research, protein structure prediction and genomics (and other omics data mining. The future need of neuromorphic hardware for DNNs is also discussed, and the two most advanced chips are reviewed: IBM TrueNorth and SpiNNaker. In addition, this review points out the importance of considering not only neurons, as DNNs and neuromorphic chips should also include glial cells, given the proven importance of astrocytes, a type of glial cell which contributes to information processing in the brain. The Deep Artificial Neuron–Astrocyte Networks (DANAN could overcome the difficulties in architecture design, learning process and scalability of the current ML methods.

  5. Tomographic and echocardiographic diagnosis of mitral prosthetic valve thrombosis

    International Nuclear Information System (INIS)

    Sainz Gonzalez de la Penna, Benito; Ramos Gutierrez, Luis Benito; Gonzalez Artiles, Iovank

    2010-01-01

    Despite the progress achieved in the design of mechanical prosthetic valves, prosthetic valve thrombosis remains a frequent cause of morbidity, usually due to incorrect anticoagulation. A patient was presented with mitral prosthetic thrombosis one year after implantation, who had been diagnosed by transthoracic transesophageal echocardiography imaging and 64-slice computed tomography. Thrombolytic therapy was successful and led to the satisfactory evolution of the patient

  6. Diagnosis of arterial prosthetic graft infection by 111In oxine white blood cell scans

    International Nuclear Information System (INIS)

    McKeown, P.P.; Miller, D.C.; Jamieson, S.W.; Mitchell, R.S.; Reitz, B.A.; Olcott, C.; Mehigan, J.T.; Silberstein, R.J.; McDougall, I.R.

    1982-01-01

    Early and accurate diagnosis of infected prosthetic arterial grafts is difficult, despite the application of diverse diagnostic modalities. Delay in making the diagnosis is largely responsible for the high amputation and mortality rates associated with this complication. In nine patients with suspected graft infections, 111 In white blood cell scanning was useful and accurate. Graft infection was proved in five cases and ruled out in three. One false-positive scan was due to a sigmoid diverticular abscess overlying the graft. 111 In white blood cell scans may improve the accuracy of diagnosing infected prosthetic grafts, which may result in better limb and patient salvage rates

  7. Application of an artificial neural network to ready-mixed concretes mix design

    Directory of Open Access Journals (Sweden)

    Setién, J.

    2003-06-01

    Full Text Available This paper presents the practical application of cm artificial neural network (ANN to the problem of concrete mix in a factory. After a brief introduction to the complex problem of concrete mixes design and a quick review of the fundamental basis of neurocomputation, an optimal neural network model has been developed to cope with such a problem. For training the net, several control mixes have been fabricated recording in all cases both the characteristic 28 days compressive strength and the workability measured in terms of the slump of the Abrams' cone. After the training process of the net, the power of its predictive ability is checked by comparison of the results obtained with those corresponding to four reference mixes; in this way, it is shown that the considered approach can be used in multicriterial search for optimal concrete mixes.

    En este trabajo se presenta la aplicación práctica de una red neuronal artificial (ANN al problema de la dosificación de hormigones en planta. Tras una breve introducción a la compleja problemática de la dosificación de hormigones y un repaso a los fundamentos de la neurocomputación, se diseña un modelo de red neuronal óptimo para abordar el problema. Para entrenar dicha red, se realizan varias amasadas de prueba, registrándose para cada una de ellas la trabajabilidad, mediante la medida del asiento del cono de Abrams, y ¡a resistencia característica a los 28 días. Una vez entrenada la red, se pone a prueba su carácter predictivo comparando los resultados que proporciona con los de cuatro amasadas de referencia, demostrándose que esta aproximación puede ser utilizada como método multicriterial para la obtención de mezclas óptimas de hormigón.

  8. Modeling by artificial neural networks. Application to the management of fuel in a nuclear power plant

    International Nuclear Information System (INIS)

    Gaudier, F.

    1999-01-01

    The determination of the family of optimum core loading patterns for Pressurized Water Reactors (PWRs) involves the assessment of the core attributes, such as the power peaking factor for thousands of candidate loading patterns. Despite the rapid advances in computer architecture, the direct calculation of these attributes by a neutronic code needs a lot of of time and memory. With the goal of reducing the calculation time and optimizing the loading pattern, we propose in this thesis a method based on ideas of neural and statistical learning to provide a feed forward neural network capable of calculating the power peaking corresponding to an eighth core PWR. We use statistical methods to deduct judicious inputs (reduction of the input space dimension) and neural methods to train the model (learning capabilities). Indeed, on one hand, a principal component analysis allows us to characterize more efficiently the fuel assemblies (neural model inputs) and the other hand, the introduction of the a priori knowledge allows us to reducing the number of freedom parameters in the neural network. The model was built using a multi layered perceptron trained with the standard back propagation algorithm. We introduced our neural network in the automatic optimization code FORMOSA, and on EDF real problems we showed an important saving in time. Finally, we propose an hybrid method which combining the best characteristics of the linear local approximator GPT (Generalized Perturbation Theory) and the artificial neural network. (author)

  9. Application of improved PSO-RBF neural network in the synthetic ammonia decarbonization

    Directory of Open Access Journals (Sweden)

    Yongwei LI

    2017-12-01

    Full Text Available The synthetic ammonia decarbonization is a typical complex industrial process, which has the characteristics of time variation, nonlinearity and uncertainty, and the on-line control model is difficult to be established. An improved PSO-RBF neural network control algorithm is proposed to solve the problems of low precision and poor robustness in the complex process of the synthetic ammonia decarbonization. The particle swarm optimization algorithm and RBF neural network are combined. The improved particle swarm algorithm is used to optimize the RBF neural network's hidden layer primary function center, width and the output layer's connection value to construct the RBF neural network model optimized by the improved PSO algorithm. The improved PSO-RBF neural network control model is applied to the key carbonization process and compared with the traditional fuzzy neural network. The simulation results show that the improved PSO-RBF neural network control method used in the synthetic ammonia decarbonization process has higher control accuracy and system robustness, which provides an effective way to solve the modeling and optimization control of a complex industrial process.

  10. Spark erosion implant prosthetics in the management of an acquired maxillofacial defect.

    Science.gov (United States)

    Bloem, T J; Baxter, W D; Vivas, J

    1996-03-01

    The concept and use of spark erosion (EDM) prosthetics in implant prosthodontics has been described and demonstrated in its application to a patient suffering maxillofacial trauma. The advantages and disadvantages of this technology have been discussed for the edification of the restorative and surgical provider.

  11. Application of Neural Network Optimized by Mind Evolutionary Computation in Building Energy Prediction

    Science.gov (United States)

    Song, Chen; Zhong-Cheng, Wu; Hong, Lv

    2018-03-01

    Building Energy forecasting plays an important role in energy management and plan. Using mind evolutionary algorithm to find the optimal network weights and threshold, to optimize the BP neural network, can overcome the problem of the BP neural network into a local minimum point. The optimized network is used for time series prediction, and the same month forecast, to get two predictive values. Then two kinds of predictive values are put into neural network, to get the final forecast value. The effectiveness of the method was verified by experiment with the energy value of three buildings in Hefei.

  12. Application of artificial neural network for heat transfer in porous cone

    Science.gov (United States)

    Athani, Abdulgaphur; Ahamad, N. Ameer; Badruddin, Irfan Anjum

    2018-05-01

    Heat transfer in porous medium is one of the classical areas of research that has been active for many decades. The heat transfer in porous medium is generally studied by using numerical methods such as finite element method; finite difference method etc. that solves coupled partial differential equations by converting them into simpler forms. The current work utilizes an alternate method known as artificial neural network that mimics the learning characteristics of neurons. The heat transfer in porous medium fixed in a cone is predicted using backpropagation neural network. The artificial neural network is able to predict this behavior quite accurately.

  13. An Application to the Prediction of LOD Change Based on General Regression Neural Network

    Science.gov (United States)

    Zhang, X. H.; Wang, Q. J.; Zhu, J. J.; Zhang, H.

    2011-07-01

    Traditional prediction of the LOD (length of day) change was based on linear models, such as the least square model and the autoregressive technique, etc. Due to the complex non-linear features of the LOD variation, the performances of the linear model predictors are not fully satisfactory. This paper applies a non-linear neural network - general regression neural network (GRNN) model to forecast the LOD change, and the results are analyzed and compared with those obtained with the back propagation neural network and other models. The comparison shows that the performance of the GRNN model in the prediction of the LOD change is efficient and feasible.

  14. Optical implementation of a feature-based neural network with application to automatic target recognition

    Science.gov (United States)

    Chao, Tien-Hsin; Stoner, William W.

    1993-01-01

    An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

  15. Genetic algorithm based adaptive neural network ensemble and its application in predicting carbon flux

    Science.gov (United States)

    Xue, Y.; Liu, S.; Hu, Y.; Yang, J.; Chen, Q.

    2007-01-01

    To improve the accuracy in prediction, Genetic Algorithm based Adaptive Neural Network Ensemble (GA-ANNE) is presented. Intersections are allowed between different training sets based on the fuzzy clustering analysis, which ensures the diversity as well as the accuracy of individual Neural Networks (NNs). Moreover, to improve the accuracy of the adaptive weights of individual NNs, GA is used to optimize the cluster centers. Empirical results in predicting carbon flux of Duke Forest reveal that GA-ANNE can predict the carbon flux more accurately than Radial Basis Function Neural Network (RBFNN), Bagging NN ensemble, and ANNE. ?? 2007 IEEE.

  16. Application of particle swarm optimization to identify gamma spectrum with neural network

    International Nuclear Information System (INIS)

    Shi Dongsheng; Di Yuming; Zhou Chunlin

    2007-01-01

    In applying neural network to identification of gamma spectra back propagation (BP) algorithm is usually trapped to a local optimum and has a low speed of convergence, whereas particle swarm optimization (PSO) is advantageous in terms of globe optimal searching. In this paper, we propose a new algorithm for neural network training, i.e. combined BP and PSO optimization, or PSO-BP algorithm. Practical example shows that the new algorithm can overcome shortcomings of BP algorithm and the neural network trained by it has a high ability of generalization with identification result of 100% correctness. It can be used effectively and reliably to identify gamma spectra. (authors)

  17. Application Of Artificial Neural Networks In Modeling Of Manufactured Front Metallization Contact Resistance For Silicon Solar Cells

    Directory of Open Access Journals (Sweden)

    Musztyfaga-Staszuk M.

    2015-09-01

    Full Text Available This paper presents the application of artificial neural networks for prediction contact resistance of front metallization for silicon solar cells. The influence of the obtained front electrode features on electrical properties of solar cells was estimated. The front electrode of photovoltaic cells was deposited using screen printing (SP method and next to manufactured by two methods: convectional (1. co-fired in an infrared belt furnace and unconventional (2. Selective Laser Sintering. Resistance of front electrodes solar cells was investigated using Transmission Line Model (TLM. Artificial neural networks were obtained with the use of Statistica Neural Network by Statsoft. Created artificial neural networks makes possible the easy modelling of contact resistance of manufactured front metallization and allows the better selection of production parameters. The following technological recommendations for the screen printing connected with co-firing and selective laser sintering technology such as optimal paste composition, morphology of the silicon substrate, co-firing temperature and the power and scanning speed of the laser beam to manufacture the front electrode of silicon solar cells were experimentally selected in order to obtain uniformly melted structure well adhered to substrate, of a small front electrode substrate joint resistance value. The prediction possibility of contact resistance of manufactured front metallization is valuable for manufacturers and constructors. It allows preserving the customers’ quality requirements and bringing also measurable financial advantages.

  18. Application of neural networks to prediction of phase transport characteristics in high-pressure two-phase turbulent bubbly flows

    International Nuclear Information System (INIS)

    Yang, A.-S.; Kuo, T.-C.; Ling, P.-H.

    2003-01-01

    The phase transport phenomenon of the high-pressure two-phase turbulent bubbly flow involves complicated interfacial interactions of the mass, momentum, and energy transfer processes between phases, revealing that an enormous effort is required in characterizing the liquid-gas flow behavior. Nonetheless, the instantaneous information of bubbly flow properties is often desired for many industrial applications. This investigation aims to demonstrate the successful use of neural networks in the real-time determination of two-phase flow properties at elevated pressures. Three back-propagation neural networks, trained with the simulation results of a comprehensive theoretical model, are established to predict the transport characteristics (specifically the distributions of void-fraction and axial liquid-gas velocities) of upward turbulent bubbly pipe flows at pressures covering 3.5-7.0 MPa. Comparisons of the predictions with the test target vectors indicate that the averaged root-mean-squared (RMS) error for each one of three back-propagation neural networks is within 4.59%. In addition, this study appraises the effects of different network parameters, including the number of hidden nodes, the type of transfer function, the number of training pairs, the learning rate-increasing ratio, the learning rate-decreasing ratio, and the momentum value, on the training quality of neural networks.

  19. Tactile Sensing Reflexes for Advanced Prosthetic Hands

    Science.gov (United States)

    2016-10-01

    Jeremy A. Fishel, Member, IEEE Figure 1. A) Custom NumaTac prosthetic fingertip sensor core and foam; B) Ottobock VariPlus Speed hand installed with two...oal – H ardw are P rototype D evelopm ent R   Identify alternatives for outcom e m easures R   E xplore sensor design param eters C Y16 G oals – C

  20. Prosthetic Management of Patients Presenting with Juvenile ...

    African Journals Online (AJOL)

    Eighteen were referred for prosthetic replacement. Their age ranged between 18 and 36 years. A total of 24 removable partial dentures were fabricated, 17[70.8%] were kennedy class III type, of which 11[64.7%] had the bounded saddle located in the anterior segment. Majority 8[44.4%] of the patients had 2-4 teeth replaced ...

  1. Successful Thrombolysis of Aortic Prosthetic Valve Thrombosis ...

    African Journals Online (AJOL)

    Arun Kumar Agnihotri

    patients with valvular heart disease). Endorsed by the Society of Cardiovascular. Anesthesiologists, Society for Cardiovascular. Angiography and Interventions, and Society of. Thoracic Surgeons. J Am Coll Cardiol. 2008;52(13):e1-142. 5. Elkayam U, Bitar F. Valvular heart disease and pregnancy. Part II: prosthetic valves.

