Decoding small surface codes with feedforward neural networks
Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen
2018-01-01
Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.
Classes of feedforward neural networks and their circuit complexity
Shawe-Taylor, John S.; Anthony, Martin H.G.; Kern, Walter
1992-01-01
This paper aims to place neural networks in the context of boolean circuit complexity. We define appropriate classes of feedforward neural networks with specified fan-in, accuracy of computation and depth and using techniques of communication complexity proceed to show that the classes fit into a
Classification of Urinary Calculi using Feed-Forward Neural Networks
African Journals Online (AJOL)
In this work the results of classification of these types of calculi (using their infrared spectra in the region 1450–450 cm–1) by feed-forward neural networks are presented. Genetic algorithms were used for optimization of neural networks and for selection of the spectral regions most suitable for classification purposes.
Adaptive training of feedforward neural networks by Kalman filtering
International Nuclear Information System (INIS)
Ciftcioglu, Oe.
1995-02-01
Adaptive training of feedforward neural networks by Kalman filtering is described. Adaptive training is particularly important in estimation by neural network in real-time environmental where the trained network is used for system estimation while the network is further trained by means of the information provided by the experienced/exercised ongoing operation. As result of this, neural network adapts itself to a changing environment to perform its mission without recourse to re-training. The performance of the training method is demonstrated by means of actual process signals from a nuclear power plant. (orig.)
Accelerated Training for Large Feedforward Neural Networks
Stepniewski, Slawomir W.; Jorgensen, Charles C.
1998-01-01
In this paper we introduce a new training algorithm, the scaled variable metric (SVM) method. Our approach attempts to increase the convergence rate of the modified variable metric method. It is also combined with the RBackprop algorithm, which computes the product of the matrix of second derivatives (Hessian) with an arbitrary vector. The RBackprop method allows us to avoid computationally expensive, direct line searches. In addition, it can be utilized in the new, 'predictive' updating technique of the inverse Hessian approximation. We have used directional slope testing to adjust the step size and found that this strategy works exceptionally well in conjunction with the Rbackprop algorithm. Some supplementary, but nevertheless important enhancements to the basic training scheme such as improved setting of a scaling factor for the variable metric update and computationally more efficient procedure for updating the inverse Hessian approximation are presented as well. We summarize by comparing the SVM method with four first- and second- order optimization algorithms including a very effective implementation of the Levenberg-Marquardt method. Our tests indicate promising computational speed gains of the new training technique, particularly for large feedforward networks, i.e., for problems where the training process may be the most laborious.
Forecasting of IBOVESPA returns using feedforward evolutionary artificial neural networks
Directory of Open Access Journals (Sweden)
Edgar Leite dos Santos Filho
2011-12-01
Full Text Available Facing the challenges of anticipating financial market uncertainties and movements, and the necessity of taking buy or sell decisions supported by rational methods, market traders found in statistics and econometrics methods, the base to support their decisions. In several scientific papers about forecasting financial time series, method selection keeps as central concern. This paper compares the performance of evolutionary feedforward artificial neural network (EANN and an AR+GARCH model, for one step ahead forecasting of IBOVESPA returns. The EANN is trained by self-adapting differential evolution algorithm and AR+GARCH model is adjusted to be used as performance reference. The root mean square error (RMSE and U-Theil inequality coefficient were used as performance metrics. Simulation results showed EANN feedforward achieved better results, fit better and captured the nonlinear behavior of returns.
Bayesian multioutput feedforward neural networks comparison: a conjugate prior approach.
Rossi, Vivien; Vila, Jean-Pierre
2006-01-01
A Bayesian method for the comparison and selection of multioutput feedforward neural network topology, based on the predictive capability, is proposed. As a measure of the prediction fitness potential, an expected utility criterion is considered which is consistently estimated by a sample-reuse computation. As opposed to classic point-prediction-based cross-validation methods, this expected utility is defined from the logarithmic score of the neural model predictive probability density. It is shown how the advocated choice of a conjugate probability distribution as prior for the parameters of a competing network, allows a consistent approximation of the network posterior predictive density. A comparison of the performances of the proposed method with the performances of usual selection procedures based on classic cross-validation and information-theoretic criteria, is performed first on a simulated case study, and then on a well known food analysis dataset.
Time series prediction by feedforward neural networks - is it difficult?
Rosen-Zvi, M; Kinzel, W
2003-01-01
The difficulties that a neural network faces when trying to learn from a quasi-periodic time series are studied analytically using a teacher-student scenario where the random input is divided into two macroscopic regions with different variances, 1 and 1/gamma sup 2 (gamma >> 1). The generalization error is found to decrease as epsilon sub g propor to exp(-alpha/gamma sup 2), where alpha is the number of examples per input dimension. In contradiction to this very slow vanishing generalization error, the next output prediction is found to be almost free of mistakes. This picture is consistent with learning quasi-periodic time series produced by feedforward neural networks, which is dominated by enhanced components of the Fourier spectrum of the input. Simulation results are in good agreement with the analytical results.
Time series prediction by feedforward neural networks - is it difficult?
Rosen-Zvi, Michal; Kanter, Ido; Kinzel, Wolfgang
2003-04-01
The difficulties that a neural network faces when trying to learn from a quasi-periodic time series are studied analytically using a teacher-student scenario where the random input is divided into two macroscopic regions with different variances, 1 and 1/gamma2 (gamma gg 1). The generalization error is found to decrease as epsilong propto exp(-alpha/gamma2), where alpha is the number of examples per input dimension. In contradiction to this very slow vanishing generalization error, the next output prediction is found to be almost free of mistakes. This picture is consistent with learning quasi-periodic time series produced by feedforward neural networks, which is dominated by enhanced components of the Fourier spectrum of the input. Simulation results are in good agreement with the analytical results.
Training Feedforward Neural Networks Using Symbiotic Organisms Search Algorithm.
Wu, Haizhou; Zhou, Yongquan; Luo, Qifang; Basset, Mohamed Abdel
2016-01-01
Symbiotic organisms search (SOS) is a new robust and powerful metaheuristic algorithm, which stimulates the symbiotic interaction strategies adopted by organisms to survive and propagate in the ecosystem. In the supervised learning area, it is a challenging task to present a satisfactory and efficient training algorithm for feedforward neural networks (FNNs). In this paper, SOS is employed as a new method for training FNNs. To investigate the performance of the aforementioned method, eight different datasets selected from the UCI machine learning repository are employed for experiment and the results are compared among seven metaheuristic algorithms. The results show that SOS performs better than other algorithms for training FNNs in terms of converging speed. It is also proven that an FNN trained by the method of SOS has better accuracy than most algorithms compared.
On the approximation by single hidden layer feedforward neural networks with fixed weights
Guliyev, Namig J.; Ismailov, Vugar E.
2017-01-01
International audience; Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the p...
Feed-Forward Neural Networks and Minimal Search Space Learning
Czech Academy of Sciences Publication Activity Database
Neruda, Roman
2005-01-01
Roč. 4, č. 12 (2005), s. 1867-1872 ISSN 1109-2750 R&D Projects: GA ČR GA201/05/0557 Institutional research plan: CEZ:AV0Z10300504 Keywords : search space * feed-forward networks * genetic algorithm s Subject RIV: BA - General Mathematics
Precision requirements for single-layer feed-forward neural networks
Annema, Anne J.; Hoen, K.; Hoen, Klaas; Wallinga, Hans
1994-01-01
This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an
Modeling of an industrial process of pleuromutilin fermentation using feed-forward neural networks
Khaouane,L.; Benkortbi,O.; Hanini,S.; Si-Moussa,C.
2013-01-01
This work investigates the use of artificial neural networks in modeling an industrial fermentation process of Pleuromutilin produced by Pleurotus mutilus in a fed-batch mode. Three feed-forward neural network models characterized by a similar structure (five neurons in the input layer, one hidden layer and one neuron in the output layer) are constructed and optimized with the aim to predict the evolution of three main bioprocess variables: biomass, substrate and product. Results show a good ...
Ding, Weifu; Zhang, Jiangshe; Leung, Yee
2016-10-01
In this paper, we predict air pollutant concentration using a feedforward artificial neural network inspired by the mechanism of the human brain as a useful alternative to traditional statistical modeling techniques. The neural network is trained based on sparse response back-propagation in which only a small number of neurons respond to the specified stimulus simultaneously and provide a high convergence rate for the trained network, in addition to low energy consumption and greater generalization. Our method is evaluated on Hong Kong air monitoring station data and corresponding meteorological variables for which five air quality parameters were gathered at four monitoring stations in Hong Kong over 4 years (2012-2015). Our results show that our training method has more advantages in terms of the precision of the prediction, effectiveness, and generalization of traditional linear regression algorithms when compared with a feedforward artificial neural network trained using traditional back-propagation.
Modelization of three-layered polymer coated steel-strip ironing process using a neural network
Sellés, M. A.; Schmid, S. R.; Sánchez-Caballero, S.; Seguí, V. J.; Reig, M. J.; Pla, R.
2012-04-01
An alternative to the traditional can manufacturing process is to use plastic laminated rolled steels as base stocks. This material consist of pre-heated steel coils that are sandwiched between one or two sheets of polymer. The heated sheets are then immediately quenched, which yields a strong bond between the layers. Such polymer-coated steels were investigated by Jaworski [1,2] and Sellés [3], and found to be suitable for ironing with carefully controlled conditions. A novel multi-layer polymer coated steel has been developed for container applications. This material presents an interesting extension to previous research on polymer laminated steel in ironing, and offers several advantages over the previous material (Sellés [3]). This document shows a modelization for the ironing process (the most crucial step in can manufacturing) done by using a neural network
Breast cancer detection via Hu moment invariant and feedforward neural network
Zhang, Xiaowei; Yang, Jiquan; Nguyen, Elijah
2018-04-01
One of eight women can get breast cancer during all her life. This study used Hu moment invariant and feedforward neural network to diagnose breast cancer. With the help of K-fold cross validation, we can test the out-of-sample accuracy of our method. Finally, we found that our methods can improve the accuracy of detecting breast cancer and reduce the difficulty of judging.
Encoding Time in Feedforward Trajectories of a Recurrent Neural Network Model.
Hardy, N F; Buonomano, Dean V
2018-02-01
Brain activity evolves through time, creating trajectories of activity that underlie sensorimotor processing, behavior, and learning and memory. Therefore, understanding the temporal nature of neural dynamics is essential to understanding brain function and behavior. In vivo studies have demonstrated that sequential transient activation of neurons can encode time. However, it remains unclear whether these patterns emerge from feedforward network architectures or from recurrent networks and, furthermore, what role network structure plays in timing. We address these issues using a recurrent neural network (RNN) model with distinct populations of excitatory and inhibitory units. Consistent with experimental data, a single RNN could autonomously produce multiple functionally feedforward trajectories, thus potentially encoding multiple timed motor patterns lasting up to several seconds. Importantly, the model accounted for Weber's law, a hallmark of timing behavior. Analysis of network connectivity revealed that efficiency-a measure of network interconnectedness-decreased as the number of stored trajectories increased. Additionally, the balance of excitation (E) and inhibition (I) shifted toward excitation during each unit's activation time, generating the prediction that observed sequential activity relies on dynamic control of the E/I balance. Our results establish for the first time that the same RNN can generate multiple functionally feedforward patterns of activity as a result of dynamic shifts in the E/I balance imposed by the connectome of the RNN. We conclude that recurrent network architectures account for sequential neural activity, as well as for a fundamental signature of timing behavior: Weber's law.
Directory of Open Access Journals (Sweden)
A. Cancelier
Full Text Available Abstract This study used a predictive controller based on an empirical nonlinear model comprising a three-layer feedforward neural network for temperature control of the suspension polymerization process. In addition to the offline training technique, an algorithm was also analyzed for online adaptation of its parameters. For the offline training, the network was statically trained and the genetic algorithm technique was used in combination with the least squares method. For online training, the network was trained on a recurring basis and only the technique of genetic algorithms was used. In this case, only the weights and bias of the output layer neuron were modified, starting from the parameters obtained from the offline training. From the experimental results obtained in a pilot plant, a good performance was observed for the proposed control system, with superior performance for the control algorithm with online adaptation of the model, particularly with respect to the presence of off-set for the case of the fixed parameters model.
Modeling of an industrial process of pleuromutilin fermentation using feed-forward neural networks
Directory of Open Access Journals (Sweden)
L. Khaouane
2013-03-01
Full Text Available This work investigates the use of artificial neural networks in modeling an industrial fermentation process of Pleuromutilin produced by Pleurotus mutilus in a fed-batch mode. Three feed-forward neural network models characterized by a similar structure (five neurons in the input layer, one hidden layer and one neuron in the output layer are constructed and optimized with the aim to predict the evolution of three main bioprocess variables: biomass, substrate and product. Results show a good fit between the predicted and experimental values for each model (the root mean squared errors were 0.4624% - 0.1234 g/L and 0.0016 mg/g respectively. Furthermore, the comparison between the optimized models and the unstructured kinetic models in terms of simulation results shows that neural network models gave more significant results. These results encourage further studies to integrate the mathematical formulae extracted from these models into an industrial control loop of the process.
International Nuclear Information System (INIS)
Ekkachai, Kittipong; Nilkhamhang, Itthisek; Tungpimolrut, Kanokvate
2013-01-01
An inverse controller is proposed for a magnetorheological (MR) damper that consists of a hysteresis model and a voltage controller. The force characteristics of the MR damper caused by excitation signals are represented by a feedforward neural network (FNN) with an elementary hysteresis model (EHM). The voltage controller is constructed using another FNN to calculate a suitable input signal that will allow the MR damper to produce the desired damping force. The performance of the proposed EHM-based FNN controller is experimentally compared to existing control methodologies, such as clipped-optimal control, signum function control, conventional FNN, and recurrent neural network with displacement or velocity inputs. The results show that the proposed controller, which does not require force feedback to implement, provides excellent accuracy, fast response time, and lower energy consumption. (paper)
Improving weather radar estimates of rainfall using feed-forward neural networks.
Teschl, Reinhard; Randeu, Walter L; Teschl, Franz
2007-05-01
In this paper an approach is described to improve weather radar estimates of rainfall based on a neural network technique. Other than rain gauges which measure the rain rate R directly on the ground, the weather radar measures the reflectivity Z aloft and the rain rate has to be determined over a Z-R relationship. Besides the fact that the rain rate has to be estimated from the reflectivity many other sources of possible errors are inherent to the radar system. In other words the radar measurements contain an amount of observation noise which makes it a demanding task to train the network properly. A feed-forward neural network with Z values as input vector was trained to predict the rain rate R on the ground. The results indicate that the model is able to generalize and the determined input-output relationship is also representative for other sites nearby with similar conditions.
Interpretation of correlated neural variability from models of feed-forward and recurrent circuits
2018-01-01
Neural populations respond to the repeated presentations of a sensory stimulus with correlated variability. These correlations have been studied in detail, with respect to their mechanistic origin, as well as their influence on stimulus discrimination and on the performance of population codes. A number of theoretical studies have endeavored to link network architecture to the nature of the correlations in neural activity. Here, we contribute to this effort: in models of circuits of stochastic neurons, we elucidate the implications of various network architectures—recurrent connections, shared feed-forward projections, and shared gain fluctuations—on the stimulus dependence in correlations. Specifically, we derive mathematical relations that specify the dependence of population-averaged covariances on firing rates, for different network architectures. In turn, these relations can be used to analyze data on population activity. We examine recordings from neural populations in mouse auditory cortex. We find that a recurrent network model with random effective connections captures the observed statistics. Furthermore, using our circuit model, we investigate the relation between network parameters, correlations, and how well different stimuli can be discriminated from one another based on the population activity. As such, our approach allows us to relate properties of the neural circuit to information processing. PMID:29408930
Dong, Zhekang; Duan, Shukai; Hu, Xiaofang; Wang, Lidan; Li, Hai
2014-01-01
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.
Dong, Zhekang; Duan, Shukai; Hu, Xiaofang; Wang, Lidan
2014-01-01
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme. PMID:25202723
Sengupta, Ranit; Nasir, Sazzad M
2015-04-01
Despite recent progress in our understanding of sensorimotor integration in speech learning, a comprehensive framework to investigate its neural basis is lacking at behaviorally relevant timescales. Structural and functional imaging studies in humans have helped us identify brain networks that support speech but fail to capture the precise spatiotemporal coordination within the networks that takes place during speech learning. Here we use neuronal oscillations to investigate interactions within speech motor networks in a paradigm of speech motor adaptation under altered feedback with continuous recording of EEG in which subjects adapted to the real-time auditory perturbation of a target vowel sound. As subjects adapted to the task, concurrent changes were observed in the theta-gamma phase coherence during speech planning at several distinct scalp regions that is consistent with the establishment of a feedforward map. In particular, there was an increase in coherence over the central region and a decrease over the fronto-temporal regions, revealing a redistribution of coherence over an interacting network of brain regions that could be a general feature of error-based motor learning in general. Our findings have implications for understanding the neural basis of speech motor learning and could elucidate how transient breakdown of neuronal communication within speech networks relates to speech disorders. Copyright © 2015 the American Physiological Society.
Magar, Kaman Thapa; Reich, Gregory W; Kondash, Corey; Slinker, Keith; Pankonien, Alexander M; Baur, Jeffery W; Smyers, Brian
2016-11-10
Distributed arrays of artificial hair sensors have bio-like sensing capabilities to obtain spatial and temporal surface flow information which is an important aspect of an effective fly-by-feel system. The spatiotemporal surface flow measurement enables further exploration of additional flow features such as flow stagnation, separation, and reattachment points. Due to their inherent robustness and fault tolerant capability, distributed arrays of hair sensors are well equipped to assess the aerodynamic and flow states in adverse conditions. In this paper, a local flow measurement from an array of artificial hair sensors in a wind tunnel experiment is used with a feedforward artificial neural network to predict aerodynamic parameters such as lift coefficient, moment coefficient, free-stream velocity, and angle of attack on an airfoil. We find the prediction error within 6% and 10% for lift and moment coefficients. The error for free-stream velocity and angle of attack were within 0.12 mph and 0.37 degrees. Knowledge of these parameters are key to finding the real time forces and moments which paves the way for effective control design to increase flight agility, stability, and maneuverability.
Modeling total solar irradiance from PMOD composite using feed-forward neural networks
Tebabal, A.; Damtie, B.; Nigussie, M.; Bires, A.; Yizengaw, E.
2015-12-01
The variability of the solar activity dominates the variability of the earth's atmosphere, which affects human life and technology on earth. To understand the effects of solar activity on earth's atmosphere different efforts are underway to model the variations of total solar irradiance (TSI) associated to the variations of photometric sunspot index (PSI) and core to wing ratio of Mg II index, for example, linear regression approach. In this study, feed-forward neural networks (NNs) algorithm, which takes the non-linear relationship between the dependent and independent variables, has been implemented to model daily TSI using PSI and Mg II index. First, data between 1978 and 2008 have been used to train and validate NNs, through which the parameters such as weights and biases are estimated. Therefore, NNs has been used to predict TSI between the years 2008 and 2013 from test data. The output of NNs have been compared with PMOD composite TSI and result has shown good agreement. Linear correlation between NNs predicted TSI and PMOD composite is found to be about 0.9307 for the years between 1978 and 2013. This means that NNs predicted TSI from solar proxies explains about 86.6% of the variance of TSI for solar cycles 21-24, and over 90% during solar cycle 23. Predicting TSI using NNs further strengthens the view that surface magnetism indeed plays a dominant role in modulating solar irradiance.
Directory of Open Access Journals (Sweden)
A. Y. Shamseldin
2002-01-01
Full Text Available The Multi-Layer Feed-Forward Neural Network (MLFFNN is applied in the context of river flow forecast combination, where a number of rainfall-runoff models are used simultaneously to produce an overall combined river flow forecast. The operation of the MLFFNN depends not only on its neuron configuration but also on the choice of neuron transfer function adopted, which is non-linear for the hidden and output layers. These models, each having a different structure to simulate the perceived mechanisms of the runoff process, utilise the information carrying capacity of the model calibration data in different ways. Hence, in a discharge forecast combination procedure, the discharge forecasts of each model provide a source of information different from that of the other models used in the combination. In the present work, the significance of the choice of the transfer function type in the overall performance of the MLFFNN, when used in the river flow forecast combination context, is investigated critically. Five neuron transfer functions are used in this investigation, namely, the logistic function, the bipolar function, the hyperbolic tangent function, the arctan function and the scaled arctan function. The results indicate that the logistic function yields the best model forecast combination performance. Keywords: River flow forecast combination, multi-layer feed-forward neural network, neuron transfer functions, rainfall-runoff models
Pahlavani, P.; Gholami, A.; Azimi, S.
2017-09-01
This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF) artificial neural networks (ANN). Most of the indoor received signal strength (RSS)-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration) phase and the online (estimation) phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening). Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg-Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.
Directory of Open Access Journals (Sweden)
Fereydoon Sarmadian
2014-01-01
Full Text Available The two common methods used to develop PTFs are multiple-linear regression method and Artificial Neural Network. One of the advantages of neural networks compared to traditional regression PTFs is that they do not require a priori regression model, which relates input and output data and in general is difficult because these models are not known. So at present research, we compare performance of feed-forward back-propagation network to predict soil properties. Soil samples were collected from different horizons profiles located in the Gorgan Province, North of Iran. Measured soil variables included texture, organic carbon, water saturation percentage Bulk density, Infiltration rate and deep percolation. Then, multiple linear regression and neural network model were employed to develop a pedotransfer function for predicting soil parameters using easily measurable characteristics of clay, silt, SP, Bd and organic carbon. The performance of the multiple linear regression and neural network model was evaluated using a test data set by R2, RMSE and RSE. Results showed that artificial neural network with two and five neurons in hidden layer had better performance in predicting soil hydraulic properties than multivariate regression. In conclusion, the result of this study showed that both ANN and regression predicted soil properties with relatively high accuracy that showed that strong relationship between input and output data and also high accuracy in determining of data.
Liu, Jinjin; Chen, Yongchun; Lan, Li; Lin, Boli; Chen, Weijian; Wang, Meihao; Li, Rui; Yang, Yunjun; Zhao, Bing; Hu, Zilong; Duan, Yuxia
2018-02-23
Anterior communicating artery (ACOM) aneurysms are the most common intracranial aneurysms, and predicting their rupture risk is challenging. We aimed to predict this risk using a two-layer feed-forward artificial neural network (ANN). 594 ACOM aneurysms, 54 unruptured and 540 ruptured, were reviewed. A two-layer feed-forward ANN was designed for ACOM aneurysm rupture-risk analysis. To improve ANN efficiency, an adaptive synthetic (ADASYN) sampling approach was applied to generate more synthetic data for unruptured aneurysms. Seventeen parameters (13 morphological parameters of ACOM aneurysm measured from these patients' CT angiography (CTA) images, two demographic factors, and hypertension and smoking histories) were adopted as ANN input. Age, vessel size, aneurysm height, perpendicular height, aneurysm neck size, aspect ratio, size ratio, aneurysm angle, vessel angle, aneurysm projection, A1 segment configuration, aneurysm lobulations and hypertension were significantly different between the ruptured and unruptured groups. Areas under the ROC curve for training, validating, testing and overall data sets were 0.953, 0.937, 0.928 and 0.950, respectively. Overall prediction accuracy for raw 594 samples was 94.8 %. This ANN presents good performance and offers a valuable tool for prediction of rupture risk in ACOM aneurysms, which may facilitate management of unruptured ACOM aneurysms. • A feed-forward ANN was designed for the prediction of rupture risk in ACOM aneurysms. • Two demographic parameters, 13 morphological aneurysm parameters, and hypertension/smoking history were acquired. • An ADASYN sampling approach was used to improve ANN quality. • Overall prediction accuracy of 94.8 % for the raw samples was achieved.
Directory of Open Access Journals (Sweden)
Paola Saccomandi
2015-01-01
Full Text Available This work shows the development and characterization of a fiber optic tactile sensor based on Fiber Bragg Grating (FBG technology. The sensor is a 3 × 3 array of FBGs encapsulated in a PDMS compliant polymer. The strain experienced by each FBG is transduced into a Bragg wavelength shift and the inverse characteristics of the sensor were computed by means of a feedforward neural network. A 21 mN RMSE error was achieved in estimating the force over the 8 N experimented load range while including all probing sites in the neural network training procedure, whereas the median force RMSE was 199 mN across the 200 instances of a Monte Carlo randomized selection of experimental sessions to evaluate the calibration under generalized probing conditions. The static metrological properties and the possibility to fabricate sensors with relatively high spatial resolution make the proposed design attractive for the sensorization of robotic hands. Furthermore, the proved MRI-compatibility of the sensor opens other application scenarios, such as the possibility to employ the array for force measurement during functional MRI-measured brain activation.
Toward the training of feed-forward neural networks with the D-optimum input sequence.
Witczak, Marcin
2006-03-01
The problem under consideration is to obtain a measurement schedule for training neural networks. This task is perceived as an experimental design in a given design space that is obtained in such a way as to minimize the difference between the neural network and the system being considered. This difference can be expressed in many different ways and one of them, namely, the D-optimality criterion is used in this paper. In particular, the paper presents a unified and comprehensive treatment of this problem by discussing the existing and previously unpublished properties of the optimum experimental design (OED) for neural networks. The consequences of the above properties are discussed as well. A hybrid algorithm that can be used for both the training and data development of neural networks is another important contribution of this paper. A careful analysis of the algorithm is presented and its comprehensive convergence analysis with the help of the Lyapunov method are given. The paper contains a number of numerical examples that justify the application of the OED theory for neural networks. Moreover, an industrial application example is given that deals with the valve actuator.
Spike-timing computation properties of a feed-forward neural network model
Directory of Open Access Journals (Sweden)
Drew Benjamin Sinha
2014-01-01
Full Text Available Brain function is characterized by dynamical interactions among networks of neurons. These interactions are mediated by network topology at many scales ranging from microcircuits to brain areas. Understanding how networks operate can be aided by understanding how the transformation of inputs depends upon network connectivity patterns, e.g. serial and parallel pathways. To tractably determine how single synapses or groups of synapses in such pathways shape transformations, we modeled feed-forward networks of 7-22 neurons in which synaptic strength changed according to a spike-timing dependent plasticity rule. We investigated how activity varied when dynamics were perturbed by an activity-dependent electrical stimulation protocol (spike-triggered stimulation; STS in networks of different topologies and background input correlations. STS can successfully reorganize functional brain networks in vivo, but with a variability in effectiveness that may derive partially from the underlying network topology. In a simulated network with a single disynaptic pathway driven by uncorrelated background activity, structured spike-timing relationships between polysynaptically connected neurons were not observed. When background activity was correlated or parallel disynaptic pathways were added, however, robust polysynaptic spike timing relationships were observed, and application of STS yielded predictable changes in synaptic strengths and spike-timing relationships. These observations suggest that precise input-related or topologically induced temporal relationships in network activity are necessary for polysynaptic signal propagation. Such constraints for polysynaptic computation suggest potential roles for higher-order topological structure in network organization, such as maintaining polysynaptic correlation in the face of relatively weak synapses.
Directory of Open Access Journals (Sweden)
Roger A. Kemp
1997-01-01
Full Text Available Normal cells in the presence of a precancerous lesion undergo subtle changes of their DNA distribution when observed by visible microscopy. These changes have been termed Malignancy Associated Changes (MACs. Using statistical models such as neural networks and discriminant functions it is possible to design classifiers that can separate these objects from truly normal cells. The correct classification rate using feed‐forward neural networks is compared to linear discriminant analysis when applied to detecting MACs. Classifiers were designed using 53 nuclear features calculated from images for each of 25,360 normal appearing cells taken from 344 slides diagnosed as normal or containing severe dysplasia. A linear discriminant function achieved a correct classification rate of 61.6% on the test data while neural networks scored as high as 72.5% on a cell‐by‐cell basis. The cell classifiers were applied to a library of 93,494 cells from 395 slides, and the results were jackknifed using a single slide feature. The discriminant function achieved a correct classification rate of 67.6% while the neural networks managed as high as 76.2%.
Real-Time Monitoring and Fault Diagnosis of a Low Power Hub Motor Using Feedforward Neural Network
Şimşir, Mehmet; Bayır, Raif; Uyaroğlu, Yılmaz
2016-01-01
Low power hub motors are widely used in electromechanical systems such as electrical bicycles and solar vehicles due to their robustness and compact structure. Such systems driven by hub motors (in wheel motors) encounter previously defined and undefined faults under operation. It may inevitably lead to the interruption of the electromechanical system operation; hence, economic losses take place at certain times. Therefore, in order to maintain system operation sustainability, the motor should be precisely monitored and the faults are diagnosed considering various significant motor parameters. In this study, the artificial feedforward backpropagation neural network approach is proposed to real-time monitor and diagnose the faults of the hub motor by measuring seven main system parameters. So as to construct a necessary model, we trained the model, using a data set consisting of 4160 samples where each has 7 parameters, by the MATLAB environment until the best model is obtained. The results are encouraging and meaningful for the specific motor and the developed model may be applicable to other types of hub motors. The prosperous model of the whole system was embedded into Arduino Due microcontroller card and the mobile real-time monitoring and fault diagnosis system prototype for hub motor was designed and manufactured. PMID:26819590
Directory of Open Access Journals (Sweden)
Trong-Ngoc Le
2016-01-01
Full Text Available Objective. Our objective is to develop a computerized scheme for liver tumor segmentation in MR images. Materials and Methods. Our proposed scheme consists of four main stages. Firstly, the region of interest (ROI image which contains the liver tumor region in the T1-weighted MR image series was extracted by using seed points. The noise in this ROI image was reduced and the boundaries were enhanced. A 3D fast marching algorithm was applied to generate the initial labeled regions which are considered as teacher regions. A single hidden layer feedforward neural network (SLFN, which was trained by a noniterative algorithm, was employed to classify the unlabeled voxels. Finally, the postprocessing stage was applied to extract and refine the liver tumor boundaries. The liver tumors determined by our scheme were compared with those manually traced by a radiologist, used as the “ground truth.” Results. The study was evaluated on two datasets of 25 tumors from 16 patients. The proposed scheme obtained the mean volumetric overlap error of 27.43% and the mean percentage volume error of 15.73%. The mean of the average surface distance, the root mean square surface distance, and the maximal surface distance were 0.58 mm, 1.20 mm, and 6.29 mm, respectively.
Real-Time Monitoring and Fault Diagnosis of a Low Power Hub Motor Using Feedforward Neural Network.
Şimşir, Mehmet; Bayır, Raif; Uyaroğlu, Yılmaz
2016-01-01
Low power hub motors are widely used in electromechanical systems such as electrical bicycles and solar vehicles due to their robustness and compact structure. Such systems driven by hub motors (in wheel motors) encounter previously defined and undefined faults under operation. It may inevitably lead to the interruption of the electromechanical system operation; hence, economic losses take place at certain times. Therefore, in order to maintain system operation sustainability, the motor should be precisely monitored and the faults are diagnosed considering various significant motor parameters. In this study, the artificial feedforward backpropagation neural network approach is proposed to real-time monitor and diagnose the faults of the hub motor by measuring seven main system parameters. So as to construct a necessary model, we trained the model, using a data set consisting of 4160 samples where each has 7 parameters, by the MATLAB environment until the best model is obtained. The results are encouraging and meaningful for the specific motor and the developed model may be applicable to other types of hub motors. The prosperous model of the whole system was embedded into Arduino Due microcontroller card and the mobile real-time monitoring and fault diagnosis system prototype for hub motor was designed and manufactured.
Real-Time Monitoring and Fault Diagnosis of a Low Power Hub Motor Using Feedforward Neural Network
Directory of Open Access Journals (Sweden)
Mehmet Şimşir
2016-01-01
Full Text Available Low power hub motors are widely used in electromechanical systems such as electrical bicycles and solar vehicles due to their robustness and compact structure. Such systems driven by hub motors (in wheel motors encounter previously defined and undefined faults under operation. It may inevitably lead to the interruption of the electromechanical system operation; hence, economic losses take place at certain times. Therefore, in order to maintain system operation sustainability, the motor should be precisely monitored and the faults are diagnosed considering various significant motor parameters. In this study, the artificial feedforward backpropagation neural network approach is proposed to real-time monitor and diagnose the faults of the hub motor by measuring seven main system parameters. So as to construct a necessary model, we trained the model, using a data set consisting of 4160 samples where each has 7 parameters, by the MATLAB environment until the best model is obtained. The results are encouraging and meaningful for the specific motor and the developed model may be applicable to other types of hub motors. The prosperous model of the whole system was embedded into Arduino Due microcontroller card and the mobile real-time monitoring and fault diagnosis system prototype for hub motor was designed and manufactured.
Nguyen, Hieu T T; Le, Hung M
2012-05-10
The classical interchange (permutation) of atoms of similar identity does not have an effect on the overall potential energy. In this study, we present feed-forward neural network structures that provide permutation symmetry to the potential energy surfaces of molecules. The new feed-forward neural network structures are employed to fit the potential energy surfaces for two illustrative molecules, which are H(2)O and ClOOCl. Modifications are made to describe the symmetric interchange (permutation) of atoms of similar identity (or mathematically, the permutation of symmetric input parameters). The combined-function-derivative approximation algorithm (J. Chem. Phys. 2009, 130, 134101) is also implemented to fit the neural-network potential energy surfaces accurately. The combination of our symmetric neural networks and the function-derivative fitting effectively produces PES fits using fewer numbers of training data points. For H(2)O, only 282 configurations are employed as the training set; the testing root-mean-squared and mean-absolute energy errors are respectively reported as 0.0103 eV (0.236 kcal/mol) and 0.0078 eV (0.179 kcal/mol). In the ClOOCl case, 1693 configurations are required to construct the training set; the root-mean-squared and mean-absolute energy errors for the ClOOCl testing set are 0.0409 eV (0.943 kcal/mol) and 0.0269 eV (0.620 kcal/mol), respectively. Overall, we find good agreements between ab initio and NN prediction in term of energy and gradient errors, and conclude that the new feed-forward neural-network models advantageously describe the molecules with excellent accuracy.
Directory of Open Access Journals (Sweden)
Giles M. Foody
2017-08-01
Full Text Available Validation data are often used to evaluate the performance of a trained neural network and used in the selection of a network deemed optimal for the task at-hand. Optimality is commonly assessed with a measure, such as overall classification accuracy. The latter is often calculated directly from a confusion matrix showing the counts of cases in the validation set with particular labelling properties. The sample design used to form the validation set can, however, influence the estimated magnitude of the accuracy. Commonly, the validation set is formed with a stratified sample to give balanced classes, but also via random sampling, which reflects class abundance. It is suggested that if the ultimate aim is to accurately classify a dataset in which the classes do vary in abundance, a validation set formed via random, rather than stratified, sampling is preferred. This is illustrated with the classification of simulated and remotely-sensed datasets. With both datasets, statistically significant differences in the accuracy with which the data could be classified arose from the use of validation sets formed via random and stratified sampling (z = 2.7 and 1.9 for the simulated and real datasets respectively, for both p < 0.05%. The accuracy of the classifications that used a stratified sample in validation were smaller, a result of cases of an abundant class being commissioned into a rarer class. Simple means to address the issue are suggested.
Energy Technology Data Exchange (ETDEWEB)
Gentili, Pier Luigi, E-mail: pierluigi.gentili@unipg.it [Department of Chemistry, Biology and Biotechnology, University of Perugia, 06123 Perugia (Italy); Gotoda, Hiroshi [Department of Mechanical Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi, Shiga 525-8577 (Japan); Dolnik, Milos; Epstein, Irving R. [Department of Chemistry, Brandeis University, Waltham, Massachusetts 02454-9110 (United States)
2015-01-15
Forecasting of aperiodic time series is a compelling challenge for science. In this work, we analyze aperiodic spectrophotometric data, proportional to the concentrations of two forms of a thermoreversible photochromic spiro-oxazine, that are generated when a cuvette containing a solution of the spiro-oxazine undergoes photoreaction and convection due to localized ultraviolet illumination. We construct the phase space for the system using Takens' theorem and we calculate the Lyapunov exponents and the correlation dimensions to ascertain the chaotic character of the time series. Finally, we predict the time series using three distinct methods: a feed-forward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.
Gentili, Pier Luigi; Gotoda, Hiroshi; Dolnik, Milos; Epstein, Irving R
2015-01-01
Forecasting of aperiodic time series is a compelling challenge for science. In this work, we analyze aperiodic spectrophotometric data, proportional to the concentrations of two forms of a thermoreversible photochromic spiro-oxazine, that are generated when a cuvette containing a solution of the spiro-oxazine undergoes photoreaction and convection due to localized ultraviolet illumination. We construct the phase space for the system using Takens' theorem and we calculate the Lyapunov exponents and the correlation dimensions to ascertain the chaotic character of the time series. Finally, we predict the time series using three distinct methods: a feed-forward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.
Directory of Open Access Journals (Sweden)
Jie-Sheng Wang
2015-01-01
Full Text Available For predicting the key technology indicators (concentrate grade and tailings recovery rate of flotation process, a feed-forward neural network (FNN based soft-sensor model optimized by the hybrid algorithm combining particle swarm optimization (PSO algorithm and gravitational search algorithm (GSA is proposed. Although GSA has better optimization capability, it has slow convergence velocity and is easy to fall into local optimum. So in this paper, the velocity vector and position vector of GSA are adjusted by PSO algorithm in order to improve its convergence speed and prediction accuracy. Finally, the proposed hybrid algorithm is adopted to optimize the parameters of FNN soft-sensor model. Simulation results show that the model has better generalization and prediction accuracy for the concentrate grade and tailings recovery rate to meet the online soft-sensor requirements of the real-time control in the flotation process.
Takita, Masatoshi; Kuramochi, Masahito; Izaki, Yoshinori; Ohtomi, Michiko
2007-05-30
Anatomical evidence suggests that rat CA1 hippocampal afferents collaterally innervate excitatory projecting pyramidal neurons and inhibitory interneurons, creating a disynaptic, feed-forward inhibition microcircuit in the medial prefrontal cortex (mPFC). We investigated the temporal relationship between the frequency of paired synaptic transmission and gamma-aminobutyric acid (GABA)ergic receptor-mediated modulation of the microcircuit in vivo under urethane anesthesia. Local perfusions of a GABAa antagonist (-)-bicuculline into the mPFC via microdialysis resulted in a statistically significant disinhibitory effect on intrinsic GABA action, increasing the first and second mPFC responses following hippocampal paired stimulation at interstimulus intervals of 100-200 ms, but not those at 25-50 ms. This (-)-bicuculline-induced disinhibition was compensated by the GABAa agonist muscimol, which itself did not attenuate the intrinsic oscillation of the local field potentials. The perfusion of a sub-minimal concentration of GABAb agonist (R)-baclofen slightly enhanced the synaptic transmission, regardless of the interstimulus interval. In addition to the tonic control by spontaneous fast-spiking GABAergic neurons, it is clear the sequential transmission of the hippocampal-mPFC pathway can phasically drive the collateral feed-forward inhibition system through activation of a GABAa receptor, bringing an active signal filter to the various types of impulse trains that enter the mPFC from the hippocampus in vivo.
Mörchen, Fabian
2004-03-01
The performance of feed-forward neural networks trained with the backpropagation algorithm on a dedicated Beowulf cluster is analyzed. The concept of training set parallelism is applied. A new model for run time and speedup prediction is developed. With the model the speedup and efficiency of one iteration of the neural networks can be estimated as a function of block size and cluster size. The model is applied to three example problems representing different applications and network architectures. The estimation of the model has a higher accuracy than traditional methods for run time estimation and can be efficiently calculated. Experiments show that speedup of one iteration does not necessarily translate to a shorter training time toward a given error level. To overcome this problem a heuristic extension to training set parallelism called weight averaging is developed. The results show that training in parallel should only be done on clusters with high performance network connections or a multiprocessor machine. A rule of thumb is given for how much network performance of the cluster is needed to achieve speedup of the training time for a neural network.
Lim, Chee Wei; Chan, Sheot Harn; Visconti, Angelo
2011-11-15
A major problem for manufacturers of cracked spores Ganoderma lucidum, a traditional functional food/Chinese medicine (TCM), is to ensure that raw materials are consistent as received from the producer. To address this, a feed-forward artificial neural network (ANN) method assisted by linear discriminant analysis (LDA) and principal component analysis (PCA) was developed for the spectroscopic discrimination of cracked spores of Ganoderma lucidum from uncracked spores. 120 samples comprising cracked spores, uncracked spores and concentrate of Ganoderma lucidum were analyzed. Differences in the absorption spectra located at ν1 (1143 - 1037 cm-1), ν2 (1660 - 1560 cm-1), ν3 (1745 - 1716 cm-1) and ν4 (2845 - 2798 cm-1) were identified by applying fourier transform infra-red (FTIR) spectroscopy and used as variables for discriminant analysis. The utilization of spectra frequencies offered maximum chemical information provided by the absorption spectra. Uncracked spores gave rise to characteristic spectrum that permitted discrimination from its cracked physical state. Parallel application of variables derived from unsupervised LDA/PCA provided useful (feed-forward) information to achieve 100% classification integrity objective in ANN. 100% model validation was obtained by utilizing 30 independent samples. ν1 was used to construct the matrix-matched calibration curve (n = 10) based on 4 levels of concentration (20%, 40%, 60% and 80% uncracked spores in cracked spores). A coefficient of correlation (r) of 0.97 was obtained. Relative standard deviation (RSD) of 11% was achieved using 100% uncracked spores (n = 30). These results demonstrate the feasibility of utilizing a combination of spectroscopy and prospective statistical tools to perform non destructive food quality assessment in a high throughput environment.
Directory of Open Access Journals (Sweden)
Shuihua Wang
2015-08-01
Full Text Available Fruit classification is quite difficult because of the various categories and similar shapes and features of fruit. In this work, we proposed two novel machine-learning based classification methods. The developed system consists of wavelet entropy (WE, principal component analysis (PCA, feedforward neural network (FNN trained by fitness-scaled chaotic artificial bee colony (FSCABC and biogeography-based optimization (BBO, respectively. The K-fold stratified cross validation (SCV was utilized for statistical analysis. The classification performance for 1653 fruit images from 18 categories showed that the proposed “WE + PCA + FSCABC-FNN” and “WE + PCA + BBO-FNN” methods achieve the same accuracy of 89.5%, higher than state-of-the-art approaches: “(CH + MP + US + PCA + GA-FNN ” of 84.8%, “(CH + MP + US + PCA + PSO-FNN” of 87.9%, “(CH + MP + US + PCA + ABC-FNN” of 85.4%, “(CH + MP + US + PCA + kSVM” of 88.2%, and “(CH + MP + US + PCA + FSCABC-FNN” of 89.1%. Besides, our methods used only 12 features, less than the number of features used by other methods. Therefore, the proposed methods are effective for fruit classification.
Real-Time Analysis of Online Product Reviews by Means of Multi-Layer Feed-Forward Neural Networks
Directory of Open Access Journals (Sweden)
Reinhold Decker
2014-11-01
Full Text Available In the recent past, the quantitative analysis of online product reviews (OPRs has become a popular manifestation of marketing intelligence activities focusing on products that are frequently subject to electronic word-of-mouth (eWOM. Typical elements of OPRs are overall star ratings, product at- tribute scores, recommendations, pros and cons, and free texts. The first three elements are of pa r- ticular interest because they provide an aggregate view of reviewers’ opinions about the products of interest. However, the significance of individual product attributes in the overall evaluation pro c- ess can vary in the course of time. Accordingly, ad hoc analyses of OPRs that have been downloaded at a certain point in time are of limited value for dynamic eWOM monitoring because of their snapshot character. On the other hand, opinion platforms can increase the meaningfulness of the OPRs posted there and, therewith, the usefulness of the platform as a whole, by directing eWOM activities to those product attributes that really matter at present. This paper therefore in- troduces a neural network-based approach that allows the dynamic tracking of the influence the posted scores of product attributes have on the overall star ratings of the concerning products. By using an elasticity measure, this approach supports the identification of those attributes that tend to lose or gain significance in the product evaluation process over time. The usability of this ap- proach is demonstrated using real OPR data on digital cameras and hotels.
Pukrittayakamee, A.; Malshe, M.; Hagan, M.; Raff, L. M.; Narulkar, R.; Bukkapatnum, S.; Komanduri, R.
2009-04-01
An improved neural network (NN) approach is presented for the simultaneous development of accurate potential-energy hypersurfaces and corresponding force fields that can be utilized to conduct ab initio molecular dynamics and Monte Carlo studies on gas-phase chemical reactions. The method is termed as combined function derivative approximation (CFDA). The novelty of the CFDA method lies in the fact that although the NN has only a single output neuron that represents potential energy, the network is trained in such a way that the derivatives of the NN output match the gradient of the potential-energy hypersurface. Accurate force fields can therefore be computed simply by differentiating the network. Both the computed energies and the gradients are then accurately interpolated using the NN. This approach is superior to having the gradients appear in the output layer of the NN because it greatly simplifies the required architecture of the network. The CFDA permits weighting of function fitting relative to gradient fitting. In every test that we have run on six different systems, CFDA training (without a validation set) has produced smaller out-of-sample testing error than early stopping (with a validation set) or Bayesian regularization (without a validation set). This indicates that CFDA training does a better job of preventing overfitting than the standard methods currently in use. The training data can be obtained using an empirical potential surface or any ab initio method. The accuracy and interpolation power of the method have been tested for the reaction dynamics of H+HBr using an analytical potential. The results show that the present NN training technique produces more accurate fits to both the potential-energy surface as well as the corresponding force fields than the previous methods. The fitting and interpolation accuracy is so high (rms error=1.2 cm-1) that trajectories computed on the NN potential exhibit point-by-point agreement with corresponding
Malshe, M.; Raff, L. M.; Hagan, M.; Bukkapatnam, S.; Komanduri, R.
2010-05-01
The variation in the fitting accuracy of neural networks (NNs) when used to fit databases comprising potential energies obtained from ab initio electronic structure calculations is investigated as a function of the number and nature of the elements employed in the input vector to the NN. Ab initio databases for H2O2, HONO, Si5, and H2CCHBr were employed in the investigations. These systems were chosen so as to include four-, five-, and six-body systems containing first, second, third, and fourth row elements with a wide variety of chemical bonding and whose conformations cover a wide range of structures that occur under high-energy machining conditions and in chemical reactions involving cis-trans isomerizations, six different types of two-center bond ruptures, and two different three-center dissociation reactions. The ab initio databases for these systems were obtained using density functional theory/B3LYP, MP2, and MP4 methods with extended basis sets. A total of 31 input vectors were investigated. In each case, the elements of the input vector were chosen from interatomic distances, inverse powers of the interatomic distance, three-body angles, and dihedral angles. Both redundant and nonredundant input vectors were investigated. The results show that among all the input vectors investigated, the set employed in the Z-matrix specification of the molecular configurations in the electronic structure calculations gave the lowest NN fitting accuracy for both Si5 and vinyl bromide. The underlying reason for this result appears to be the discontinuity present in the dihedral angle for planar geometries. The use of trigometric functions of the angles as input elements produced significantly improved fitting accuracy as this choice eliminates the discontinuity. The most accurate fitting was obtained when the elements of the input vector were taken to have the form Rij-n, where the Rij are the interatomic distances. When the Levenberg-Marquardt procedure was modified
Polymer electrolyte membrane fuel cell control with feed-forward ...
African Journals Online (AJOL)
Feed-forward and feedback control is developed in this work for Polymer electrolyte membrane (PEM) fuel cell stacks. The feed-forward control is achieved using different methods, including look-up table, fuzzy logic and neural network, to improve the fuel cell stack breathing control and prevent the problem of oxygen ...
Introduction to Artificial Neural Networks
DEFF Research Database (Denmark)
Larsen, Jan
1999-01-01
The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....
A SIMULATION OF THE PENICILLIN G PRODUCTION BIOPROCESS APPLYING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
A.J.G. da Cruz
1997-12-01
Full Text Available The production of penicillin G by Penicillium chrysogenum IFO 8644 was simulated employing a feedforward neural network with three layers. The neural network training procedure used an algorithm combining two procedures: random search and backpropagation. The results of this approach were very promising, and it was observed that the neural network was able to accurately describe the nonlinear behavior of the process. Besides, the results showed that this technique can be successfully applied to control process algorithms due to its long processing time and its flexibility in the incorporation of new data
Feedforward Approximations to Dynamic Recurrent Network Architectures.
Muir, Dylan R
2018-02-01
Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solving systems of differential equations, and the number of evaluations required to determine their response to a given input can vary with the input or can be indeterminate altogether in the case of oscillations or instability. In feedforward networks, by contrast, only a single pass through the network is needed to determine the response to a given input. Modern machine learning systems are designed to operate efficiently on feedforward architectures. We hypothesized that two-layer feedforward architectures with simple, deterministic dynamics could approximate the responses of single-layer recurrent network architectures. By identifying the fixed-point responses of a given recurrent network, we trained two-layer networks to directly approximate the fixed-point response to a given input. These feedforward networks then embodied useful computations, including competitive interactions, information transformations, and noise rejection. Our approach was able to find useful approximations to recurrent networks, which can then be evaluated in linear and deterministic time complexity.
Czech Academy of Sciences Publication Activity Database
Holeňa, Martin; Baerns, M.
2003-01-01
Roč. 81, - (2003), s. 485-494 ISSN 0920-5861 Grant - others:BMBF(DE) FKZ 03C3013 Institutional research plan: CEZ:AV0Z1030915 Keywords : artificial neural networks * multilayer perceptron * dependency * approximation * network training * overtraining * knowledge extraction * logical rules * oxidative dehydrogenation of propane Subject RIV: BA - General Mathematics Impact factor: 2.627, year: 2003
Kiang, Richard K.
1992-01-01
Neural networks have been applied to classifications of remotely sensed data with some success. To improve the performance of this approach, an examination was made of how neural networks are applied to the optical character recognition (OCR) of handwritten digits and letters. A three-layer, feedforward network, along with techniques adopted from OCR, was used to classify Landsat-4 Thematic Mapper data. Good results were obtained. To overcome the difficulties that are characteristic of remote sensing applications and to attain significant improvements in classification accuracy, a special network architecture may be required.
Land, Walker H., Jr.; Masters, Timothy D.; Lo, Joseph Y.; McKee, Dan
2001-07-01
A new neural network technology was developed for improving the benign/malignant diagnosis of breast cancer using mammogram findings. A new paradigm, Adaptive Boosting (AB), uses a markedly different theory in solutioning Computational Intelligence (CI) problems. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than random performance (i.e., approximately 55%) when processing a mammogram training set. Then, by successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves the performance of the basic Evolutionary Programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization focused on improving specificity and positive predictive value at very high sensitivities, where an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, on average this hybrid was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.
PAC learning algorithms for functions approximated by feedforward networks
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Protopopescu, V. [Oak Ridge National Lab., TN (United States). Center for Engineering Systems Advanced Research
1996-06-01
The authors present a class of efficient algorithms for PAC learning continuous functions and regressions that are approximated by feedforward networks. The algorithms are applicable to networks with unknown weights located only in the output layer and are obtained by utilizing the potential function methods of Aizerman et al. Conditions relating the sample sizes to the error bounds are derived using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.
Finite-sample based learning algorithms for feedforward networks
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Protopopescu, V.; Mann, R.C.; Oblow, E.M. [Oak Ridge National Lab., TN (United States); Iyengar, S.S. [Louisiana State Univ., Baton Rouge, LA (United States). Dept. of Computer Science
1995-04-01
We discuss two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by FeedForward Networks (FFN). The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can also be directly applied to concept learning problems. A main distinguishing feature of the this work is that the sample sizes are based on explicit algorithms rather than information-based methods.
Learning algorithms for feedforward networks based on finite samples
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Protopopescu, V.; Mann, R.C.; Oblow, E.M.; Iyengar, S.S.
1994-09-01
Two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by feedforward networks, are discussed. The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.
Introduction to neural networks
James, Frederick E
1994-02-02
1. Introduction and overview of Artificial Neural Networks. 2,3. The Feed-forward Network as an inverse Problem, and results on the computational complexity of network training. 4.Physics applications of neural networks.
Directory of Open Access Journals (Sweden)
R. H. R. Garcel1
2015-09-01
Full Text Available AbstractIn the present study a preliminary neural network modelling to improve our understanding of Recombinant Human Erythropoietin purification process in a plant was explored. A three layer feed-forward back propagation neural network was constructed for predicting the efficiency of the purification section comprising four chromatographic steps as a function of eleven operational variables. The neural network model performed very well in the training and validation phases. Using the connection weight method the predictor variables were ranked based on their estimated explanatory importance in the neural network and five input variables were found to be predominant over the others. These results provided useful information showing that the first chromatographic step and the third chromatographic step are decisive to achieve high efficiencies in the purification section, thus enriching the control strategy of the plant.
Coulomb oscillations in three-layer graphene nanostructures
International Nuclear Information System (INIS)
Guettinger, J; Stampfer, C; Molitor, F; Graf, D; Ihn, T; Ensslin, K
2008-01-01
We present transport measurements on a tunable three-layer graphene single electron transistor (SET). The device consists of an etched three-layer graphene flake with two narrow constrictions separating the island from source and drain contacts. Three lateral graphene gates are used to electrostatically tune the device. An individual three-layer graphene constriction has been investigated separately showing a transport gap near the charge neutrality point. The graphene tunneling barriers show a strongly nonmonotonic coupling as a function of gate voltage indicating the presence of localized states in the constrictions. We show Coulomb oscillations and Coulomb diamond measurements proving the functionality of the graphene SET. A charging energy of ∼0.6 meV is extracted.
Minimization of material volume of three layer compound cylinder ...
African Journals Online (AJOL)
This paper introduces the methodology for minimization of volume of shrink-fitted three layer compound cylinder and to get equal maximum hoop stresses in all the cylinders. The analytical results are validated in comparison with FEM in ANSYS Workbench. Both the results agree with each other. Thus methodology can be ...
Character Recognition Using Genetically Trained Neural Networks
Energy Technology Data Exchange (ETDEWEB)
Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.
1998-10-01
Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the
Chaotic diagonal recurrent neural network
International Nuclear Information System (INIS)
Wang Xing-Yuan; Zhang Yi
2012-01-01
We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)
A Three-Layer Network Model of Direction Selective Circuits in the Optic Tectum.
Abbas, Fatima; Triplett, Marcus A; Goodhill, Geoffrey J; Meyer, Martin P
2017-01-01
The circuit mechanisms that give rise to direction selectivity in the retina have been studied extensively but how direction selectivity is established in retinorecipient areas of the brain is less well understood. Using functional imaging in larval zebrafish we examine how the direction of motion is encoded by populations of neurons at three layers of the optic tectum; retinal ganglion cell axons (RGCs), a layer of superficial inhibitory interneurons (SINs), and periventricular neurons (PVNs), which constitute the majority of neurons in the tectum. We show that the representation of motion direction is transformed at each layer. At the level of RGCs and SINs the direction of motion is encoded by three direction-selective (DS) subtypes tuned to upward, downward, and caudal-to-rostral motion. However, the tuning of SINs is significantly narrower and this leads to a conspicuous gap in the representation of motion in the rostral-to-caudal direction at the level of SINs. Consistent with previous findings we demonstrate that, at the level of PVNs the direction of motion is encoded by four DS cell types which include an additional DS PVN cell type tuned to rostral-to-caudal motion. Strikingly, the tuning profile of this emergent cell type overlaps with the gap in the representation of rostral-to-caudal motion at the level of SINs. Using our functional imaging data we constructed a simple computational model that demonstrates how the emergent population of PVNs is generated by the interactions of cells at each layer of the tectal network. The model predicts that PVNs tuned to rostral-to-caudal motion can be generated via convergence of DS RGCs tuned to upward and downward motion and feedforward tuned inhibition via SINs which suppresses responses to non-preferred directions. Thus, by reshaping directional tuning that is inherited from the retina inhibitory inputs from SINs can generate a novel subtype of DS PVN and in so doing enhance the encoding of directional stimuli.
SANS study of three-layer micellar particles
Plestil, J; Kuklin, A I; Cubitt, R
2002-01-01
Three-layer nanoparticles were prepared by polymerization of methyl methacrylate (MMA) in aqueous micellar solutions of poly(methyl methacrylate)-block-poly(methacrylic acid) (PMMA-b-PMA) and polystyrene-block-poly(methacrylic acid) (PS-b-PMA). The resulting polymer forms a layer on the core surface of the original micelles. SANS curves were fitted using an ellipsoidal (PMMA/PMMA/PMA) or spherical (PS/PMMA/PMA) model for the particle core. The particle size (for the presented series of the PMMA/PMMA/PMA particles, the core semiaxes ranged from 87 to 187 A and the axis ratio was about 6) can be finely tuned by variation of monomer concentration. Time-resolved SANS experiments were carried out to describe the growth of the PS/PMMA/PMA particles during polymerization. (orig.)
Feed-forward segmentation of figure-ground and assignment of border-ownership.
Directory of Open Access Journals (Sweden)
Hans Supèr
Full Text Available Figure-ground is the segmentation of visual information into objects and their surrounding backgrounds. Two main processes herein are boundary assignment and surface segregation, which rely on the integration of global scene information. Recurrent processing either by intrinsic horizontal connections that connect surrounding neurons or by feedback projections from higher visual areas provide such information, and are considered to be the neural substrate for figure-ground segmentation. On the contrary, a role of feedforward projections in figure-ground segmentation is unknown. To have a better understanding of a role of feedforward connections in figure-ground organization, we constructed a feedforward spiking model using a biologically plausible neuron model. By means of surround inhibition our simple 3-layered model performs figure-ground segmentation and one-sided border-ownership coding. We propose that the visual system uses feed forward suppression for figure-ground segmentation and border-ownership assignment.
Neural networks within multi-core optic fibers.
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-07
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Yang, Yimin; Wu, Q. M. Jonathan; Huang, Guangbin; Wang, Yaonan
2014-01-01
According to conventional neural network theories, the feature of single-hidden-layer feedforward neural networks(SLFNs) resorts to parameters of the weighted connections and hidden nodes. SLFNs are universal approximators when at least the parameters of the networks including hidden-node parameter and output weight are exist. Unlike above neural network theories, this paper indicates that in order to let SLFNs work as universal approximators, one may simply calculate the hidden node paramete...
Ultrasound radiation from a three-layer thermoacoustic transformation device.
Nishioka, Takuya; Teshima, Yu; Mano, Takashi; Sakai, Ken; Asada, Takaaki; Matsukawa, Mami; Ohta, Tetsuo; Hiryu, Shizuko
2015-03-01
A thermophone is a thermoacoustic transducer, which generates sound via time-varying Joule heating of an electrically conductive layer, which leads to expansion and contraction of a small pocket of air near the surface of the film. In this work, a 10-μm-thick Ag-Pd conductive film was coupled with heat-insulating and heat-releasing layers to fabricate a three-layer thermophone for generating ultrasound. The heat-insulating layer was 47 μm thick, and was made of glass. The heat-releasing layer was 594 μm thick, and was made of 94% alumina. Because of the simple sound-generation mechanism, which does not require mechanical moving parts, the Ag-Pd conductive film on the glass substrate can produce ultrasound radiation with broadband frequency characteristics, where exiting commercial electrode materials were used. We also demonstrate that the measured directivity patterns are in good agreement with theoretical predictions, assuming a rectangular diaphragm with the same size as the metallic film. Copyright © 2014 Elsevier B.V. All rights reserved.
Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong
2013-11-01
In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Tosun Erdi
2017-01-01
Full Text Available This study was aimed at estimating the variation of several engine control parameters within the rotational speed-load map, using regression analysis and artificial neural network techniques. Duration of injection, specific fuel consumption, exhaust gas at turbine inlet, and within the catalytic converter brick were chosen as the output parameters for the models, while engine speed and brake mean effective pressure were selected as independent variables for prediction. Measurements were performed on a turbocharged direct injection spark ignition engine fueled with gasoline. A three-layer feed-forward structure and back-propagation algorithm was used for training the artificial neural network. It was concluded that this technique is capable of predicting engine parameters with better accuracy than linear and non-linear regression techniques.
Feedforward inhibition and synaptic scaling--two sides of the same coin?
Directory of Open Access Journals (Sweden)
Christian Keck
Full Text Available Feedforward inhibition and synaptic scaling are important adaptive processes that control the total input a neuron can receive from its afferents. While often studied in isolation, the two have been reported to co-occur in various brain regions. The functional implications of their interactions remain unclear, however. Based on a probabilistic modeling approach, we show here that fast feedforward inhibition and synaptic scaling interact synergistically during unsupervised learning. In technical terms, we model the input to a neural circuit using a normalized mixture model with Poisson noise. We demonstrate analytically and numerically that, in the presence of lateral inhibition introducing competition between different neurons, Hebbian plasticity and synaptic scaling approximate the optimal maximum likelihood solutions for this model. Our results suggest that, beyond its conventional use as a mechanism to remove undesired pattern variations, input normalization can make typical neural interaction and learning rules optimal on the stimulus subspace defined through feedforward inhibition. Furthermore, learning within this subspace is more efficient in practice, as it helps avoid locally optimal solutions. Our results suggest a close connection between feedforward inhibition and synaptic scaling which may have important functional implications for general cortical processing.
Directory of Open Access Journals (Sweden)
Jorge F Mejias
2014-02-01
Full Text Available The control of input-to-output mappings, or gain control, is one of the main strategies used by neural networks for the processing and gating of information. Using a spiking neural network model, we studied the gain control induced by a form of inhibitory feedforward circuitry — also known as ’open-loop feedback’ —, which has been experimentally observed in a cerebellum-like structure in weakly electric fish. We found, both analytically and numerically, that this network displays three different regimes of gain control: subtractive, divisive, and non-monotonic. Subtractive gain control was obtained when noise is very low in the network. Also, it was possible to change from divisive to non-monotonic gain control by simply modulating the strength of the feedforward inhibition, which may be achieved via long-term synaptic plasticity. The particular case of divisive gain control has been previously observed in vivo in weakly electric fish. These gain control regimes were robust to the presence of temporal delays in the inhibitory feedforward pathway, which were found to linearize the input-to-output mappings (or f-I curves via a novel variability-increasing mechanism. Our findings highlight the feedforward-induced gain control analyzed here as a highly versatile mechanism of information gating in the brain.