  2. Multimodality Imaging Assessment of Prosthetic Heart Valves

    NARCIS (Netherlands)

    Suchá, D.; Symersky, Petr; Tanis, W; Mali, Willem P Th M; Leiner, Tim; van Herwerden, LA; Budde, Ricardo P J

    Echocardiography and fluoroscopy are the main techniques for prosthetic heart valve (PHV) evaluation, but because of specific limitations they may not identify the morphological substrate or the extent of PHV pathology. Cardiac computed tomography (CT) and magnetic resonance imaging (MRI) have

  3. The Prosthetic Experience Between Body and Technology

    DEFF Research Database (Denmark)

    Søndergaard, Morten

    2018-01-01

    In this paper, I argue that a prosthetic aesthetic instigated by experimental art practices operate with and within a ‘second nature’ – in-between science and art. Drawing on theories from Dewey and Edelman and examples from Da Vinci, Brancusi, Man Ray, Dali and Stelarc, I am calling...

  4. Consumer satisfaction in prosthetics and orthotics facilities

    NARCIS (Netherlands)

    Geertzen, J.H.B.; Gankema, H.G.J.; Groothoff, J.W.; Dijkstra, P.U.

    The aim of this study was to assess consumer/patient satisfaction with the services of the prosthetics and orthotics (P&O) facilities in the north of the Netherlands, using a modified SERVQUAL questionnaire. In this questionnaire, consumer interests and experiences are assessed on a 5-point Likert

  5. The relevance of aortic endograft prosthetic infection

    NARCIS (Netherlands)

    Cernohorsky, Paul; Reijnen, Michel M. P. J.; Tielliu, Ignace F. J.; van Sterkenburg, Steven M. M.; van den Dungen, Jan J. A. M.; Zeebregts, Clark J.

    Background: Vascular prosthetic graft infection is a severe complication after open aortic aneurysm repair. Reports of infected endografts are scarce. General treatment consensus with infected graft material is that it should be removed completely. The objective of this study was to describe the

  6. METHODOLOGY OF PROSTHETIC TREATMENT IN PATIENTS WITH MAXILLECTOMY

    Directory of Open Access Journals (Sweden)

    Ivan Gerdzhikov

    2018-06-01

    Full Text Available Aim: The aim of the described method is to present the main stages in the prosthetic treatment with hollow bulb obturator, which provides optimum defect hermetization and restoration of the damaged functions. Materials and methods: The clinical case, described is on a 70-years-old patient with edentulous jaws and maxillary defect in the right half of the upper jaw. The preliminary impressions were taken with irreversible hydrocolloid impression material, and the final impressions were taken with additive silicone material. The occlusion height and the centric relations were registered as the classical technique. After the successful trial denture appointment, the surface of the plaster master model was covered by isolation polish. After this procedure, the master model was covered by even wax layer with 5mm thickness. It was designed to be thinner in the area of the resection line. The designed cavity was filled in with silicone impression material and covered with the folio. The base plate with the arranged teeth was fixed to the model, packed in the cuvette and finished from heat-cured acrylic resin with low quantity of residual monomer. After the polymerization process, the silicone material was removed, and the obturators cap was fixed to the denture’s base plate with cold cured acrylic resin. The obturator and the complete denture of the mandible were adjusted and articulated in patient’s mouth in the final clinical stage. Results: The applied prosthetic method allowed successful defect hermetization and helped for the restoration of the speech, feeding and patient’s self-esteem. Conclusion: Prosthetic rehabilitation of patients with maxillary resection is possible only with the application of specific treatment methods.

  7. Pregnancy after Prosthetic Aortic Valve Replacement: How Do We Monitor Prosthetic Valvular Function during Pregnancy?

    Directory of Open Access Journals (Sweden)

    Nicole Sahasrabudhe

    2018-01-01

    Full Text Available Background. With modern medicine, many women after structural heart repair are deciding to experience pregnancy. There is a need for further study to identify normal echocardiographic parameters to better assess prosthetic valvular function in pregnancy. In addition, a multidisciplinary approach is essential in managing pregnant patients with complex cardiac conditions. Case. A 22-year-old nulliparous woman with an aortic valve replacement 18 months prior to her pregnancy presented to prenatal care at 20-week gestation. During her prenatal care, serial echocardiography showed a significant increase in the mean gradient across the prosthetic aortic valve. Multidisciplinary management and a serial echocardiography played an integral role in her care that resulted in a successful spontaneous vaginal delivery without complications. Conclusion. Further characterization of the normal echocardiographic parameters in pregnant patients with prosthetic valves is critical to optimize prenatal care for this patient population. This case report is novel in that serial echocardiograms were obtained throughout prenatal care, which showed significant changes across the prosthetic aortic valve. Teaching Points. (1 Further study is needed to identify normal echocardiographic parameters to best assess prosthetic valvular function in pregnancy. (2 Multidisciplinary management is encouraged to optimize prenatal care for women with prosthetic aortic valve replacements.

  8. Seafloor classification using acoustic backscatter echo-waveform - Artificial neural network applications

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Mahale, V.; Navelkar, G.S.; Desai, R.G.P.

    In this paper seafloor classifications system based on artificial neural network (ANN) has been designed. The ANN architecture employed here is a combination of Self Organizing Feature Map (SOFM) and Linear Vector Quantization (LVQ1). Currently...

  9. Adaptive control using a hybrid-neural model: application to a polymerisation reactor

    Directory of Open Access Journals (Sweden)

    Cubillos F.

    2001-01-01

    Full Text Available This work presents the use of a hybrid-neural model for predictive control of a plug flow polymerisation reactor. The hybrid-neural model (HNM is based on fundamental conservation laws associated with a neural network (NN used to model the uncertain parameters. By simulations, the performance of this approach was studied for a peroxide-initiated styrene tubular reactor. The HNM was synthesised for a CSTR reactor with a radial basis function neural net (RBFN used to estimate the reaction rates recursively. The adaptive HNM was incorporated in two model predictive control strategies, a direct synthesis scheme and an optimum steady state scheme. Tests for servo and regulator control showed excellent behaviour following different setpoint variations, and rejecting perturbations. The good generalisation and training capacities of hybrid models, associated with the simplicity and robustness characteristics of the MPC formulations, make an attractive combination for the control of a polymerisation reactor.

  10. Application of artificial neural networks in analysis of CHF experimental data in round tubes

    International Nuclear Information System (INIS)

    Huang Yanping; Chen Bingde; Lang Xuemei; Wang Xiaojun; Shan Jianqiang; Jia Dounan

    2004-01-01

    Artificial neural networks (ANNs) are applied successfully to analyze the critical heat flux (CHF) experimental data from some round tubes in this paper. A set of software adopting artificial neural network method for predicting CHF in round tube and a set of CHF database are gotten. Comparing with common CHF correlations and CHF look-up table, ANN method has stronger ability of allow-wrong and nice robustness. The CHF predicting software adopting artificial neural network technology can improve the predicting accuracy in a wider parameter range, and is easier to update and to use. The artificial neural network method used in this paper can be applied to some similar physical problems. (authors)

  11. Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines

    Directory of Open Access Journals (Sweden)

    Santosh Kumar Nanda

    2011-01-01

    Full Text Available Functional link-based neural network models were applied to predict opencast mining machineries noise. The paper analyzes the prediction capabilities of functional link neural network based noise prediction models vis-à-vis existing statistical models. In order to find the actual noise status in opencast mines, some of the popular noise prediction models, for example, ISO-9613-2, CONCAWE, VDI, and ENM, have been applied in mining and allied industries to predict the machineries noise by considering various attenuation factors. Functional link artificial neural network (FLANN, polynomial perceptron network (PPN, and Legendre neural network (LeNN were used to predict the machinery noise in opencast mines. The case study is based on data collected from an opencast coal mine of Orissa, India. From the present investigations, it could be concluded that the FLANN model give better noise prediction than the PPN and LeNN model.

  12. Bidirectional Joint Representation Learning with Symmetrical Deep Neural Networks for Multimodal and Crossmodal Applications

    OpenAIRE

    Vukotic , Vedran; Raymond , Christian; Gravier , Guillaume

    2016-01-01

    International audience; Common approaches to problems involving multiple modalities (classification, retrieval, hyperlinking, etc.) are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. In this work, we propose a flexible cross-modal deep neural network architecture for multimodal and ...

  13. An Exploratory Application of Neural Networks to the Sortie Generation Forecasting Problem

    Science.gov (United States)

    1991-09-01

    research of Dr. David A. Diener, Major, USAF. As the initial research increment to be improved upon by future researchers, this study (1) provides a... David A. Diener, Major, USAF, who virtually transformed my dream of exploring neural network techniques into concrete reality. His talents in...New York: John Wiley & Sons, 1978. Barron R. L., Gilstrap, L. 0., and Shrier , S. "Polynomial al and Neural Networks: Analogies and Engineering

  14. Neural Networks and Their Applications for the Oil Industry Les réseaux neuronaux et leurs applications pour l'industrie pétrolière

    Directory of Open Access Journals (Sweden)

    Fogelman-Soulie F.

    2006-11-01

    Full Text Available Neural Networks can be used in many different areas of problems related to Petroleum Exploration and Production. There already exist well defined classes of applications, together with appropriate Neural Networks architectures. Detailed theoretical results allow to monitor and evaluate the results obtained by Neural Networks. Sophisticated applications will certainly require the use of multi-modular architectures. Les réseaux neuronaux peuvent être utilisés pour de nombreux problèmes dans les domaines de l'exploration et la production de pétrole. Il existe d'ores et déjà des classes d'applications bien définies, pour lesquelles on connaît les architectures neuronales les plus adaptées. Des résultats théoriques précis permettent de contrôler et d'évaluer les performances obtenues avec les réseaux neuronaux. Les applications complexes demanderont certainement la mise en oeuvre d'architectures multi-modulaires.

  15. Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

    Science.gov (United States)

    Witoonchart, Peerajak; Chongstitvatana, Prabhas

    2017-08-01

    In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

  16. Applications of neural networks to real-time data processing at the Environmental and Molecular Sciences Laboratory (EMSL)

    International Nuclear Information System (INIS)

    Keller, P.E.; Kouzes, R.T.; Kangas, L.J.

    1993-06-01

    Detailed design of the Environmental and Molecular Sciences Laboratory (EMSL) at the Pacific Northwest Laboratory (PNL) is nearing completion and construction is scheduled to begin later this year. This facility will assist in the environmental restoration and waste management mission at the Hanford Site. This paper identifies several real-time data processing applications within the EMSL where neural networks can potentially be beneficial. These applications include real-time sensor data acquisition and analysis, spectral analysis, process control, theoretical modeling, and data compression

  17. Application of neural networks to measurement methods based on radiation interactions with matter

    International Nuclear Information System (INIS)

    Pilato, V.

    1999-01-01

    The possibility of improving by neuronal techniques the preparation and interpretation of nuclear measurements was investigated. A general methodology was developed and applied to various problems in this field. Whatever the problem to be treated, to solve it comes to determine the relation which binds the inputs to the outputs. Neural networks based on supervised training, like the multilayer Perceptron, have the capability to calculate any relation between a set of input and output data. On the other hand, the training phase is often a long and delicate operation whose difficulties grow with the size of the network: it is thus interesting to reduce it by introducing knowledge a priori and/or by reducing the number of inputs in order to extract the relevant information. If the correlations between the inputs are linear, the Principal Components Analysis (PCA) and its neuronal equivalents make it possible to obtain by orthogonal projection a reduced number of input components while preserving the maximum of initial information. If the correlations are nonlinear, the Curvilinear Components Analysis (CCA) allows, by a unsupervised training, to carry out a nonlinear projection of the inputs in a space of reduced size. Besides, it is noticed that when the dimension of the input space is equal to the intrinsic dimension of the problem, this last is practically solved by CCA. We propose a general method which consists in characterizing as well as possible the problem by its inputs and then to extract and classify the information contained in those by projection in a space of reduced size. Association between the projected data and the problem outputs is then carried out by a supervised training network. Certain results having to be provided with their associated uncertainty, a statistical method based on the bootstrap algorithm is proposed. Potential applications other that those treated are considered. (author)

  18. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.

    Science.gov (United States)

    Hirasawa, Toshiaki; Aoyama, Kazuharu; Tanimoto, Tetsuya; Ishihara, Soichiro; Shichijo, Satoki; Ozawa, Tsuyoshi; Ohnishi, Tatsuya; Fujishiro, Mitsuhiro; Matsuo, Keigo; Fujisaki, Junko; Tada, Tomohiro

    2018-07-01

    Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.

  19. Neural networks for aircraft control

    Science.gov (United States)

    Linse, Dennis

    1990-01-01

    Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

  20. Implant salvage in breast reconstruction with severe peri-prosthetic infection.

    Science.gov (United States)

    Meybodi, Farid; Sedaghat, Negin; French, James; Keighley, Caitlin; Mitchell, David; Elder, Elisabeth

    2017-12-01

    Although treatment of mild peri-prosthetic infection in implant-based breast reconstruction results in high rates of resolution, successful management of severe peri-prosthetic infection remains a significant challenge. In this case series, a protocol utilizing a novel dressing - negative pressure wound therapy with instillation (NPWTi) - for the management of severe peri-prosthetic infection in breast reconstruction patients is described. This is an operative technique involving: (i) explantation of the breast prosthesis and application of the NPWTi dressing to the implant pocket; (ii) change of the NPWTi dressing; (iii) intraoperative fluid/tissue cultures; and (iv) reimplantation of the breast prosthesis when cultures yield no growth. This protocol was utilized in six cases of severe peri-prosthetic infection in five patients with immediate breast reconstruction for breast cancer or risk-reducing surgery. Cultures of fluid/tissue grew typical and/or unusual organisms. Only one case did not yield an organism. The hospital length of stay upon completion of the protocol ranged from 7-16 days (mean, 12 days). Successful implant salvage was achieved in five of six cases. The protocol was aborted in one case to allow for completion of adjuvant chemotherapy. Early findings from this case series suggest that in cases of severe peri-prosthetic infection this novel operative protocol may result in successful implant salvage for breast reconstruction patients. Further studies are needed to more fully elaborate the role of NPWTi to achieve implant salvage in challenging cases of peri-prosthetic infection. © 2015 Royal Australasian College of Surgeons.

  1. Machine and component residual life estimation through the application of neural networks

    International Nuclear Information System (INIS)

    Herzog, M.A.; Marwala, T.; Heyns, P.S.