Stochastic resonance in feedforward acupuncture networks
Qin, Ying-Mei; Wang, Jiang; Men, Cong; Deng, Bin; Wei, Xi-Le; Yu, Hai-Tao; Chan, Wai-Lok
2014-10-01
Effects of noises and some other network properties on the weak signal propagation are studied systematically in feedforward acupuncture networks (FFN) based on FitzHugh-Nagumo neuron model. It is found that noises with medium intensity can enhance signal propagation and this effect can be further increased by the feedforward network structure. Resonant properties in the noisy network can also be altered by several network parameters, such as heterogeneity, synapse features, and feedback connections. These results may also provide a novel potential explanation for the propagation of acupuncture signal.
An Artificial Neural Network Controller for Intelligent Transportation Systems Applications
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...
Guliyev, Namig; Ismailov, Vugar
2016-01-01
The possibility of approximating a continuous function on a compact subset of the real line by a feedforward single hidden layer neural network with a sigmoidal activation function has been studied in many papers. Such networks can approximate an arbitrary continuous function provided that an unlimited number of neurons in a hidden layer is permitted. In this paper, we consider constructive approximation on any finite interval of $\\mathbb{R}$ by neural networks with only one neuron in the hid...
Isolated Speech Recognition Using Artificial Neural Networks
National Research Council Canada - National Science Library
Polur, Prasad
2001-01-01
.... A small size vocabulary containing the words YES and NO is chosen. Spectral features using cepstral analysis are extracted per frame and imported to a feedforward neural network which uses a backpropagation with momentum training algorithm...
The XCNN flow meter - a combined cross-correlation and neural network model
International Nuclear Information System (INIS)
Roverso, Davide
2004-05-01
In this report we propose the XCNN flow meter model, which consists of an integration of a cross-correlator (XC) of pressure measurements and an ensemble of neural network (NN) estimators. Since pressure information does not only travel with the fluid, like for example particles, bubbles, eddies and, to a big extent, temperature, but also through the fluid, the transit time of a pressure disturbance estimated by cross-correlation needs to be corrected to take into account the propagation velocity of pressure differentials in the fluid. This correction is performed by the neural network models, which in this case are simple single input single output three layer feed-forward neural networks. Instead of a single neural network an ensemble is used to reduce the variance of the estimate. The proposed method involves several stages where pressure transmitter data is first filtered, then fed to the cross-correlator whose result is interpolated and filtered again before being fed to the ensemble of neural networks, which produce the final flow estimate. An average accuracy of 0.29% (with 0.18 standard deviation) of a reference ultrasonic meter has been obtained on experimental measurements performed at Tecnatom s.a. This report marks the conclusion of the Virtual Sensors for Feedwater Flow Measurement project at the HRP, which run in the 2001-2003 period. (Author)
Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm
International Nuclear Information System (INIS)
Yu, Lean; Wang, Shouyang; Lai, Kin Keung
2008-01-01
In this study, an empirical mode decomposition (EMD) based neural network ensemble learning paradigm is proposed for world crude oil spot price forecasting. For this purpose, the original crude oil spot price series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). Then a three-layer feed-forward neural network (FNN) model was used to model each of the extracted IMFs, so that the tendencies of these IMFs could be accurately predicted. Finally, the prediction results of all IMFs are combined with an adaptive linear neural network (ALNN), to formulate an ensemble output for the original crude oil price series. For verification and testing, two main crude oil price series, West Texas Intermediate (WTI) crude oil spot price and Brent crude oil spot price, are used to test the effectiveness of the proposed EMD-based neural network ensemble learning methodology. Empirical results obtained demonstrate attractiveness of the proposed EMD-based neural network ensemble learning paradigm. (author)
The role of the feedforward paradigm in cognitive psychology.
Basso, Demis; Olivetti Belardinelli, Marta
2006-06-01
Feedforward control is a process adjusting behaviour in a continuative way. Feedforward takes place when an equilibrium state is disrupted and the system has to automatically retrieve the homeostatic stable state. It also occurs when a perturbation is previewed and must be eliminated in order to achieve a desired goal. According to the most general definition, a feedforward process operates by fixing the future representation of the desired state, the achieving of which stops the process. Then, feedforward works by means of the refinement determined by successive comparisons between the actual and target products. In its applications, a feedforward process is thought to be modulated by the subject's purpose and the environmental state. Over the years, the feedforward process has assumed different connotations in several contests of cognitive psychology. An overview of the research fields in psychology that significantly progressed with the introduction of a feedforward paradigm is provided by: (a) reviewing models in which the feedforward concept plays a fundamental role in the system control; (b) examining critical experiments related to the interaction of feedforward and feedback processes; (c) evidencing practical applications for some of the presented feedforward-based architectures.
Feature and Model Selection in Feedforward Neural Networks
1994-06-01
output of middle nodej - M is the number of feature inputs -wij is the weight from input node i to middle node j - e0 is the input layer bias term, and is...is the updated weight from input i to middle node j - (wtuj) is the old weight from from input i to middle nodej - q7 is the step size - 62 = (d
Analyzing Divisia Rules Extracted from a Feedforward Neural Network
National Research Council Canada - National Science Library
Schmidt, Vincent A; Binner, Jane M
2006-01-01
This paper introduces a mechanism for generating a series of rules that characterize the money-price relationship, defined as the relationship between the rate of growth of the money supply and inflation...
Classification of Urinary Calculi using Feed-Forward Neural Networks
African Journals Online (AJOL)
NJD
the chromosome(s) with best performance(s) among the group of chromosomes so called population. Using natural selection and genetic operations (crossover and mutation), chromosomes with better performances are selected. Natural selection retains the genetic material from chromosomes with best performances.
Modified geometry three-layered tablet as a platform for class II ...
African Journals Online (AJOL)
Modified geometry three-layered tablet as a platform for class II drugs zero-order release system. Abdullah Monahi Albogami, Mustafa E. Omer, Abdulkareem M. Al Bekairy, Abdulmalik Alkatheri, Alaa Eldeen B. Yassin ...
Visual areas exert feedforward and feedback influences through distinct frequency channels
Bastos, A.M.; Vezoli, J.; Bosman, C.A.; Schoffelen, J.M.; Oostenveld, R.; Dowdall, J.R.; de Weerd, P.; Kennedy, H.; Fries, P.
2015-01-01
Visual cortical areas subserve cognitive functions by interacting in both feedforward and feedback directions. While feedforward influences convey sensory signals, feedback influences modulate feedforward signaling according to the current behavioral context. We investigated whether these interareal
Tapia, Evelina; Beck, Diane M
2014-01-01
A number of influential theories posit that visual awareness relies not only on the initial, stimulus-driven (i.e., feedforward) sweep of activation but also on recurrent feedback activity within and between brain regions. These theories of awareness draw heavily on data from masking paradigms in which visibility of one stimulus is reduced due to the presence of another stimulus. More recently transcranial magnetic stimulation (TMS) has been used to study the temporal dynamics of visual awareness. TMS over occipital cortex affects performance on visual tasks at distinct time points and in a manner that is comparable to visual masking. We draw parallels between these two methods and examine evidence for the neural mechanisms by which visual masking and TMS suppress stimulus visibility. Specifically, both methods have been proposed to affect feedforward as well as feedback signals when applied at distinct time windows relative to stimulus onset and as a result modify visual awareness. Most recent empirical evidence, moreover, suggests that while visual masking and TMS impact stimulus visibility comparably, the processes these methods affect may not be as similar as previously thought. In addition to reviewing both masking and TMS studies that examine feedforward and feedback processes in vision, we raise questions to guide future studies and further probe the necessary conditions for visual awareness.
Neural networks for offline analysis in high-energy physics
de Angelis, Alessandro D.
1995-04-01
Feed-forward neural networks are nowadays a standard tool in the toolbox of high energy physicists. This talk summarizes the fields of application in offline analysis, and discusses some open problems.
Analysis of Nanoparticle Additive Couple Stress Fluids in Three-layered Journal Bearing
Rao, T. V. V. L. N.; Sufian, S.; Mohamed, N. M.
2013-04-01
The present theoretical study investigates the load capacity and friction coefficient in a three-layered journal bearing lubricated with nanoparticle additive couple stress fluids. The couple stresses effects are analyzed based on Stokes micro-continuum theory. The nondimensional pressure and shear stress expressions are derived using modified Reynolds equation. The nondimensional load capacity increases and the coefficient of friction decreases using nanoparticle additive lubricants with couple stress effects. The three-layered journal bearing performance characteristics are improved with increase in both (i) surface adsorbent fluid film layer thickness and (ii) dynamic viscosity ratio of surface to core layer.
Analysis of Nanoparticle Additive Couple Stress Fluids in Three-layered Journal Bearing
International Nuclear Information System (INIS)
Rao, T V V L N; Sufian, S; Mohamed, N M
2013-01-01
The present theoretical study investigates the load capacity and friction coefficient in a three-layered journal bearing lubricated with nanoparticle additive couple stress fluids. The couple stresses effects are analyzed based on Stokes micro-continuum theory. The nondimensional pressure and shear stress expressions are derived using modified Reynolds equation. The nondimensional load capacity increases and the coefficient of friction decreases using nanoparticle additive lubricants with couple stress effects. The three-layered journal bearing performance characteristics are improved with increase in both (i) surface adsorbent fluid film layer thickness and (ii) dynamic viscosity ratio of surface to core layer.
Wave transmission prediction of multilayer floating breakwater using neural network
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Patil, S.G.; Hegde, A.V.
. Among many neural network architectures, the three layers feed forward error backpropagation neural network (BNN) is the most commonly used representing the input nodes as first layer, hidden nodes as second layer and output nodes as third layer...
Measuring Feedforward Inhibition and Its Impact on Local Circuit Function.
Hull, Court
2017-05-01
This protocol describes a series of approaches to measure feedforward inhibition in acute brain slices from the cerebellar cortex. Using whole-cell voltage and current clamp recordings from Purkinje cells in conjunction with electrical stimulation of the parallel fibers, these methods demonstrate how to measure the relationship between excitation and inhibition in a feedforward circuit. This protocol also describes how to measure the impact of feedforward inhibition on Purkinje cell excitability, with an emphasis on spike timing. © 2017 Cold Spring Harbor Laboratory Press.
Nonlinear Feedforward Control for Wind Disturbance Rejection on Autonomous Helicopter
DEFF Research Database (Denmark)
Bisgaard, Morten; la Cour-Harbo, Anders; A. Danapalasingam, Kumeresan
2010-01-01
This paper presents the design and verification of a model based nonlinear feedforward controller for wind disturbance rejection on autonomous helicopters. The feedforward control is based on a helicopter model that is derived using a number of carefully chosen simplifications to make it suitable...... for the purpose. The model is inverted for the calculation of rotor collective and cyclic pitch angles given the wind disturbance. The control strategy is then applied on a small helicopter in a controlled wind environment and flight tests demonstrates the effectiveness and advantage of the feedforward controller....
Laidi, Maamar; Hanini, Salah; Rezrazi, Ahmed; Yaiche, Mohamed Redha; El Hadj, Abdallah Abdallah; Chellali, Farouk
2017-04-01
In this study, a backpropagation artificial neural network (BP-ANN) model is used as an alternative approach to predict solar radiation on tilted surfaces (SRT) using a number of variables involved in physical process. These variables are namely the latitude of the site, mean temperature and relative humidity, Linke turbidity factor and Angstrom coefficient, extraterrestrial solar radiation, solar radiation data measured on horizontal surfaces (SRH), and solar zenith angle. Experimental solar radiation data from 13 stations spread all over Algeria around the year (2004) were used for training/validation and testing the artificial neural networks (ANNs), and one station was used to make the interpolation of the designed ANN. The ANN model was trained, validated, and tested using 60, 20, and 20 % of all data, respectively. The configuration 8-35-1 (8 inputs, 35 hidden, and 1 output neurons) presented an excellent agreement between the prediction and the experimental data during the test stage with determination coefficient of 0.99 and root meat squared error of 5.75 Wh/m2, considering a three-layer feedforward backpropagation neural network with Levenberg-Marquardt training algorithm, a hyperbolic tangent sigmoid and linear transfer function at the hidden and the output layer, respectively. This novel model could be used by researchers or scientists to design high-efficiency solar devices that are usually tilted at an optimum angle to increase the solar incident on the surface.
A high-speed analog neural processor
Masa, P.; Masa, Peter; Hoen, Klaas; Hoen, Klaas; Wallinga, Hans
1994-01-01
Targeted at high-energy physics research applications, our special-purpose analog neural processor can classify up to 70 dimensional vectors within 50 nanoseconds. The decision-making process of the implemented feedforward neural network enables this type of computation to tolerate weight
Processing Oscillatory Signals by Incoherent Feedforward Loops.
Zhang, Carolyn; Tsoi, Ryan; Wu, Feilun; You, Lingchong
2016-09-01
From the timing of amoeba development to the maintenance of stem cell pluripotency, many biological signaling pathways exhibit the ability to differentiate between pulsatile and sustained signals in the regulation of downstream gene expression. While the networks underlying this signal decoding are diverse, many are built around a common motif, the incoherent feedforward loop (IFFL), where an input simultaneously activates an output and an inhibitor of the output. With appropriate parameters, this motif can exhibit temporal adaptation, where the system is desensitized to a sustained input. This property serves as the foundation for distinguishing input signals with varying temporal profiles. Here, we use quantitative modeling to examine another property of IFFLs-the ability to process oscillatory signals. Our results indicate that the system's ability to translate pulsatile dynamics is limited by two constraints. The kinetics of the IFFL components dictate the input range for which the network is able to decode pulsatile dynamics. In addition, a match between the network parameters and input signal characteristics is required for optimal "counting". We elucidate one potential mechanism by which information processing occurs in natural networks, and our work has implications in the design of synthetic gene circuits for this purpose.
Shared internal models for feedforward and feedback control.
Wagner, Mark J; Smith, Maurice A
2008-10-15
A child often learns to ride a bicycle in the driveway, free of unforeseen obstacles. Yet when she first rides in the street, we hope that if a car suddenly pulls out in front of her, she will combine her innate goal of avoiding an accident with her learned knowledge of the bicycle, and steer away or brake. In general, when we train to perform a new motor task, our learning is most robust if it updates the rules of online error correction to reflect the rules and goals of the new task. Here we provide direct evidence that, after a new feedforward motor adaptation, motor feedback responses to unanticipated errors become precisely task appropriate, even when such errors were never experienced during training. To study this ability, we asked how, if at all, do online responses to occasional, unanticipated force pulses during reaching arm movements change after adapting to altered arm dynamics? Specifically, do they change in a task-appropriate manner? In our task, subjects learned novel velocity-dependent dynamics. However, occasional force-pulse perturbations produced unanticipated changes in velocity. Therefore, after adaptation, task-appropriate responses to unanticipated pulses should compensate corresponding changes in velocity-dependent dynamics. We found that after adaptation, pulse responses precisely compensated these changes, although they were never trained to do so. These results provide evidence for a smart feedback controller which automatically produces responses specific to the learned dynamics of the current task. To accomplish this, the neural processes underlying feedback control must (1) be capable of accurate real-time state prediction for velocity via a forward model and (2) have access to recently learned changes in internal models of limb dynamics.
Artificial Neural Network Analysis of Xinhui Pericarpium Citri ...
African Journals Online (AJOL)
Purpose: To develop an effective analytical method to distinguish old peels of Xinhui Pericarpium citri reticulatae (XPCR) stored for > 3 years from new peels stored for < 3 years. Methods: Artificial neural networks (ANN) models, including general regression neural network (GRNN) and multi-layer feedforward neural ...
On PAC learning of functions with smoothness properties using feedforward sigmoidal networks
Energy Technology Data Exchange (ETDEWEB)
Rao, N.S.V.; Protopopescu, V.A.
1996-04-01
We consider Probably and Approximately Corrct (PAC) learning of an unknown function f: [0,1]{sup d} {r_arrow} [0,1], based on finite samples using feedforward sigmoidal networks. The unknown function f is chosen from the family F{intersection}C([0,1]{sup d}) or F{intersection}L{sup {infinity}}([0,1]{sup d}), where F has either bounded modulus of smoothness or bounded capacity or both. The learning sample is given by (X{sub 1},f(X{sub 1})),(X{sub 2},f(X{sub 2})),{hor_ellipsis},(X{sub n},f(X{sub n})), where X{sub 1},X{sub 2},{hor_ellipsis},X{sub n} are independently and identically distributed according to an unknown distribution. We consider the feedforward networks with a a single hidden layer of 1/(1 + e{sup {minus}{gamma}z})-units and bounded parameters, but the results can be extended to other neural networks where the hidden units satisfy suitable smoothness conditions. We analyze three function estimators based on nearest neighbor rule, local averaging, and Nadaraya-Watson estimator, all computed using the Haar system. It is shown that given a sufficiently large sample, each of these estimators approximates the best neural network to any given error with arbitrarily high probability. This result is crucical for establishing the essentially equivalent capabilities of neural networks and the above estimators for PAC learning from finite samples. Practical importance of this ``equivalence`` stems from the fact that computing a neural network which approximates the best possible one is computationally difficult, whereas the three estimators are linear-time computable in terms of sample size.
Additive Feed Forward Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1999-01-01
. A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...
Plasticity and fracture modeling of three-layer steel composite Tribond® 1200 for crash simulation
Eller, Tom; Ramaker, Kenny; Greve, Lars; Andres, M.T.; Hazrati Marangalou, Javad; van den Boogaard, Antonius H.
2017-01-01
A constitutive model is presented for the three-layer steel composite Tribond® 1200. Tribond® is a hot forming steel which consists of three layers: a high strength steel core between two outer layers of ductile low strength steel. The model is designed to provide an accurate prediction of the
The Influence of Three-Layer Knitted Fabrics’ Structure on Electrostatic and Comfort Properties
Directory of Open Access Journals (Sweden)
Sandra VARNAITĖ ŽURAVLIOVA
2013-12-01
Full Text Available In our times, when electricity and electrical devices are around us every day, it is very important to be protected from electrostatic discharge. The best protection from electric charge dissipation provides conductive textile materials. For the last few decades fine and flexible conductive yarns were developed, which ensure very good electrostatic properties. Unfortunately, due to their chemical nature, these yarns do not distinguish good comfort properties. The main purpose of development of such textiles is to determine the influence of conductive yarns and hollow fiber yarns arrangements in the middle layer of the three layer weft-knitted fabrics to electrostatic and comfort properties. So, in order to have flexible textile materials with good electrostatic and comfort properties, multifunctional three layer weft-knitted fabrics of combined pattern were designed and manufactured for this research work. Two groups of polyester based three layer knitted fabrics with different arrangement of conductive yarns (such as carbon core yarn and polyester silver coated yarn and polyester yarn of special design (Coolmax®, Thermolite® were investigated. The parameters of electrostatic characteristics, such as surface and vertical resistances as well as charge decay properties were measured. The results have showed that all tested fabrics have excellent shielding properties. The main influence on the electrostatic properties of tested fabrics has the arrangement of conductive carbon core yarns inserted in the knits. In order to evaluate the comfort of knitted fabrics the air permeability, hygroscopicity, time of absorption and drying degree of fabrics were evaluated. It was determined, that the values of comfort parameters depend on the quantity and distribution of Coolmax® and Thermolite® yarns in the fabrics.DOI: http://dx.doi.org/10.5755/j01.ms.19.4.2235
Feedforward Tracking Control of Flat Recurrent Fuzzy Systems
Gering, Stefan; Adamy, Jürgen
2014-12-01
Flatness based feedforward control has proven to be a feasible solution for the problem of tracking control, which may be applied to a broad class of nonlinear systems. If a flat output of the system is known, the control is often based on a feedforward controller generating a nominal input in combination with a linear controller stabilizing the linearized error dynamics around the trajectory. We show in this paper that the very same idea may be incorporated for tracking control of MIMO recurrent fuzzy systems. Their dynamics is given by means of linguistic differential equations but may be converted into a hybrid system representation, which then serves as the basis for controller synthesis.
Thermal-Force Deformation of a Physically Nonlinear Three-Layer Stepped Rod
Starovoitov, É. I.; Leonenko, D. V.; Tarlakovskii, D. V.
2016-11-01
Consideration has been given to the thermal-force deformation of a three-layer plastoelastic rod with a stepped thickness of one supporting layer. The physical equations of state are consistent with the Il'yushin theory of small plastoelastic deformations. To describe the kinematics of a rod bundle nonsymmetric across the thickness, the authors adopted the broken-normal hypotheses. A system of equilibrium equations has been derived, and its general iterative solution in displacements has been obtained. A numerical parametric analysis of the rod's stress-strain state has been made.
Stienen, Bernard M C; Schindler, Konrad; de Gelder, Beatrice
2012-07-01
Given the presence of massive feedback loops in brain networks, it is difficult to disentangle the contribution of feedforward and feedback processing to the recognition of visual stimuli, in this case, of emotional body expressions. The aim of the work presented in this letter is to shed light on how well feedforward processing explains rapid categorization of this important class of stimuli. By means of parametric masking, it may be possible to control the contribution of feedback activity in human participants. A close comparison is presented between human recognition performance and the performance of a computational neural model that exclusively modeled feedforward processing and was engineered to fulfill the computational requirements of recognition. Results show that the longer the stimulus onset asynchrony (SOA), the closer the performance of the human participants was to the values predicted by the model, with an optimum at an SOA of 100 ms. At short SOA latencies, human performance deteriorated, but the categorization of the emotional expressions was still above baseline. The data suggest that, although theoretically, feedback arising from inferotemporal cortex is likely to be blocked when the SOA is 100 ms, human participants still seem to rely on more local visual feedback processing to equal the model's performance.
Xue, Ming; Wang, Jiang; Jia, Chenhui; Yu, Haitao; Deng, Bin; Wei, Xile; Che, Yanqiu
2013-03-01
In this paper, we proposed a new approach to estimate unknown parameters and topology of a neuronal network based on the adaptive synchronization control scheme. A virtual neuronal network is constructed as an observer to track the membrane potential of the corresponding neurons in the original network. When they achieve synchronization, the unknown parameters and topology of the original network are obtained. The method is applied to estimate the real-time status of the connection in the feedforward network and the neurotransmitter release probability of unreliable synapses is obtained by statistic computation. Numerical simulations are also performed to demonstrate the effectiveness of the proposed adaptive controller. The obtained results may have important implications in system identification in neural science.
CUDA-accelerated genetic feedforward-ANN training for data mining
International Nuclear Information System (INIS)
Patulea, Catalin; Peace, Robert; Green, James
2010-01-01
We present an implementation of genetic algorithm (GA) training of feedforward artificial neural networks (ANNs) targeting commodity graphics cards (GPUs). By carefully mapping the problem onto the unique GPU architecture, we achieve order-of-magnitude speedup over a conventional CPU implementation. Furthermore, we show that the speedup is consistent across a wide range of data set sizes, making this implementation ideal for large data sets. This performance boost enables the genetic algorithm to search a larger subset of the solution space, which results in more accurate pattern classification. Finally, we demonstrate this method in the context of the 2009 UC San Diego Data Mining Contest, achieving a world-class lift on a data set of 94682 e-commerce transactions.
CUDA-accelerated genetic feedforward-ANN training for data mining
Energy Technology Data Exchange (ETDEWEB)
Patulea, Catalin; Peace, Robert; Green, James, E-mail: cpatulea@sce.carleton.ca, E-mail: rpeace@sce.carleton.ca, E-mail: jrgreen@sce.carleton.ca [School of Systems and Computer Engineering, Carleton University, Ottawa, K1S 5B6 (Canada)
2010-11-01
We present an implementation of genetic algorithm (GA) training of feedforward artificial neural networks (ANNs) targeting commodity graphics cards (GPUs). By carefully mapping the problem onto the unique GPU architecture, we achieve order-of-magnitude speedup over a conventional CPU implementation. Furthermore, we show that the speedup is consistent across a wide range of data set sizes, making this implementation ideal for large data sets. This performance boost enables the genetic algorithm to search a larger subset of the solution space, which results in more accurate pattern classification. Finally, we demonstrate this method in the context of the 2009 UC San Diego Data Mining Contest, achieving a world-class lift on a data set of 94682 e-commerce transactions.
Simulation of thermal environment in a three-layer vinyl greenhouse by natural ventilation control
Jin, Tea-Hwan; Shin, Ki-Yeol; Yoon, Si-Won; Im, Yong-Hoon; Chang, Ki-Chang
2017-11-01
A high energy, efficient, harmonious, ecological greenhouse has been highlighted by advanced future agricultural technology recently. This greenhouse is essential for expanding the production cycle toward growth conditions through combined thermal environmental control. However, it has a negative effect on farming income via huge energy supply expenses. Because not only production income, but operating costs related to thermal load for thermal environment control is important in farming income, it needs studies such as a harmonious ecological greenhouse using natural ventilation control. This study is simulated for energy consumption and thermal environmental conditions in a three-layered greenhouse by natural ventilation using window opening. A virtual 3D model of a three-layered greenhouse was designed based on the real one in the Gangneung area. This 3D model was used to calculate a thermal environment state such as indoor temperature, relative humidity, and thermal load in the case of a window opening rate from 0 to 100%. There was also a heat exchange operated for heating or cooling controlled by various setting temperatures. The results show that the cooling load can be reduced by natural ventilation control in the summer season, and the heat exchange capacity for heating can also be simulated for growth conditions in the winter season.
A three-layered model of nursing based on hospital observation data.
Ohboshi, N; Tanaka, T; Kuwahara, N; Ozaku, H I; Naya, F; Kogure, K
2009-01-01
Our aim is to investigate causes of medical incidents and construct a knowledge base for preventing malpractice based on monitored data. To monitor nursing care, we developed an observing system of nursing activities with a ubiquitous sensor network and detecting errors in nursing care. This system is composed of a voice-recording device, mobile sensors and environmental setting type sensors. In cooperation with a hospital in western Japan, we have collected nursing activity data of nurses engaged at a combined ward, including ophthalmology, otolaryngology, and internal medicine for diabetes. After analyzing intravenous drip injection procedure (IVDI procedure) data, we introduce a three-layered model of nursing to understand nursing activities based on observed data. This model consists of three layers, 1) nursing care classification layer: Class, 2) nursing care step layer: Step, and 3) nursing care action layer: Action. This model is designed to take consistency with existing nursing care workflows. We implemented a detection system and succeeded in comprehending the workflow of IVDI procedure at the rate of over 95%. This system also can distinguish IVDI workflows performed in parallel by at least two or several nurses. We implemented a picture showing interface of IVDI workflows which can show each patient with a specific color and distinct nurses. Our system succeeded in verification of nursing care steps in IVDI procedure in ratios of more than 95%. Detection errors are due to the sensor system, so it is necessary to use or develop more precise devices.
Release Kinetics of Paclitaxel and Cisplatin from Two and Three Layered Gold Nanoparticles
England, Christopher G.; Miller, M. Clarke; Kuttan, Ashani; Trent, John O.; Frieboes, Hermann B.
2015-01-01
Gold nanoparticles functionalized with biologically-compatible layers may achieve stable drug release while avoiding adverse effects in cancer treatment. We study cisplatin and paclitaxel release from gold cores functionalized with hexadecanethiol (TL) and phosphatidylcholine (PC) to form two-layer nanoparticles, or TL, PC, and high density lipoprotein (HDL) to form three-layer nanoparticles. Drug release was monitored for 14 days to assess long term effects of the core surface modifications on release kinetics. Release profiles were fitted to previously developed kinetic models to differentiate possible release mechanisms. The hydrophilic drug (cisplatin) showed an initial (5-hr.) burst, followed by a steady release over 14 days. The hydrophobic drug (paclitaxel) showed a steady release over the same time period. Two layer nanoparticles released 64.0 ± 2.5% of cisplatin and 22.3 ± 1.5% of paclitaxel, while three layer nanoparticles released the entire encapsulated drug. The Korsmeyer-Peppas model best described each release scenario, while the simplified Higuchi model also adequately described paclitaxel release from the two layer formulation. We conclude that functionalization of gold nanoparticles with a combination of TL and PC may help to modulate both hydrophilic and hydrophobic drug release kinetics, while the addition of HDL may enhance long term release of hydrophobic drug. PMID:25753197
Three-Layer Model for the design of a Protocol Support System.
van Oosterhout, E M W; Talmon, J L; de Clercq, P A; Schouten, H C; Tange, H J; Hasman, A
2005-03-01
The aim of the PropeR project is to investigate the impact of Active Computerized Protocol Support (ACPS) on daily care processes in different settings (home care and hospital care). ACPS consists of an active Protocol Support System (PSS) that is linked to an Electronic Patient Record system. The aim of this paper is to describe how we have taken the organizational and social aspects into account in the hospital setting and the consequences of this approach for the design of the PSS. Socio-technical approaches have been applied. Observations and interviews with various health care providers were performed at the hematology and oncology department of the University Hospital Maastricht. Ten extensive sessions with a specialist physician and research nurse took place to further elaborate a study protocol and to discuss how it is integrated in daily practice. The knowledge editor component of Gaston was used to build a computer interpretable version of the selected protocol. To support the representation of a study protocol integrated in routine clinical care, a Three-Layer Model was developed. This model distinguishes the protocol description, local adaptations to the protocol and communication as three separate layers. These layers have been incorporated into the knowledge acquisition tool Gaston. The Three-Layer Model makes easy updating possible, and also supports transferability of computerized (study) protocols to other organizations.
Time-difference imaging of magnetic induction tomography in a three-layer brain physical phantom
International Nuclear Information System (INIS)
Liu, Ruigang; Li, Ye; Fu, Feng; You, Fusheng; Shi, Xuetao; Dong, Xiuzhen
2014-01-01
Magnetic induction tomography (MIT) is a contactless and noninvasive technique to reconstruct the conductivity distribution in a human cross-section. In this paper, we want to study the feasibility of imaging the low-contrast perturbation and small volume object in human brains. We construct a three-layer brain physical phantom which mimics the real conductivity distribution of brains by introducing an artificial skull layer. Using our MIT data acquisition system on this phantom and differential algorithm, we have obtained a series of reconstructed images of conductivity perturbation objects. All of the conductivity perturbation objects in the brain phantom can be clearly distinguished in the reconstructed images. The minimum detectable conductivity difference between the object and the background is 0.03 S m −1 (12.5%). The minimum detectable inner volume of the objects is 3.4 cm 3 . The three-layer brain physical phantom is able to simulate the conductivity distribution of the main structures of a human brain. The images of the low-contrast perturbation and small volume object show the prospect of MIT in the future. (paper)
Feedback and feedforward adaptation to visuomotor delay during reaching and slicing movements.