    2009-01-01

    This paper concerns the use of neural networks for predicting the residual life of machines and components. In addition, the advantage of using condition-monitoring data to enhance the predictive capability of these neural networks was also investigated. A number of neural network variations were trained and tested with the data of two different reliability-related datasets. The first dataset represents the renewal case where the failed unit is repaired and restored to a good-as-new condition. Data were collected in the laboratory by subjecting a series of similar test pieces to fatigue loading with a hydraulic actuator. The average prediction error of the various neural networks being compared varied from 431 to 841 s on this dataset, where test pieces had a characteristic life of 8971 s. The second dataset were collected from a group of pumps used to circulate a water and magnetite solution within a plant. The data therefore originated from a repaired system affected by reliability degradation. When optimized, the multi-layer perceptron neural networks trained with the Levenberg-Marquardt algorithm and the general regression neural network produced a sum-of-squares error within 11.1% of each other for the renewal dataset. The small number of inputs and poorly mapped input space on the second dataset meant that much larger errors were recorded on some of the test data. The potential for using neural networks for residual life prediction and the advantage of incorporating condition-based data into the model was nevertheless proven for both examples

  2. A review on cluster estimation methods and their application to neural spike data

    Science.gov (United States)

    Zhang, James; Nguyen, Thanh; Cogill, Steven; Bhatti, Asim; Luo, Lingkun; Yang, Samuel; Nahavandi, Saeid

    2018-06-01

    The extracellular action potentials recorded on an electrode result from the collective simultaneous electrophysiological activity of an unknown number of neurons. Identifying and assigning these action potentials to their firing neurons—‘spike sorting’—is an indispensable step in studying the function and the response of an individual or ensemble of neurons to certain stimuli. Given the task of neural spike sorting, the determination of the number of clusters (neurons) is arguably the most difficult and challenging issue, due to the existence of background noise and the overlap and interactions among neurons in neighbouring regions. It is not surprising that some researchers still rely on visual inspection by experts to estimate the number of clusters in neural spike sorting. Manual inspection, however, is not suitable to processing the vast, ever-growing amount of neural data. To address this pressing need, in this paper, thirty-three clustering validity indices have been comprehensively reviewed and implemented to determine the number of clusters in neural datasets. To gauge the suitability of the indices to neural spike data, and inform the selection process, we then calculated the indices by applying k-means clustering to twenty widely used synthetic neural datasets and one empirical dataset, and compared the performance of these indices against pre-existing ground truth labels. The results showed that the top five validity indices work consistently well across variations in noise level, both for the synthetic datasets and the real dataset. Using these top performing indices provides strong support for the determination of the number of neural clusters, which is essential in the spike sorting process.

  3. A review on cluster estimation methods and their application to neural spike data.

    Science.gov (United States)

    Zhang, James; Nguyen, Thanh; Cogill, Steven; Bhatti, Asim; Luo, Lingkun; Yang, Samuel; Nahavandi, Saeid

    2018-06-01

    The extracellular action potentials recorded on an electrode result from the collective simultaneous electrophysiological activity of an unknown number of neurons. Identifying and assigning these action potentials to their firing neurons-'spike sorting'-is an indispensable step in studying the function and the response of an individual or ensemble of neurons to certain stimuli. Given the task of neural spike sorting, the determination of the number of clusters (neurons) is arguably the most difficult and challenging issue, due to the existence of background noise and the overlap and interactions among neurons in neighbouring regions. It is not surprising that some researchers still rely on visual inspection by experts to estimate the number of clusters in neural spike sorting. Manual inspection, however, is not suitable to processing the vast, ever-growing amount of neural data. To address this pressing need, in this paper, thirty-three clustering validity indices have been comprehensively reviewed and implemented to determine the number of clusters in neural datasets. To gauge the suitability of the indices to neural spike data, and inform the selection process, we then calculated the indices by applying k-means clustering to twenty widely used synthetic neural datasets and one empirical dataset, and compared the performance of these indices against pre-existing ground truth labels. The results showed that the top five validity indices work consistently well across variations in noise level, both for the synthetic datasets and the real dataset. Using these top performing indices provides strong support for the determination of the number of neural clusters, which is essential in the spike sorting process.

  4. Multi-objective evolutionary optimization for constructing neural networks for virtual reality visual data mining: application to geophysical prospecting.

    Science.gov (United States)

    Valdés, Julio J; Barton, Alan J

    2007-05-01

    A method for the construction of virtual reality spaces for visual data mining using multi-objective optimization with genetic algorithms on nonlinear discriminant (NDA) neural networks is presented. Two neural network layers (the output and the last hidden) are used for the construction of simultaneous solutions for: (i) a supervised classification of data patterns and (ii) an unsupervised similarity structure preservation between the original data matrix and its image in the new space. A set of spaces are constructed from selected solutions along the Pareto front. This strategy represents a conceptual improvement over spaces computed by single-objective optimization. In addition, genetic programming (in particular gene expression programming) is used for finding analytic representations of the complex mappings generating the spaces (a composition of NDA and orthogonal principal components). The presented approach is domain independent and is illustrated via application to the geophysical prospecting of caves.

  5. Neural Networks

    International Nuclear Information System (INIS)

    Smith, Patrick I.

    2003-01-01

    Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

  6. Uptake of radiolabeled leukocytes in prosthetic graft infection

    International Nuclear Information System (INIS)

    Serota, A.I.; Williams, R.A.; Rose, J.G.; Wilson, S.E.

    1981-01-01

    The utility of radionuclide labeled leukocytes in the demonstration of infection within vascular prostheses was examined. The infrarenal aorta was replaced with a 3 cm Dacron graft in 12 dogs. On the third postoperative day, six of the animals received an intravenous injection of 10(8) Staphylococcus aureus. Labeled leukocyte scans were performed at postoperative days one and three, and then weekly for 8 weeks with indium-111 and technetium-99 labeled autologous leukocytes. When scans showed focal uptake of isotope in the area of prosthetic material, the grafts were aseptically excised and cultured on mannitol-salt agar. Both control and infected animals had retroperitoneal isotope activity in the immediate postoperative period that disappeared by the end of the first week. By the eighth postoperative week, all of the animals that received the bacteremic challenge had both radionuclide concentration in the region of the vascular prosthesis and S. aureus cultured subsequently from the perigraft tissues. None of the control animals had either radionuclide or bacteriologic evidence of infection at the eighth postoperative week. The radiolabeled leukocyte scan is a highly sensitive and specific technique, clinically applicable for the diagnosis of vascular prosthetic infections

  7. Application of neural networks to software quality modeling of a very large telecommunications system.

    Science.gov (United States)

    Khoshgoftaar, T M; Allen, E B; Hudepohl, J P; Aud, S J

    1997-01-01

    Society relies on telecommunications to such an extent that telecommunications software must have high reliability. Enhanced measurement for early risk assessment of latent defects (EMERALD) is a joint project of Nortel and Bell Canada for improving the reliability of telecommunications software products. This paper reports a case study of neural-network modeling techniques developed for the EMERALD system. The resulting neural network is currently in the prototype testing phase at Nortel. Neural-network models can be used to identify fault-prone modules for extra attention early in development, and thus reduce the risk of operational problems with those modules. We modeled a subset of modules representing over seven million lines of code from a very large telecommunications software system. The set consisted of those modules reused with changes from the previous release. The dependent variable was membership in the class of fault-prone modules. The independent variables were principal components of nine measures of software design attributes. We compared the neural-network model with a nonparametric discriminant model and found the neural-network model had better predictive accuracy.

  8. Differentiation of Equine Mesenchymal Stromal Cells into Cells of Neural Lineage: Potential for Clinical Applications

    Directory of Open Access Journals (Sweden)

    Claudia Cruz Villagrán

    2014-01-01

    Full Text Available Mesenchymal stromal cells (MSCs are able to differentiate into extramesodermal lineages, including neurons. Positive outcomes were obtained after transplantation of neurally induced MSCs in laboratory animals after nerve injury, but this is unknown in horses. Our objectives were to test the ability of equine MSCs to differentiate into cells of neural lineage in vitro, to assess differences in morphology and lineage-specific protein expression, and to investigate if horse age and cell passage number affected the ability to achieve differentiation. Bone marrow-derived MSCs were obtained from young and adult horses. Following demonstration of stemness, MSCs were neurally induced and microscopically assessed at different time points. Results showed that commercially available nitrogen-coated tissue culture plates supported proliferation and differentiation. Morphological changes were immediate and all the cells displayed a neural crest-like cell phenotype. Expression of neural progenitor proteins, was assessed via western blot or immunofluorescence. In our study, MSCs generated from young and middle-aged horses did not show differences in their ability to undergo differentiation. The effect of cell passage number, however, is inconsistent and further experiments are needed. Ongoing work is aimed at transdifferentiating these cells into Schwann cells for transplantation into a peripheral nerve injury model in horses.

  9. APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTION OF AIR POLLUTION LEVELS IN ENVIRONMENTAL MONITORING

    Directory of Open Access Journals (Sweden)

    Małgorzata Pawul

    2016-09-01

    Full Text Available Recently, a lot of attention was paid to the improvement of methods which are used to air quality forecasting. Artificial neural networks can be applied to model these problems. Their advantage is that they can solve the problem in the conditions of incomplete information, without the knowledge of the analytical relationship between the input and output data. In this paper we applied artificial neural networks to predict the PM 10 concentrations as factors determining the occurrence of smog phenomena. To create these networks we used meteorological data and concentrations of PM 10. The data were recorded in 2014 and 2015 at three measuring stations operating in Krakow under the State Environmental Monitoring. The best results were obtained by three-layer perceptron with back-propagation algorithm. The neural networks received a good fit in all cases.

  10. An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings

    Directory of Open Access Journals (Sweden)

    Luis Gonzaga Baca Ruiz

    2016-08-01

    Full Text Available This paper addresses the problem of energy consumption prediction using neural networks over a set of public buildings. Since energy consumption in the public sector comprises a substantial share of overall consumption, the prediction of such consumption represents a decisive issue in the achievement of energy savings. In our experiments, we use the data provided by an energy consumption monitoring system in a compound of faculties and research centers at the University of Granada, and provide a methodology to predict future energy consumption using nonlinear autoregressive (NAR and the nonlinear autoregressive neural network with exogenous inputs (NARX, respectively. Results reveal that NAR and NARX neural networks are both suitable for performing energy consumption prediction, but also that exogenous data may help to improve the accuracy of predictions.

  11. The fundamentals of fuzzy neural network and application in nuclear monitoring

    International Nuclear Information System (INIS)

    Feng Diqing; Lei Ming

    1995-01-01

    The authors presents a fuzzy modeling method using fuzzy neural network with the back-propagation algorithm. The new method can identify the fuzzy model of a nonlinear system automatically. Fuzzy neural network is used to generate fuzzy rules and membership functions. The feasibility and inferential statistic of the method is examined by using numerical data and XOR problem. The FNN improves accuracy and reliability, reduces design time and minimizes system cost of fuzzy design. The FNN can be used for estimation of human injury in nuclear explosions and can be simplified to a rule neural network (RNN), which is used for pole extraction of signal. Preliminary simulation show that FNN has vest vistas in nuclear monitoring

  12. Application of neural networks to signal prediction in nuclear power plant

    International Nuclear Information System (INIS)

    Wan Joo Kim; Soon Heung Chang; Byung Ho Lee

    1993-01-01

    This paper describes the feasibility study of an artificial neural network for signal prediction. The purpose of signal prediction is to estimate the value of undetected next time step signal. As the prediction method, based on the idea of auto regression, a few previous signals are inputs to the artificial neural network and the signal value of next time step is estimated with the outputs of the network. The artificial neural network can be applied to the nonlinear system and answers in short time. The training algorithm is a modified backpropagation model, which can effectively reduce the training time. The target signal of the simulation is the steam generator water level, which is one of the important parameters in nuclear power plants. The simulation result shows that the predicted value follows the real trend well

  13. Application of CMAC Neural Network to Solar Energy Heliostat Field Fault Diagnosis

    Directory of Open Access Journals (Sweden)

    Neng-Sheng Pai

    2013-01-01

    Full Text Available Solar energy heliostat fields comprise numerous sun tracking platforms. As a result, fault detection is a highly challenging problem. Accordingly, the present study proposes a cerebellar model arithmetic computer (CMAC neutral network for automatically diagnosing faults within the heliostat field in accordance with the rotational speed, vibration, and temperature characteristics of the individual heliostat transmission systems. As compared with radial basis function (RBF neural network and back propagation (BP neural network in the heliostat field fault diagnosis, the experimental results show that the proposed neural network has a low training time, good robustness, and a reliable diagnostic performance. As a result, it provides an ideal solution for fault diagnosis in modern, large-scale heliostat fields.

  14. Application of neural networks and neutron noise for diagnostics of reactor internals vibration

    International Nuclear Information System (INIS)

    Garis, N.S.; Pazsit, I.; Gloeckler, O.

    1995-01-01

    It has long been known that vibration of reactor internals, in particular excessive vibrations of control rods, can be detected via the neutron noise they induce. Noise measurements are actually suitable to determine important diagnostic parameters such as the location of the vibrating rod and the vibration amplitude. An algorithm was earlier elaborated for this purpose, which is based on inversion of the expression describing the neutron noise as a function of vibration parameters. This inversion procedure is nevertheless complicated and not always unique. It was investigated whether a properly trained neural network can perform the inversion more effectively. It was found that artificial neural networks can be trained effectively to perform vibration diagnostics from neutron noise data fast, effectively and reliably. The present paper gives a description of the development and use of the neural networks for purposes of vibration diagnostics

  15. The application of neural network for the advancement of the eddy current testing

    International Nuclear Information System (INIS)

    Sakai, T.; Soneda, N.