Botzer, Lior; Karniel, Amir
2013-07-01
It has been suggested that the brain and in particular the cerebellum and motor cortex adapt to represent the environment during reaching movements under various visuomotor perturbations. It is well known that significant delay is present in neural conductance and processing; however, the possible representation of delay and adaptation to delayed visual feedback has been largely overlooked. Here we investigated the control of reaching movements in human subjects during an imposed visuomotor delay in a virtual reality environment. In the first experiment, when visual feedback was unexpectedly delayed, the hand movement overshot the end-point target, indicating a vision-based feedback control. Over the ensuing trials, movements gradually adapted and became accurate. When the delay was removed unexpectedly, movements systematically undershot the target, demonstrating that adaptation occurred within the vision-based feedback control mechanism. In a second experiment designed to broaden our understanding of the underlying mechanisms, we revealed similar after-effects for rhythmic reversal (out-and-back) movements. We present a computational model accounting for these results based on two adapted forward models, each tuned for a specific modality delay (proprioception or vision), and a third feedforward controller. The computational model, along with the experimental results, refutes delay representation in a pure forward vision-based predictor and suggests that adaptation occurred in the forward vision-based predictor, and concurrently in the state-based feedforward controller. Understanding how the brain compensates for conductance and processing delays is essential for understanding certain impairments concerning these neural delays as well as for the development of brain-machine interfaces. © 2013 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.
Hybrid neural network for density limit disruption prediction and avoidance on J-TEXT tokamak
Zheng, W.; Hu, F. R.; Zhang, M.; Chen, Z. Y.; Zhao, X. Q.; Wang, X. L.; Shi, P.; Zhang, X. L.; Zhang, X. Q.; Zhou, Y. N.; Wei, Y. N.; Pan, Y.; J-TEXT team
2018-05-01
Increasing the plasma density is one of the key methods in achieving an efficient fusion reaction. High-density operation is one of the hot topics in tokamak plasmas. Density limit disruptions remain an important issue for safe operation. An effective density limit disruption prediction and avoidance system is the key to avoid density limit disruptions for long pulse steady state operations. An artificial neural network has been developed for the prediction of density limit disruptions on the J-TEXT tokamak. The neural network has been improved from a simple multi-layer design to a hybrid two-stage structure. The first stage is a custom network which uses time series diagnostics as inputs to predict plasma density, and the second stage is a three-layer feedforward neural network to predict the probability of density limit disruptions. It is found that hybrid neural network structure, combined with radiation profile information as an input can significantly improve the prediction performance, especially the average warning time ({{T}warn} ). In particular, the {{T}warn} is eight times better than that in previous work (Wang et al 2016 Plasma Phys. Control. Fusion 58 055014) (from 5 ms to 40 ms). The success rate for density limit disruptive shots is above 90%, while, the false alarm rate for other shots is below 10%. Based on the density limit disruption prediction system and the real-time density feedback control system, the on-line density limit disruption avoidance system has been implemented on the J-TEXT tokamak.
Neural network model to control an experimental chaotic pendulum
Bakker, R; Schouten, JC; Takens, F; vandenBleek, CM
1996-01-01
A feedforward neural network was trained to predict the motion of an experimental, driven, and damped pendulum operating in a chaotic regime. The network learned the behavior of the pendulum from a time series of the pendulum's angle, the single measured variable. The validity of the neural
Heart abnormality detection by using artificial neural network
African Journals Online (AJOL)
2017-09-10
Sep 10, 2017 ... Multilayer Perceptron (MLP) [17] is the most suitable and referred neural networks in the pattern recognition detection. This network can be trained to form various decision surfaces in the input space [3]. 2.1. Hybrid Multilayer Perceptron (HMLP). An MLP network is a feed-forward artificial neural network that ...
Artificial Neural Network Analysis of Xinhui Pericarpium Citri ...
African Journals Online (AJOL)
and multi-layer feedforward neural network (MLFN), were used to analyze the Gas Chromatography -. Mass Spectrometer ... Keywords: Artificial neural networks, Xinhui, Pericarpium, Citri reticulatae, Gas Chromatography,. Automated Mass Spectral ... drawbacks without applying further exploratory data analysis to identify ...
Size-dependent vibration and bending analyses of the piezomagnetic three-layer nanobeams
Arefi, Mohammed; Zenkour, Ashraf M.
2017-03-01
Vibration and electro-magneto-elastic bending analysis of a three-layer nanobeam with a nanocore and two piezomagnetic face sheets are studied in this paper. Timoshenko model of beam as well as nonlocal magneto-electro-elastic relations are used for analysis of this problem. The nanoface sheets are subjected to applied electric and magnetic potentials. The nanobeam rests on Winkler-Pasternak foundation. Electric and magnetic potentials are assumed as combination of linear function along the thickness direction that reflects applied electric and magnetic potentials and a cosine function that satisfies boundary conditions. Numerical results of this problem investigate the effect of some important parameters of nanobeam, such as nonlocal parameter, applied electric and magnetic potentials, and parameters of foundation on the vibration and magneto-electro-mechanical bending behaviors of the problem.
Stress Analysis of a Three-Layer Metal Composite System of Bearing Assemblies During Grinding
Pashnyov, V. A.; Pimenov, D. Yu.
2015-03-01
A mathematical model of the stress state of a three-layer metal composite system caused by cutting forces during grinding the working layer of the system is elaborated. The implementation of the model by using the finite-element method made it possible to assess the effect of structure of the system, the deformation properties of layer materials, and grinding conditions on the distribution and level of normal and tangential stresses in layers, which determine the load-carrying capacity of the system. The results of an analysis of stress fields can serve as a basis for determining the grinding conditions ensuring retention of the load-carrying capacity of the metal composite system.
Full-Wave Analysis of Microstrip Antennas in Three-Layered Spherical Media
Directory of Open Access Journals (Sweden)
Tao Yu
2013-01-01
Full Text Available A model of three-layered spherical microstrip antenna has been analyzed based on Rao-Wilton-Glisson (RWG triangular basis functions using mixed potential integral equation (MPIE. Firstly, the model of antenna and the dyadic Green’s function in spherical microstrip antennas are given at the beginning of this paper. Then, due to the infinite series convergence problem, asymptotic extraction approach is presented to accelerate the Green’s functions convergence speed when source and field points are located in the same layer and different layers. The convergence speed can be accelerated observably by using this method. Finally, in order to simplify impedance matrix elements calculation at the junction of the probe and patch, a novel division fashion of pair of triangles is adopted in this paper. The input impedance result obtained shows the validity and effectiveness of the analysis method comparing with published data.
A Decomposition Method for Security Constrained Economic Dispatch of a Three-Layer Power System
Yang, Junfeng; Luo, Zhiqiang; Dong, Cheng; Lai, Xiaowen; Wang, Yang
2018-01-01
This paper proposes a new decomposition method for the security-constrained economic dispatch in a three-layer large-scale power system. The decomposition is realized using two main techniques. The first is to use Ward equivalencing-based network reduction to reduce the number of variables and constraints in the high-layer model without sacrificing accuracy. The second is to develop a price response function to exchange signal information between neighboring layers, which significantly improves the information exchange efficiency of each iteration and results in less iterations and less computational time. The case studies based on the duplicated RTS-79 system demonstrate the effectiveness and robustness of the proposed method.
The three-layered mismatched media diffusion equation in frequency domain
Wang, Xichang; Wang, Shumei; Meng, Zhaokun; Yang, Shangming
2006-09-01
Near-IR radiation has great potential in medical diagnosis and therapy because of the non-invasive nature of light and the selectively poisonous effect to tumors of photodynarnic treatment. Therefore, Near-IR light propagation in highly scattering biological tissue must be understudied for basic research and clinical application of biomedical optics. A tissue is multi-layered mismatched medium, but many investigators only study the diffusion equation of matched medium. they take the tissue as the same refractive index. In order to understand the light transport in tissue, We analyze the diffusion of photons three-layered mismatched medium and set up the solution of Green's function in frequency domain, we employ the extrapolated boundary condition to set up a solution of the diffusion equation. At the same time, we utilize the diffuse equation to calculate the phase in different situation
Pawlus, Dorota
2017-12-01
The paper presents the dynamic response of annular three-layered plate subjected to loads variable in time. The plate is loaded in the plane of outer layers. The plate core has the electrorheological properties expressed by the Bingham body model. The dynamic stability loss of plate with elastic core is determined by the critical state parameters, particularly by the critical stresses. Numerous numerical observations show the influence of the values of viscosity constant and critical shear stresses, being the Bingham body parameters, on the supercritical viscous fluid plate behaviour. The problem has been solved analytically and numerically using the orthogonalization method and finite difference method. The solution includes both axisymmetric and asymmetric plate dynamic modes.
Three-Layered Atmospheric Structure in Accretion Disks Around Stellar-Mass Black Holes
Zhang, S. N.; Cui, Wei; Chen, Wan; Yao, Yangsen; Zhang, Xiaoling; Sun, Xuejun; Wu, Xue-Bing; Xu, Haiguang
2000-01-01
Modeling of the x-ray spectra of the Galactic superluminal jet sources GRS 1915+105 and GRO J1655-40 reveals a three-layered atmospheric structure in the inner region of the inner accretion disks. Above the cold and optically thick disk with a temperature of 0.2 to 0.5 kiloelectron volts, there is a warm layer with a temperature of 1.0 to 1.5 kiloelectron volts and an optical depth around 10. Sometimes there is also a much hotter, optically thin corona above the warm layer, with a temperature of 100 kiloelectron volts or higher and an optical depth around unity. The structural similarity between the accretion disks and the solar atmosphere suggests that similar physical processes may be operating in these different systems.
Maritime shipping and emissions: A three-layered, damage-based approach
DEFF Research Database (Denmark)
Lindstad, Haakon; Eskeland, Gunnar S.; Psaraftis, Harilaos N.
2015-01-01
to location and operational conditions. Since environmental policy originates in damages relating to ecosystems and jurisdictions, a three-layered approach. to vessel emissions is intuitive and practical. Here, we suggest associating damages and policies with ports, coastal areas possibly defined as Emission...... Control Areas (ECA) as in the North Sea and the Baltic, and open seas globally. This approach offers important practical opportunities: in ports, clean fuels or even electrification is possible; in ECAs, cleaner fuels and penalties for damaging fuels are important, but so is vessel handling......, such as speeds and utilization. Globally we argue that it may be desirable to allow burning very dirty fuels at high seas, due to the cost advantages, the climate cooling benefits, and the limited ecosystem impacts. We quantify the benefits and cost savings from reforming current IMO and other approaches towards...
Research on performance of three-layer MG-OXC system based on MLAG and OCDM
Wang, Yubao; Ren, Yanfei; Meng, Ying; Bai, Jian
2017-10-01
At present, as traffic volume which optical transport networks convey and species of traffic grooming methods increase rapidly, optical switching techniques are faced with a series of issues, such as more requests for the number of wavelengths and complicated structure management and implementation. This work introduces optical code switching based on wavelength switching, constructs the three layers multi-granularity optical cross connection (MG-OXC) system on the basis of optical code division multiplexing (OCDM) and presents a new traffic grooming algorithm. The proposed architecture can improve the flexibility of traffic grooming, reduce the amount of used wavelengths and save the number of consumed ports, hence, it can simplify routing device and enhance the performance of the system significantly. Through analyzing the network model of switching structure on multicast layered auxiliary graph (MLAG) and the establishment of traffic grooming links, and the simulation of blocking probability and throughput, this paper shows the excellent performance of this mentioned architecture.
Akbari Hasanjani, Hamid Reza; Sohrabi, Mahmoud Reza
2017-01-01
Simultaneous spectrophotometric estimation of Fluoxetine and Sertraline in tablets were performed using UV-Vis spectroscopic and Artificial Neural Networks (ANN). Absorption spectra of two components were recorded in 200-300 nm wavelengths region with an interval of 1 nm. The calibration models were thoroughly evaluated at several concentration levels using the spectra of synthetic binary mixture (prepared using orthogonal design). Three layers feed-forward neural networks using the back-propagation algorithm (B.P) has been employed for building and testing models. Several parameters such as the number of neurons in the hidden layer, learning rate and the number of epochs were optimized. The Relative Standard Deviation (RSD) for each component in real sample was calculated as 1.06 and 1.33 for Fluoxetine and Sertraline, respectively. The results showed a very good agreement between true values and predicted concentration values. The proposed procedure is a simple, precise and convenient method for the determination of Fluoxetine and Sertraline in commercial tablets.
Hu, Songlin; Yue, Dong; Xie, Xiangpeng; Ma, Yong; Yin, Xiuxia
2018-03-01
This paper focuses on a problem of event-triggered stabilization for a class of nonuniformly sampled neural-network-based control systems (NNBCSs). First, a new event-triggered data transmission mechanism is designed based on the nonperiodic sampled data. Different from the previous works, the proposed triggering scheme enables the NNBCSs design to enjoy the advantages of both nonuniform and event-triggered sampling schemes. Second, under the nonperiodic event-triggered data transmission scheme, the nonperiodic sampled-data three-layer fully connected feedforward neural-network (TLFCFFNN)-based event-triggered controller is constructed, and the resulting closed-loop TLFCFFNN-based event-triggered control system is modeled as a state delay system based on time-delay system modeling approach. Then, the stability criteria for the closed-loop system is formulated using Lyapunov-Krasovskii functional approach. Third, the sufficient conditions for the codesign of the TLFCFFNN-based controller and triggering parameters are given in terms of solvability of matrix inequalities to guarantee the asymptotical stability of the closed-loop system and an upper bound on the given cost function while reducing the updates of the controller. Finally, three numerical examples are provided to illustrate the effectiveness and benefits of the proposed results.
3-D inversion of borehole-to-surface electrical data using a back-propagation neural network
Ho, Trong Long
2009-08-01
The "fluid-flow tomography", an advanced technique for geoelectrical survey based on the conventional mise-à-la-masse measurement, has been developed by Exploration Geophysics Laboratory at the Kyushu University. This technique is proposed to monitor fluid-flow behavior during water injection and production in a geothermal field. However data processing of this technique is very costly. In this light, this paper will discuss the solution to cost reduction by applying a neural network in the data processing. A case study in the Takigami geothermal field in Japan will be used to illustrate this. The achieved neural network in this case study is three-layered and feed-forward. The most successful learning algorithm in this network is the Resilient Propagation (RPROP). Consequently, the study advances the pragmatism of the "fluid-flow tomography" technique which can be widely used for geothermal fields. Accuracy of the solution is then verified by using root mean square (RMS) misfit error as an indicator.
Visualization of neural networks using saliency maps
DEFF Research Database (Denmark)
Mørch, Niels J.S.; Kjems, Ulrik; Hansen, Lars Kai
1995-01-01
The saliency map is proposed as a new method for understanding and visualizing the nonlinearities embedded in feedforward neural networks, with emphasis on the ill-posed case, where the dimensionality of the input-field by far exceeds the number of examples. Several levels of approximations...
Optimal Decision Making in Neural Inhibition Models
van Ravenzwaaij, Don; van der Maas, Han L. J.; Wagenmakers, Eric-Jan
2012-01-01
In their influential "Psychological Review" article, Bogacz, Brown, Moehlis, Holmes, and Cohen (2006) discussed optimal decision making as accomplished by the drift diffusion model (DDM). The authors showed that neural inhibition models, such as the leaky competing accumulator model (LCA) and the feedforward inhibition model (FFI), can mimic the…
Parameter estimation using compensatory neural networks
Indian Academy of Sciences (India)
of interconnections among neurons but also reduces the total computing time for training. The suggested model has properties of the basic neuron ..... Engelbrecht A P, Cloete I, Geldenhuys J, Zurada J M 1995 Automatic scaling using gamma learning for feedforward neural networks. From natural to artificial computing.
Efficient Feedforward Linearization Technique Using Genetic Algorithms for OFDM Systems
Directory of Open Access Journals (Sweden)
García Paloma
2010-01-01
Full Text Available Feedforward is a linearization method that simultaneously offers wide bandwidth and good intermodulation distortion suppression; so it is a good choice for Orthogonal Frequency Division Multiplexing (OFDM systems. Feedforward structure consists of two loops, being necessary an accurate adjustment between them along the time, and when temperature, environmental, or operating changes are produced. Amplitude and phase imbalances of the circuit elements in both loops produce mismatched effects that lead to degrade its performance. A method is proposed to compensate these mismatches, introducing two complex coefficients calculated by means of a genetic algorithm. A full study is carried out to choose the optimal parameters of the genetic algorithm applied to wideband systems based on OFDM technologies, which are very sensitive to nonlinear distortions. The method functionality has been verified by means of simulation.
Predictive Feedback and Feedforward Control for Systems with Unknown Disturbances
Juang, Jer-Nan; Eure, Kenneth W.
1998-01-01
Predictive feedback control has been successfully used in the regulation of plate vibrations when no reference signal is available for feedforward control. However, if a reference signal is available it may be used to enhance regulation by incorporating a feedforward path in the feedback controller. Such a controller is known as a hybrid controller. This paper presents the theory and implementation of the hybrid controller for general linear systems, in particular for structural vibration induced by acoustic noise. The generalized predictive control is extended to include a feedforward path in the multi-input multi-output case and implemented on a single-input single-output test plant to achieve plate vibration regulation. There are cases in acoustic-induce vibration where the disturbance signal is not available to be used by the hybrid controller, but a disturbance model is available. In this case the disturbance model may be used in the feedback controller to enhance performance. In practice, however, neither the disturbance signal nor the disturbance model is available. This paper presents the theory of identifying and incorporating the noise model into the feedback controller. Implementations are performed on a test plant and regulation improvements over the case where no noise model is used are demonstrated.
Hybrid Feedforward-Feedback Noise Control Using Virtual Sensors
Bean, Jacob; Fuller, Chris; Schiller, Noah
2016-01-01
Several approaches to active noise control using virtual sensors are evaluated for eventual use in an active headrest. Specifically, adaptive feedforward, feedback, and hybrid control structures are compared. Each controller incorporates the traditional filtered-x least mean squares algorithm. The feedback controller is arranged in an internal model configuration to draw comparisons with standard feedforward control theory results. Simulation and experimental results are presented that illustrate each controllers ability to minimize the pressure at both physical and virtual microphone locations. The remote microphone technique is used to obtain pressure estimates at the virtual locations. It is shown that a hybrid controller offers performance benefits over the traditional feedforward and feedback controllers. Stability issues associated with feedback and hybrid controllers are also addressed. Experimental results show that 15-20 dB reduction in broadband disturbances can be achieved by minimizing the measured pressure, whereas 10-15 dB reduction is obtained when minimizing the estimated pressure at a virtual location.
DeMarse, Thomas B; Pan, Liangbin; Alagapan, Sankaraleengam; Brewer, Gregory J; Wheeler, Bruce C
2016-01-01
Transient propagation of information across neuronal assembles is thought to underlie many cognitive processes. However, the nature of the neural code that is embedded within these transmissions remains uncertain. Much of our understanding of how information is transmitted among these assemblies has been derived from computational models. While these models have been instrumental in understanding these processes they often make simplifying assumptions about the biophysical properties of neurons that may influence the nature and properties expressed. To address this issue we created an in vitro analog of a feed-forward network composed of two small populations (also referred to as assemblies or layers) of living dissociated rat cortical neurons. The populations were separated by, and communicated through, a microelectromechanical systems (MEMS) device containing a strip of microscale tunnels. Delayed culturing of one population in the first layer followed by the second a few days later induced the unidirectional growth of axons through the microtunnels resulting in a primarily feed-forward communication between these two small neural populations. In this study we systematically manipulated the number of tunnels that connected each layer and hence, the number of axons providing communication between those populations. We then assess the effect of reducing the number of tunnels has upon the properties of between-layer communication capacity and fidelity of neural transmission among spike trains transmitted across and within layers. We show evidence based on Victor-Purpura's and van Rossum's spike train similarity metrics supporting the presence of both rate and temporal information embedded within these transmissions whose fidelity increased during communication both between and within layers when the number of tunnels are increased. We also provide evidence reinforcing the role of synchronized activity upon transmission fidelity during the spontaneous synchronized
Laser-excited photoluminescence of three-layer GaAs double-heterostructure laser material
International Nuclear Information System (INIS)
Nash, F.R.; Dixon, R.W.; Barnes, P.A.; Schumaker, N.E.
1975-01-01
The successful fabrication of high-quality DH GaAs lasers from a simplified three-layer structure is reported. A major asset of this structure is the transparency of its final layer to recombination radiation occurring in the active layer, thus permitting the use of nondestructive photoluminescent techniques for material evaluation prior to device fabrication. In the course of photoluminescence investigations on this material the additional important observation has been made that indirect excitation (in which photocarriers are generated in the top ternary layer) has significant advantages over direct excitation (in which photocarriers are generated directly in the active layer). These include (i) the direct measurement of Al concentrations in both upper layers, (ii) the measurements of the minority-carrier diffusion length in the upper layer, (iii) an easily obtained indication of taper in the thickness of the upper layer, and (iv) surprisingly effective excitation of the active layer. By combining direct and indirect excitation it is shown that a clearer understanding of the location and detrimental influences of defects in the GaAs laser structure may be obtained. For example, the width of the region of reduced luminescence associated with many defects is found to be very excitation dependent and is confirmed to arise fr []m reduced active region luminescence. The photoluminescent excitation techniques described should be useful in the study of other heterostructure devices and material systems
Feasibility study of a new unsaturated three-layer landfill cover system
Directory of Open Access Journals (Sweden)
Coo Jason Lim
2016-01-01
Full Text Available As an improvement of the two-layer cover with capillary barrier effect (CCBE (i.e. fine-grained soil overlying a coarse-grained soil, a new three-layer landfill cover system is proposed and investigated for humid climate. This new system is to add a fine-grained soil (i.e., clay underneath a two-layer CCBE (i.e., a silt overlying a gravelly sand layer. The feasibility of this proposed cover system was investigated by conducting a one-dimensional water infiltration test. In addition, transient seepage simulations were carried out to back-analyse the test results and investigate the importance of hydraulic properties of the CCBE on the proposed cover. Based on the infiltration experiment and numerical back-analysis, it is found that no percolation was observed after 48 hours of ponding, which is equivalent to a rainfall return period of greater than 1000 years. However, the upper two-layer CCBE is only effective for a rainfall return period of about 35 years. This implies that the proposed bottom clay layer is needed for humid climate. Numerical parametric simulations reveal that increasing the saturated permeability of the upper fine-grained soil by two orders of magnitude (1.4x10-6 m/s to 2.1x10-4 m/s, the wetting front is still within the clay layer after 12 hours of constant water ponding (>1000 year rainfall and no percolation occurred.
A three-layer magnetic shielding for the MAIUS-1 mission on a sounding rocket
Energy Technology Data Exchange (ETDEWEB)
Kubelka-Lange, André, E-mail: andre.kubelka@zarm.uni-bremen.de; Herrmann, Sven; Grosse, Jens; Lämmerzahl, Claus [Center of Applied Space Technology and Microgravity (ZARM), University of Bremen, Am Fallturm, 28359 Bremen (Germany); Rasel, Ernst M. [Institut für Quantenoptik, Leibniz Universität Hannover, Welfengarten 1, 30167 Hannover (Germany); Braxmaier, Claus [Center of Applied Space Technology and Microgravity (ZARM), University of Bremen, Am Fallturm, 28359 Bremen (Germany); DLR Institute for Space Systems, Robert-Hooke-Str. 7, 28359 Bremen (Germany)
2016-06-15
Bose-Einstein-Condensates (BECs) can be used as a very sensitive tool for experiments on fundamental questions in physics like testing the equivalence principle using matter wave interferometry. Since the sensitivity of these experiments in ground-based environments is limited by the available free fall time, the QUANTUS project started to perform BEC interferometry experiments in micro-gravity. After successful campaigns in the drop tower, the next step is a space-borne experiment. The MAIUS-mission will be an atom-optical experiment that will show the feasibility of experiments with ultra-cold quantum gases in microgravity in a sounding rocket. The experiment will create a BEC of 10{sup 5} {sup 87}Rb-atoms in less than 5 s and will demonstrate application of basic atom interferometer techniques over a flight time of 6 min. The hardware is specifically designed to match the requirements of a sounding rocket mission. Special attention is thereby spent on the appropriate magnetic shielding from varying magnetic fields during the rocket flight, since the experiment procedures are very sensitive to external magnetic fields. A three-layer magnetic shielding provides a high shielding effectiveness factor of at least 1000 for an undisturbed operation of the experiment. The design of this magnetic shielding, the magnetic properties, simulations, and tests of its suitability for a sounding rocket flight are presented in this article.
Directory of Open Access Journals (Sweden)
Yuriy Goykhman
2012-01-01
Full Text Available A solution to the inverse problem for a three-layer medium with nonsmooth boundaries, representing a large class of natural subsurface structures, is developed in this paper using simulated radar data. The retrieval of the layered medium parameters is accomplished as a sequential nonlinear optimization starting from the top layer and progressively characterizing the layers below. The optimization process is achieved by an iterative technique built around the solution of the forward scattering problem. The forward scattering process is formulated by using the extended boundary condition method (EBCM and constructing reflection and transmission matrices for each interface. These matrices are then combined into the generalized scattering matrix for the entire system, from which radar scattering coefficients are then computed. To be efficiently utilized in the inverse problem, the forward scattering model is simulated over a wide range of unknowns to obtain a complete set of subspace-based equivalent closed-form models that relate radar backscattering coefficients to the sought-for parameters including dielectric constants of each layer and separation of the layers. The inversion algorithm is implemented as a modified conjugate-gradient-based nonlinear optimization. It is shown that this technique results in accurate retrieval of surface and subsurface parameters, even in the presence of noise.
Artificial neural network-aided image analysis system for cell counting.
Sjöström, P J; Frydel, B R; Wahlberg, L U
1999-05-01
In histological preparations containing debris and synthetic materials, it is difficult to automate cell counting using standard image analysis tools, i.e., systems that rely on boundary contours, histogram thresholding, etc. In an attempt to mimic manual cell recognition, an automated cell counter was constructed using a combination of artificial intelligence and standard image analysis methods. Artificial neural network (ANN) methods were applied on digitized microscopy fields without pre-ANN feature extraction. A three-layer feed-forward network with extensive weight sharing in the first hidden layer was employed and trained on 1,830 examples using the error back-propagation algorithm on a Power Macintosh 7300/180 desktop computer. The optimal number of hidden neurons was determined and the trained system was validated by comparison with blinded human counts. System performance at 50x and lO0x magnification was evaluated. The correlation index at 100x magnification neared person-to-person variability, while 50x magnification was not useful. The system was approximately six times faster than an experienced human. ANN-based automated cell counting in noisy histological preparations is feasible. Consistent histology and computer power are crucial for system performance. The system provides several benefits, such as speed of analysis and consistency, and frees up personnel for other tasks.
Detection of malfunctions in the secondary system of a nuclear power plant by neural networks
International Nuclear Information System (INIS)
Carlos, S.; Zio, E.
2005-01-01
In nuclear power systems the early identification of transients caused by malfunctions is of great importance for preventing the development of serious accidents and performing adequate operation and maintenance practice. For this reason, various plant system parameters are monitored to provide information about the systems state. This information can be used to detect and classify the transients that occur inadvertently in a nuclear system. In this paper, a neural network methodology is developed which exploits the information provided by the online monitoring of different variables for classifying transients that can occur in the secondary system of a boiling water reactor (BWR). The initiating events of the transients in the scope of this work consist of leakages, of different sizes, performed in different locations of the secondary system. Each initiating event considered defines a class of transients which can be identified by analyzing the evolution in time of a group of variables monitored. In this work a three layered feed-forward neural network has been trained to assign an integer value, corresponding to the class of transient number, as output when the neural network is fed with the evolution of different variables of the system monitored online. This methodology has been applied to the identification of transient classes using data provided by the simulator HAMBO. This simulator has been developed to reproduce the behaviour of Forsmark nuclear power plant. Five classes of transients were considered, corresponding to leakages in different locations of the secondary system, and the evolution of ten variables, corresponding to temperatures and level positions of different control valves has been monitored. Using this information, the network was trained, and the trained system has been successful in classifying new transients belonging to any of the classes considered and also in identifying as ''un-known'' transients belonging to other classes not
Shakiba, Mohammad; Parson, Nick; Chen, X-Grant
2016-06-30
The hot deformation behavior of Al-0.12Fe-0.1Si alloys with varied amounts of Cu (0.002-0.31 wt %) was investigated by uniaxial compression tests conducted at different temperatures (400 °C-550 °C) and strain rates (0.01-10 s -1 ). The results demonstrated that flow stress decreased with increasing deformation temperature and decreasing strain rate, while flow stress increased with increasing Cu content for all deformation conditions studied due to the solute drag effect. Based on the experimental data, an artificial neural network (ANN) model was developed to study the relationship between chemical composition, deformation variables and high-temperature flow behavior. A three-layer feed-forward back-propagation artificial neural network with 20 neurons in a hidden layer was established in this study. The input parameters were Cu content, temperature, strain rate and strain, while the flow stress was the output. The performance of the proposed model was evaluated using the K-fold cross-validation method. The results showed excellent generalization capability of the developed model. Sensitivity analysis indicated that the strain rate is the most important parameter, while the Cu content exhibited a modest but significant influence on the flow stress.
Directory of Open Access Journals (Sweden)
Y. Srinivas
2012-09-01
Full Text Available The applications of intelligent techniques have increased exponentially in recent days to study most of the non-linear parameters. In particular, the behavior of earth resembles the non-linearity applications. An efficient tool is needed for the interpretation of geophysical parameters to study the subsurface of the earth. Artificial Neural Networks (ANN perform certain tasks if the structure of the network is modified accordingly for the purpose it has been used. The three most robust networks were taken and comparatively analyzed for their performance to choose the appropriate network. The single-layer feed-forward neural network with the back propagation algorithm is chosen as one of the well-suited networks after comparing the results. Initially, certain synthetic data sets of all three-layer curves have been taken for training the network, and the network is validated by the field datasets collected from Tuticorin Coastal Region (78°7′30"E and 8°48′45"N, Tamil Nadu, India. The interpretation has been done successfully using the corresponding learning algorithm in the present study. With proper training of back propagation networks, it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data concerning the synthetic data trained earlier in the appropriate network. The network is trained with more Vertical Electrical Sounding (VES data, and this trained network is demonstrated by the field data. Groundwater table depth also has been modeled.
Three-layer GSO depth-of-interaction detector for high-energy gamma camera
Yamamoto, S.; Watabe, H.; Kawachi, N.; Fujimaki, S.; Kato, K.; Hatazawa, J.
2014-04-01
Using Ce-doped Gd2SiO5 (GSO) of different Ce concentrations, three-layer DOI block detectors were developed to reduce the parallax error at the edges of a pinhole gamma camera for high-energy gamma photons. GSOs with Ce concentrations of 1.5 mol% (decay time ~40 ns), 0.5 mol% crystal (~60 ns), 0.4 mol% (~80 ns) were selected for the depth of interaction (DOI) detectors. These three types of GSOs were optically coupled in the depth direction, arranged in a 22×22 matrix and coupled to a flat panel photomultiplier tube (FP-PMT, Hamamatsu H8500). Sizes of these GSO cells were 1.9 mm×1.9 mm×4 mm, 1.9 mm×1.9 mm×5 mm, and 1.9 mm×1.9 mm×6 mm for 1.5 mol%, 0.5 mol%, and 0.4 mol%, respectively. With these combinations of GSOs, all spots corresponding to GSO cells were clearly resolved in the position histogram. Pulse shape spectra showed three peaks for these three decay times of GSOs. The block detector was contained in a 2-cm-thick tungsten shield, and a pinhole collimator with a 0.5-mm aperture was mounted. With pulse shape discrimination, we separated the point source images of the Cs-137 for each DOI layer. The point source image of the lower layer was detected at the most central part of the field-of-view, and the distribution was the smallest. The point source image of the higher layer was detected at the most peripheral part of the field-of-view, and the distribution was widest. With this information, the spatial resolution of the pinhole gamma camera can be improved. We conclude that DOI detection is effective for pinhole gamma cameras for high energy gamma photons.