    1996-01-01

    All the steam generator (SG) tubes of Japanese pressurized water reactors (PWRs) are inspected by the eddy current testing (ECT) method in every annual scheduled inspection. Here, a neural network system to estimate the class and size of defects from signals obtained by the eddy current testing (ECT) method has been developed. A trajectory of ECT signal is characterized by four representative parameters, and totally eight parameters obtained from two trajectories by different AC current frequencies are used as input parameters for neutral networks. A probabilistic descent method is employed to minimize the error at the learning process of neural networks. It is indicated that using multiple neutral networks which are separately responsible to each class of defects is effective to the improvement of their estimation accuracy. And, it is demonstrated that the neural network system which the authors developed can estimate the class and size of defects from unlearned trajectories with high accuracy

  16. The application of artificial neural network in radon disaster model of uranium mining

    International Nuclear Information System (INIS)

    Zhu Yufeng; Zhu Guogen; Zhou Shijian

    2012-01-01

    The structural features, data analysis and learning process of feed-forward neural network (BP ANN) were analyzed at first. Rodon sample from Fuzhou Jinan Uranium Industry Limited Company were used to training the network and make the forecast then, and a forecasting model was established for the radon disaster in uranium mines. The method and effectiveness of BP neural network in predicting radon disaster was discussed. The test of training samples showed that the BP network had gotten fairly satisfied result in predicting mine radon disaster. (authors)

  17. Application of artificial neural networks with backpropagation technique in the financial data

    Science.gov (United States)

    Jaiswal, Jitendra Kumar; Das, Raja

    2017-11-01

    The propensity of applying neural networks has been proliferated in multiple disciplines for research activities since the past recent decades because of its powerful control with regulatory parameters for pattern recognition and classification. It is also being widely applied for forecasting in the numerous divisions. Since financial data have been readily available due to the involvement of computers and computing systems in the stock market premises throughout the world, researchers have also developed numerous techniques and algorithms to analyze the data from this sector. In this paper we have applied neural network with backpropagation technique to find the data pattern from finance section and prediction for stock values as well.

  18. Morphological self-organizing feature map neural network with applications to automatic target recognition

    Science.gov (United States)

    Zhang, Shijun; Jing, Zhongliang; Li, Jianxun

    2005-01-01

    The rotation invariant feature of the target is obtained using the multi-direction feature extraction property of the steerable filter. Combining the morphological operation top-hat transform with the self-organizing feature map neural network, the adaptive topological region is selected. Using the erosion operation, the topological region shrinkage is achieved. The steerable filter based morphological self-organizing feature map neural network is applied to automatic target recognition of binary standard patterns and real-world infrared sequence images. Compared with Hamming network and morphological shared-weight networks respectively, the higher recognition correct rate, robust adaptability, quick training, and better generalization of the proposed method are achieved.

  19. Application of a neural network to control a pressurized water reactor

    International Nuclear Information System (INIS)

    Lin, C.; Ku, C.C.; Lee, C.S.

    1993-01-01

    A neural network has been trained to control a pressurized water reactor. The inputs of the training pattern are the plant signals, and the outputs are the control rod actions. The training patterns are some kind of lookup table of control action. The table is designed by the heuristic method, which is based on the designer's knowledge of the controlled system and the operation experience. This method has two advantages: The controller's performance does not depend on the mathematical model of the plant, and the controller could be a nonlinear one. The advantages of using neural networks to implement the controller are to save computing time and overcome partial hardware failure

  20. Implantable neurotechnologies: bidirectional neural interfaces--applications and VLSI circuit implementations.

    Science.gov (United States)

    Greenwald, Elliot; Masters, Matthew R; Thakor, Nitish V

    2016-01-01

    A bidirectional neural interface is a device that transfers information into and out of the nervous system. This class of devices has potential to improve treatment and therapy in several patient populations. Progress in very large-scale integration has advanced the design of complex integrated circuits. System-on-chip devices are capable of recording neural electrical activity and altering natural activity with electrical stimulation. Often, these devices include wireless powering and telemetry functions. This review presents the state of the art of bidirectional circuits as applied to neuroprosthetic, neurorepair, and neurotherapeutic systems.

  1. The Application of Helicopter Rotor Defect Detection Using Wavelet Analysis and Neural Network Technique

    Directory of Open Access Journals (Sweden)

    Jin-Li Sun

    2014-06-01

    Full Text Available When detect the helicopter rotor beam with ultrasonic testing, it is difficult to realize the noise removing and quantitative testing. This paper used the wavelet analysis technique to remove the noise among the ultrasonic detection signal and highlight the signal feature of defect, then drew the curve of defect size and signal amplitude. Based on the relationship of defect size and signal amplitude, a BP neural network was built up and the corresponding estimated value of the simulate defect was obtained by repeating training. It was confirmed that the wavelet analysis and neural network technique met the requirements of practical testing.

  2. Mitral Prosthetic Valve Obstruction and Its Complications

    Directory of Open Access Journals (Sweden)

    Rajesh Rajan

    2015-12-01

    Full Text Available Prosthetic Valve Obstruction (PVO is a serious complication which is associated with increased morbidity and mortality. This could result from thrombus formation, development of pannus, or a combination of both. Patients with this complication often present with symptoms and signs of heart failure, systemic embolism, acute cardiovascular collapse, and sudden death. Transesophageal echocardiography and cine fluoroscopy play a vital role in diagnosis of this potentially lethal condition. Herein, we reported a 56-year-old male patient who presented with severe heart failure and was found to have obstructed ATS27 bileaflet mitral prosthetic valve. Thrombolysis and redo surgery are two important options for treating this condition although guidelines for choosing between the two are not very definite.

  3. Prosthetic valve obstruction: Redo surgery or fibrinolysis?

    Directory of Open Access Journals (Sweden)

    Avinash Inamdar

    2017-01-01

    Full Text Available Objective: The aim of this study was to compare the efficacy and safety of surgery versus fibrinolytic therapy in patients with prosthetic valve obstruction. Materials and Methods: We compared 15 patients of prosthetic valve thrombosis treated by surgical line of management and another 15 patients treated by thrombolysis. All patients were initially assessed by clinical evaluation and diagnosis confirmed by transthoracic and transesophageal two-dimensional echocardiography. Depending on hemodynamic stability, pannus, or thrombus on transesophageal echocardiography, the patients were assigned surgical or medical line of management. Results: Patients mortality rate was 40% in fibrinolytic group and 13.33% in surgical group. Recurrence was 40% in fibrinolytic group while there was no recurrence till date in surgery group. Complications were more in fibrinolytic group as opposed to surgery group patient. Conclusion: From our experience, we conclude that redo surgery is effective and definitive treatment, especially in patients with stable hemodynamic conditions.

  4. The radiology of prosthetic heart valves

    International Nuclear Information System (INIS)

    Steiner, R.M.; Flicker, S.

    1985-01-01

    The development of prosthetic heart valves in the late 1950s ushered in a new era in the treatment of heart disease. The radiologist has an important role to play preoperatively in the diagnosis of valvular heart disease. Radiology is valuable in identification of the implanted prosthetic valve and recognition of complications associated with valve implantation. Radiologists must be familiar with the imaging techniques best suited to evaluate the function of the valve prosthesis in question. In this chapter the authors discuss the radiographic approach to the evaluation of the status of patients for valve replacement and the imaging problems peculiar to the types of valves in current use. The relative value of plain-film radiography, fluoroscopy, videorecording and cinerecording, and aortography is addressed, as well as the potential value of magnetic resonance imaging and subsecond dynamic computed tomography

  5. Prosthetic vascular graft infection and prosthetic joint infection caused by Pseudomonas stutzeri.

    Science.gov (United States)

    Bonares, Michael J; Vaisman, Alon; Sharkawy, Abdu

    2016-01-01

    Pseudomonas stutzeri is infrequently isolated from clinical specimens, and if isolated, more likely represents colonization or contamination rather than infection. Despite this, there are dozens of case reports which describe clinically significant P. stutzeri infections at variable sites. A 69-year-old man had a P. stutzeri infection of a prosthetic vascular graft infection, which he received in Panama City. He was successfully treated with a single antipseudomonal agent for 6 weeks and the removal of the infected vascular graft. A 70-year-old man had a P. stutzeri infection of a prosthetic joint, which was successfully treated with a single anti-pseudomonal agent for 6 weeks. There is only one other documented case of a prosthetic vascular graft infection secondary to P. stutzeri . There are 5 documented cases of P. stutzeri prosthetic joint infections. The previous cases were treated with antibiotics and variably, source control with the removal of prosthetic material. Most cases of P. stutzeri infection are due to exposure in health care settings. Immunocompromised states such as HIV or hematological and solid tumor malignancies are risk factors for P. stutzeri infection. Infections caused by P. stutzeri are far less frequent and less fatal than those caused by P. aeruginosa. The etiology of a P. stutzeri infection could be exposure to soil and water, but also contaminated material in the health care setting or an immunocompromised state. Iatrogenic infections that are secondary to health care tourism are a potential cause of fever in the returned traveler.

  6. Biologically inspired multi-layered synthetic skin for tactile feedback in prosthetic limbs.

    Science.gov (United States)

    Osborn, Luke; Nguyen, Harrison; Betthauser, Joseph; Kaliki, Rahul; Thakor, Nitish

    2016-08-01

    The human body offers a template for many state-of-the-art prosthetic devices and sensors. In this work, we present a novel, sensorized synthetic skin that mimics the natural multi-layered nature of mechanoreceptors found in healthy glabrous skin to provide tactile information. The multi-layered sensor is made up of flexible piezoresistive textiles that act as force sensitive resistors (FSRs) to convey tactile information, which are embedded within a silicone rubber to resemble the compliant nature of human skin. The top layer of the synthetic skin is capable of detecting small loads less than 5 N whereas the bottom sensing layer responds reliably to loads over 7 N. Finite element analysis (FEA) of a simplified human fingertip and the synthetic skin was performed. Results suggest similarities in behavior during loading. A natural tactile event is simulated by loading the synthetic skin on a prosthetic limb. Results show the sensors' ability to detect applied loads as well as the ability to simulate neural spiking activity based on the derivative and temporal differences of the sensor response. During the tactile loading, the top sensing layer responded 0.24 s faster than the bottom sensing layer. A synthetic biologically-inspired skin such as this will be useful for enhancing the functionality of prosthetic limbs through tactile feedback.

  7. Prosthetic management of an ocular defect

    Directory of Open Access Journals (Sweden)

    Siddesh Kumar Chintal

    2010-01-01

    Full Text Available The disfigurement associated with the loss of an eye can cause significant physical and emotional problems. Various treatment modalities are available, one of which is implants. Although implant has a superior outcome, it may not be advisable in all patients due to economic factors. The present article describes the prosthetic management of an ocular defect with a custom-made ocular prosthesis.

  8. New developments in prosthetic arm systems

    Directory of Open Access Journals (Sweden)

    Vujaklija I

    2016-07-01

    Full Text Available Ivan Vujaklija,1 Dario Farina,1 Oskar C Aszmann2 1Institute of Neurorehabilitation Systems, Bernstein Focus Neurotechnology Göttingen, University Medical Center Göttingen, Georg-August University, Göttingen, Germany; 2Christian Doppler Laboratory for Restoration of Extremity Function, Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria Abstract: Absence of an upper limb leads to severe impairments in everyday life, which can further influence the social and mental state. For these reasons, early developments in cosmetic and body-driven prostheses date some centuries ago, and they have been evolving ever since. Following the end of the Second World War, rapid developments in technology resulted in powered myoelectric hand prosthetics. In the years to come, these devices were common on the market, though they still suffered high user abandonment rates. The reasons for rejection were trifold – insufficient functionality of the hardware, fragile design, and cumbersome control. In the last decade, both academia and industry have reached major improvements concerning technical features of upper limb prosthetics and methods for their interfacing and control. Advanced robotic hands are offered by several vendors and research groups, with a variety of active and passive wrist options that can be articulated across several degrees of freedom. Nowadays, elbow joint designs include active solutions with different weight and power options. Control features are getting progressively more sophisticated, offering options for multiple sensor integration and multi-joint articulation. Latest developments in socket designs are capable of facilitating implantable and multiple surface electromyography sensors in both traditional and osseointegration-based systems. Novel surgical techniques in combination with modern, sophisticated hardware are enabling restoration of dexterous upper limb

  9. Control system and method for prosthetic devices

    Science.gov (United States)

    Bozeman, Richard J., Jr. (Inventor)

    1992-01-01

    A control system and method for prosthetic devices is provided. The control system comprises a transducer for receiving movement from a body part for generating a sensing signal associated with that movement. The sensing signal is processed by a linearizer for linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part. The linearized sensing signal is normalized to be a function of the entire range of body part movement from the no-shrug position of the movable body part through the full-shrug position of the movable body part. The normalized signal is divided into a plurality of discrete command signals. The discrete command signals are used by typical converter devices which are in operational association with the prosthetic device. The converter device uses the discrete command signals for driving the movable portions of the prosthetic device and its sub-prosthesis. The method for controlling a prosthetic device associated with the present invention comprises the steps of receiving the movement from the body part, generating a sensing signal in association with the movement of the body part, linearizing the sensing signal to be a linear function of the magnitude of the distance moved by the body part, normalizing the linear signal to be a function of the entire range of the body part movement, dividing the normalized signal into a plurality of discrete command signals, and implementing the plurality of discrete command signals for driving the respective movable prosthesis device and its sub-prosthesis.

  10. Smart Prosthetic Hand Technology - Phase 2

    Science.gov (United States)

    2011-05-01

    functional magnetic resonance imaging (f- MRI ) was used to analyze the reciprocal adaptation between the human brain and the prosthetic hand by the...Schmidt PC. Influence of compacted hydrophobic and hydrophilic colloidal silicon dioxide on tableting properties of pharmaceutical excipients. Drug Dev...nanoparticles, and manganese nanoparticles) in magnetic resonance imaging ( MRI ) in the detection and staging of cancer [2]. 2.1 Iron Oxide

  11. Neural speech recognition: continuous phoneme decoding using spatiotemporal representations of human cortical activity

    Science.gov (United States)

    Moses, David A.; Mesgarani, Nima; Leonard, Matthew K.; Chang, Edward F.

    2016-10-01

    Objective. The superior temporal gyrus (STG) and neighboring brain regions play a key role in human language processing. Previous studies have attempted to reconstruct speech information from brain activity in the STG, but few of them incorporate the probabilistic framework and engineering methodology used in modern speech recognition systems. In this work, we describe the initial efforts toward the design of a neural speech recognition (NSR) system that performs continuous phoneme recognition on English stimuli with arbitrary vocabulary sizes using the high gamma band power of local field potentials in the STG and neighboring cortical areas obtained via electrocorticography. Approach. The system implements a Viterbi decoder that incorporates phoneme likelihood estimates from a linear discriminant analysis model and transition probabilities from an n-gram phonemic language model. Grid searches were used in an attempt to determine optimal parameterizations of the feature vectors and Viterbi decoder. Main results. The performance of the system was significantly improved by using spatiotemporal representations of the neural activity (as opposed to purely spatial representations) and by including language modeling and Viterbi decoding in the NSR system. Significance. These results emphasize the importance of modeling the temporal dynamics of neural responses when analyzing their variations with respect to varying stimuli and demonstrate that speech recognition techniques can be successfully leveraged when decoding speech from neural signals. Guided by the results detailed in this work, further development of the NSR system could have applications in the fields of automatic speech recognition and neural prosthetics.