Analysis of landing behaviour of three layer lines on different perch designs.
Scholz, B; Kjaer, J B; Schrader, L
2014-01-01
1. The prevalence of keel bone deformities in laying hens is high and is partly associated with unsuitable perch designs, which impose a risk of injury due to an unstable footing. 2. Over two experiments, 9 or 10 hens of each of three layer lines (Lohmann Selected Leghorn (LSL), Lohmann Tradition (LT) and Lohmann Brown (LB)) were filmed while landing on three different perch types, including steel perches of various diameters, a commercial mushroom-shaped plastic perch and a newly developed prototype perch with a soft surface material. 3. Data on landing behaviour (safe vs. unsafe or failed landing) following downward jumps were collected for 25, 50 and 60 cm vertical distances and 75 cm horizontal distance between a wooden start perch and the different destination perches. 4. The highest proportion of safe landings occurred on the prototype perch, whereas least safe landings were observed on steel perches, irrespective of their diameter. The mushroom-shaped perch was intermediate with regard to the safeness of landing. 5. A threshold of 50 cm vertical distance (34° slope) was identified as the optimum for downward jumps on perches in order to reduce the risk of unsafe or failed landings. Above this threshold, the proportion of safe landings declined significantly. 6. Brown shell layer types (LB and LT) had a lower proportion of safe landings compared to the white shell layer type (LSL), whereas no difference was found between LB and LT layer lines. 7. Although steel perches prevail in commercial housing, these perches were found to be least advantageous with regard to landing behaviour. The prototype perch provided the most stable footing on perching and is a promising alternative to replace commercial steel perches, thus helping to reduce the risk of perch-related keel bone injury.
International Nuclear Information System (INIS)
Ekomasov, E.G.; Murtazin, R.R.; Nazarov, V.N.
2015-01-01
The generation and evolution of magnetic inhomogeneities, emerging in a thin flat layer with the parameters of the magnetic anisotropy and exchange interaction, with the parameters different from other two thick layers of the three-layer ferromagnetic structure, were investigated. The parameters ranges that determine the possibility of their existence were found. The possibility of the external magnetic field influence on the structure and dynamic properties of localized magnetic inhomogeneities was shown. - Highlights: • The generation of magnetic inhomogeneities in the three-layer ferromagnetic. • The influence of an external field on the parameters of magnetic inhomogeneities. • Numerical study of the structure and dynamics of magnetic inhomogeneities
Directory of Open Access Journals (Sweden)
Abdul Ghafar Shah
2012-01-01
Full Text Available Vibrations of a cylindrical shell composed of three layers of different materials resting on elastic foundations are studied out. This configuration is formed by three layers of material in thickness direction where the inner and outer layers are of isotropic materials and the middle is of functionally graded material. Love shell dynamical equations are considered to describe the vibration problem. The expressions for moduli of the Winkler and Pasternak foundations are combined with the shell dynamical equations. The wave propagation approach is used to solve the present shell problem. A number of comparisons of numerical results are performed to check the validity and accuracy of the present approach.
Directory of Open Access Journals (Sweden)
Cheng-Te Wang
Full Text Available Recent physiological studies have shown that neurons in various regions of the central nervous systems continuously receive noisy excitatory and inhibitory synaptic inputs in a balanced and covaried fashion. While this balanced synaptic input (BSI is typically described in terms of maintaining the stability of neural circuits, a number of experimental and theoretical studies have suggested that BSI plays a proactive role in brain functions such as top-down modulation for executive control. Two issues have remained unclear in this picture. First, given the noisy nature of neuronal activities in neural circuits, how do the modulatory effects change if the top-down control implements BSI with different ratios between inhibition and excitation? Second, how is a top-down BSI realized via only excitatory long-range projections in the neocortex? To address the first issue, we systematically tested how the inhibition/excitation ratio affects the accuracy and reaction times of a spiking neural circuit model of perceptual decision. We defined an energy function to characterize the network dynamics, and found that different ratios modulate the energy function of the circuit differently and form two distinct functional modes. To address the second issue, we tested BSI with long-distance projection to inhibitory neurons that are either feedforward or feedback, depending on whether these inhibitory neurons do or do not receive inputs from local excitatory cells, respectively. We found that BSI occurs in both cases. Furthermore, when relying on feedback inhibitory neurons, through the recurrent interactions inside the circuit, BSI dynamically and automatically speeds up the decision by gradually reducing its inhibitory component in the course of a trial when a decision process takes too long.
Pilot-aided feedforward data recovery in optical coherent communications
Qi, Bing
2017-09-19
A method and a system for pilot-aided feedforward data recovery are provided. The method and system include a receiver including a strong local oscillator operating in a free running mode independent of a signal light source. The phase relation between the signal light source and the local oscillator source is determined based on quadrature measurements on pilot pulses from the signal light source. Using the above phase relation, information encoded in an incoming signal can be recovered, optionally for use in communication with classical coherent communication protocols and quantum communication protocols.
Three-layer GSO depth-of-interaction detector for high-energy gamma camera
Energy Technology Data Exchange (ETDEWEB)
Yamamoto, S., E-mail: s-yama@met.nagoya-u.ac.jp [Department of Radiological and Medical Laboratory Sciences, Nagoya University Graduate School of Medicine, 1-1-20 Daiko-Minami, Higashi-ku, Nagoya 461-8673 (Japan); Watabe, H. [Department of Molecular Imaging, Osaka University Graduate School of Medicine, Osaka (Japan); Kawachi, N.; Fujimaki, S. [Radiotracer Imaging Group, Japan Atomic Energy Agency, Takasaki (Japan); Kato, K. [Department of Radiological and Medical Laboratory Sciences, Nagoya University Graduate School of Medicine, 1-1-20 Daiko-Minami, Higashi-ku, Nagoya 461-8673 (Japan); Hatazawa, J. [Department of Molecular Imaging, Osaka University Graduate School of Medicine, Osaka (Japan); Department of Nuclear Medicine and Tracer Kinetics, Osaka University Graduate School of Medicine, Osaka (Japan)
2014-04-11
Using Ce-doped Gd{sub 2}SiO{sub 5} (GSO) of different Ce concentrations, three-layer DOI block detectors were developed to reduce the parallax error at the edges of a pinhole gamma camera for high-energy gamma photons. GSOs with Ce concentrations of 1.5 mol% (decay time ∼40 ns), 0.5 mol% crystal (∼60 ns), 0.4 mol% (∼80 ns) were selected for the depth of interaction (DOI) detectors. These three types of GSOs were optically coupled in the depth direction, arranged in a 22×22 matrix and coupled to a flat panel photomultiplier tube (FP-PMT, Hamamatsu H8500). Sizes of these GSO cells were 1.9 mm×1.9 mm×4 mm, 1.9 mm×1.9 mm×5 mm, and 1.9 mm×1.9 mm×6 mm for 1.5 mol%, 0.5 mol%, and 0.4 mol%, respectively. With these combinations of GSOs, all spots corresponding to GSO cells were clearly resolved in the position histogram. Pulse shape spectra showed three peaks for these three decay times of GSOs. The block detector was contained in a 2-cm-thick tungsten shield, and a pinhole collimator with a 0.5-mm aperture was mounted. With pulse shape discrimination, we separated the point source images of the Cs-137 for each DOI layer. The point source image of the lower layer was detected at the most central part of the field-of-view, and the distribution was the smallest. The point source image of the higher layer was detected at the most peripheral part of the field-of-view, and the distribution was widest. With this information, the spatial resolution of the pinhole gamma camera can be improved. We conclude that DOI detection is effective for pinhole gamma cameras for high energy gamma photons.
Potential Vorticity Asymmetries and Tropical Cyclone Evolution in a Moist Three-Layer Model.
Shapiro, Lloyd J.
2000-11-01
The role of potential vorticity (PV) asymmetries in the evolution of a tropical cyclone is investigated using a three-layer model that includes boundary layer friction, surface moisture fluxes, and a convergence-based convective parameterization. In a benchmark experiment, a symmetric vortex is first spun up on an f plane for 24 h. The symmetric vortex has a realistic structure, including a local PV maximum inside its radius of maximum wind (RMW). A weak azimuthal-wavenumber 2 PV asymmetry confined to the lower two layers of the model is then added to the vortex near the RMW. After an additional 2 h (for a total 26-h simulation), the asymmetric PV anomaly produces changes in the symmetric vortex that have significant differences from those in dry experiments with the present model or previous barotropic studies. A diagnosis of the contributions to changes in the symmetric wind tendency due to the asymmetry confirm the dominance of horizontal eddy fluxes at early times. The barotropic eddy kick provided by the anomaly lasts 2 h, which is the damping timescale for the disturbance.Additional experiments with an imposed isolated double-PV anomaly are made. Contrary to expectation from the dry experiments or barotropic studies, based on arguments involving `wave activity,' moving the anomaly closer to the center of the vortex or farther out does not change the overall evolution of the symmetric vortex. The physical mechanism responsible for the differences between the barotropic studies and those including moist physics as well as for the robustness of the response is established using a budget for the asymmetric vorticity. It is shown that the interactions between the asymmetries and the symmetric hurricane vortex at early times depend on realistic features of the model hurricane and not on interactions between the asymmetries and the boundary layer, which possibly depend on the convective parameterization. In particular, the changes in the symmetric wind tendency due
Production of high-performance three-layer emitters of X-ray tube cathodes by diffusion welding
Golovin, N. A.; Taubin, M. L.; Chesnokov, D. A.; Kiselev, D. S.
2018-02-01
The paper presents the description of the investigation of x-ray tube cathode emitters made of refractory metals by diffusion welding. The weld seam structure has been analyzed. Comparison of the emissivity characteristics of three-layer Ta-W-Ta and Nb-W-Nb cathode emitters has been made.
TEKNIK JARINGAN SYARAF TIRUAN FEEDFORWARD UNTUK PREDIKSI HARGA SAHAM PADA PASAR MODAL INDONESIA
Directory of Open Access Journals (Sweden)
Budi Bambang DP.
1999-01-01
Full Text Available To predict the condition of stock price, several technical analysis models have been used and expanded such as MACD, Fourier Transform, Accumulator Swing Index , Stochastic Oscillator etc. For input they are using the various prices such as Open, high, low , close , volume, BID, ASK price, and the output is a graphic that shows the decision whether to sell, buy or hold. Another method to determine the stock price by using Fundamental Analysis method. Fundamental method is an analysis that is based on the ratio or financial report from the existing company. Neural Network System Technology has been implemented in various applications especially in introduce the pattern. This power has attracted several people to use Neural Network for medical, Finance, Investment and marketing. Assuming that the prediction of the output system (next output prediction is deterministic, than the suitable N.N model to predict it is Feed Forward. The prediction of the stock price is the complex interaction between unstable market and unknown random processes factor. The data from stock price can be determined by time series. If we have daily data from a certain period, for example : Xt(t = 1,2,... than the stock price for the next period (t+h can be predicted (the timing used can be in hourly, daily, weekly, monthly or yearly. To get the good prediction, the inputs from several aspects of the share prices have to be input in Neural Network after that the weighing principal can be adapted to minimize the wrong prediction in the first future steps. By using the final weighing, an action is done to done to minimize the total error in the second future steps. Due to that, the risk of Investor's decision to sell or buy the stock can be minimized. This paper will discuss on how to use and implement Time Series Neural Network to predict the stock market in Semen Gresik (SMGR and Gudang Garam (GGRM Abstract in Bahasa Indonesia : Dalam memprediksi suatu kondisi harga saham
Directory of Open Access Journals (Sweden)
Denggui Fan
2017-07-01
Full Text Available The mechanisms underlying electrophysiologically observed two-way transitions between absence and tonic-clonic epileptic seizures in cerebral cortex remain unknown. The interplay within thalamocortical network is believed to give rise to these epileptic multiple modes of activity and transitions between them. In particular, it is thought that in some areas of cortex there exists feedforward inhibition from specific relay nucleus of thalamus (TC to inhibitory neuronal population (IN which has even more stronger functions on cortical activities than the known feedforward excitation from TC to excitatory neuronal population (EX. Inspired by this, we proposed a modified computational model by introducing feedforward inhibitory connectivity within thalamocortical circuit, to systematically investigate the combined effects of feedforward inhibition and excitation on transitions of epileptic seizures. We first found that the feedforward excitation can induce the transition from tonic oscillation to spike and wave discharges (SWD in cortex, i.e., the epileptic tonic-absence seizures, with the fixed weak feedforward inhibition. Thereinto, the phase of absence seizures corresponding to strong feedforward excitation can be further transformed into the clonic oscillations with the increasing of feedforward inhibition, representing the epileptic absence-clonic seizures. We also observed the other fascinating dynamical states, such as periodic 2/3/4-spike and wave discharges, reversed SWD and clonic oscillations, as well as saturated firings. More importantly, we can identify the stable parameter regions representing the tonic-clonic oscillations and SWD discharges of epileptic seizures on the 2-D plane composed of feedforward inhibition and excitation, where the physiologically plausible transition pathways between tonic-clonic and absence seizures can be figured out. These results indicate the functional role of feedforward pathways in controlling epileptic
A Robust Feedforward Model of the Olfactory System.
Directory of Open Access Journals (Sweden)
Yilun Zhang
2016-04-01
Full Text Available Most natural odors have sparse molecular composition. This makes the principles of compressed sensing potentially relevant to the structure of the olfactory code. Yet, the largely feedforward organization of the olfactory system precludes reconstruction using standard compressed sensing algorithms. To resolve this problem, recent theoretical work has shown that signal reconstruction could take place as a result of a low dimensional dynamical system converging to one of its attractor states. However, the dynamical aspects of optimization slowed down odor recognition and were also found to be susceptible to noise. Here we describe a feedforward model of the olfactory system that achieves both strong compression and fast reconstruction that is also robust to noise. A key feature of the proposed model is a specific relationship between how odors are represented at the glomeruli stage, which corresponds to a compression, and the connections from glomeruli to third-order neurons (neurons in the olfactory cortex of vertebrates or Kenyon cells in the mushroom body of insects, which in the model corresponds to reconstruction. We show that should this specific relationship hold true, the reconstruction will be both fast and robust to noise, and in particular to the false activation of glomeruli. The predicted connectivity rate from glomeruli to third-order neurons can be tested experimentally.
Modeling and inverse feedforward control for conducting polymer actuators with hysteresis
International Nuclear Information System (INIS)
Wang, Xiangjiang; Alici, Gursel; Tan, Xiaobo
2014-01-01
Conducting polymer actuators are biocompatible with a small footprint, and operate in air or liquid media under low actuation voltages. This makes them excellent actuators for macro- and micro-manipulation devices, however, their positioning ability or accuracy is adversely affected by their hysteresis non-linearity under open-loop control strategies. In this paper, we establish a hysteresis model for conducting polymer actuators, based on a rate-independent hysteresis model known as the Duhem model. The hysteresis model is experimentally identified and integrated with the linear dynamics of the actuator. This combined model is inverted to control the displacement of the tri-layer actuators considered in this study, without using any external feedback. The inversion requires an inverse hysteresis model which was experimentally identified using an inverse neural network model. Experimental results show that the position tracking errors are reduced by more than 50% when the hysteresis inverse model is incorporated into an inversion-based feedforward controller, indicating the potential of the proposed method in enabling wider use of such smart actuators. (paper)
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...
Self-tuning MIMO disturbance feedforward control for active hard-mounted vibration isolators
Beijen, M.A.; Heertjes, M.F.; Van Dijk, J.; Hakvoort, W. B.J.
2018-01-01
© 2017 Elsevier Ltd This paper proposes a multi-input multi-output (MIMO) disturbance feedforward controller to improve the rejection of floor vibrations in active vibration isolation systems for high-precision machinery. To minimize loss of performance due to model uncertainties, the feedforward
An artificial neural network to predict resting energy expenditure in obesity.
Disse, Emmanuel; Ledoux, Séverine; Bétry, Cécile; Caussy, Cyrielle; Maitrepierre, Christine; Coupaye, Muriel; Laville, Martine; Simon, Chantal
2017-09-01
The resting energy expenditure (REE) determination is important in nutrition for adequate dietary prescription. The gold standard i.e. indirect calorimetry is not available in clinical settings. Thus, several predictive equations have been developed, but they lack of accuracy in subjects with extreme weight including obese populations. Artificial neural networks (ANN) are useful predictive tools in the area of artificial intelligence, used in numerous clinical fields. The aim of this study was to determine the relevance of ANN in predicting REE in obesity. A Multi-Layer Perceptron (MLP) feed-forward neural network with a back propagation algorithm was created and cross-validated in a cohort of 565 obese subjects (BMI within 30-50 kg m -2 ) with weight, height, sex and age as clinical inputs and REE measured by indirect calorimetry as output. The predictive performances of ANN were compared to those of 23 predictive REE equations in the training set and in two independent sets of 100 and 237 obese subjects for external validation. Among the 23 established prediction equations for REE evaluated, the Harris & Benedict equations recalculated by Roza were the most accurate for the obese population, followed by the USA DRI, Müller and the original Harris & Benedict equations. The final 5-fold cross-validated three-layer 4-3-1 feed-forward back propagation ANN model developed in that study improved precision and accuracy of REE prediction over linear equations (precision = 68.1%, MAPE = 8.6% and RMSPE = 210 kcal/d), independently from BMI subgroups within 30-50 kg m -2 . External validation confirmed the better predictive performances of ANN model (precision = 73% and 65%, MAPE = 7.7% and 8.6%, RMSPE = 187 kcal/d and 200 kcal/d in the 2 independent datasets) for the prediction of REE in obese subjects. We developed and validated an ANN model for the prediction of REE in obese subjects that is more precise and accurate than established REE predictive
THE CALCULATION OF STRESS-STRAIN STATE OF THREE-LAYER BEAM TAKING INTO ACCOUNT EDGE EFFECTS
Directory of Open Access Journals (Sweden)
Kh. M. Muselemov
2015-01-01
Full Text Available The work is dedicated to the calculation of the stress-strain state (SSS of the three-layer beam (TLB subject to boundary effects.In this paper, a system of differential equations of equilibrium of the threelayer beam. To solve these equations, it is necessary to know the 12 boundary conditions, co-which depend on support conditions and loading of sandwich beams under study. This system of equations is solved by the application package of mathematical modeling "Maple 5.4." The solution of this system we obtain expressions for determining de-formations and stress all components (bearing layers and filler, a three-layer beam anywhere under specified conditions of fastening the ends of the beam and its loading.
Adaptive feedforward control of exhaust recirculation in large diesel engines
DEFF Research Database (Denmark)
Nielsen, Kræn Vodder; Blanke, Mogens; Eriksson, Lars
2017-01-01
Environmental concern has led the International Maritime Organization to restrict NO푥 emissions from marine diesel engines. Exhaust gas recirculation (EGR) systems have been introduced in order to comply to the new standards. Traditional fixed-gain feedback methods are not able to control the EGR...... is generalized to a class of first order Hammerstein systems with sensor delay and exponentially converging bounds of the control error are proven analytically. It is then shown how to apply the method to the EGR system of a two-stroke crosshead diesel engine. The controller is validated by closed loop...... system adequately in engine loading transients so alternative methods are needed. This paper presents the design, convergence proofs and experimental validation of an adaptive feedforward controller that significantly improves the performance in loading transients. First the control concept...
Quantum teleportation over 143 kilometres using active feed-forward
Ma, Xiaosong; Herbst, Thomas; Scheidl, Thomas; Wang, Daqing; Kropatschek, Sebastian; Naylor, William; Mech, Alexandra; Wittmann, Bernhard; Kofler, Johannes; Anisimova, Elena; Makarov, Vadim; Jennewein, Thomas; Ursin, Rupert; Zeilinger, Anton
2013-03-01
Quantum teleportation is a quintessential prerequisite of many quantum information processing protocols. By using quantum teleportation, one can circumvent the no-cloning theorem and faithfully transfer unknown quantum states to a party whose location is even unknown over arbitrary distances. Ever since the first experimental demonstrations of quantum teleportation of independent qubits and of squeezed states, researchers have progressively extended the communication distance in teleportation. Here we report the first long-distance quantum teleportation experiment with active feed-forward in real time. The experiment employed two optical links, quantum and classical, over 143 km free space between the two Canary Islands of La Palma and Tenerife. To achieve this, the experiment had to employ a combination of advanced techniques such as a frequency-uncorrelated polarization-entangled photon pair source, ultra-low-noise single-photon detectors, and entanglement-assisted clock synchronization. The average teleported state fidelity was well beyond the classical limit of 2/3.
Enhanced HMAX model with feedforward feature learning for multiclass categorization
Directory of Open Access Journals (Sweden)
Yinlin eLi
2015-10-01
Full Text Available In recent years, the interdisciplinary research between neuroscience and computer vision has promoted the development in both fields. Many biologically inspired visual models are proposed, and among them, the Hierarchical Max-pooling model (HMAX is a feedforward model mimicking the structures and functions of V1 to posterior inferotemporal (PIT layer of the primate visual cortex, which could generate a series of position- and scale- invariant features. However, it could be improved with attention modulation and memory processing, which are two important properties of the primate visual cortex. Thus, in this paper, based on recent biological research on the primate visual cortex, we still mimic the first 100-150 milliseconds of visual cognition to enhance the HMAX model, which mainly focuses on the unsupervised feedforward feature learning process. The main modifications are as follows: 1 To mimic the attention modulation mechanism of V1 layer, a bottom-up saliency map is computed in the S1 layer of the HMAX model, which can support the initial feature extraction for memory processing; 2 To mimic the learning, clustering and short-term memory to long-term memory conversion abilities of V2 and IT, an unsupervised iterative clustering method is used to learn clusters with multiscale middle level patches, which are taken as long-term memory; 3 Inspired by the multiple feature encoding mode of the primate visual cortex, information including color, orientation, and spatial position are encoded in different layers of the HMAX model progressively. By adding a softmax layer at the top of the model, multiclass categorization experiments can be conducted, and the results on Caltech101 show that the enhanced model with a smaller memory size exhibits higher accuracy than the original HMAX model, and could also achieve better accuracy than other unsupervised feature learning methods in multiclass categorization task.
PEAK TRACKING WITH A NEURAL NETWORK FOR SPECTRAL RECOGNITION
COENEGRACHT, PMJ; METTING, HJ; VANLOO, EM; SNOEIJER, GJ; DOORNBOS, DA
1993-01-01
A peak tracking method based on a simulated feed-forward neural network with back-propagation is presented. The network uses the normalized UV spectra and peak areas measured in one chromatogram for peak recognition. It suffices to train the network with only one set of spectra recorded in one
Bringing Interpretability and Visualization with Artificial Neural Networks
Gritsenko, Andrey
2017-01-01
Extreme Learning Machine (ELM) is a training algorithm for Single-Layer Feed-forward Neural Network (SLFN). The difference in theory of ELM from other training algorithms is in the existence of explicitly-given solution due to the immutability of initialed weights. In practice, ELMs achieve performance similar to that of other state-of-the-art…
Adaptive Regularization of Neural Networks Using Conjugate Gradient
DEFF Research Database (Denmark)
Goutte, Cyril; Larsen, Jan
1998-01-01
Andersen et al. (1997) and Larsen et al. (1996, 1997) suggested a regularization scheme which iteratively adapts regularization parameters by minimizing validation error using simple gradient descent. In this contribution we present an improved algorithm based on the conjugate gradient technique........ Numerical experiments with feedforward neural networks successfully demonstrate improved generalization ability and lower computational cost...
Artificial neural network approach for estimation of surface specific ...
Indian Academy of Sciences (India)
R. Narasimhan (Krishtel eMaging) 1461 1996 Oct 15 13:05:22
However, with the advent of satellite technology, there are unique and .... neurons. The neurons are connected by links in term of weights. Each neuron in one layer has direct connection to the neurons of the subsequent layer. .... The structure of 5 layers feed-forward neural network and the details of single neuron. with the ...
Recognition of decays of charged tracks with neural network techniques
International Nuclear Information System (INIS)
Stimpfl-Abele, G.
1991-01-01
We developed neural-network learning techniques for the recognition of decays of charged tracks using a feed-forward network with error back-propagation. Two completely different methods are described in detail and their efficiencies for several NN architectures are compared with conventional methods. Excellent results are obtained. (orig.)
Neural Classifier Construction using Regularization, Pruning
DEFF Research Database (Denmark)
Hintz-Madsen, Mads; Hansen, Lars Kai; Larsen, Jan
1998-01-01
In this paper we propose a method for construction of feed-forward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme, we derive a modified form of the entropic error measure and an algebraic estimate of the test error. In conjunctio...... with optimal brain damage pruning, a test error estimate is used to select the network architecture. The scheme is evaluated on four classification problems.......In this paper we propose a method for construction of feed-forward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme, we derive a modified form of the entropic error measure and an algebraic estimate of the test error. In conjunction...
Universal approximation in p-mean by neural networks
Burton, R.M; Dehling, H.G
A feedforward neural net with d input neurons and with a single hidden layer of n neurons is given by [GRAPHICS] where a(j), theta(j), w(ji) is an element of R. In this paper we study the approximation of arbitrary functions f: R-d --> R by a neural net in an L-p(mu) norm for some finite measure mu
Permutation parity machines for neural cryptography.
Reyes, Oscar Mauricio; Zimmermann, Karl-Heinz
2010-06-01
Recently, synchronization was proved for permutation parity machines, multilayer feed-forward neural networks proposed as a binary variant of the tree parity machines. This ability was already used in the case of tree parity machines to introduce a key-exchange protocol. In this paper, a protocol based on permutation parity machines is proposed and its performance against common attacks (simple, geometric, majority and genetic) is studied.
Simplified Learning Scheme For Analog Neural Network
Eberhardt, Silvio P.
1991-01-01
Synaptic connections adjusted one at a time in small increments. Simplified gradient-descent learning scheme for electronic neural-network processor less efficient than better-known back-propagation scheme, but offers two advantages: easily implemented in circuitry because data-access circuitry separated from learning circuitry; and independence of data-access circuitry makes possible to implement feedforward as well as feedback networks, including those of multiple-attractor type. Important in such applications as recognition of patterns.
Podder, M. S.; Majumder, C. B.
2017-11-01
An artificial neural network (ANN) model was developed to predict the phycoremediation efficiency of Chlorella pyrenoidosa for the removal of both As(III) and As(V) from synthetic wastewater based on 49 data-sets obtained from experimental study and increased the data using CSCF technique. The data were divided into training (60%) validation (20%) and testing (20%) sets. The data collected was used for training a three-layer feed-forward back propagation (BP) learning algorithm having 4-5-1 architecture. The model used tangent sigmoid transfer function at input to hidden layer ( tansing) while a linear transfer function ( purelin) was used at output layer. Comparison between experimental results and model results gave a high correlation coefficient (R allANN 2 equal to 0.99987 for both ions and exhibited that the model was able to predict the phycoremediation of As(III) and As(V) from wastewater. Experimental parameters influencing phycoremediation process like pH, inoculum size, contact time and initial arsenic concentration [either As(III) or As(V)] were investigated. A contact time of 168 h was mainly required for achieving equilibrium at pH 9.0 with an inoculum size of 10% (v/v). At optimum conditions, metal ion uptake enhanced with increasing initial metal ion concentration.
Neural networks for function approximation in nonlinear control
Linse, Dennis J.; Stengel, Robert F.
1990-01-01
Two neural network architectures are compared with a classical spline interpolation technique for the approximation of functions useful in a nonlinear control system. A standard back-propagation feedforward neural network and a cerebellar model articulation controller (CMAC) neural network are presented, and their results are compared with a B-spline interpolation procedure that is updated using recursive least-squares parameter identification. Each method is able to accurately represent a one-dimensional test function. Tradeoffs between size requirements, speed of operation, and speed of learning indicate that neural networks may be practical for identification and adaptation in a nonlinear control environment.
Modeling Broadband Microwave Structures by Artificial Neural Networks
Directory of Open Access Journals (Sweden)
V. Otevrel
2004-06-01
Full Text Available The paper describes the exploitation of feed-forward neural networksand recurrent neural networks for replacing full-wave numerical modelsof microwave structures in complex microwave design tools. Building aneural model, attention is turned to the modeling accuracy and to theefficiency of building a model. Dealing with the accuracy, we describea method of increasing it by successive completing a training set.Neural models are mutually compared in order to highlight theiradvantages and disadvantages. As a reference model for comparisons,approximations based on standard cubic splines are used. Neural modelsare used to replace both the time-domain numeric models and thefrequency-domain ones.
Lee S.-H.; Lee S.R.
2015-01-01
A multi-layered complex aluminum alloy was successfully fabricated by three-layer stack accumulative roll bonding(ARB) process. The ARB using AA1050 and AA5052 alloy sheets was performed up to 7 cycles at ambient temperature without lubrication. The specimen processed by the ARB showed a multi-layer aluminum alloy sheet in which two aluminum alloys are alternately stacked. The grain size of the specimen decreased with the number of ARB cycles, became about 350nm in diameter after 7cycles. The...
Design and regularization of neural networks: the optimal use of a validation set
DEFF Research Database (Denmark)
Larsen, Jan; Hansen, Lars Kai; Svarer, Claus
1996-01-01
We derive novel algorithms for estimation of regularization parameters and for optimization of neural net architectures based on a validation set. Regularisation parameters are estimated using an iterative gradient descent scheme. Architecture optimization is performed by approximative...... combinatorial search among the relevant subsets of an initial neural network architecture by employing a validation set based optimal brain damage/surgeon (OBD/OBS) or a mean field combinatorial optimization approach. Numerical results with linear models and feed-forward neural networks demonstrate...
Synchrony with shunting inhibition in a feedforward inhibitory network.
Talathi, Sachin S; Hwang, Dong-Uk; Carney, Paul R; Ditto, William L
2010-04-01
Recent experiments have shown that GABA(A) receptor mediated inhibition in adult hippocampus is shunting rather than hyperpolarizing. Simulation studies of realistic interneuron networks with strong shunting inhibition have been demonstrated to exhibit robust gamma band (20-80 Hz) synchrony in the presence of heterogeneity in the intrinsic firing rates of individual neurons in the network. In order to begin to understand how shunting can contribute to network synchrony in the presence of heterogeneity, we develop a general theoretical framework using spike time response curves (STRC's) to study patterns of synchrony in a simple network of two unidirectionally coupled interneurons (UCI network) interacting through a shunting synapse in the presence of heterogeneity. We derive an approximate discrete map to analyze the dynamics of synchronous states in the UCI network by taking into account the nonlinear contributions of the higher order STRC terms. We show how the approximate discrete map can be used to successfully predict the domain of synchronous 1:1 phase locked state in the UCI network. The discrete map also allows us to determine the conditions under which the two interneurons can exhibit in-phase synchrony. We conclude by demonstrating how the information from the study of the discrete map for the dynamics of the UCI network can give us valuable insight into the degree of synchrony in a larger feed-forward network of heterogeneous interneurons.
Adaptive Feed-Forward Control of Low Frequency Interior Noise
Kletschkowski, Thomas
2012-01-01
This book presents a mechatronic approach to Active Noise Control (ANC). It describes the required elements of system theory, engineering acoustics, electroacoustics and adaptive signal processing in a comprehensive, consistent and systematic manner using a unified notation. Furthermore, it includes a design methodology for ANC-systems, explains its application and describes tools to be used for ANC-system design. From the research point of view, the book presents new approaches to sound source localization in weakly damped interiors. One is based on the inverse finite element method, the other is based on a sound intensity probe with an active free field. Furthermore, a prototype of an ANC-system able to reach the physical limits of local (feed-forward) ANC is described. This is one example for applied research in ANC-system design. Other examples are given for (i) local ANC in a semi-enclosed subspace of an aircraft cargo hold and (ii) for the combination of audio entertainment with ANC.
Feed-forward regulation of microbisporicin biosynthesis in Microbispora corallina.
Foulston, Lucy; Bibb, Mervyn
2011-06-01
Lantibiotics are ribosomally synthesized, posttranslationally modified peptide antibiotics. Microbisporicin is a potent lantibiotic produced by the actinomycete Microbispora corallina and contains unique chlorinated tryptophan and dihydroxyproline residues. The biosynthetic gene cluster for microbisporicin encodes several putative regulatory proteins, including, uniquely, an extracytoplasmic function (ECF) σ factor, σ(MibX), a likely cognate anti-σ factor, MibW, and a potential helix-turn-helix DNA binding protein, MibR. Here we examine the roles of these proteins in regulating microbisporicin biosynthesis. S1 nuclease protection assays were used to determine transcriptional start sites in the microbisporicin gene cluster and confirmed the presence of the likely ECF sigma factor -10 and -35 sequences in five out of six promoters. In contrast, the promoter of mibA, encoding the microbisporicin prepropeptide, has a typical Streptomyces vegetative sigma factor consensus sequence. The ECF sigma factor σ(MibX) was shown to interact with the putative anti-sigma factor MibW in Escherichia coli using bacterial two-hybrid analysis. σ(MibX) autoregulates its own expression but does not directly regulate expression of mibA. On the basis of quantitative reverse transcriptase PCR (qRT-PCR) data, we propose a model for the biosynthesis of microbisporicin in which MibR functions as an essential master regulator and the ECF sigma factor/anti-sigma factor pair, σ(MibX)/MibW, induces feed-forward biosynthesis of microbisporicin and producer immunity.
Feedforward control of sound transmission using an active acoustic metamaterial
Cheer, Jordan; Daley, Stephen; McCormick, Cameron
2017-02-01
Metamaterials have received significant interest in recent years due to their potential ability to exhibit behaviour not found in naturally occurring materials. This includes the generation of band gaps, which are frequency regions with high levels of wave attenuation. In the context of acoustics, these band gaps can be tuned to occur at low frequencies where the acoustic wavelength is large compared to the material, and where the performance of traditional passive noise control treatments is limited. Therefore, such acoustic metamaterials have been shown to offer a significant performance advantage compared to traditional passive control treatments, however, due to their resonant behaviour, the band gaps tend to occur over a relatively narrow frequency range. A similar long wavelength performance advantage can be achieved using active noise control, but the systems in this case do not rely on resonant behaviour. This paper demonstrates how the performance of an acoustic metamaterial, consisting of an array of Helmholtz resonators, can be significantly enhanced by the integration of an active control mechanism that is facilitated by embedding loudspeakers into the resonators. Crucially, it is then also shown how the active acoustic metamaterial significantly outperforms an equivalent traditional active noise control system. In both cases a broadband feedforward control strategy is employed to minimise the transmitted pressure in a one-dimensional acoustic control problem and a new method of weighting the control effort over a targeted frequency range is described.
Why vision is not both hierarchical and feedforward
Directory of Open Access Journals (Sweden)
Michael H Herzog
2014-10-01
Full Text Available In classical models of object recognition, first, basic features (e.g., edges and lines are analyzed by independent filters that mimic the receptive field profiles of V1 neurons. In a feedforward fashion, the outputs of these filters are fed to filters at the next processing stage, pooling information across several filters from the previous level, and so forth at subsequent processing stages. Low-level processing determines high-level processing. Information lost on lower stages is irretrievably lost. Models of this type have proven to be very successful in many fields of vision, but have failed to explain object recognition in general. Here, we present experiments that, first, show that, similar to demonstrations from the Gestaltists, figural aspects determine low-level processing (as much as the other way around. Second, performance on a single element depends on all the other elements in the visual scene. Small changes in the overall configuration can lead to large changes in performance. Third, grouping of elements is key. Only if we know how elements group across the entire visual field, we can determine performance on individual elements, i.e., challenging the classical stereotypical filtering approach, which is at the very heart of most vision models.
Feedback and feedforward: Focal points for improving academic performance
Directory of Open Access Journals (Sweden)
María José García San Pedro
2012-09-01
Full Text Available The effective integration of competencies in university programmes follows a holistic and diversified assessment model and the educational potential development of students’ assessment results. This work questions: how are students informed about the results of their learning? Specifically, it aims to understand students’ and professors’ perspectives about the use of learning results and the strategies that are promoted in the practice of improved use of their educational potential. The results described are derived from a case study on 12 degree graduates adapted to the EEES. Although feedback and the feedfoward are strategies for informing students about their learning results, the results of the study show that their use is not entirely generalised and frequently only inform the grades obtained. Students identify the difference between knowing the grade and obtaining feedback. The relational dimension is also valued positively when students are informed about the results of their assessment. However, it seems that use of the educational potential is pending. The students say that the tutorials and the follow up through continual assessment helps to reduce failure. Also, the faculty identifies that reflection about the results obtained is very much linked to metacognitive reflection, although it is not generalised in practice. The students recognise the limitations and the work load involved for the professor to individually monitor them. The study is concluded with the need for systematically incorporating feedback and feedforward in teaching practices and offers guidelines for orienting these strategies towards improving academic performance.
Generalized single-hidden layer feedforward networks for regression problems.
Wang, Ning; Er, Meng Joo; Han, Min
2015-06-01
In this paper, traditional single-hidden layer feedforward network (SLFN) is extended to novel generalized SLFN (GSLFN) by employing polynomial functions of inputs as output weights connecting randomly generated hidden units with corresponding output nodes. The significant contributions of this paper are as follows: 1) a primal GSLFN (P-GSLFN) is implemented using randomly generated hidden nodes and polynomial output weights whereby the regression matrix is augmented by full or partial input variables and only polynomial coefficients are to be estimated; 2) a simplified GSLFN (S-GSLFN) is realized by decomposing the polynomial output weights of the P-GSLFN into randomly generated polynomial nodes and tunable output weights; 3) both P- and S-GSLFN are able to achieve universal approximation if the output weights are tuned by ridge regression estimators; and 4) by virtue of the developed batch and online sequential ridge ELM (BR-ELM and OSR-ELM) learning algorithms, high performance of the proposed GSLFNs in terms of generalization and learning speed is guaranteed. Comprehensive simulation studies and comparisons with standard SLFNs are carried out on real-world regression benchmark data sets. Simulation results demonstrate that the innovative GSLFNs using BR-ELM and OSR-ELM are superior to standard SLFNs in terms of accuracy, training speed, and structure compactness.
Marshall, Paul; Murphy, Bernadette
2006-01-01
To determine the incidence of delayed feed-forward activation (FFA) times in a group of healthy young males; to retest those subjects who showed delayed FFA after 6 months to determine the reliability of the measure in the absence of treatment or injury in the intervening period; and to determine the effect of sacroiliac joint manipulation on delayed FFA times. Ninety young males were assessed for the FFA of their deep abdominal muscles in relation to rapid upper limb movements. Those who met the criteria for delayed FFA (failure of deep abdominal activation within 50 milliseconds of deltoid activation) were then reassessed 6 months later. These subjects then underwent sacroiliac joint manipulation on the side demonstrating decreased joint movement during hip flexion and lateral flexion. Feed-forward activation times were then reassessed after joint manipulation. Seventeen (18.9%) of 90 subjects met the criteria of impaired FFA. Thirteen of 17 were available to be remeasured at 6-month follow-up. The intraclass correlation coefficient for FFA at this time was greater than 0.70 for all movement directions. There was a significant improvement (38.4%) in FFA times for this group when remeasured immediately after the sacroiliac joint manipulation. Delayed FFA is a highly reproducible measure at long-term follow-up. This technique appears to be a sensitive marker of the neural effects of sacroiliac joint manipulation. Future prospective studies are needed to determine if delayed FFA times are a marker for those at risk for developing back pain.
Short-Term Load Forecasting Model Based on Quantum Elman Neural Networks
Directory of Open Access Journals (Sweden)
Zhisheng Zhang
2016-01-01
Full Text Available Short-term load forecasting model based on quantum Elman neural networks was constructed in this paper. The quantum computation and Elman feedback mechanism were integrated into quantum Elman neural networks. Quantum computation can effectively improve the approximation capability and the information processing ability of the neural networks. Quantum Elman neural networks have not only the feedforward connection but also the feedback connection. The feedback connection between the hidden nodes and the context nodes belongs to the state feedback in the internal system, which has formed specific dynamic memory performance. Phase space reconstruction theory is the theoretical basis of constructing the forecasting model. The training samples are formed by means of K-nearest neighbor approach. Through the example simulation, the testing results show that the model based on quantum Elman neural networks is better than the model based on the quantum feedforward neural network, the model based on the conventional Elman neural network, and the model based on the conventional feedforward neural network. So the proposed model can effectively improve the prediction accuracy. The research in the paper makes a theoretical foundation for the practical engineering application of the short-term load forecasting model based on quantum Elman neural networks.
Noise-enhanced categorization in a recurrently reconnected neural network
Monterola, Christopher; Zapotocky, Martin
2005-03-01
We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails.
Noise-enhanced categorization in a recurrently reconnected neural network
International Nuclear Information System (INIS)
Monterola, Christopher; Zapotocky, Martin
2005-01-01
We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails
Image Restoration Technology Based on Discrete Neural network
Directory of Open Access Journals (Sweden)
Zhou Duoying
2015-01-01
Full Text Available With the development of computer science and technology, the development of artificial intelligence advances rapidly in the field of image restoration. Based on the MATLAB platform, this paper constructs a kind of image restoration technology of artificial intelligence based on the discrete neural network and feedforward network, and carries out simulation and contrast of the restoration process by the use of the bionic algorithm. Through the application of simulation restoration technology, this paper verifies that the discrete neural network has a good convergence and identification capability in the image restoration technology with a better effect than that of the feedforward network. The restoration technology based on the discrete neural network can provide a reliable mathematical model for this field.
2011-03-01
are made of three different meats (20 Beef, 17 “ Meat ”, & 17 Poultry ). The data set containing the following features: • $/oz • $/lb protein...structure in minimal training time. Data sets used include an XOR data set, Fisher’s iris data set, and a financial industry data set, among others. v...4.2.3. Finance Industry Data Set ...................................................................................................... 38 4.2.4. Hot
Feed-forward motor control of ultrafast, ballistic movements.
Kagaya, K; Patek, S N
2016-02-01
To circumvent the limits of muscle, ultrafast movements achieve high power through the use of springs and latches. The time scale of these movements is too short for control through typical neuromuscular mechanisms, thus ultrafast movements are either invariant or controlled prior to movement. We tested whether mantis shrimp (Stomatopoda: Neogonodactylus bredini) vary their ultrafast smashing strikes and, if so, how this control is achieved prior to movement. We collected high-speed images of strike mechanics and electromyograms of the extensor and flexor muscles that control spring compression and latch release. During spring compression, lateral extensor and flexor units were co-activated. The strike initiated several milliseconds after the flexor units ceased, suggesting that flexor activity prevents spring release and determines the timing of strike initiation. We used linear mixed models and Akaike's information criterion to serially evaluate multiple hypotheses for control mechanisms. We found that variation in spring compression and strike angular velocity were statistically explained by spike activity of the extensor muscle. The results show that mantis shrimp can generate kinematically variable strikes and that their kinematics can be changed through adjustments to motor activity prior to the movement, thus supporting an upstream, central-nervous-system-based control of ultrafast movement. Based on these and other findings, we present a shishiodoshi model that illustrates alternative models of control in biological ballistic systems. The discovery of feed-forward control in mantis shrimp sets the stage for the assessment of targets, strategic variation in kinematics and the role of learning in ultrafast animals. © 2016. Published by The Company of Biologists Ltd.
Directory of Open Access Journals (Sweden)
Djeison Cesar Batista
2007-06-01
Full Text Available This work evaluated the physical and mechanical properties of three-layer particleboard manufactured with Eucalyptus pellita bark and Pinus elliottii wood. The mechanical properties evaluated were static bending (modulus of rupture and modulus of elasticity and internal bonding, while physical ones were water absorption and thickness swelling. Three different bark and wood compositions in the core and on the layers were evaluated: one without bark and two with bark. It was even studied the addition or not of 1% of paraffin (over the particles dry weight, resulting in six treatments, each one with four repetitions. There were showed better results of MOR, MOE e LI among the treatments with bark and without paraffin than in those with bark and paraffin.
Directory of Open Access Journals (Sweden)
D. Llanwyn Jones
Full Text Available Formulas for computing the Cartesian components of the static (DC fields of horizontal electric dipoles ( HEDs and vertical electric dipoles ( VEDs located in the central zone of a three-layer horizontally stratified medium are derived and presented in a summary form suitable for immediate computation. Formulas are given for the electric and magnetic field components in the upper and central regions. In the general case the computation involves the summation of a convergent infinite series. For the particular case of an infinitely thick central region (corresponding to the two-layer problem, the analysis produces relatively simple closed-form equations for the field components which are suitable for a 'hand calculation'. Specimen calculations for dipoles in seawaters are included and the derived results are compared with computations made using an ac model.
Directory of Open Access Journals (Sweden)
D. Llanwyn Jones
1997-04-01
Full Text Available Formulas for computing the Cartesian components of the static (DC fields of horizontal electric dipoles ( HEDs and vertical electric dipoles ( VEDs located in the central zone of a three-layer horizontally stratified medium are derived and presented in a summary form suitable for immediate computation. Formulas are given for the electric and magnetic field components in the upper and central regions. In the general case the computation involves the summation of a convergent infinite series. For the particular case of an infinitely thick central region (corresponding to the two-layer problem, the analysis produces relatively simple closed-form equations for the field components which are suitable for a 'hand calculation'. Specimen calculations for dipoles in seawaters are included and the derived results are compared with computations made using an ac model.
TEM observation and study of three-layer Al2O3/ZrO2 ceramics.
Chen, Bei; Cheng, Chuan; Chen, Bin
2010-03-01
The micrograph and the crystal orientation relationship of Al2O3/ZrO2 laminated ceramics were studied with the help of transmission electronic microscope (TEM). The experiment results showed that: the Al2O3 and ZrO2 grain sizes were small and the links among the crystals were good. No flaws such as pores or micro-cracks were observed in the micro-structure. Further TEM analyses and electronic diffraction spot calculation proved that interface compressive stress could greatly restrain the transformation of the tetragonal phase and increase the contents of transformable tetragon, but did not change the orientation relation between the tetragonal and monoclinic phase, while (100),m//(010), still exist in the three-layer ZrO2 ceramics.
Three-layered polyplex as a microRNA targeted delivery system for breast cancer gene therapy
Li, Yan; Dai, Yu; Zhang, Xiaojin; Chen, Jihua
2017-07-01
MicroRNAs (miRNAs), small non-coding RNAs, play an important role in modulating cell proliferation, migration, and differentiation. Since miRNAs can regulate multiple cancer-related genes simultaneously, regulating miRNAs could target a set of related oncogenic genes or pathways. Owing to their reduced immune response and low toxicity, miRNAs with small size and low molecular weight have become increasingly promising therapeutic drugs in cancer therapy. However, one of the major challenges of miRNAs-based cancer therapy is to achieve specific, effective, and safe delivery of therapeutic miRNAs into cancer cells. Here we provide a strategy using three-layered polyplex with folic acid as a targeting group to systemically deliver miR-210 into breast cancer cells, which results in breast cancer growth being inhibited.
A Study on Internal Explosion Testing of the “Rigid-Flexible-Rigid” Three-Layer Sealed Structure
Directory of Open Access Journals (Sweden)
Y. L. Xue
2018-01-01
Full Text Available Multilayered combination of protective structures is an important means of effectively weakening the explosive shockwave. On this basis, a “rigid-flexible-rigid” three-layer sealed structure was proposed in this paper and two models for the sealed structure were designed. Meanwhile, internal explosion tests of the two models were conducted. One model used foam concrete as the energy absorbing material and the other used dense sand. The comparisons between the test results and the computed results obtained from the formulae were made, and the test results agreed well with the computed results. Test results showed that both models had favorable energy-dissipating capacity, and the model that used foam concrete as the energy absorbing material had a superior energy-dissipating capacity.
Satoh, Masahiro; Yoshino, Hiroyuki; Fujimura, Akira; Hitomi, Jiro; Isogai, Sumio
2016-09-01
When patients report pain in the popliteal fossa upon knee extension, the pain is usually localized in the lower region of the popliteal fossa. However, some patients complain of pain in the upper region of the popliteal fossa as the knee is flexed, which motivated us to examine the role of the popliteal fascia as the retinaculum of the hamstring muscles. Thirty-four thighs from 19 Japanese cadavers were dissected. The popliteal fascia was defined as the single aponeurotic sheet covering the popliteal fossa. We found that the fascia acted as a three-layered retinaculum for the flexor muscles of the thigh and provided a secure route for neurovascular structures to the lower leg in any kinetic position of the knee joint. The superficial layer of the popliteal fascia covering the thigh was strongly interwoven with the epimysium of biceps femoris along its lateral aspect and with that of the semimembranosus along its medial aspect, ensuring that the flexor muscles remained in their correct positions. The intermediate layer arose from the medial side of biceps femoris and merged medially with the superficial layer. The profound layer stretched transversely between the biceps femoris and the semimembranosus. Moreover, we investigated the nerve distribution in the popliteal fascia using Sihler's staining and whole-mount immunostaining for neurofilaments. The three-layered fascia was constantly innervated by branches from the posterior femoral cutaneous or saphenous nerve. The nerves were closely related and distributed to densely packed collagen fibers in the superficial layer as free or encapsulated nerve endings, suggesting that the fascia is involved in pain in the upper region of the popliteal fossa.
The role of feed-forward and feedback processes for closed-loop prosthesis control
Directory of Open Access Journals (Sweden)
Saunders Ian
2011-10-01
Full Text Available Abstract Background It is widely believed that both feed-forward and feed-back mechanisms are required for successful object manipulation. Open-loop upper-limb prosthesis wearers receive no tactile feedback, which may be the cause of their limited dexterity and compromised grip force control. In this paper we ask whether observed prosthesis control impairments are due to lack of feedback or due to inadequate feed-forward control. Methods Healthy subjects were fitted with a closed-loop robotic hand and instructed to grasp and lift objects of different weights as we recorded trajectories and force profiles. We conducted three experiments under different feed-forward and feed-back configurations to elucidate the role of tactile feedback (i in ideal conditions, (ii under sensory deprivation, and (iii under feed-forward uncertainty. Results (i We found that subjects formed economical grasps in ideal conditions. (ii To our surprise, this ability was preserved even when visual and tactile feedback were removed. (iii When we introduced uncertainty into the hand controller performance degraded significantly in the absence of either visual or tactile feedback. Greatest performance was achieved when both sources of feedback were present. Conclusions We have introduced a novel method to understand the cognitive processes underlying grasping and lifting. We have shown quantitatively that tactile feedback can significantly improve performance in the presence of feed-forward uncertainty. However, our results indicate that feed-forward and feed-back mechanisms serve complementary roles, suggesting that to improve on the state-of-the-art in prosthetic hands we must develop prostheses that empower users to correct for the inevitable uncertainty in their feed-forward control.
Control of beam halo-chaos using neural network self-adaptation method
International Nuclear Information System (INIS)
Fang Jinqing; Huang Guoxian; Luo Xiaoshu
2004-11-01
Taking the advantages of neural network control method for nonlinear complex systems, control of beam halo-chaos in the periodic focusing channels (network) of high intensity accelerators is studied by feed-forward back-propagating neural network self-adaptation method. The envelope radius of high-intensity proton beam is reached to the matching beam radius by suitably selecting the control structure of neural network and the linear feedback coefficient, adjusted the right-coefficient of neural network. The beam halo-chaos is obviously suppressed and shaking size is much largely reduced after the neural network self-adaptation control is applied. (authors)
Feedforward interview technique in obstetrics and gynaecology residents: a fact or fallacy.
Sami, Shehla; Ahmad, Amina
2015-01-01
To determine the role of Feedforward Interview (FFI) technique in motivating residents of Obstetrics and Gynaecology for better learning and performance. An explorative study with mixed method approach being employed. Department of Obstetrics and Gynaecology, Sandeman (Provincial) Hospital, Quetta, from November 2010 till May 2013. Feedforward interview technique was complimented by survey questionnaire employing similar philosophy of FFI to triangulate data through two methods. Survey questionnaire was filled-up by 21 residents and analysed by SPSS version 17. Fourteen of these participants were identified for in-depth Feedforward Interviews (FFI), based on nonprobability purposive sampling after informed consent, and content analysis was done. Feedforward interview technique enabled majority of residents in recalling minimum of 3 positive experiences, mainly related to surgical experiences, which enhanced their motivation to aspire for further improvement in this area. Hard work was the main personal contributing factor both in FFI and survey. In addition to identifying clinical experiences enhancing desire to learn, residents also reported need for more academic support as an important factor which could also boost motivation to attain better performance. Feedforward interview technique not only helps residents in recalling positive learning experiences during their training but it also has a significant influence on developing insight about one's performance and motivating residents to achieve higher academic goals.
Beneficial role of noise in artificial neural networks
International Nuclear Information System (INIS)
Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin
2008-01-01
We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
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...... concerning canonical, observable state space forms (minimum realizable form) for SISO as wll as MIMO processes. The tests show that all models, after succeeeful training, which is judged by correlation analysis of the prediction errors, are able to perform non-linear system identification, prediction...
Salathé, Yves; Kurpiers, Philipp; Karg, Thomas; Lang, Christian; Andersen, Christian Kraglund; Akin, Abdulkadir; Krinner, Sebastian; Eichler, Christopher; Wallraff, Andreas
2018-03-01
Quantum computing architectures rely on classical electronics for control and readout. Employing classical electronics in a feedback loop with the quantum system allows us to stabilize states, correct errors, and realize specific feedforward-based quantum computing and communication schemes such as deterministic quantum teleportation. These feedback and feedforward operations are required to be fast compared to the coherence time of the quantum system to minimize the probability of errors. We present a field-programmable-gate-array-based digital signal processing system capable of real-time quadrature demodulation, a determination of the qubit state, and a generation of state-dependent feedback trigger signals. The feedback trigger is generated with a latency of 110 ns with respect to the timing of the analog input signal. We characterize the performance of the system for an active qubit initialization protocol based on the dispersive readout of a superconducting qubit and discuss potential applications in feedback and feedforward algorithms.
Yu, Zhenpeng; Wang, Jiandong
2016-09-01
This paper assesses the performance of feedforward controllers for disturbance rejection in univariate feedback plus feedforward control loops. The structures of feedback and feedforward controllers are confined to proportional-integral-derivative and static-lead-lag forms, respectively, and the effects of feedback controllers are not considered. The integral squared error (ISE) and total squared variation (TSV) are used as performance metrics. A performance index is formulated by comparing the current ISE and TSV metrics to their own lower bounds as performance benchmarks. A controller performance assessment (CPA) method is proposed to calculate the performance index from measurements. The proposed CPA method resolves two critical limitations in the existing CPA methods, in order to be consistent with industrial scenarios. Numerical and experimental examples illustrate the effectiveness of the obtained results. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.
Sidemode suppression for coupled optoelectronic oscillator by optical pulse power feedforward.
Dai, Yitang; Wang, Ruixin; Yin, Feifei; Dai, Jian; Yu, Lan; Li, Jianqiang; Xu, Kun
2015-10-19
Multiple sidemodes have been observed in a coupled optoelectronic oscillator (COEO) when the contained actively mode-locked fiber ring laser employs erbium-doped fiber (EDF). We propose that such sidemodes can be suppressed significantly by an optical pulse power feedforward scheme, through which the mode-locked optical pulse is reversely intensity-modulated by itself, resulting in a fast power limiting. Experimentally we show that sidemodes are suppressed as much as 40 dB in a 10-GHz COEO. The additional noise induced by the power feedforward technique is analyzed numerically. We show that for a COEO with a typical cavity length, the feedforward contribution to final single-side band (SSB) noise is minor and neglectable.
Disturbance rejection using feed-forward control system on self balancing robot
Directory of Open Access Journals (Sweden)
Henryranu Prasetio Barlian
2018-01-01
Full Text Available This research implements self-balancing robot using 3 algorithms. There are PID Controller, Ensemble Kalman Filter and Feed-Forward Control system. The PID controller function is as a robot equilibrium control system. The Kalman Ensemble algorithm is used to reduce noise measurement of accelerometer and gyroscope sensors. The PID controller and Ensemble Kalman filter were implemented on self-balancing robot in previous research. In this paper, we added the Feed-Forward controller that serves to detect disturbance derived from the unevenness of the ground. Disturbance is detected using 2 proximity sensors. Base on test results that the system can detect disturbance with an average delay of 2.15 seconds at Kff optimal value is 2.92. Feed-Forward effects result in self-balancing robots increasing power so that the pitch of the robot changes to anticipation of disturbance.
Ohta, Hiromichi; Ogura, Gaku; Waseda, Yoshio; Suzuki, Mustumi
1990-10-01
A simple cell and easy data processing are described for measuring the thermal diffusivity of a liquid sample at high temperatures using the laser flash method. A cell consists of a liquid sample sandwiched by two metallic plates. The front surface of one metallic plate is exposed to a single pulse of beam laser and the resulting temperature rise of the back surface of the other metallic plate is measured. The logarithmic analysis proposed by James using the initial time region of the temperature response curve of a two layered cell system has been extended to apply to the present three layered cell system in order to estimate the thermal diffusivity value of a liquid sample. Measurements of distilled water and methanol were made first and the results were found to be in good agreement with the reference data. Then, the thermal diffusivities of molten NaNO3 at 593-660 K and of molten KNO3 at 621-694 K were determined and the results also appear to agree reasonably well with those reported in the literature.
Gradient Mn-La-Pt Catalysts with Three-layered Structure for Li-O2 battery
Cai, Kedi; Yang, Rui; Lang, Xiaoshi; Zhang, Qingguo; Wang, Zhenhua; He, Tieshi
2016-01-01
Gradient Mn-La-Pt catalysts with three-layered structure of manganese dioxide (MnO2), lanthanum oxide (La2O3), and Platinum (Pt) for Li-O2 battery are prepared in this study. The mass ratio of the catalysts is respectively 5:2:3, 4:2:4, and 3:2:5 (MnO2: La2O3: Pt) which is start from the side of the electrolyte. The relationship between morphology structure and electrochemical performance of gradient catalyst is investigated by energy dispersive spectrometry and constant current charge/discharge test. The Li-O2 battery based on gradient Mn-La-Pt catalysts shows high discharge specific capacity (2707 mAh g−1), specific energy density (8400 Wh kg−1) and long cycle life (56 cycles). The improvement of the Li-O2 battery discharge capacity is attributed to the gradient distribution of MnO2 and Pt and the involvement of La2O3 that can improve the energy density of the battery. More important, this work will also provide new ideas and methods for the research of other metal-air battery. PMID:27731340
Feature to prototype transition in neural networks
Krotov, Dmitry; Hopfield, John
Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.
Artificial Neural Networks to Detect Risk of Type 2 Diabetes | Baha ...
African Journals Online (AJOL)
A multilayer feedforward architecture with backpropagation algorithm was designed using Neural Network Toolbox of Matlab. The network was trained using batch mode backpropagation with gradient descent and momentum. Best performed network identified during the training was 2 hidden layers of 6 and 3 neurons, ...
Placing Spline Knots in Neural Networks Using Splines as Activation Functions
Czech Academy of Sciences Publication Activity Database
Hlaváčková, Kateřina; Verleysen, M.
1997-01-01
Roč. 17, 3/4 (1997), s. 159-166 ISSN 0925-2312 R&D Projects: GA ČR GA201/93/0427; GA ČR GA201/96/0971 Keywords : cubic -spline function * approximation error * knots of spline function * feedforward neural network Impact factor: 0.422, year: 1997
Multiobjective training of artificial neural networks for rainfall-runoff modeling
De Vos, N.J.; Rientjes, T.H.M.
2008-01-01
This paper presents results on the application of various optimization algorithms for the training of artificial neural network rainfall-runoff models. Multilayered feed-forward networks for forecasting discharge from two mesoscale catchments in different climatic regions have been developed for
Neural estimation of kinetic rate constants from dynamic PET-scans
DEFF Research Database (Denmark)
Fog, Torben L.; Nielsen, Lars Hupfeldt; Hansen, Lars Kai
1994-01-01
A feedforward neural net is trained to invert a simple three compartment model describing the tracer kinetics involved in the metabolism of [18F]fluorodeoxyglucose in the human brain. The network can estimate rate constants from positron emission tomography sequences and is about 50 times faster ...
53 MHZ Feedforward beam loading compensation in the Fermilab main injector
International Nuclear Information System (INIS)
Joseph E Dey et al.
2003-01-01
53 MHz feedforward beam loading compensation is crucial to all operations of the Main Injector. Recently a system using a fundamental frequency down converter mixer, a digital bucket delay module and a fundamental frequency up converter mixer were used to produce a one-turn-delay feedforward signal. This signal was then combined with the low level RF signal to the cavities to cancel the transient beam induced voltage. During operation they have shown consistently over 20 dB reduction in side-band voltage around the fundamental frequency during Proton coalescing and over 14 dB in multi-batch antiproton coalescing
Parrell, Benjamin; Agnew, Zarinah; Nagarajan, Srikantan; Houde, John; Ivry, Richard B
2017-09-20
The cerebellum has been hypothesized to form a crucial part of the speech motor control network. Evidence for this comes from patients with cerebellar damage, who exhibit a variety of speech deficits, as well as imaging studies showing cerebellar activation during speech production in healthy individuals. To date, the precise role of the cerebellum in speech motor control remains unclear, as it has been implicated in both anticipatory (feedforward) and reactive (feedback) control. Here, we assess both anticipatory and reactive aspects of speech motor control, comparing the performance of patients with cerebellar degeneration and matched controls. Experiment 1 tested feedforward control by examining speech adaptation across trials in response to a consistent perturbation of auditory feedback. Experiment 2 tested feedback control, examining online corrections in response to inconsistent perturbations of auditory feedback. Both male and female patients and controls were tested. The patients were impaired in adapting their feedforward control system relative to controls, exhibiting an attenuated anticipatory response to the perturbation. In contrast, the patients produced even larger compensatory responses than controls, suggesting an increased reliance on sensory feedback to guide speech articulation in this population. Together, these results suggest that the cerebellum is crucial for maintaining accurate feedforward control of speech, but relatively uninvolved in feedback control. SIGNIFICANCE STATEMENT Speech motor control is a complex activity that is thought to rely on both predictive, feedforward control as well as reactive, feedback control. While the cerebellum has been shown to be part of the speech motor control network, its functional contribution to feedback and feedforward control remains controversial. Here, we use real-time auditory perturbations of speech to show that patients with cerebellar degeneration are impaired in adapting feedforward control of
Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks
Maca, Petr; Pech, Pavel
2016-01-01
The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI) and the standardized precipitation evaporation index (SPEI) and were derived for the period of 1948–2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons. PMID:26880875
Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Petr Maca
2016-01-01
Full Text Available The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI and the standardized precipitation evaporation index (SPEI and were derived for the period of 1948–2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons.