  12. An application of neural network for Structural Health Monitoring of an adaptive wing with an array of FBG sensors

    International Nuclear Information System (INIS)

    Mieloszyk, Magdalena; Skarbek, Lukasz; Ostachowicz, Wieslaw; Krawczuk, Marek

    2011-01-01

    This paper presents an application of neural networks to determinate the level of activation of shape memory alloy actuators of an adaptive wing. In this concept the shape of the wing can be controlled and altered thanks to the wing design and the use of integrated shape memory alloy actuators. The wing is assumed as assembled from a number of wing sections that relative positions can be controlled independently by thermal activation of shape memory actuators. The investigated wing is employed with an array of Fibre Bragg Grating sensors. The Fibre Bragg Grating sensors with combination of a neural network have been used to Structural Health Monitoring of the wing condition. The FBG sensors are a great tool to control the condition of composite structures due to their immunity to electromagnetic fields as well as their small size and weight. They can be mounted onto the surface or embedded into the wing composite material without any significant influence on the wing strength. The paper concentrates on analysis of the determination of the twisting moment produced by an activated shape memory alloy actuator. This has been analysed both numerically using the finite element method by a commercial code ABAQUS (registered) and experimentally using Fibre Bragg Grating sensor measurements. The results of the analysis have been then used by a neural network to determine twisting moments produced by each shape memory alloy actuator.

  13. Dynamic elasticity measurement for prosthetic socket design.

    Science.gov (United States)

    Kim, Yujin; Kim, Junghoon; Son, Hyeryon; Choi, Youngjin

    2017-07-01

    The paper proposes a novel apparatus to measure the dynamic elasticity of human limb in order to help the design and fabrication of the personalized prosthetic socket. To take measurements of the dynamic elasticity, the desired force generated as an exponential chirp signal in which the frequency increases and amplitude is maintained according to time progress is applied to human limb and then the skin deformation is recorded, ultimately, to obtain the frequency response of its elasticity. It is referred to as a Dynamic Elasticity Measurement Apparatus (DEMA) in the paper. It has three core components such as linear motor to provide the desired force, loadcell to implement the force feedback control, and potentiometer to record the skin deformation. After measuring the force/deformation and calculating the dynamic elasticity of the limb, it is visualized as 3D color map model of the limb so that the entire dynamic elasticity can be shown at a glance according to the locations and frequencies. For the visualization, the dynamic elasticities measured at specific locations and frequencies are embodied using the color map into 3D limb model acquired by using 3D scanner. To demonstrate the effectiveness, the visualized dynamic elasticities are suggested as outcome of the proposed system, although we do not have any opportunity to apply the proposed system to the amputees. Ultimately, it is expected that the proposed system can be utilized to design and fabricate the personalized prosthetic socket in order for releasing the wearing pain caused by the conventional prosthetic socket.

  14. Adaptive sports technology and biomechanics: prosthetics.

    Science.gov (United States)

    De Luigi, Arthur Jason; Cooper, Rory A

    2014-08-01

    With the technologic advances in medicine and an emphasis on maintaining physical fitness, the population of athletes with impairments is growing. It is incumbent upon health care practitioners to make every effort to inform these individuals of growing and diverse opportunities and to encourage safe exercise and athletic participation through counseling and education. Given the opportunities for participation in sports for persons with a limb deficiency, the demand for new, innovative prosthetic designs is challenging the clinical and technical expertise of the physician and prosthetist. When generating a prosthetic prescription, physicians and prosthetists should consider the needs and preferences of the athlete with limb deficiency, as well as the functional demands of the chosen sporting activity. The intent of this article is to provide information regarding the current advancements in the adaptive sports technology and biomechanics in the field of prosthetics, and to assist clinicians and their patients in facilitating participation in sporting activities. Copyright © 2014 American Academy of Physical Medicine and Rehabilitation. Published by Elsevier Inc. All rights reserved.

  15. Improving Neural Network Approximations in Applications: Case Study in Materials Science

    Czech Academy of Sciences Publication Activity Database

    Holeňa, Martin; Steinfeldt, N.

    2009-01-01

    Roč. 19, č. 2 (2009), s. 165-190 ISSN 1210-0552 Institutional research plan: CEZ:AV0Z10300504 Keywords : artificial neural networks * approximation capability * crossvalidation Subject RIV: IN - Informatics, Computer Science Impact factor: 0.475, year: 2009

  16. The parallel implementation of a backpropagation neural network and its applicability to SPECT image reconstruction

    Energy Technology Data Exchange (ETDEWEB)

    Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)

    1992-01-01

    The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.

  17. Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation

    Directory of Open Access Journals (Sweden)

    M. Agatonović

    2012-12-01

    Full Text Available A novel method to provide high-resolution Two-Dimensional Direction of Arrival (2D DOA estimation employing Artificial Neural Networks (ANNs is presented in this paper. The observed space is divided into azimuth and elevation sectors. Multilayer Perceptron (MLP neural networks are employed to detect the presence of a source in a sector while Radial Basis Function (RBF neural networks are utilized for DOA estimation. It is shown that a number of appropriately trained neural networks can be successfully used for the high-resolution DOA estimation of narrowband sources in both azimuth and elevation. The training time of each smaller network is significantly re¬duced as different training sets are used for networks in detection and estimation stage. By avoiding the spectral search, the proposed method is suitable for real-time ap¬plications as it provides DOA estimates in a matter of seconds. At the same time, it demonstrates the accuracy comparable to that of the super-resolution 2D MUSIC algorithm.

  18. GPU implementation of Bayesian neural network construction for data-intensive applications

    International Nuclear Information System (INIS)

    Perry, Michelle; Meyer-Baese, Anke; Prosper, Harrison B

    2014-01-01

    We describe a graphical processing unit (GPU) implementation of the Hybrid Markov Chain Monte Carlo (HMC) method for training Bayesian Neural Networks (BNN). Our implementation uses NVIDIA's parallel computing architecture, CUDA. We briefly review BNNs and the HMC method and we describe our implementations and give preliminary results.

  19. Cellular Neural Networks: A genetic algorithm for parameters optimization in artificial vision applications

    Energy Technology Data Exchange (ETDEWEB)

    Taraglio, S. [ENEA, Centro Ricerche Casaccia, Rome (Italy). Dipt. Innovazione; Zanela, A. [Rome Univ. `La Sapienza` (Italy). Dipt. di Fisica

    1997-03-01

    An optimization method for some of the CNN`s (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN`s literature.

  20. Application of an artificial neural network and morphing techniques in the redesign of dysplastic trochlea.

    Science.gov (United States)

    Cho, Kyung Jin; Müller, Jacobus H; Erasmus, Pieter J; DeJour, David; Scheffer, Cornie

    2014-01-01

    Segmentation and computer assisted design tools have the potential to test the validity of simulated surgical procedures, e.g., trochleoplasty. A repeatable measurement method for three dimensional femur models that enables quantification of knee parameters of the distal femur is presented. Fifteen healthy knees are analysed using the method to provide a training set for an artificial neural network. The aim is to use this artificial neural network for the prediction of parameter values that describe the shape of a normal trochlear groove geometry. This is achieved by feeding the artificial neural network with the unaffected parameters of a dysplastic knee. Four dysplastic knees (Type A through D) are virtually redesigned by way of morphing the groove geometries based on the suggested shape from the artificial neural network. Each of the four resulting shapes is analysed and compared to its initial dysplastic shape in terms of three anteroposterior dimensions: lateral, central and medial. For the four knees the trochlear depth is increased, the ventral trochlear prominence reduced and the sulcus angle corrected to within published normal ranges. The results show a lateral facet elevation inadequate, with a sulcus deepening or a depression trochleoplasty more beneficial to correct trochlear dysplasia.

  1. Cellular Neural Networks: A genetic algorithm for parameters optimization in artificial vision applications

    International Nuclear Information System (INIS)

    Taraglio, S.; Zanela, A.

    1997-03-01

    An optimization method for some of the CNN's (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN's literature

  2. Application of radial basis function neural network to predict soil sorption partition coefficient using topological descriptors.

    Science.gov (United States)

    Sabour, Mohammad Reza; Moftakhari Anasori Movahed, Saman

    2017-02-01

    The soil sorption partition coefficient logK oc is an indispensable parameter that can be used in assessing the environmental risk of organic chemicals. In order to predict soil sorption partition coefficient for different and even unknown compounds in a fast and accurate manner, a radial basis function neural network (RBFNN) model was developed. Eight topological descriptors of 800 organic compounds were used as inputs of the model. These 800 organic compounds were chosen from a large and very diverse data set. Generalized Regression Neural Network (GRNN) was utilized as the function in this neural network model due to its capability to adapt very quickly. Hence, it can be used to predict logK oc for new chemicals, as well. Out of total data set, 560 organic compounds were used for training and 240 to test efficiency of the model. The obtained results indicate that the model performance is very well. The correlation coefficients (R2) for training and test sets were 0.995 and 0.933, respectively. The root-mean square errors (RMSE) were 0.2321 for training set and 0.413 for test set. As the results for both training and test set are extremely satisfactory, the proposed neural network model can be employed not only to predict logK oc of known compounds, but also to be adaptive for prediction of this value precisely for new products that enter the market each year. Copyright © 2016 Elsevier Ltd. All rights reserved.

  3. Application of associative emulator neural network for power control of nuclear reactor

    International Nuclear Information System (INIS)

    Datta, A.K.; Bandyopadhyay, Somnath

    1993-01-01

    This paper addresses the question of how to perform on-line training of emulator neural network for power control in a nuclear reactor. The computation and convergence problem can be reduced by judicious choice of bidirectional associative recall. (author). 10 refs., 2 figs

  4. Application of artificial neural networks in the CT study of solitary pulmonary nodule

    International Nuclear Information System (INIS)

    Wang Xiaohua; Ma Daqing; Chen Hui; Gao Peiyi; Zhou Xinhua

    2006-01-01

    Objective: To establish a new-type discriminative method in differentiating benign from malignant solitary pulmonary nodule (SPN) on high-resolution CT/thin-section CT by using artificial neural networks theory in the CT diagnostic study of SPN. Methods: Two hundred SPNs pathologically proved by operation or biopsy (primary pulmonary carcinoma 135 eases, benign nodules 65 cases) were collected, 3 clinical characteristics (age, sex, with or without bloody sputum) and 9 high-resolution CT/thin-section CT characteristics (location, long and short diameter, contour, spiculation, halo sign, air-space, relation with the adjacent blood vessels and pleura) were analyzed. 140 cases were randomly selected to form the training samples, on which artificial neural networks model (BP networks) was built and compared with Logistic model from Statistical Package for the Social Science (SPSS) software. Results: The total consistent rate of BP neural networks (98.0%, 196/200) was higher than that of Logistic model (86.0%, 172/200) (P<0.001). Areas under ROC curve were 0.996±0.004 and 0.936±0.017, respectively, and the difference between the two was significant (P<0.001). Conclusion: Using high-resolution CT and thin-section CT in combination with artificial neural networks theory is feasible, and it is expected to become a useful and reliable clinical tool in differentiating benign from malignant SPN. (authors)

  5. Maximizing performance of fuel cell using artificial neural network approach for smart grid applications

    International Nuclear Information System (INIS)

    Bicer, Y.; Dincer, I.; Aydin, M.

    2016-01-01

    This paper presents an artificial neural network (ANN) approach of a smart grid integrated proton exchange membrane (PEM) fuel cell and proposes a neural network model of a 6 kW PEM fuel cell. The data required to train the neural network model are generated by a model of 6 kW PEM fuel cell. After the model is trained and validated, it is used to analyze the dynamic behavior of the PEM fuel cell. The study results demonstrate that the model based on neural network approach is appropriate for predicting the outlet parameters. Various types of training methods, sample numbers and sample distribution methods are utilized to compare the results. The fuel cell stack efficiency considerably varies between 20% and 60%, according to input variables and models. The rapid changes in the input variables can be recovered within a short time period, such as 10 s. The obtained response graphs point out the load tracking features of ANN model and the projected changes in the input variables are controlled quickly in the study. - Highlights: • An ANN approach of a proton exchange membrane (PEM) fuel cell is proposed. • Dynamic behavior of the PEM fuel cell is analyzed. • The effects of various variables on model accuracy are investigated. • Response curves indicate the load following characteristics of the model.

  6. Application of power spectrum, cepstrum, higher order spectrum and neural network analyses for induction motor fault diagnosis

    Science.gov (United States)

    Liang, B.; Iwnicki, S. D.; Zhao, Y.

    2013-08-01

    The power spectrum is defined as the square of the magnitude of the Fourier transform (FT) of a signal. The advantage of FT analysis is that it allows the decomposition of a signal into individual periodic frequency components and establishes the relative intensity of each component. It is the most commonly used signal processing technique today. If the same principle is applied for the detection of periodicity components in a Fourier spectrum, the process is called the cepstrum analysis. Cepstrum analysis is a very useful tool for detection families of harmonics with uniform spacing or the families of sidebands commonly found in gearbox, bearing and engine vibration fault spectra. Higher order spectra (HOS) (also known as polyspectra) consist of higher order moment of spectra which are able to detect non-linear interactions between frequency components. For HOS, the most commonly used is the bispectrum. The bispectrum is the third-order frequency domain measure, which contains information that standard power spectral analysis techniques cannot provide. It is well known that neural networks can represent complex non-linear relationships, and therefore they are extremely useful for fault identification and classification. This paper presents an application of power spectrum, cepstrum, bispectrum and neural network for fault pattern extraction of induction motors. The potential for using the power spectrum, cepstrum, bispectrum and neural network as a means for differentiating between healthy and faulty induction motor operation is examined. A series of experiments is done and the advantages and disadvantages between them are discussed. It has been found that a combination of power spectrum, cepstrum and bispectrum plus neural network analyses could be a very useful tool for condition monitoring and fault diagnosis of induction motors.

  7. Signal-independent timescale analysis (SITA) and its application for neural coding during reaching and walking.

    Science.gov (United States)

    Zacksenhouse, Miriam; Lebedev, Mikhail A; Nicolelis, Miguel A L

    2014-01-01

    What are the relevant timescales of neural encoding in the brain? This question is commonly investigated with respect to well-defined stimuli or actions. However, neurons often encode multiple signals, including hidden or internal, which are not experimentally controlled, and thus excluded from such analysis. Here we consider all rate modulations as the signal, and define the rate-modulations signal-to-noise ratio (RM-SNR) as the ratio between the variance of the rate and the variance of the neuronal noise. As the bin-width increases, RM-SNR increases while the update rate decreases. This tradeoff is captured by the ratio of RM-SNR to bin-width, and its variations with the bin-width reveal the timescales of neural activity. Theoretical analysis and simulations elucidate how the interactions between the recovery properties of the unit and the spectral content of the encoded signals shape this ratio and determine the timescales of neural coding. The resulting signal-independent timescale analysis (SITA) is applied to investigate timescales of neural activity recorded from the motor cortex of monkeys during: (i) reaching experiments with Brain-Machine Interface (BMI), and (ii) locomotion experiments at different speeds. Interestingly, the timescales during BMI experiments did not change significantly with the control mode or training. During locomotion, the analysis identified units whose timescale varied consistently with the experimentally controlled speed of walking, though the specific timescale reflected also the recovery properties of the unit. Thus, the proposed method, SITA, characterizes the timescales of neural encoding and how they are affected by the motor task, while accounting for all rate modulations.

  8. Signal-Independent Timescale Analysis (SITA and its Application for Neural Coding during Reaching and Walking

    Directory of Open Access Journals (Sweden)

    Miriam eZacksenhouse

    2014-08-01

    Full Text Available What are the relevant timescales of neural encoding in the brain? This question is commonly investigated with respect to well-defined stimuli or actions. However, neurons often encode multiple signals, including hidden or internal, which are not experimentally controlled, and thus excluded from such analysis. Here we consider all rate modulations as the signal, and define the rate-modulations signal-to-noise ratio (RM-SNR as the ratio between the variance of the rate and the variance of the neuronal noise. As the bin-width increases, RM-SNR increases while the update rate decreases. This tradeoff is captured by the ratio of RM-SNR to bin-width, and its variations with the bin-width reveal the timescales of neural activity. Theoretical analysis and simulations elucidate how the interactions between the recovery properties of the unit and the spectral content of the encoded signals shape this ratio and determine the timescales of neural coding. The resulting signal-independent timescale analysis (SITA is applied to investigate timescales of neural activity recorded from the motor cortex of monkeys during: (i reaching experiments with Brain-Machine Interface (BMI, and (ii locomotion experiments at different speeds. Interestingly, the timescales during BMI experiments did not change significantly with the control mode or training. During locomotion, the analysis identified units whose timescale varied consistently with the experimentally controlled speed of walking, though the specific timescale reflected also the recovery properties of the unit. Thus, the proposed method, SITA, characterizes the timescales of neural encoding and how they are affected by the motor task, while accounting for all rate modulations.

  9. Vascular complications of prosthetic inter-vertebral discs

    OpenAIRE

    Daly, Kevin J.; Ross, E. Raymond S.; Norris, Heather; McCollum, Charles N.

    2006-01-01

    Five consecutive cases of prosthetic inter-vertebral disc displacement with severe vascular complications on revisional surgery are described. The objective of this case report is to warn spinal surgeons that major vascular complications are likely with anterior displacement of inter-vertebral discs. We have not been able to find a previous report on vascular complications associated with anterior displacement of prosthetic inter-vertebral discs. In all five patients the prosthetic disc had e...

  10. Stiffness and hysteresis properties of some prosthetic feet

    OpenAIRE

    van Jaarsveld, H.W.L.; Grootenboer, H.J.; de Vries, J.; Koopman, Hubertus F.J.M.

    1990-01-01

    A prosthetic foot is an important element of a prosthesis, although it is not always fully recognized that the properties of the foot, along with the prosthetic knee joint and the socket, are in part responsible for the stability and metabolic energy cost during walking. The stiffness and the hysteresis, which are the topics of this paper, are not properly prescribed, but could be adapted to improve the prosthetic walking performance. The shape is strongly related to the cosmetic appearance a...

  11. Fused Filament Fabrication of Prosthetic Components for Trans-Humeral Upper Limb Prosthetics

    Science.gov (United States)

    Lathers, Steven M.

    Presented below is the design and fabrication of prosthetic components consisting of an attachment, tactile sensing, and actuator systems with Fused Filament Fabrication (FFF) technique. The attachment system is a thermoplastic osseointegrated upper limb prosthesis for average adult trans-humeral amputation with mechanical properties greater than upper limb skeletal bone. The prosthetic designed has: a one-step surgical process, large cavities for bone tissue ingrowth, uses a material that has an elastic modulus less than skeletal bone, and can be fabricated on one system. FFF osseointegration screw is an improvement upon the current two-part osseointegrated prosthetics that are composed of a fixture and abutment. The current prosthetic design requires two invasive surgeries for implantation and are made of titanium, which has an elastic modulus greater than bone. An elastic modulus greater than bone causes stress shielding and overtime can cause loosening of the prosthetic. The tactile sensor is a thermoplastic piezo-resistive sensor for daily activities for a prosthetic's feedback system. The tactile sensor is manufactured from a low elastic modulus composite comprising of a compressible thermoplastic elastomer and conductive carbon. Carbon is in graphite form and added in high filler ratios. The printed sensors were compared to sensors that were fabricated in a gravity mold to highlight the difference in FFF sensors to molded sensors. The 3D printed tactile sensor has a thickness and feel similar to human skin, has a simple fabrication technique, can detect forces needed for daily activities, and can be manufactured in to user specific geometries. Lastly, a biomimicking skeletal muscle actuator for prosthetics was developed. The actuator developed is manufactured with Fuse Filament Fabrication using a shape memory polymer composite that has non-linear contractile and passive forces, contractile forces and strains comparable to mammalian skeletal muscle, reaction

  12. Factors Associated with Prosthetic Looseness in Lower Limb Amputees.

    Science.gov (United States)

    Phonghanyudh, Thong; Sutpasanon, Taweesak; Hathaiareerug, Chanasak; Devakula, M L Buddhibongsa; Kumnerddee, Wipoo

    2015-12-01

    To determine the factors associated with prosthetic looseness in lower limb amputees in Sisaket province. The present was a cross-sectional descriptive study. Subjects were lower limb amputees who previously obtained prostheses and required prosthetic replacements at the mobile prosthetic laboratory unit under the Prostheses Foundation of H.R.H. the Princess Mother at Khun Han Hospital, Sisaket province, in February 2013. Data including participant characteristics, prosthetic looseness data, and various variables were collected by direct semi-structured interview. Energy expenditures in physical activities were measured using the Thai version of the short format international physical activity questionnaire. Data between participants with and without prosthetic looseness were compared to determine prosthetic loosening associated factors. Among 101 participants enrolled, 33 (32.7%) had prosthetic looseness with average onset of 1.76 ± 1.67 years. Diabetes mellitus was the only significant factor associated with prosthetic looseness from both univariate and multivariate analyses (HR = 7.05, p = 0.002 and HR = 5.93, p = 0.007 respectively). Among the lower limb amputees in Sisaket province, diabetes mellitus was the only factor associated with prosthetic looseness. Therefore, diabetic screening should be supplemented in lower limb amputee assessment protocol. In addition, we recommend that amputees with diabetes mellitus should receive prosthesis check out at approximately

  13. The role of osteoblasts in peri-prosthetic osteolysis.

    LENUS (Irish Health Repository)

    O'Neill, S C

    2013-08-01

    Peri-prosthetic osteolysis and subsequent aseptic loosening is the most common reason for revising total hip replacements. Wear particles originating from the prosthetic components interact with multiple cell types in the peri-prosthetic region resulting in an inflammatory process that ultimately leads to peri-prosthetic bone loss. These cells include macrophages, osteoclasts, osteoblasts and fibroblasts. The majority of research in peri-prosthetic osteolysis has concentrated on the role played by osteoclasts and macrophages. The purpose of this review is to assess the role of the osteoblast in peri-prosthetic osteolysis. In peri-prosthetic osteolysis, wear particles may affect osteoblasts and contribute to the osteolytic process by two mechanisms. First, particles and metallic ions have been shown to inhibit the osteoblast in terms of its ability to secrete mineralised bone matrix, by reducing calcium deposition, alkaline phosphatase activity and its ability to proliferate. Secondly, particles and metallic ions have been shown to stimulate osteoblasts to produce pro inflammatory mediators in vitro. In vivo, these mediators have the potential to attract pro-inflammatory cells to the peri-prosthetic area and stimulate osteoclasts to absorb bone. Further research is needed to fully define the role of the osteoblast in peri-prosthetic osteolysis and to explore its potential role as a therapeutic target in this condition.

  14. Prosthetic hip joint infection due to Campylobacter fetus.

    OpenAIRE

    Bates, C J; Clarke, T C; Spencer, R C

    1994-01-01

    A case of postoperative prosthetic hip joint infection due to Campylobacter fetus subsp. fetus is described. Difficulties in isolation and antimicrobial susceptibility testing of this organism are discussed.

  15. Successful Management of Prosthetic Valve Brucella Endocarditis with Antibiotherapy Alone

    Directory of Open Access Journals (Sweden)

    José Pedro Fonseca

    2018-01-01

    Full Text Available Objectives: To report a case of mechanical aortic prosthesis Brucella endocarditis successfully treated with antibiotics alone. Materials and methods: We describe a clinical case and present a review of the literature. Results: A 60-year-old female farmer with a mechanical aortic prosthetic valve presented with low back pain and fever. She was diagnosed with prosthetic valve Brucella mellitensis endocarditis and was cured with antibiotic therapy alone. Few cases of successfully treated prosthetic valve Brucella endocarditis without surgery have been reported. Conclusion: Prosthetic valve Brucella endocarditis usually requires surgical valve replacement. However, selected patients may be successfully treated with antibiotic therapy alone.

  16. Conventional and molecular diagnostic strategies for prosthetic joint infections.

    Science.gov (United States)

    Esteban, Jaime; Sorlí, Luisa; Alentorn-Geli, Eduard; Puig, Lluís; Horcajada, Juan P

    2014-01-01

    An accurate diagnosis of prosthetic joint infection (PJI) is the mainstay for an optimized clinical management. This review analyzes different diagnostic strategies of PJI, with special emphasis on molecular diagnostic tools and their current and future applications. Until now, the culture of periprosthetic tissues has been considered the gold standard for the diagnosis of PJI. However, sonication of the implant increases the sensitivity of those cultures and is being increasingly adopted by many centers. Molecular diagnostic methods compared with intraoperative tissue culture, especially if combined with sonication, have a higher sensitivity, a faster turnaround time and are not influenced by previous antimicrobial therapy. However, they still lack a system for detection of antimicrobial susceptibility, which is crucial for an optimized and less toxic therapy of PJI. More studies are needed to assess the clinical value of these methods and their cost-effectiveness.

  17. Mechanical design of a shape memory alloy actuated prosthetic hand.

    Science.gov (United States)

    De Laurentis, Kathryn J; Mavroidis, Constantinos

    2002-01-01

    This paper presents the mechanical design for a new five fingered, twenty degree-of-freedom dexterous hand patterned after human anatomy and actuated by Shape Memory Alloy artificial muscles. Two experimental prototypes of a finger, one fabricated by traditional means and another fabricated by rapid prototyping techniques, are described and used to evaluate the design. An important aspect of the Rapid Prototype technique used here is that this multi-articulated hand will be fabricated in one step, without requiring assembly, while maintaining its desired mobility. The use of Shape Memory Alloy actuators combined with the rapid fabrication of the non-assembly type hand, reduce considerably its weight and fabrication time. Therefore, the focus of this paper is the mechanical design of a dexterous hand that combines Rapid Prototype techniques and smart actuators. The type of robotic hand described in this paper can be utilized for applications requiring low weight, compactness, and dexterity such as prosthetic devices, space and planetary exploration.

  18. Comparison of the applicability of neural networks and cluster classification methods on the example company's financial situation

    Directory of Open Access Journals (Sweden)

    Oldřich Trenz

    2010-01-01

    Full Text Available The paper is focused on comparing the classification ability of the model with self-learning neutral network and methods from cluster analysis. The emphasis is particularly on the comparison of different approaches to a specific application example of the commitment, the classification of then financial situation. The aim is to critically evaluate different approaches at the level of application and deployment options.The verify the classification capability of the different approaches were used financial data from the database „Credit Info“, in particular data describing the financial situation of the two hundred eleven farms of homogeneous and uniform primary field.Input data were from the methods used, modified and evaluated by appropriate methodology. Found the final solution showed that the used approaches do not show significant differences, and they can say that they are equivalent. Based on this finding can formulate the conclusion that the approach of artificial intelligence (self-learning neural network is as effective as a partial methods in the field of cluster analysis. In both cases, these approaches can be an invaluable tool in decision making.When the financial situation is evaluated by the expert, the calculation of liquidity, profitability and other financial indicators are making some simplification. In this respect, neural networks perform better, since these simplifications in them selves are not natively included. They can better assess and somewhat ambiguous cases, including businesses with undefined financial situation, the so-called data in the border region. In this respect, support and representation of the graphical layout of the resulting situation sorted out objects using software implemented neural network model.

  19. Neural network model for growth of Salmonella serotypes in ground chicken subjected to temperature abuse during cold storage for application in HACCP and risk assessment

    Science.gov (United States)

    With the advent of commercial software applications, it is now easy to develop neural network models for predictive microbiology applications. However, different versions of the model may be required to meet the divergent needs of model users. In the current study, the commercial software applicat...

  20. Distributed computing methodology for training neural networks in an image-guided diagnostic application.

    Science.gov (United States)

    Plagianakos, V P; Magoulas, G D; Vrahatis, M N

    2006-03-01

    Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

  1. Application of neural network to multi-dimensional design window search

    International Nuclear Information System (INIS)

    Kugo, T.; Nakagawa, M.

    1996-01-01

    In the reactor core design, many parametric survey calculations should be carried out to decide an optimal set of basic design parameter values. They consume a large amount of computation time and labor in the conventional way. To support directly such a work, we investigate a procedure to search efficiently a design window, which is defined as feasible design parameter ranges satisfying design criteria and requirements, in a multi-dimensional space composed of several basic design parameters. A principle of the present method is to construct the multilayer neural network to simulate quickly a response of an analysis code through a training process, and to reduce computation time using the neural network as a substitute of an analysis code. We apply the present method to a fuel pin design of high conversion light water reactors for the neutronics and thermal hydraulics fields to demonstrate performances of the method. (author)

  2. Applications of Deep Neural Networks in a Top Quark Mass Measurement at the LHC

    CERN Document Server

    Lange, Torben; Kasieczka, Gregor

    2018-01-01

    In this analysis the usage of deep neural networks for an improved event selection forthe top-quark-mass measurement in the t¯ muon+jets channel for events at the CMS ext√periment for the LHC run II with a center of mass energy s = 13 TeV was investigated.The composition of the event selection with respect to different jet-assignment permutationtypes was found to have a strong influence on the systematic uncertainty of the top-quarkmass measurement. A selection based on the output of neural network trained on classifyingevent permutations of the t¯ muon+jets final state into these permutation types could thentbe used to improve the systematical uncertainty of the current mass measurement from asystematical uncertainty of around 630 MeV to 560 MeV.