Neural networks for control of NO{sub x} emissions in fossil plants
Energy Technology Data Exchange (ETDEWEB)
Reifman, J.; Feldman, E.E.
1997-04-01
We discuss the use of two classes of artificial neural networks, multilayer feedforward networks and fully-recurrent networks, in the development of a closed-loop controller for discrete-time dynamical systems. We apply the neural system to the control of oxides of nitrogen (NO{sub x}) emissions for a simplified representation of a furnace of a coal-fired fossil plant. Plant data from one of Commonwealth Edison`s fossil power plants were used to build a recurrent neural model of NO{sub x} formation which is then used in the training of the feedforward neural controller. Preliminary simulation results demonstrate the feasibility of the approach and additional tests with increasingly realistic models should be pursued.
Zhang, S. N.; Zhang, Xiaoling; Sun, Xuejun; Yao, Yangsen; Cui, Wei; Chen, Wan; Wu, Xuebing; Xu, Haiguang
1999-01-01
We have carried out systematic modeling of the X-ray spectra of the Galactic superluminal jet sources GRS 1915+105 and GRO J1655-40, using our newly developed spectral fitting methods. Our results reveal, for the first time, a three-layered structure of the atmosphere in the inner region of the accretion disks. Above the conanonly known, cold and optically thick disk of a blackbody temperature 0.2-0.5 keV, there is a layer of warm gas with a temperature of 1.0-1.5 keV and an optical depth of around 10. Compton scattering of the underlying disk blackbody photons produces the soft X-ray component we comonly observe. Under certain conditions, there is also a much hotter, optically thin corona above the warm layer, characterized by a temperature of 100 keV or higher and an optical depth of unity or less. The corona produces the hard X-ray component typically seen in these sources. We emphasize that the existence of the warm layer seem to be independent of the presence of the hot corona and, therefore, it is not due to irradiation of the disk by hard X-rays from the corona. Our results suggest a striking structural similarity between the accretion disks and the solar atmosphere, which may provide a new stimulus to study the common underlying physical processes operating in these vastly different systems. We also report the first unambiguous detection of an emission line around 6.4 keV in GRO J1655-40, which may allow further constraining of the accretion disk structure. We acknowledge NASA GSFC and MFC for partial financial support. (copyright) 1999: American Astronomical Society. All rights reverved.
DETERMINATION OF STRESS-STRAIN STATE OF A THREE-LAYER BEAM WITH APPLICATION OF CONTACT LAYER METHOD
Directory of Open Access Journals (Sweden)
Andreev Vladimir Igorevich
2016-04-01
Full Text Available The article deals with the solution for the stress-strain state of a multilayer composite beam with rectangular cross-section, which is bended by normally distributed load. The intermolecular interaction between layers is accomplished by the contact layer, in which the substances of adhesive and substrate are mixed. We consider the contact layer as a transversal anisotropic medium with such parameters that it can be represented as a set of short elastic rods, which are not connected to each other. For simplicity, we assume that the rods are normally oriented to the contact surface. The contact layer method allows us to solve the problem of determining the concentration of tangential stresses arising at the boundaries between the layers and the corner points, their changes, as well as to determine the physical properties of the contact layer basing on experimental data. Resolving the equations obtained in this article can be used for the solution of many problems of the theory of layered substances. These equations were derived from the fundamental laws of the theory of elasticity and generally accepted hypotheses of the theory of plates for the general case of the bending problem of a multilayer beam with any number of layers. The article deals with the example of the numerical solution of the problem of bending of a three-layer beam. On the basis of this solution the curves were obtained, which reflect the stress-strain state of one of the layers. All these curves have a narrow area of the edge effect. The edge effect is associated with a large gradient tangential stresses in the contact layer. The experimental data suggest that in this zone the destruction of the samples occurs. This fact allows us to say that the equations obtained in this article can be used to construct a theory of the strength layered beams under bending.
Analysis and optimization of gas-centrifugal separation of uranium isotopes by neural networks
Directory of Open Access Journals (Sweden)
Migliavacca S.C.P.
2002-01-01
Full Text Available Neural networks are an attractive alternative for modeling complex problems with too many difficulties to be solved by a phenomenological model. A feed-forward neural network was used to model a gas-centrifugal separation of uranium isotopes. The prediction showed good agreement with the experimental data. An optimization study was carried out. The optimal operational condition was tested by a new experiment and a difference of less than 1% was found.
Chin Kim On; Teo Kein Yau; Rayner Alfred; Jason Teo; Patricia Anthony; Wang Cheng
2016-01-01
In this paper, we describe a research project that autonomously localizes and recognizes non-standardized Malaysian’s car plates using conventional Backpropagation algorithm (BPP) in combination with Ensemble Neural Network (ENN). We compared the results with the results obtained using simple Feed-Forward Neural Network (FFNN). This research aims to solve four main issues; (1) localization of car plates that has the same colour with the vehicle colour, (2) detection and recognition of car pla...
Dror, Shahar
1992-01-01
Approved for public release; distribution is unlimited Identification and control of non-linear dynamical systems is a very complex task which requires new methods of approaching. This research addresses the problem of emulation and control via the use of distributed parallel processing, namely artificial neural networks. Four models for describing non-linear MIMO dynamical systems are presented. Based on these models a combined feedforward and recurrent neural networks are structured t...
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.)
Learning and Generalisation in Neural Networks with Local Preprocessing
Kutsia, Merab
2007-01-01
We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the net...
Image Restoration Technology Based on Discrete Neural network
Zhou Duoying
2015-01-01
With the development of computer science and technology, the development of artificial intelligence advances rapidly in the field of image restoration. Based on the MATLAB platform, this paper constructs a kind of image restoration technology of artificial intelligence based on the discrete neural network and feedforward network, and carries out simulation and contrast of the restoration process by the use of the bionic algorithm. Through the application of simulation restoration technology, ...
Fastest learning in small-world neural networks
International Nuclear Information System (INIS)
Simard, D.; Nadeau, L.; Kroeger, H.
2005-01-01
We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition
Development of a feed-forward controller for a tracking telescope
Allen, John S.; Stufflebeam, Joseph L.; Feller, Dan
2004-07-01
This paper develops a State Space model of a feed-forward control system in the frequency domain, and time domain. The results of the mathematical model are implemented and the responses of the Elevation and Azimuth servo controller in a tracking telescope called a Cine-Sextant developed for the Utah Test and Training Range.
High-speed linear optics quantum computing using active feed-forward.
Prevedel, Robert; Walther, Philip; Tiefenbacher, Felix; Böhi, Pascal; Kaltenbaek, Rainer; Jennewein, Thomas; Zeilinger, Anton
2007-01-04
As information carriers in quantum computing, photonic qubits have the advantage of undergoing negligible decoherence. However, the absence of any significant photon-photon interaction is problematic for the realization of non-trivial two-qubit gates. One solution is to introduce an effective nonlinearity by measurements resulting in probabilistic gate operations. In one-way quantum computation, the random quantum measurement error can be overcome by applying a feed-forward technique, such that the future measurement basis depends on earlier measurement results. This technique is crucial for achieving deterministic quantum computation once a cluster state (the highly entangled multiparticle state on which one-way quantum computation is based) is prepared. Here we realize a concatenated scheme of measurement and active feed-forward in a one-way quantum computing experiment. We demonstrate that, for a perfect cluster state and no photon loss, our quantum computation scheme would operate with good fidelity and that our feed-forward components function with very high speed and low error for detected photons. With present technology, the individual computational step (in our case the individual feed-forward cycle) can be operated in less than 150 ns using electro-optical modulators. This is an important result for the future development of one-way quantum computers, whose large-scale implementation will depend on advances in the production and detection of the required highly entangled cluster states.
Video Feedforward for Rapid Learning of a Picture-Based Communication System
Smith, Jemma; Hand, Linda; Dowrick, Peter W.
2014-01-01
This study examined the efficacy of video self modeling (VSM) using feedforward, to teach various goals of a picture exchange communication system (PECS). The participants were two boys with autism and one man with Down syndrome. All three participants were non-verbal with no current functional system of communication; the two children had long…
Feed-Forward versus Feedback Inhibition in a Basic Olfactory Circuit.
Directory of Open Access Journals (Sweden)
Tiffany Kee
2015-10-01
Full Text Available Inhibitory interneurons play critical roles in shaping the firing patterns of principal neurons in many brain systems. Despite difference in the anatomy or functions of neuronal circuits containing inhibition, two basic motifs repeatedly emerge: feed-forward and feedback. In the locust, it was proposed that a subset of lateral horn interneurons (LHNs, provide feed-forward inhibition onto Kenyon cells (KCs to maintain their sparse firing--a property critical for olfactory learning and memory. But recently it was established that a single inhibitory cell, the giant GABAergic neuron (GGN, is the main and perhaps sole source of inhibition in the mushroom body, and that inhibition from this cell is mediated by a feedback (FB loop including KCs and the GGN. To clarify basic differences in the effects of feedback vs. feed-forward inhibition in circuit dynamics we here use a model of the locust olfactory system. We found both inhibitory motifs were able to maintain sparse KCs responses and provide optimal odor discrimination. However, we further found that only FB inhibition could create a phase response consistent with data recorded in vivo. These findings describe general rules for feed-forward versus feedback inhibition and suggest GGN is potentially capable of providing the primary source of inhibition to the KCs. A better understanding of how inhibitory motifs impact post-synaptic neuronal activity could be used to reveal unknown inhibitory structures within biological networks.
Sliding-mode control combined with improved adaptive feedforward for wafer scanner
Li, Xiaojie; Wang, Yiguang
2018-03-01
In this paper, a sliding-mode control method combined with improved adaptive feedforward is proposed for wafer scanner to improve the tracking performance of the closed-loop system. Particularly, In addition to the inverse model, the nonlinear force ripple effect which may degrade the tracking accuracy of permanent magnet linear motor (PMLM) is considered in the proposed method. The dominant position periodicity of force ripple is determined by using the Fast Fourier Transform (FFT) analysis for experimental data and the improved feedforward control is achieved by the online recursive least-squares (RLS) estimation of the inverse model and the force ripple. The improved adaptive feedforward is given in a general form of nth-order model with force ripple effect. This proposed method is motivated by the motion controller design of the long-stroke PMLM and short-stroke voice coil motor for wafer scanner. The stability of the closed-loop control system and the convergence of the motion tracking are guaranteed by the proposed sliding-mode feedback and adaptive feedforward methods theoretically. Comparative experiments on a precision linear motion platform can verify the correctness and effectiveness of the proposed method. The experimental results show that comparing to traditional method the proposed one has better performance of rapidity and robustness, especially for high speed motion trajectory. And, the improvements on both tracking accuracy and settling time can be achieved.
Feedforward and Feedback Control in Apraxia of Speech: Effects of Noise Masking on Vowel Production
Maas, Edwin; Mailend, Marja-Liisa; Guenther, Frank H.
2015-01-01
Purpose: This study was designed to test two hypotheses about apraxia of speech (AOS) derived from the Directions Into Velocities of Articulators (DIVA) model (Guenther et al., 2006): the feedforward system deficit hypothesis and the feedback system deficit hypothesis. Method: The authors used noise masking to minimize auditory feedback during…
Feed-forward and its role in conditional linear optical quantum dynamics
International Nuclear Information System (INIS)
Scheel, S.; Munro, W. J.; Kok, P.; Eisert, J.; Nemoto, K.
2006-01-01
Nonlinear optical quantum gates can be created probabilistically using only single-photon sources, linear optical elements, and photon-number-resolving detectors. These gates are heralded but operate with probabilities much less than 1. There is currently a large gap between the performance of the known circuits and the established upper bounds on their success probabilities. One possibility for increasing the probability of success of such gates is feed-forward, where one attempts to correct certain failure events that occurred in the gate's operation. In this Brief Report we examine the role of feed-forward in improving the success probability. In particular, for the nonlinear sign-shift gate, we find that in a three-mode implementation with a single round of feed-forward the optimal average probability of success is approximately given by p success =0.272. This value is only slightly larger than the general optimal success probability without feed-forward, p success =0.25
Active gust load alleviation system for flexible aircraft: Mixed feedforward/feedback approach
DEFF Research Database (Denmark)
Alam, Mushfiqul; Hromcik, Martin; Hanis, Tomas
2015-01-01
Lightweight flexible blended-wing-body (BWB) aircraft concept seems as a highly promising configuration for future high capacity airliners which suffers from reduced stiffness for disturbance loads such as gusts. A robust feedforward gust load alleviation system (GLAS) was developed to alleviate...
Reflexions on feedforward control strategies for a class of sailing vehicles
DEFF Research Database (Denmark)
Xiao, Lin; Jouffroy, Jerome
2010-01-01
Sailing vehicles, whether they are sea or land-based, share the unique property of exhibiting totally different trajectories depending on where their direction of travel is with respect to the wind. Following our previous work, this paper discusses a few points related to feedforward control and ...
A quantum-implementable neural network model
Chen, Jialin; Wang, Lingli; Charbon, Edoardo
2017-10-01
A quantum-implementable neural network, namely quantum probability neural network (QPNN) model, is proposed in this paper. QPNN can use quantum parallelism to trace all possible network states to improve the result. Due to its unique quantum nature, this model is robust to several quantum noises under certain conditions, which can be efficiently implemented by the qubus quantum computer. Another advantage is that QPNN can be used as memory to retrieve the most relevant data and even to generate new data. The MATLAB experimental results of Iris data classification and MNIST handwriting recognition show that much less neuron resources are required in QPNN to obtain a good result than the classical feedforward neural network. The proposed QPNN model indicates that quantum effects are useful for real-life classification tasks.
Computational neural networks: enhancing supervised learning algorithms via self-organization.
Holdaway, R M; White, M W
1990-04-01
A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifier network. The results of a series of benchmarking studies based upon artificial statistical pattern recognition tasks indicate that the proposed architecture performs significantly better than conventional feedforward classifier networks when the decision regions are disjoint. This is attributed to the fact that the self-organization process allows internal units in the succeeding classifier network to be sensitive to a specific set of features in the input space at the outset of training.
Artificial neural network based approach to transmission lines protection
International Nuclear Information System (INIS)
Joorabian, M.
1999-05-01
The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection
Kim, Ki Hwan; Park, Sung-Hong
2017-04-01
The balanced steady-state free precession (bSSFP) MR sequence is frequently used in clinics, but is sensitive to off-resonance effects, which can cause banding artifacts. Often multiple bSSFP datasets are acquired at different phase cycling (PC) angles and then combined in a special way for banding artifact suppression. Many strategies of combining the datasets have been suggested for banding artifact suppression, but there are still limitations in their performance, especially when the number of phase-cycled bSSFP datasets is small. The purpose of this study is to develop a learning-based model to combine the multiple phase-cycled bSSFP datasets for better banding artifact suppression. Multilayer perceptron (MLP) is a feedforward artificial neural network consisting of three layers of input, hidden, and output layers. MLP models were trained by input bSSFP datasets acquired from human brain and knee at 3T, which were separately performed for two and four PC angles. Banding-free bSSFP images were generated by maximum-intensity projection (MIP) of 8 or 12 phase-cycled datasets and were used as targets for training the output layer. The trained MLP models were applied to another brain and knee datasets acquired with different scan parameters and also to multiple phase-cycled bSSFP functional MRI datasets acquired on rat brain at 9.4T, in comparison with the conventional MIP method. Simulations were also performed to validate the MLP approach. Both the simulations and human experiments demonstrated that MLP suppressed banding artifacts significantly, superior to MIP in both banding artifact suppression and SNR efficiency. MLP demonstrated superior performance over MIP for the 9.4T fMRI data as well, which was not used for training the models, while visually preserving the fMRI maps very well. Artificial neural network is a promising technique for combining multiple phase-cycled bSSFP datasets for banding artifact suppression. Copyright Â© 2016 Elsevier Inc. All
Carvalho, Luis Alberto
2005-02-01
Our main goal in this work was to develop an artificial neural network (NN) that could classify specific types of corneal shapes using Zernike coefficients as input. Other authors have implemented successful NN systems in the past and have demonstrated their efficiency using different parameters. Our claim is that, given the increasing popularity of Zernike polynomials among the eye care community, this may be an interesting choice to add complementing value and precision to existing methods. By using a simple and well-documented corneal surface representation scheme, which relies on corneal elevation information, one can generate simple NN input parameters that are independent of curvature definition and that are also efficient. We have used the Matlab Neural Network Toolbox (MathWorks, Natick, MA) to implement a three-layer feed-forward NN with 15 inputs and 5 outputs. A database from an EyeSys System 2000 (EyeSys Vision, Houston, TX) videokeratograph installed at the Escola Paulista de Medicina-Sao Paulo was used. This database contained an unknown number of corneal types. From this database, two specialists selected 80 corneas that could be clearly classified into five distinct categories: (1) normal, (2) with-the-rule astigmatism, (3) against-the-rule astigmatism, (4) keratoconus, and (5) post-laser-assisted in situ keratomileusis. The corneal height (SAG) information of the 80 data files was fit with the first 15 Vision Science and it Applications (VSIA) standard Zernike coefficients, which were individually used to feed the 15 neurons of the input layer. The five output neurons were associated with the five typical corneal shapes. A group of 40 cases was randomly selected from the larger group of 80 corneas and used as the training set. The NN responses were statistically analyzed in terms of sensitivity [true positive/(true positive + false negative)], specificity [true negative/(true negative + false positive)], and precision [(true positive + true
Chen, Chau-Kuang
2010-01-01
Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…
Identification of aerodynamic coefficients using computational neural networks
Linse, Dennis J.; Stengel, Robert F.
1992-01-01
Precise, smooth aerodynamic models are required for implementing adaptive, nonlinear control strategies. Accurate representations of aerodynamic coefficients can be generated for the complete flight envelope by combining computational neural network models with an Estimation-Before-Modeling paradigm for on-line training information. A novel method of incorporating first-partial-derivative information is employed to estimate the weights in individual feedforward neural networks for each aerodynamic coefficient. The method is demonstrated by generating a model of the normal force coefficient of a twin-jet transport aircraft from simulated flight data, and promising results are obtained.
Applying neural networks as software sensors for enzyme engineering.
Linko, S; Zhu, Y H; Linko, P
1999-04-01
The on-line control of enzyme-production processes is difficult, owing to the uncertainties typical of biological systems and to the lack of suitable on-line sensors for key process variables. For example, intelligent methods to predict the end point of fermentation could be of great economic value. Computer-assisted control based on artificial-neural-network models offers a novel solution in such situations. Well-trained feedforward-backpropagation neural networks can be used as software sensors in enzyme-process control; their performance can be affected by a number of factors.
Control of 12-Cylinder Camless Engine with Neural Networks
Ashhab Moh’d Sami
2017-01-01
The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s). The inputs to the net are the intake valve lift (IVL) and intake valve closing timing (IVC) whereas the output of the net is the cylinder air charge (CAC). The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and appl...
Dynamic Pricing in Electronic Commerce Using Neural Network
Ghose, Tapu Kumar; Tran, Thomas T.
In this paper, we propose an approach where feed-forward neural network is used for dynamically calculating a competitive price of a product in order to maximize sellers’ revenue. In the approach we considered that along with product price other attributes such as product quality, delivery time, after sales service and seller’s reputation contribute in consumers purchase decision. We showed that once the sellers, by using their limited prior knowledge, set an initial price of a product our model adjusts the price automatically with the help of neural network so that sellers’ revenue is maximized.
Modelling of word usage frequency dynamics using artificial neural network
International Nuclear Information System (INIS)
Maslennikova, Yu S; Bochkarev, V V; Voloskov, D S
2014-01-01
In this paper the method for modelling of word usage frequency time series is proposed. An artificial feedforward neural network was used to predict word usage frequencies. The neural network was trained using the maximum likelihood criterion. The Google Books Ngram corpus was used for the analysis. This database provides a large amount of data on frequency of specific word forms for 7 languages. Statistical modelling of word usage frequency time series allows finding optimal fitting and filtering algorithm for subsequent lexicographic analysis and verification of frequency trend models
Nationwide lithological interpretation of cone penetration tests using neural networks
van Maanen, Peter-Paul; Schokker, Jeroen; Harting, Ronald; de Bruijn, Renée
2017-04-01
lithological classification script that is also used in GeoTOP to classify the visual sample descriptions. Based on this data a three-layer feedforward neural network was trained containing 5 different inputs: cone resistance, friction ratio, coordinates x and y, and interval depth z. Previous training attempts showed an increased performance when using additional inputs such as pore water pressure, but since these variables are not measured in the majority of CPTs, these were left out in the training procedure. The Newton conjugate-gradient algorithm was applied to train the network. 20-Fold cross-validation yielded 20 different trained nets and independent performance outcomes. Significant performance increase was found as compared to performances of conventional lithological classification charts. A similar neural network was then applied to new CPT data from a pilot area in the city of Rotterdam. This area has a limited number of visual sample descriptions and therefore, additional lithological information of the subsurface is desirable. The results of an evaluation of the neural network's outcomes in this area by geological experts are positive, which paves the way for future nationwide application of this method.
Robust recurrent neural network modeling for software fault detection and correction prediction
International Nuclear Information System (INIS)
Hu, Q.P.; Xie, M.; Ng, S.H.; Levitin, G.
2007-01-01
Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set
Time-optimal control of nuclear reactor power with adaptive proportional- integral-feedforward gains
International Nuclear Information System (INIS)
Park, Moon Ghu; Cho, Nam Zin
1993-01-01
A time-optimal control method which consists of coarse and fine control stages is described here. During the coarse control stage, the maximum control effort (time-optimal) is used to direct the system toward the switching boundary which is set near the desired power level. At this boundary, the controller is switched to the fine control stage in which an adaptive proportional-integral-feedforward (PIF) controller is used to compensate for any unmodeled reactivity feedback effects. This fine control is also introduced to obtain a constructive method for determining the (adaptive) feedback gains against the sampling effect. The feedforward control term is included to suppress the over-or undershoot. The estimation and feedback of the temperature-induced reactivity is also discussed
Escapa, Alberto; Fukushima, Toshio
2010-05-01
The internal structure of numerous celestial bodies are well approximated by means of a three layer model composed of a solid external layer, which encloses a fluid layer containing a solid body. An analysis of the inner dynamics of this model can provide some constrains on its rheological characteristics; an information that in many situations is only accessible through this indirect way. In addition, the understanding of this kind of motions, especially of those associated with a rigid displacement (a rotation or a relative translation) of the solid layers, is of primary importance to establish with enough accuracy the definition of the terrestrial reference frames. In the Earth case, most approaches to this formidable problem rely on the numerical solution of the respective elastic field equations, once they have been projected on a set of spherical harmonics functions of a given degree. Due to its intrinsic nature these numerical methods do not provide by themselves much insight into the internal dynamics, hence the interest to develop simpler dynamical models that reproduces the main characteristics of the motion and allows obtaining analytical approximate solutions of the problem. To this aim, and as a first stage, we have considered the internal dynamics of a simple Earth model made up of a spherical rigid mantle, an inviscid, homogeneous fluid outer core and a spherical rigid inner core. Initially the barycenters of all the constituents are located at the same point (isobarycentric model) and the whole system rotates with constant angular velocity around the figure axis. When this situation is perturbed both the motions of the fluid and of the solid layers depart from the reference uniform rotation. However, following Busse (1974) we have assumed that the motion of the mantle is the same as in the unperturbed state, and that the inner core dynamics only suffers a variation of oscillatory nature in the translational motion of its barycenter. As a consequence
Design of A Novel Feed-Forward Control Strategy for A Non-Minimum Phase System
Sharma, Kajal; Pradhan, Raseswari
2017-08-01
This paper proposes a new feed-forward control strategy for a plant with non-minimum phase dynamics. A Feed-Forward controller is very essential for controlling plants with time-varying reference signals. However, designing this type of controller is a non-trivial problem in case the plant dynamics is non-minimum-phase. This is because, this controller design involves the concept of inversion of the plant model and inverse of a non-minimum-phase plant model is unstable or non-causal. For this problem, usually an approximate inversion of a plant model is applied. An approach with corrected-approximate-inverse (CAI) method is available for feed forward controller design. After analyzing the results and discussion of this CAI technique, it is seen that although it seems to be working perfectly for small duration of time but its performance is unsatisfactory in case of large span of time. Therefore, in this paper, a new feed-forward control strategy has been designed to erase the above said problem. This method has adopted a simple version of an internal plant-model structure in its time domain. The fixed-structure feed forward controller that is constructed using this method is usually a linear amalgamation of a reference trajectory and its time-derivatives with suitable weighting factors. This control strategy has been verified with appropriate simulation results applied to a studied plant and results are compared with that of the CAI technique.
Feed-forward and feedback projections of midbrain reticular formation neurons in the cat
Directory of Open Access Journals (Sweden)
Eddie ePerkins
2014-01-01
Full Text Available Gaze changes involving the eyes and head are orchestrated by brainstem gaze centers found within the superior colliculus (SC, paramedian pontine reticular formation (PPRF, and medullary reticular formation (MdRF. The mesencephalic reticular formation (MRF also plays a role in gaze. It receives a major input from the ipsilateral SC and contains cells that fire in relation to gaze changes. Moreover, it provides a feedback projection to the SC and feed-forward projections to the PPRF and MdRF. We sought to determine whether these MRF feedback and feed-forward projections originate from the same or different neuronal populations by utilizing paired fluorescent retrograde tracers in cats. Specifically, we tested: 1. whether MRF neurons that control eye movements form a single population by injecting the SC and PPRF with different tracers, and 2. whether MRF neurons that control head movements form a single population by injecting the SC and MdRF with different tracers. In neither case were double labeled neurons observed, indicating that feedback and feed-forward projections originate from separate MRF populations. In both cases, the labeled reticulotectal and reticuloreticular neurons were distributed bilaterally in the MRF. However, neurons projecting to the MdRF were generally constrained to the medial half of the MRF, while those projecting to the PPRF, like MRF reticulotectal neurons, were spread throughout the mediolateral axis. Thus, the medial MRF may be specialized for control of head movements, with control of eye movements being more widespread in this structure.
Feedforward Delay Estimators in Adverse Multipath Propagation for Galileo and Modernized GPS Signals
Directory of Open Access Journals (Sweden)
Lohan Elena Simona
2006-01-01
Full Text Available The estimation with high accuracy of the line-of-sight delay is a prerequisite for all global navigation satellite systems. The delay locked loops and their enhanced variants are the structures of choice for the commercial GNSS receivers, but their performance in severe multipath scenarios is still rather limited. The new satellite positioning system proposals specify higher code-epoch lengths compared to the traditional GPS signal and the use of a new modulation, the binary offset carrier (BOC modulation, which triggers new challenges in the delay tracking stage. We propose and analyze here the use of feedforward delay estimation techniques in order to improve the accuracy of the delay estimation in severe multipath scenarios. First, we give an extensive review of feedforward delay estimation techniques for CDMA signals in fading channels, by taking into account the impact of BOC modulation. Second, we extend the techniques previously proposed by the authors in the context of wideband CDMA delay estimation (e.g., Teager-Kaiser and the projection onto convex sets to the BOC-modulated signals. These techniques are presented as possible alternatives to the feedback tracking loops. A particular attention is on the scenarios with closely spaced paths. We also discuss how these feedforward techniques can be implemented via DSPs.
Ammonia-based feedforward and feedback aeration control in activated sludge processes.
Rieger, Leiv; Jones, Richard M; Dold, Peter L; Bott, Charles B
2014-01-01
Aeration control at wastewater treatment plants based on ammonia as the controlled variable is applied for one of two reasons: (1) to reduce aeration costs, or (2) to reduce peaks in effluent ammonia. Aeration limitation has proven to result in significant energy savings, may reduce external carbon addition, and can improve denitrification and biological phosphorus (bio-P) performance. Ammonia control for limiting aeration has been based mainly on feedback control to constrain complete nitrification by maintaining approximately one to two milligrams of nitrogen per liter of ammonia in the effluent. Increased attention has been given to feedforward ammonia control, where aeration control is based on monitoring influent ammonia load. Typically, the intent is to anticipate the impact of sudden load changes, and thereby reduce effluent ammonia peaks. This paper evaluates the fundamentals of ammonia control with a primary focus on feedforward control concepts. A case study discussion is presented that reviews different ammonia-based control approaches. In most instances, feedback control meets the objectives for both aeration limitation and containment of effluent ammonia peaks. Feedforward control, applied specifically for switching aeration on or off in swing zones, can be beneficial when the plant encounters particularly unusual influent disturbances.
Sun, Di-Hua; Zhang, Geng; Zhao, Min; Cheng, Sen-Lin; Cao, Jian-Dong
2018-03-01
Recently, the influence of driver's individual behaviors on traffic stability is research hotspot with the fasting developing transportation cyber-physical systems. In this paper, a new traffic lattice hydrodynamic model is proposed with consideration of driver's feedforward anticipation optimal flux difference. The neutral stability condition of the new model is obtained through linear stability analysis theory. The results show that the stable region will be enlarged on the phase diagram when the feedforward anticipation optimal flux difference effect is taken into account. In order to depict traffic jamming transition properties theoretically, the mKdV equation near the critical point is derived via nonlinear reductive perturbation method. The propagation behavior of traffic density waves can be described by the kink-antikink solution of the mKdV equation. Numerical simulations are conducted to verify the analytical results and all the results confirms that traffic stability can be enhanced significantly by considering the feedforward anticipation optimal flux difference in traffic lattice hydrodynamic theory.
International Nuclear Information System (INIS)
Avezova, N.R.; Avezov, R.R.; Rashidov, Y.K. et al.
2014-01-01
The results of the model-based study of nonstationary thermal mode in premises with an insolation passive heating system with a three-layer translucent shield are presented. The article is aimed at determining daily variations in the air temperature of the heated premise on typical heating season days and analyzing the optimization of the thermal capacity of the short-term (daily) thermal battery of the heating system on this basis. (author)
Phelps, G. A.; Miller, D. M.
2003-12-01
train a three-layer multilayer feedforward network. Multilayer feedforward networks are reasonably immune to noise and correlation of input variables, and so are ideal for distinguishing inputs that interact in complex ways. The method produced results consistent with recent mapping. The method was further tested by applying it to a test area, roughly 20 km southwest of the training area. This test also produced results consistent with recent mapping. The method has several advantages compared to training using other common remote sensing data sets: (1) it uses 1-m resolution DOQs, so classifies at higher resolution than possible with many data sets; (2) it examines neighbors to classify pixels, thus honoring spatial patterns, an advantage for mapping spatially-dependent features such as geomorphology and vegetation, and (3) it allows for both mixed classification and rejection of classification of the given classes on an individual pixel level, which allows for the identification of mixed geomorphic units and new (unclassified) geomorphic units.