  3. Applications of deep convolutional neural networks to digitized natural history collections

    Directory of Open Access Journals (Sweden)

    Eric Schuettpelz

    2017-11-01

    Full Text Available Natural history collections contain data that are critical for many scientific endeavors. Recent efforts in mass digitization are generating large datasets from these collections that can provide unprecedented insight. Here, we present examples of how deep convolutional neural networks can be applied in analyses of imaged herbarium specimens. We first demonstrate that a convolutional neural network can detect mercury-stained specimens across a collection with 90% accuracy. We then show that such a network can correctly distinguish two morphologically similar plant families 96% of the time. Discarding the most challenging specimen images increases accuracy to 94% and 99%, respectively. These results highlight the importance of mass digitization and deep learning approaches and reveal how they can together deliver powerful new investigative tools.

  4. Neural Network Control-Based Drive Design of Servomotor and Its Application to Automatic Guided Vehicle

    Directory of Open Access Journals (Sweden)

    Ming-Shyan Wang

    2015-01-01

    Full Text Available An automatic guided vehicle (AGV is extensively used for productions in a flexible manufacture system with high efficiency and high flexibility. A servomotor-based AGV is designed and implemented in this paper. In order to steer the AGV to go along a predefined path with corner or arc, the conventional proportional-integral-derivative (PID control is used in the system. However, it is difficult to tune PID gains at various conditions. As a result, the neural network (NN control is considered to assist the PID control for gain tuning. The experimental results are first provided to verify the correctness of the neural network plus PID control for 400 W-motor control system. Secondly, the AGV includes two sets of the designed motor systems and CAN BUS transmission so that it can move along the straight line and curve paths shown in the taped videos.

  5. Application of artificial neural networks for response surface modelling in HPLC method development

    Directory of Open Access Journals (Sweden)

    Mohamed A. Korany

    2012-01-01

    Full Text Available This paper discusses the usefulness of artificial neural networks (ANNs for response surface modelling in HPLC method development. In this study, the combined effect of pH and mobile phase composition on the reversed-phase liquid chromatographic behaviour of a mixture of salbutamol (SAL and guaiphenesin (GUA, combination I, and a mixture of ascorbic acid (ASC, paracetamol (PAR and guaiphenesin (GUA, combination II, was investigated. The results were compared with those produced using multiple regression (REG analysis. To examine the respective predictive power of the regression model and the neural network model, experimental and predicted response factor values, mean of squares error (MSE, average error percentage (Er%, and coefficients of correlation (r were compared. It was clear that the best networks were able to predict the experimental responses more accurately than the multiple regression analysis.

  6. Application of BP neural network for LRAD-based alpha contamination monitoring inside pipes

    International Nuclear Information System (INIS)

    Wu Xuemei; Li Zhe; Zhang Jinzhao; Li Pingchuan; Su Jilong; Tuo Xianguo; Liu Mingzhe

    2012-01-01

    Factors of airspeed, flux, activity, source position, pipe length and pipe diameter affect nonlinearly source activity readout of the Long Range Alpha Detection (LRAD). In this paper, multiparameter influence experiment is carried out using variable-control method, aiming at studying relationships between the readout and each of the factors. The back propagation (BP) neural network model is established to overcome the nonlinear effects of the factors on the readout, with the readout and the multiparameters being the input, and the source activity being the output. Experiment data of 948 groups are used for BP neural network forecasting, with an average relative error of 3.4218×10 -4 . And in a 100-group test, an average relative error of 2.217×10 -2 is obtained. It shows that with this method source radioactivity in pipes can be simulated. (authors)

  7. A Neural Network: Family Competition Genetic Algorithm and Its Applications in Electromagnetic Optimization

    Directory of Open Access Journals (Sweden)

    P.-Y. Chen

    2009-01-01

    Full Text Available This study proposes a neural network-family competition genetic algorithm (NN-FCGA for solving the electromagnetic (EM optimization and other general-purpose optimization problems. The NN-FCGA is a hybrid evolutionary-based algorithm, combining the good approximation performance of neural network (NN and the robust and effective optimum search ability of the family competition genetic algorithms (FCGA to accelerate the optimization process. In this study, the NN-FCGA is used to extract a set of optimal design parameters for two representative design examples: the multiple section low-pass filter and the polygonal electromagnetic absorber. Our results demonstrate that the optimal electromagnetic properties given by the NN-FCGA are comparable to those of the FCGA, but reducing a large amount of computation time and a well-trained NN model that can serve as a nonlinear approximator was developed during the optimization process of the NN-FCGA.

  8. Artificial neural networks in variable process control: application in particleboard manufacture

    Energy Technology Data Exchange (ETDEWEB)

    Esteban, L. G.; Garcia Fernandez, F.; Palacios, P. de; Conde, M.

    2009-07-01

    Artificial neural networks are an efficient tool for modelling production control processes using data from the actual production as well as simulated or design of experiments data. In this study two artificial neural networks were combined with the control process charts and it was checked whether the data obtained by the networks were valid for variable process control in particleboard manufacture. The networks made it possible to obtain the mean and standard deviation of the internal bond strength of the particleboard within acceptable margins using known data of thickness, density, moisture content, swelling and absorption. The networks obtained met the acceptance criteria for test values from non-standard test methods, as well as the criteria for using these values in statistical process control. (Author) 47 refs.

  9. Applications of deep convolutional neural networks to digitized natural history collections.

    Science.gov (United States)

    Schuettpelz, Eric; Frandsen, Paul B; Dikow, Rebecca B; Brown, Abel; Orli, Sylvia; Peters, Melinda; Metallo, Adam; Funk, Vicki A; Dorr, Laurence J

    2017-01-01

    Natural history collections contain data that are critical for many scientific endeavors. Recent efforts in mass digitization are generating large datasets from these collections that can provide unprecedented insight. Here, we present examples of how deep convolutional neural networks can be applied in analyses of imaged herbarium specimens. We first demonstrate that a convolutional neural network can detect mercury-stained specimens across a collection with 90% accuracy. We then show that such a network can correctly distinguish two morphologically similar plant families 96% of the time. Discarding the most challenging specimen images increases accuracy to 94% and 99%, respectively. These results highlight the importance of mass digitization and deep learning approaches and reveal how they can together deliver powerful new investigative tools.

  10. Application of BP Neural Network Algorithm in Traditional Hydrological Model for Flood Forecasting

    Directory of Open Access Journals (Sweden)

    Jianjin Wang

    2017-01-01

    Full Text Available Flooding contributes to tremendous hazards every year; more accurate forecasting may significantly mitigate the damages and loss caused by flood disasters. Current hydrological models are either purely knowledge-based or data-driven. A combination of data-driven method (artificial neural networks in this paper and knowledge-based method (traditional hydrological model may booster simulation accuracy. In this study, we proposed a new back-propagation (BP neural network algorithm and applied it in the semi-distributed Xinanjiang (XAJ model. The improved hydrological model is capable of updating the flow forecasting error without losing the leading time. The proposed method was tested in a real case study for both single period corrections and real-time corrections. The results reveal that the proposed method could significantly increase the accuracy of flood forecasting and indicate that the global correction effect is superior to the second-order autoregressive correction method in real-time correction.

  11. Simplified application of probabilistic safety analysis in nuclear power plants by means of artificial neural networks

    International Nuclear Information System (INIS)

    Oehmgen, T.; Knorr, J.

    2004-01-01

    Probabilistic safety analyses (PSA) are conducted to assess the balanced nature of plant design in terms of technical safety and the administrative management of plant operation in nuclear power plants. In the evaluation shown in this article of the operating experience accumulated in two nuclear power plants, all failures are traced back consistently to the plant media and component levels, respectively, for the calculation of reliability coefficients. Moreover, the use of neural networks for probabilistic calculations is examined. The results are verified on the basis of test examples. Calculations with neural networks are very easy to carry out in a kind of 'black box'. There is a possibility, for instance, to use the system in plant maintenance. (orig.) [de

  12. Definition of new 3D invariants. Applications to pattern recognition problems with neural networks

    International Nuclear Information System (INIS)

    Proriol, J.

    1996-01-01

    We propose a definition of new 3D invariants. Usual pattern recognition methods use 2D descriptions of 3D objects, we propose a 2D approximation of the defined 3D invariants which can be used with neural networks to solve pattern recognition problems. We describe some methods to use the 2 D approximants. This work is an extension of previous 3D invariants used to solve some high energy physics problems. (author)

  13. PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications

    OpenAIRE

    Pasquier, Claude; Promponas, Vasilis; Hamodrakas, Stavros

    2009-01-01

    International audience; A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the av...

  14. Application of neural networks to validation of feedwater flow rate in a nuclear power plant

    International Nuclear Information System (INIS)

    Khadem, M.; Ipakchi, A.; Alexandro, F.J.; Colley, R.W.

    1993-01-01

    Feedwater flow rate measurement in nuclear power plants requires periodic calibration. This is due to the fact that the venturi surface condition of the feedwater flow rate sensor changes because of a chemical reaction between the surface coating material and the feedwater. Fouling of the venturi surface, due to this chemical reaction and the deposits of foreign materials, has been observed shortly after a clean venturi is put in operation. A fouled venturi causes an incorrect measurement of feedwater flow rate, which in turn results in an inaccurate calculation of the generated power. This paper presents two methods for verifying incipient and continuing fouling of the venturi of the feedwater flow rate sensors. Both methods are based on the use of a set of dissimilar process variables dynamically related to the feedwater flow rate variable. The first method uses a neural network to generate estimates of the feedwater flow rate readings. Agreement, within a given tolerance, of the feedwater flow rate instrument reading, and the corresponding neural network output establishes that the feedwater flow rate instrument is operating properly. The second method is similar to the first method except that the neural network predicts the core power which is calculated from measurements on the primary loop, rather than the feedwater flow rates. This core power is referred to the primary core power in this paper. A comparison of the power calculated from the feedwater flow measurements in the secondary loop, with the calculated and neural network predicted primary core power provides information from which it can be determined whether fouling is beginning to occur. The two methods were tested using data from the feedwater flow meters in the two feedwater flow loops of the TMI-1 nuclear power plant

  15. Artificial neural network models' application for radioactive substances' migration forecasting in soil

    International Nuclear Information System (INIS)

    Kovalenko, V.I.; Khil'ko, O.S.; Kundas, S.P.

    2009-01-01

    The work is indicated to the use of artificial neural network (ANN) models in program complex SPS for radioactive substances' migration forecasting in soil. For the problem solution two ANN models are used. One of them forecasts radioactive substances' migration, another carries out forecasting of physical and chemical soil properties. Program complex SPS allows to achieve a low error of forecasting (no more than 5 %) and high training speed. (authors)

  16. Application of Artificial Neural Networks in Modeling Direction Wheelchairs Using Neurosky Mindset Mobile (EEG Device

    Directory of Open Access Journals (Sweden)

    Agus Siswoyo

    2017-07-01

    Full Text Available The implementation of Artificial Neural Network in prediction the direction of electric wheelchair from brain signal input for physical mobility impairment.. The control of the wheelchair as an effort in improving disabled person life quality. The interaction from disabled person is helping in relation to social life with others. Because of the mobility impairment, the wheelchair with brain signal input is made. This wheel chair is purposed to help the disabled person and elderly for their daily activity. ANN helps to develop the mapping from input to target. ANN is developed in 3 level: input level, one hidden level, and output level (6-2-1. There are 6 signal from Neurosky Mindset sensor output, Alpha1, Alpha2, Raw signal, Total time signal, Attention Signal, and Meditation signal. The purpose of this research is to find out the output value from ANN: value in turning right, turning left, and forward. From those outputs, we can prove the relevance to the target. One of the main problem that interfering with success is the problem of proper neural network training. Arduino uno is chosen to implement the learning program algorithm because it is a popular microcontroller that is economic and efficient. The training of artificial neural network in this research uses 21 data package from raw data, Alpha1, Aplha2, Meditation data, Attention data, total time data. At the time of the test there is a value of Mean square Error(MSE at the end of training amounted to 0.92495 at epoch 9958, value a correlation coefficient of 0.92804 shows that accuracy the results of the training process good.     Keywords: Navigation, Neural network, Real-time training, Arduino

  17. Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications

    International Nuclear Information System (INIS)

    Reifman, J.; Vitela, J.E.

    1994-01-01

    The method of conjugate gradients is used to expedite the learning process of feedforward multilayer artificial neural networks and to systematically update both the learning parameter and the momentum parameter at each training cycle. The mechanism for the occurrence of premature saturation of the network nodes observed with the back propagation algorithm is described, suggestions are made to eliminate this undesirable phenomenon, and the reason by which this phenomenon is precluded in the method of conjugate gradients is presented. The proposed method is compared with the standard back propagation algorithm in the training of neural networks to classify transient events in neural power plants simulated by the Midland Nuclear Power Plant Unit 2 simulator. The comparison results indicate that the rate of convergence of the proposed method is much greater than the standard back propagation, that it reduces both the number of training cycles and the CPU time, and that it is less sensitive to the choice of initial weights. The advantages of the method are more noticeable and important for problems where the network architecture consists of a large number of nodes, the training database is large, and a tight convergence criterion is desired

  18. A novel application of artificial neural network for wind speed estimation

    Science.gov (United States)

    Fang, Da; Wang, Jianzhou

    2017-05-01

    Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.

  19. Using Neural Data to Test A Theory of Investor Behavior: An Application to Realization Utility.

    Science.gov (United States)

    Frydman, Cary; Barberis, Nicholas; Camerer, Colin; Bossaerts, Peter; Rangel, Antonio

    2014-04-01

    We use measures of neural activity provided by functional magnetic resonance imaging (fMRI) to test the "realization utility" theory of investor behavior, which posits that people derive utility directly from the act of realizing gains and losses. Subjects traded stocks in an experimental market while we measured their brain activity. We find that all subjects exhibit a strong disposition effect in their trading, even though it is suboptimal. Consistent with the realization utility explanation for this behavior, we find that activity in the ventromedial prefrontal cortex, an area known to encode the value of options during choices, correlates with the capital gains of potential trades; that the neural measures of realization utility correlate across subjects with their individual tendency to exhibit a disposition effect; and that activity in the ventral striatum, an area known to encode information about changes in the present value of experienced utility, exhibits a positive response when subjects realize capital gains. These results provide support for the realization utility model and, more generally, demonstrate how neural data can be helpful in testing models of investor behavior.

  20. Firing rate estimation using infinite mixture models and its application to neural decoding.

    Science.gov (United States)

    Shibue, Ryohei; Komaki, Fumiyasu

    2017-11-01

    Neural decoding is a framework for reconstructing external stimuli from spike trains recorded by various neural recordings. Kloosterman et al. proposed a new decoding method using marked point processes (Kloosterman F, Layton SP, Chen Z, Wilson MA. J Neurophysiol 111: 217-227, 2014). This method does not require spike sorting and thereby improves decoding accuracy dramatically. In this method, they used kernel density estimation to estimate intensity functions of marked point processes. However, the use of kernel density estimation causes problems such as low decoding accuracy and high computational costs. To overcome these problems, we propose a new decoding method using infinite mixture models to estimate intensity. The proposed method improves decoding performance in terms of accuracy and computational speed. We apply the proposed method to simulation and experimental data to verify its performance. NEW & NOTEWORTHY We propose a new neural decoding method using infinite mixture models and nonparametric Bayesian statistics. The proposed method improves decoding performance in terms of accuracy and computation speed. We have successfully applied the proposed method to position decoding from spike trains recorded in a rat hippocampus. Copyright © 2017 the American Physiological Society.

  1. Neural network application for illicit substances identification; Aplicacao de redes neurais para a identificacao de substancias ilicitas

    Energy Technology Data Exchange (ETDEWEB)

    Nunes, Wallace V.; Silva, Ademir X. da; Crispim, Verginia R.; Schirru, Roberto [Universidade Federal, Rio de Janeiro, RJ (Brazil). Coordenacao dos Programas de Pos-graduacao de Engenharia. Programa de Engenharia Nuclear

    2000-07-01

    Thermal neutron activation analysis is based on neutron capture prompt gamma-ray analysis and has been used in wide variety of fields, for examples, for inspection of checked airline baggage and for detection of buried land mines. In all of these applications, the detected {gamma}-ray intensities from the elements present are used to estimate their concentrations. A study about application using a trained neutral network is presented to determine the presence of illicit substances, such as explosives and drugs, carried out in the luggages. The illicit substances emit characteristic detected {gamma}-ray which are the fingerprint of each isotope. The fingerprint data-base of the gamma-ray spectrum of substances is obtained via Monte Carlo N-Particle Transport code, MCNP, version 4B. It was possible to train the neural network to determine the presence of explosives and narcotics even hidden by several materials. (author)

  2. Parallelization of learning problems by artificial neural networks. Application in external radiotherapy; Parallelisation de problemes d'apprentissage par des reseaux neuronaux artificiels. Application en radiotherapie externe

    Energy Technology Data Exchange (ETDEWEB)

    Sauget, M

    2007-12-15

    This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

  3. Exophiala (Wangiella dermatitidis Prosthetic Aortic Valve Endocarditis and Prosthetic Graft Infection in an Immune Competent Patient

    Directory of Open Access Journals (Sweden)

    Jay S. Berger

    2017-01-01

    Full Text Available Exophiala (Wangiella dermatitidis is an emerging dematiaceous fungus associated with high mortality rates and is a rare cause of endocarditis. We describe the first case of E. dermatitidis endocarditis of a prosthetic aortic valve and aortic graft in an immune competent patient with no clear risk factors of hematological acquisition.

  4. Pre prosthetic reconstruction of alveolar ridge

    Directory of Open Access Journals (Sweden)

    Prabhuji Munivenkatappa Lakshmaiahenkatesh

    2011-01-01

    Full Text Available Dento-alveolar bony defects are common and occur due to a variety of causes, such as, pulpal pathology, traumatic tooth extraction, advanced periodontal disease, implant failure, tumor or congenital anomalies. These defects often cause a significant problem in dental treatment and rehabilitation. Many techniques exist for effective soft and hard tissue augmentation. The approach is largely based on the extent of the defect and specific procedures to be performed for the implant or prosthetic rehabilitation. This article presents case reports of soft and hard tissue ridge augmentation.

  5. Prevention of Infection in Orthopedic Prosthetic Surgery.

    Science.gov (United States)

    Chirca, Ioana; Marculescu, Camelia

    2017-06-01

    Total joint arthroplasty is a generally safe orthopedic procedure; however, infection is a potentially devastating complication. Multiple risk factors have been identified for development of prosthetic joint infections. Identification of patients at risk and preoperative correction of known risk factors, such as smoking, diabetes mellitus, anemia, malnutrition, and decolonization of Staphylococcus carriers, represent well-established actions to decrease the infection risk. Careful operative technique, proper draping and skin preparation, and appropriate selection and dosing of antimicrobials for perioperative prophylaxis are also very important in prevention of infection. Published by Elsevier Inc.

  6. Recurrent-neural-network-based Boolean factor analysis and its application to word clustering.

    Science.gov (United States)

    Frolov, Alexander A; Husek, Dusan; Polyakov, Pavel Yu

    2009-07-01

    The objective of this paper is to introduce a neural-network-based algorithm for word clustering as an extension of the neural-network-based Boolean factor analysis algorithm (Frolov , 2007). It is shown that this extended algorithm supports even the more complex model of signals that are supposed to be related to textual documents. It is hypothesized that every topic in textual data is characterized by a set of words which coherently appear in documents dedicated to a given topic. The appearance of each word in a document is coded by the activity of a particular neuron. In accordance with the Hebbian learning rule implemented in the network, sets of coherently appearing words (treated as factors) create tightly connected groups of neurons, hence, revealing them as attractors of the network dynamics. The found factors are eliminated from the network memory by the Hebbian unlearning rule facilitating the search of other factors. Topics related to the found sets of words can be identified based on the words' semantics. To make the method complete, a special technique based on a Bayesian procedure has been developed for the following purposes: first, to provide a complete description of factors in terms of component probability, and second, to enhance the accuracy of classification of signals to determine whether it contains the factor. Since it is assumed that every word may possibly contribute to several topics, the proposed method might be related to the method of fuzzy clustering. In this paper, we show that the results of Boolean factor analysis and fuzzy clustering are not contradictory, but complementary. To demonstrate the capabilities of this attempt, the method is applied to two types of textual data on neural networks in two different languages. The obtained topics and corresponding words are at a good level of agreement despite the fact that identical topics in Russian and English conferences contain different sets of keywords.

  7. Prosthetic Rehabilitation in Children: An Alternative Clinical Technique

    Directory of Open Access Journals (Sweden)

    Nádia Carolina Teixeira Marques

    2013-01-01

    Full Text Available Complete and partial removable dentures have been used successfully in numerous patients with oligodontia and/or anodontia. However, there is little information in the literature regarding the principles and guidelines to prosthetic rehabilitation for growing children. This case report describes the management of a young child with oligodontia as well as the treatment planning and the prosthetic rehabilitation technique.

  8. 21 CFR 890.3025 - Prosthetic and orthotic accessory.

    Science.gov (United States)

    2010-04-01

    ... (CONTINUED) MEDICAL DEVICES PHYSICAL MEDICINE DEVICES Physical Medicine Prosthetic Devices § 890.3025... intended for medical purposes to support, protect, or aid in the use of a cast, orthosis (brace), or prosthesis. Examples of prosthetic and orthotic accessories include the following: A pelvic support band and...

  9. Successful thrombolysis of aortic prosthetic valve thrombosis during ...

    African Journals Online (AJOL)

    Successful thrombolysis of aortic prosthetic valve thrombosis during first trimester of pregnancy. A Shukla, AP Raval, R Shah. Abstract. Prosthetic heart valve thrombosis during pregnancy is life-threatening. Standard surgical treatment using cardiopulmonary bypass carries high maternal and fetal complications. Here we ...

  10. Stiffness and hysteresis properties of some prosthetic feet

    NARCIS (Netherlands)

    van Jaarsveld, H.W.L.; Grootenboer, H.J.; de Vries, J.; Koopman, Hubertus F.J.M.

    1990-01-01

    A prosthetic foot is an important element of a prosthesis, although it is not always fully recognized that the properties of the foot, along with the prosthetic knee joint and the socket, are in part responsible for the stability and metabolic energy cost during walking. The stiffness and the

  11. Prosthetic prescription in the Netherlands: An interview with clinical experts

    NARCIS (Netherlands)

    Van Der Linde, H.; Geertzen, J.H.B.; Hofstad, C.J.; Van Limbeek, Jacques; Postema, K.

    2004-01-01

    In the process of guideline development for prosthetic prescription in the Netherlands the authors made a study of the daily clinical practice of lower limb prosthetics. Besides the evidence-based knowledge from literature the more implicit knowledge from clinical experts is of importance for

  12. 38 CFR 17.150 - Prosthetic and similar appliances.

    Science.gov (United States)

    2010-07-01

    ... appliances. 17.150 Section 17.150 Pensions, Bonuses, and Veterans' Relief DEPARTMENT OF VETERANS AFFAIRS MEDICAL Prosthetic, Sensory, and Rehabilitative Aids § 17.150 Prosthetic and similar appliances... appliances including invalid lifts and therapeutic and rehabilitative devices, and special clothing made...

  13. Synchronization of stochastic delayed neural networks with markovian switching and its application.

    Science.gov (United States)

    Tang, Yang; Fang, Jian-An; Miao, Qing-Ying

    2009-02-01

    In this paper, the problem of adaptive synchronization for a class of stochastic neural networks (SNNs) which involve both mixed delays and Markovian jumping parameters is investigated. The mixed delays comprise the time-varying delays and distributed delays, both of which are mode-dependent. The stochastic perturbations are described in terms of Browian motion. By the adaptive feedback technique, several sufficient criteria have been proposed to ensure the synchronization of SNNs in mean square. Moreover, the proposed adaptive feedback scheme is applied to the secure communication. Finally, the corresponding simulation results are given to demonstrate the usefulness of the main results obtained.

  14. Statistical inference, the bootstrap, and neural-network modeling with application to foreign exchange rates.

    Science.gov (United States)

    White, H; Racine, J

    2001-01-01

    We propose tests for individual and joint irrelevance of network inputs. Such tests can be used to determine whether an input or group of inputs "belong" in a particular model, thus permitting valid statistical inference based on estimated feedforward neural-network models. The approaches employ well-known statistical resampling techniques. We conduct a small Monte Carlo experiment showing that our tests have reasonable level and power behavior, and we apply our methods to examine whether there are predictable regularities in foreign exchange rates. We find that exchange rates do appear to contain information that is exploitable for enhanced point prediction, but the nature of the predictive relations evolves through time.

  15. Rotation-invariant neural pattern recognition system with application to coin recognition.

    Science.gov (United States)

    Fukumi, M; Omatu, S; Takeda, F; Kosaka, T

    1992-01-01

    In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition.

  16. The Application of Classical and Neural Regression Models for the Valuation of Residential Real Estate

    Directory of Open Access Journals (Sweden)

    Mach Łukasz

    2017-06-01

    Full Text Available The research process aimed at building regression models, which helps to valuate residential real estate, is presented in the following article. Two widely used computational tools i.e. the classical multiple regression and regression models of artificial neural networks were used in order to build models. An attempt to define the utilitarian usefulness of the above-mentioned tools and comparative analysis of them is the aim of the conducted research. Data used for conducting analyses refers to the secondary transactional residential real estate market.

  17. Method of image segmentation using a neural network. Application to MR imaging of brain tumors

    International Nuclear Information System (INIS)

    Engler, E.; Gautherie, M.

    1992-01-01

    An original method of numerical images segmentation has been developed. This method is based on pixel clustering using a formal neural network configurated by supervised learning of pre-classified examples. The method has been applied to series of MR images of brain tumors (gliomas) with a view to proceed with a 3D-extraction of the tumor volume. This study is part of a project on cancer thermotherapy including the development of a scan-focused ultrasound system of tumor heating and a 3D-numerical thermal model

  18. Workplace injuries, safety climate and behaviors: application of an artificial neural network.

    Science.gov (United States)

    Abubakar, A Mohammed; Karadal, Himmet; Bayighomog, Steven W; Merdan, Ethem

    2018-05-09

    This article proposes and tests a model for the interaction effect of the organizational safety climate and behaviors on workplace injuries. Using artificial neural network and survey data from 306 metal casting industry employees in central Anatolia, we found that an organizational safety climate mitigates workplace injuries, and safety behaviors enforce the strength of the negative impact of the safety climate on workplace injuries. The results suggest a complex relationship between the organizational safety climate, safety behavior and workplace injuries. Theoretical and practical implications are discussed in light of decreasing workplace injuries in the Anatolian metal casting industry.

  19. Modelling of hardness prediction of magnesium alloys using artificial neural networks applications

    OpenAIRE

    L.A. Dobrzański; T. Tański; J. Trzaska; L. Čížek

    2008-01-01

    Purpose: In the following paper there have been presented the optimisation of heat treatment condition and structure of the MCMgAl12Zn1, MCMgAl9Zn1, MCMgAl6Zn1, MCMgAl3Zn1 magnesium cast alloy as-cast state and after a heat treatment.Design/methodology/approach: Working out of a neural network model for simulation of influence of temperature, solution heat treatment and ageing time and aluminium content on hardness of the analyzed magnesium cast alloys.Findings: The different heat treatment k...

  20. An L∞/L1-Constrained Quadratic Optimization Problem with Applications to Neural Networks

    International Nuclear Information System (INIS)

    Leizarowitz, Arie; Rubinstein, Jacob

    2003-01-01

    Pattern formation in associative neural networks is related to a quadratic optimization problem. Biological considerations imply that the functional is constrained in the L ∞ norm and in the L 1 norm. We consider such optimization problems. We derive the Euler-Lagrange equations, and construct basic properties of the maximizers. We study in some detail the case where the kernel of the quadratic functional is finite-dimensional. In this case the optimization problem can be fully characterized by the geometry of a certain convex and compact finite-dimensional set