ECO INVESTMENT PROJECT MANAGEMENT THROUGH TIME APPLYING ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Tamara Gvozdenović
2007-06-01
Full Text Available he concept of project management expresses an indispensable approach to investment projects. Time is often the most important factor in these projects. The artificial neural network is the paradigm of data processing, which is inspired by the one used by the biological brain, and it is used in numerous, different fields, among which is the project management. This research is oriented to application of artificial neural networks in managing time of investment project. The artificial neural networks are used to define the optimistic, the most probable and the pessimistic time in PERT method. The program package Matlab: Neural Network Toolbox is used in data simulation. The feed-forward back propagation network is chosen.
Neural network training by Kalman filtering in process system monitoring
International Nuclear Information System (INIS)
Ciftcioglu, Oe.
1996-03-01
Kalman filtering approach for neural network training is described. Its extended form is used as an adaptive filter in a nonlinear environment of the form a feedforward neural network. Kalman filtering approach generally provides fast training as well as avoiding excessive learning which results in enhanced generalization capability. The network is used in a process monitoring application where the inputs are measurement signals. Since the measurement errors are also modelled in Kalman filter the approach yields accurate training with the implication of accurate neural network model representing the input and output relationships in the application. As the process of concern is a dynamic system, the input source of information to neural network is time dependent so that the training algorithm presents an adaptive form for real-time operation for the monitoring task. (orig.)
Robust Neural Network Control of Electrically Driven Robot Manipulator using Backstepping Approach
Directory of Open Access Journals (Sweden)
Seyed Ehsan Shafiei
2010-02-01
Full Text Available A novel approach to neural network based tracking-control of robot manipulator including actuator dynamics is proposed by using of backstepping method. A simple two-step backstepping is considered for an nlink robotic system, and a feedforward neural controller is designed at second step where structured and unstructured uncertainties in robot dynamics and actuator model are approximated by this neural controller. Bounds of network reconstruction error and other imprecisions are estimated adaptively and for compensating them, a robust control signal is added and modified. Stability analysis is performed by the Lyapunov direct method and performance efficiency of the proposed controller is justified by the simulations.
Forecasting the mortality rates of Indonesian population by using neural network
Safitri, Lutfiani; Mardiyati, Sri; Rahim, Hendrisman
2018-03-01
A model that can represent a problem is required in conducting a forecasting. One of the models that has been acknowledged by the actuary community in forecasting mortality rate is the Lee-Certer model. Lee Carter model supported by Neural Network will be used to calculate mortality forecasting in Indonesia. The type of Neural Network used is feedforward neural network aligned with backpropagation algorithm in python programming language. And the final result of this study is mortality rate in forecasting Indonesia for the next few years
Ross, Muriel D.
1991-01-01
The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.
Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.
Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus
2017-01-01
Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.
Empirical modeling of nuclear power plants using neural networks
International Nuclear Information System (INIS)
Parlos, A.G.; Atiya, A.; Chong, K.T.
1991-01-01
A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios
Ng, Charles W W; Liu, Jian; Chen, Rui; Xu, Jie
2015-04-01
As an extension of the two-layer capillary barrier, a three-layer capillary barrier landfill cover system is proposed for minimizing rainfall infiltration in humid climates. This system consists of a compacted clay layer lying beneath a conventional cover with capillary barrier effects (CCBE), which is in turn composed of a silt layer sitting on top of a gravelly sand layer. To explore the effectiveness of the new system in minimizing rainfall infiltration, a flume model (3.0 m × 1.0 m × 1.1 m) was designed and set up in this study. This physical model was heavily instrumented to monitor pore water pressure, volumetric water content, surface runoff, infiltration and lateral drainage of each layer, and percolation of the cover system. The cover system was subjected to extreme rainfall followed by evaporation. The experiment was also back-analyzed using a piece of finite element software called CODE_BRIGHT to simulate transient water flows in the test. Based on the results obtained from various instruments, it was found that breakthrough of the two upper layers occurred for a 4-h rainfall event having a 100-year return period. Due to the presence of the newly introduced clay layer, the percolation of the three-layer capillary barrier cover system was insignificant because the clay layer enabled lateral diversion in the gravelly sand layer above. In other words, the gravelly sand layer changed from being a capillary barrier in a convention CCBE cover to being a lateral diversion passage after the breakthrough of the two upper layers. Experimental and back-analysis results confirm that no infiltrated water seeped through the proposed three-layer barrier system. The proposed system thus represents a promising alternative landfill cover system for use in humid climates. Copyright © 2014 Elsevier Ltd. All rights reserved.
A neural network with modular hierarchical learning
Baldi, Pierre F. (Inventor); Toomarian, Nikzad (Inventor)
1994-01-01
This invention provides a new hierarchical approach for supervised neural learning of time dependent trajectories. The modular hierarchical methodology leads to architectures which are more structured than fully interconnected networks. The networks utilize a general feedforward flow of information and sparse recurrent connections to achieve dynamic effects. The advantages include the sparsity of units and connections, the modular organization. A further advantage is that the learning is much more circumscribed learning than in fully interconnected systems. The present invention is embodied by a neural network including a plurality of neural modules each having a pre-established performance capability wherein each neural module has an output outputting present results of the performance capability and an input for changing the present results of the performance capabilitiy. For pattern recognition applications, the performance capability may be an oscillation capability producing a repeating wave pattern as the present results. In the preferred embodiment, each of the plurality of neural modules includes a pre-established capability portion and a performance adjustment portion connected to control the pre-established capability portion.
International Nuclear Information System (INIS)
Smith, J R; Grote, H; Hewitson, M; Hild, S; Lueck, H; Parsons, M; Strain, K A; Willke, B
2005-01-01
The core instrument of the GEO 600 gravitational wave detector is a Michelson interferometer with folded arms. The five main optics that form this interferometer are suspended in vacuum by triple pendulums with quasi-monolithic lower stages of fused silica. After installation of these pendulums in early 2003, a larger than expected coupling of longitudinal ground motion to tilt misalignment of the suspended optics was observed. Because of this, the uncontrolled misalignment of the optics during average conditions was several μrad Hz -1/2 in the frequency band around the pendulum resonance frequencies (0.5-4 Hz). In addition, it was found that longitudinal control signals applied to the intermediate pendulum stages also resulted in excessive mirror tilt. The resulting misalignment exceeded the level tolerable for stable operation of GEO 600. In order to reduce the level of mirror tilt, a bipartite feedforward system was implemented. One part feeds signals derived from seismic measurements to piezo-electric crystals in the stacks supporting the suspensions, reducing the longitudinal motion of the uppermost suspension points. The other applies tilt correction signals, derived from longitudinal control signals, to the intermediate level of the suspensions. The seismic feedforward correction reduces the root-mean-squared tilt misalignment of each main optic between 0.1 and 5 Hz by about 10 dB, typically. The intermediate-mass feedforward correction reduces the differential tilt misalignment of the Michelson interferometer by about 10 dB between 0.1 and 0.8 Hz, typically
Osler, Callum J; Tersteeg, M C A; Reynolds, Raymond F; Loram, Ian D
2013-10-01
Circumstances may render the consequence of falling quite severe, thus maximising the motivation to control postural sway. This commonly occurs when exposed to height and may result from the interaction of many factors, including fear, arousal, sensory information and perception. Here, we examined human vestibular-evoked balance responses during exposure to a highly threatening postural context. Nine subjects stood with eyes closed on a narrow walkway elevated 3.85 m above ground level. This evoked an altered psycho-physiological state, demonstrated by a twofold increase in skin conductance. Balance responses were then evoked by galvanic vestibular stimulation. The sway response, which comprised a whole-body lean in the direction of the edge of the walkway, was significantly and substantially attenuated after ~800 ms. This demonstrates that a strong reason to modify the balance control strategy was created and subjects were highly motivated to minimise sway. Despite this, the initial response remained unchanged. This suggests little effect on the feedforward settings of the nervous system responsible for coupling pure vestibular input to functional motor output. The much stronger, later effect can be attributed to an integration of balance-relevant sensory feedback once the body was in motion. These results demonstrate that the feedforward and feedback components of a vestibular-evoked balance response are differently affected by postural threat. Although a fear of falling has previously been linked with instability and even falling itself, our findings suggest that this relationship is not attributable to changes in the feedforward vestibular control of balance. © 2013 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.
Feedforward Control Strategy for the state-decoupling Stand-alone UPS with LC output filter
DEFF Research Database (Denmark)
Lu, Jinghang; Savaghebi, Mehdi; Guerrero, Josep M.
2017-01-01
In this paper, the disturbance rejection performance of the cascaded control strategy for UPS system is investigated. The comparison of closed loop system performance between conventional cascaded control (CCC) strategy and state-decoupling cascaded control (SDCC) strategy are further explored....... In order to further increase the load current disturbance rejection capability of the state-decoupling in UPS system, a feedforward control strategy is proposed. In addition, the design principle for the current and voltage regulators are discussed. Simulation and experimental results are provided...
A Feed-Forward Controlled AC-DC Boost Converter for Biomedical Implants
DEFF Research Database (Denmark)
Jiang, Hao; Lan, Di; Lin, Dahsien
2012-01-01
circuit for low turn-on voltage) [1]. In order to have a high induced voltage, the size of the receiving coil often is significantly larger than rest of the implant. A rotating magnets based wireless power transfer has been demonstrated to deliver the same amount of power at much lower frequency (around...... 100 Hz) because of the superior magnetic strength produced by rare-earth magnets [2]. Taking the advantage of the low operating frequency, an innovative feed-forward controlled AC to DC boost converter has been demonstrated for the first time to accomplish the following two tasks simultaneously: (1...
Discrete-time quantum walk with feed-forward quantum coin.
Shikano, Yutaka; Wada, Tatsuaki; Horikawa, Junsei
2014-03-21
Constructing a discrete model like a cellular automaton is a powerful method for understanding various dynamical systems. However, the relationship between the discrete model and its continuous analogue is, in general, nontrivial. As a quantum-mechanical cellular automaton, a discrete-time quantum walk is defined to include various quantum dynamical behavior. Here we generalize a discrete-time quantum walk on a line into the feed-forward quantum coin model, which depends on the coin state of the previous step. We show that our proposed model has an anomalous slow diffusion characterized by the porous-medium equation, while the conventional discrete-time quantum walk model shows ballistic transport.
Directory of Open Access Journals (Sweden)
Yasir Hassan Ali
2015-01-01
Full Text Available The thickness of an oil film lubricant can contribute to less gear tooth wear and surface failure. The purpose of this research is to use artificial neural network (ANN computational modelling to correlate spur gear data from acoustic emissions, lubricant temperature, and specific film thickness (λ. The approach is using an algorithm to monitor the oil film thickness and to detect which lubrication regime the gearbox is running either hydrodynamic, elastohydrodynamic, or boundary. This monitoring can aid identification of fault development. Feed-forward and recurrent Elman neural network algorithms were used to develop ANN models, which are subjected to training, testing, and validation process. The Levenberg-Marquardt back-propagation algorithm was applied to reduce errors. Log-sigmoid and Purelin were identified as suitable transfer functions for hidden and output nodes. The methods used in this paper shows accurate predictions from ANN and the feed-forward network performance is superior to the Elman neural network.
Cummine, Jacqueline; Cribben, Ivor; Luu, Connie; Kim, Esther; Bahktiari, Reyhaneh; Georgiou, George; Boliek, Carol A
2016-05-01
The neural circuitry associated with language processing is complex and dynamic. Graphical models are useful for studying complex neural networks as this method provides information about unique connectivity between regions within the context of the entire network of interest. Here, the authors explored the neural networks during covert reading to determine the role of feedforward and feedback loops in covert speech production. Brain activity of skilled adult readers was assessed in real word and pseudoword reading tasks with functional MRI (fMRI). The authors provide evidence for activity coherence in the feedforward system (inferior frontal gyrus-supplementary motor area) during real word reading and in the feedback system (supramarginal gyrus-precentral gyrus) during pseudoword reading. Graphical models provided evidence of an extensive, highly connected, neural network when individuals read real words that relied on coordination of the feedforward system. In contrast, when individuals read pseudowords the authors found a limited/restricted network that relied on coordination of the feedback system. Together, these results underscore the importance of considering multiple pathways and articulatory loops during language tasks and provide evidence for a print-to-speech neural network. (PsycINFO Database Record (c) 2016 APA, all rights reserved).
Kriegeskorte, Nikolaus
2015-11-24
Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications. Human-level visual recognition abilities are coming within reach of artificial systems. Artificial neural networks are inspired by the brain, and their computations could be implemented in biological neurons. Convolutional feedforward networks, which now dominate computer vision, take further inspiration from the architecture of the primate visual hierarchy. However, the current models are designed with engineering goals, not to model brain computations. Nevertheless, initial studies comparing internal representations between these models and primate brains find surprisingly similar representational spaces. With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build biologically faithful feedforward and recurrent computational models of how biological brains perform high-level feats of intelligence, including vision.
Application of a neural network to the sign problem via the path optimization method
Mori, Yuto; Kashiwa, Kouji; Ohnishi, Akira
2018-02-01
We introduce the feedforward neural network to attack the sign problem via the path optimization method. The variables of integration are complexified and the integration path is optimized in the complexified space by minimizing the cost function, which reflects the seriousness of the sign problem. For the preparation and optimization of the integral path in multi-dimensional systems, we utilize the feedforward neural network. We examine the validity and usefulness of the method in the 2D complex λ φ^4 theory at finite chemical potential as an example of the quantum field theory with the sign problem. We show that the average phase factor is significantly enhanced after the optimization and then we can safely perform the hybrid Monte Carlo method.
Zhong, Nianbing; Zhao, Mingfu; Zhong, Lianchao; Liao, Qiang; Zhu, Xun; Luo, Binbin; Li, Yishan
2016-11-15
In this paper, we present a high-sensitivity polymer fiber-optic evanescent wave (FOEW) sensor with a three-layer structure that includes bottom, inter-, and surface layers in the sensing region. The bottom layer and inter-layer are POFs composed of standard cladding and the core of the plastic optical fiber, and the surface layer is made of dilute Canada balsam in xylene doped with GeO2. We examine the morphology of the doped GeO2, the refractive index and composition of the surface layer and the surface luminous properties of the sensing region. We investigate the effects of the content and morphology of the GeO2 particles on the sensitivity of the FOEW sensors by using glucose solutions. In addition, we examine the response of sensors incubated with staphylococcal protein A plus mouse IgG isotype to goat anti-mouse IgG solutions. Results indicate very good sensitivity of the three-layer FOEW sensor, which showed a 3.91-fold improvement in the detection of the target antibody relative to a conventional sensor with a core-cladding structure, and the novel sensor showed a lower limit of detection of 0.2ng/l and a response time around 320s. The application of this high-sensitivity FOEW sensor can be extended to biodefense, disease diagnosis, biomedical and biochemical analysis. Copyright © 2016 Elsevier B.V. All rights reserved.
Panagou, Efstathios Z; Mohareb, Fady R; Argyri, Anthoula A; Bessant, Conrad M; Nychas, George-John E
2011-06-01
A series of partial least squares (PLS) models were employed to correlate spectral data from FTIR analysis with beef fillet spoilage during aerobic storage at different temperatures (0, 5, 10, 15, and 20 °C) using the dataset presented by Argyri et al. (2010). The performance of the PLS models was compared with a three-layer feed-forward artificial neural network (ANN) developed using the same dataset. FTIR spectra were collected from the surface of meat samples in parallel with microbiological analyses to enumerate total viable counts. Sensory evaluation was based on a three-point hedonic scale classifying meat samples as fresh, semi-fresh, and spoiled. The purpose of the modelling approach employed in this work was to classify beef samples in the respective quality class as well as to predict their total viable counts directly from FTIR spectra. The results obtained demonstrated that both approaches showed good performance in discriminating meat samples in one of the three predefined sensory classes. The PLS classification models showed performances ranging from 72.0 to 98.2% using the training dataset, and from 63.1 to 94.7% using independent testing dataset. The ANN classification model performed equally well in discriminating meat samples, with correct classification rates from 98.2 to 100% and 63.1 to 73.7% in the train and test sessions, respectively. PLS and ANN approaches were also applied to create models for the prediction of microbial counts. The performance of these was based on graphical plots and statistical indices (bias factor, accuracy factor, root mean square error). Furthermore, results demonstrated reasonably good correlation of total viable counts on meat surface with FTIR spectral data with PLS models presenting better performance indices compared to ANN. Copyright © 2010 Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Haojie Wang
2016-07-01
Full Text Available It is a common practice for storage batteries to be connected to DC microgrid buses through DC-DC converters for voltage support on islanded operation mode. A feed-forward control based dual-loop constant voltage PI control for three-branch interleaved DC-DC converters (TIDC is proposed for storage batteries in DC microgrids. The working principle of TIDC is analyzed, and the factors influencing the response rate based on the dual-loop constant voltage control for TIDC are discussed, and then the method of feed-forward control for TIDC is studied to improve the response rate for load changing. A prototype of the TIDC is developed and an experimental platform is built. The experiment results show that DC bus voltage sags or swells caused by load changing can be reduced and the time for voltage recovery can be decreased significantly with the proposed feed-forward control.
System Dynamics and Feedforward Control for Tether-Net Space Robot System
Directory of Open Access Journals (Sweden)
Guang Zhai
2009-06-01
Full Text Available A new concept using flexible tether-net system to capture space debris is presented in this paper. With a mass point assumption the tether-net system dynamic model is established in orbital frame by applying Lagrange Equations. In order to investigate the net in-plane trajectories during after cast, the non-control R-bar and V-bar captures are simulated with ignoring the out-of-plane libration, the effect of in-plane libration on the trajectories of the capture net is demonstrated by simulation results. With an effort to damp the in-plane libration, the control scheme based on tether tension is investigated firstly, after that an integrated control scheme is proposed by introduced the thrusters into the system, the nonlinear close-loop dynamics is linearised by feedforward strategy, the simulation results show that feedforward controllor is effective for in-plane libration damping and enable the capture net to track an expected trajectory.
Counteracting Rotor Imbalance in a Bearingless Motor System with Feedforward Control
Kascak, Peter Eugene; Jansen, Ralph H.; Dever, Timothy; Nagorny, Aleksandr; Loparo, Kenneth
2012-01-01
In standard motor applications, traditional mechanical bearings represent the most economical approach to rotor suspension. However, in certain high performance applications, rotor suspension without bearing contact is either required or highly beneficial. Such applications include very high speed, extreme environment, or limited maintenance access applications. This paper extends upon a novel bearingless motor concept, in which full five-axis levitation and rotation of the rotor is achieved using two motors with opposing conical air-gaps. By leaving the motors' pole-pairs unconnected, different d-axis flux in each pole-pair is created, generating a flux imbalance which creates lateral force. Note this is approach is different than that used in previous bearingless motors, which use separate windings for levitation and rotation. This paper will examine the use of feedforward control to counteract synchronous whirl caused by rotor imbalance. Experimental results will be presented showing the performance of a prototype bearingless system, which was sized for a high speed flywheel energy storage application, with and without feedforward control.
Performance of active feedforward control systems in non-ideal, synthesized diffuse sound fields.
Misol, Malte; Bloch, Christian; Monner, Hans Peter; Sinapius, Michael
2014-04-01
The acoustic performance of passive or active panel structures is usually tested in sound transmission loss facilities. A reverberant sending room, equipped with one or a number of independent sound sources, is used to generate a diffuse sound field excitation which acts as a disturbance source on the structure under investigation. The spatial correlation and coherence of such a synthesized non-ideal diffuse-sound-field excitation, however, might deviate significantly from the ideal case. This has consequences for the operation of an active feedforward control system which heavily relies on the acquisition of coherent disturbance source information. This work, therefore, evaluates the spatial correlation and coherence of ideal and non-ideal diffuse sound fields and considers the implications on the performance of a feedforward control system. The system under consideration is an aircraft-typical double panel system, equipped with an active sidewall panel (lining), which is realized in a transmission loss facility. Experimental results for different numbers of sound sources in the reverberation room are compared to simulation results of a comparable generic double panel system excited by an ideal diffuse sound field. It is shown that the number of statistically independent noise sources acting on the primary structure of the double panel system depends not only on the type of diffuse sound field but also on the sample lengths of the processed signals. The experimental results show that the number of reference sensors required for a defined control performance exhibits an inverse relationship to control filter length.
Local excitation-inhibition ratio for synfire chain propagation in feed-forward neuronal networks
Guo, Xinmeng; Yu, Haitao; Wang, Jiang; Liu, Jing; Cao, Yibin; Deng, Bin
2017-09-01
A leading hypothesis holds that spiking activity propagates along neuronal sub-populations which are connected in a feed-forward manner, and the propagation efficiency would be affected by the dynamics of sub-populations. In this paper, how the interaction between local excitation and inhibition effects on synfire chain propagation in feed-forward network (FFN) is investigated. The simulation results show that there is an appropriate excitation-inhibition (EI) ratio maximizing the performance of synfire chain propagation. The optimal EI ratio can significantly enhance the selectivity of FFN to synchronous signals, which thereby increases the stability to background noise. Moreover, the effect of network topology on synfire chain propagation is also investigated. It is found that synfire chain propagation can be maximized by an optimal interlayer linking probability. We also find that external noise is detrimental to synchrony propagation by inducing spiking jitter. The results presented in this paper may provide insights into the effects of network dynamics on neuronal computations.
System Dynamics and Feedforward Control for Tether-Net Space Robot System
Directory of Open Access Journals (Sweden)
Bin Liang
2009-11-01
Full Text Available A new concept using flexible tether-net system to capture space debris is presented in this paper. With a mass point assumption the tether-net system dynamic model is established in orbital frame by applying Lagrange Equations. In order to investigate the net in-plane trajectories during after cast, the non-control R-bar and V-bar captures are simulated with ignoring the out-of-plane libration, the effect of in-plane libration on the trajectories of the capture net is demonstrated by simulation results. With an effort to damp the in-plane libration, the control scheme based on tether tension is investigated firstly, after that an integrated control scheme is proposed by introduced the thrusters into the system, the nonlinear close-loop dynamics is linearised by feedforward strategy, the simulation results show that feedforward controllor is effective for in-plane libration damping and enable the capture net to track an expected trajectory.
Visual language recognition with a feed-forward network of spiking neurons
Energy Technology Data Exchange (ETDEWEB)
Rasmussen, Craig E [Los Alamos National Laboratory; Garrett, Kenyan [Los Alamos National Laboratory; Sottile, Matthew [GALOIS; Shreyas, Ns [INDIANA UNIV.
2010-01-01
An analogy is made and exploited between the recognition of visual objects and language parsing. A subset of regular languages is used to define a one-dimensional 'visual' language, in which the words are translational and scale invariant. This allows an exploration of the viewpoint invariant languages that can be solved by a network of concurrent, hierarchically connected processors. A language family is defined that is hierarchically tiling system recognizable (HREC). As inspired by nature, an algorithm is presented that constructs a cellular automaton that recognizes strings from a language in the HREC family. It is demonstrated how a language recognizer can be implemented from the cellular automaton using a feed-forward network of spiking neurons. This parser recognizes fixed-length strings from the language in parallel and as the computation is pipelined, a new string can be parsed in each new interval of time. The analogy with formal language theory allows inferences to be drawn regarding what class of objects can be recognized by visual cortex operating in purely feed-forward fashion and what class of objects requires a more complicated network architecture.
Directory of Open Access Journals (Sweden)
Bidhan eLamichhane
2015-09-01
Full Text Available Diverse cortical structures are known to coordinate activity as a network in relaying and processing of visual information to discriminate visual objects. However, how this discrimination is achieved is still largely unknown. To contribute to answering this question, we used face-house categorization tasks with three levels of noise in face and house images in functional magnetic resonance imaging (fMRI experiments involving thirty-three participants. The behavioral performance error and response time (RT were correlated with noise in face-house images. We then built dynamical causal models (DCM of fMRI blood-oxygenation level dependent (BOLD signals from the face and house category-specific regions in ventral temporal cortex, the fusiform face area (FFA and parahippocampal place area (PPA, and the dorsolateral prefrontal cortex (dlPFC. We found a strong feed-forward intrinsic connectivity pattern from FFA and PPA to dlPFC. Importantly, the feed-forward connectivity to dlPFC was significantly modulated by the perception of both faces and houses. The dlPFC-BOLD activity, the connectivity from FFA and PPA to the dlPFC all increased with noise level. These results suggest that the FFA-PPA-dlPFC network plays an important role for relaying and integrating competing sensory information to arrive at perceptual decisions.
Force Tracking with Feed-Forward Motion Estimation for Beating Heart Surgery.
Yuen, Shelten G; Perrin, Douglas P; Vasilyev, Nikolay V; Del Nido, Pedro J; Howe, Robert D
2010-08-16
The manipulation of fast moving, delicate tissues in beating heart procedures presents a considerable challenge to the surgeon. A robotic force tracking system can assist the surgeon by applying precise contact forces to the beating heart during surgical manipulation. Standard force control approaches cannot safely attain the required bandwidth for this application due to vibratory modes within the robot structure. These vibrations are a limitation even for single degree of freedom systems driving long surgical instruments. These bandwidth limitations can be overcome by incorporating feed-forward motion terms in the control law. For intracardiac procedures, the required motion estimates can be derived from 3D ultrasound imaging. Dynamic analysis shows that a force controller with feed-forward motion terms can provide safe and accurate force tracking for contact with structures within the beating heart. In vivo validation confirms that this approach confers a 50% reduction in force fluctuations when compared to a standard force controller and a 75% reduction in fluctuations when compared to manual attempts to maintain the same force.
Zech, Philipp; Lato, Victorio; Rinderknecht, Stephan
2017-08-01
The effectiveness of common algorithms for feedforward compensation of narrowband disturbance depends mainly on the model quality. To avoid this dependency several direct adaptive control algorithms without explicitly identified secondary path models have been developed over the last years. However an overview of their properties and a comparison of their performances in a standardized benchmark is still lacking. In this paper the three most promising algorithms are modified for narrowband feedforward vibration control for the use in rotating machinery. As in this application the reference signal is generated using the frequency measurement from a speed sensor it can be assumed that there is no coupling between reference measurement and the secondary path. First the algorithms are tested in simulation, then they are implemented on a test rig for active vibration control of unbalance induced rotor vibration. In simulation as well as for the test rig the performances of the algorithms are compared to each other. Advantages and drawbacks of the algorithms are discussed and practical instructions for implementation are given. The work is intended to serve as starting point and motivation for future research in this field of study.
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control.
Reinhart, René Felix; Shareef, Zeeshan; Steil, Jochen Jakob
2017-02-08
Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant's intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †
Reinhart, René Felix; Shareef, Zeeshan; Steil, Jochen Jakob
2017-01-01
Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant’s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms. PMID:28208697
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †
Directory of Open Access Journals (Sweden)
René Felix Reinhart
2017-02-01
Full Text Available Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant’s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.
A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study
Directory of Open Access Journals (Sweden)
C. A. Mitrea
2009-10-01
Full Text Available Forecasting accuracy drives the performance of inventory management. This study is to investigate and compare different forecasting methods like Moving Average (MA and Autoregressive Integrated Moving Average (ARIMA with Neural Networks (NN models as Feed-forward NN and Nonlinear Autoregressive network with eXogenous inputs (NARX. Data used to forecast is acquired from inventory database of Panasonic Refrigeration Devices Company located in Singapore. Results have shown that forecasting with NN offers better performance in comparison with traditional methods.
Application of Artificial Neural Network to Predict Static Loads on an Aircraft Rib
Amali , Ramin; Cooper , Samson; Noroozi , Siamak
2014-01-01
Part 13: AI Applications - Mobile Applications; International audience; Aircraft wing structures are subjected to different types of loads such as static and dynamic loads throughout their life span. A methodology was developed to predict the static load applied on a wing rib without load cells using Artificial Neural Network (ANN). In conjunction with the finite element modelling of the rib, a classic two layer feed-forward networks were created and trained on MATLAB using the back-propagati...
Adiabatic superconducting cells for ultra-low-power artificial neural networks
Directory of Open Access Journals (Sweden)
Andrey E. Schegolev
2016-10-01
Full Text Available We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.
Using Artificial Neural Networks for ECG Signals Denoising
Directory of Open Access Journals (Sweden)
Zoltán Germán-Salló
2010-12-01
Full Text Available The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1th sample from n previous samples To train and adjust the network weights, the backpropagation (BP algorithm was used. In this paper, prediction of ECG signals (as time series using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.
Neural networks for predicting breeding values and genetic gains
Directory of Open Access Journals (Sweden)
Gabi Nunes Silva
2014-12-01
Full Text Available Analysis using Artificial Neural Networks has been described as an approach in the decision-making process that, although incipient, has been reported as presenting high potential for use in animal and plant breeding. In this study, we introduce the procedure of using the expanded data set for training the network. Wealso proposed using statistical parameters to estimate the breeding value of genotypes in simulated scenarios, in addition to the mean phenotypic value in a feed-forward back propagation multilayer perceptron network. After evaluating artificial neural network configurations, our results showed its superiority to estimates based on linear models, as well as its applicability in the genetic value prediction process. The results further indicated the good generalization performance of the neural network model in several additional validation experiments.
Le, Trong-Ngoc; Bao, Pham The; Huynh, Hieu Trung
2016-01-01
Objective. Our objective is to develop a computerized scheme for liver tumor segmentation in MR images. Materials and Methods. Our proposed scheme consists of four main stages. Firstly, the region of interest (ROI) image which contains the liver tumor region in the T1-weighted MR image series was extracted by using seed points. The noise in this ROI image was reduced and the boundaries were enhanced. A 3D fast marching algorithm was applied to generate the initial labeled regions which are co...
Feeding patterns in group-housed grow-finishing pigs have been investigated for use in management decisions, identifying sick animals, and determining genetic differences within a herd. Development of models to predict swine feeding behaviour has been limited due the large number of potential enviro...
Ross, Muriel D.; Meyer, Glenn; Lam, Tony; Cutler, Lynn; Vaziri, Parshaw
1990-01-01
Computer-assisted reconstructions of small parts of the macular neural network show how the nerve terminals and receptive fields are organized in 3-dimensional space. This biological neural network is anatomically organized for parallel distributed processing of information. Processing appears to be more complex than in computer-based neural network, because spatiotemporal factors figure into synaptic weighting. Serial reconstruction data show anatomical arrangements which suggest that (1) assemblies of cells analyze and distribute information with inbuilt redundancy, to improve reliability; (2) feedforward/feedback loops provide the capacity for presynaptic modulation of output during processing; (3) constrained randomness in connectivities contributes to adaptability; and (4) local variations in network complexity permit differing analyses of incoming signals to take place simultaneously. The last inference suggests that there may be segregation of information flow to central stations subserving particular functions.
Random neural Q-learning for obstacle avoidance of a mobile robot in unknown environments
Directory of Open Access Journals (Sweden)
Jing Yang
2016-07-01
Full Text Available The article presents a random neural Q-learning strategy for the obstacle avoidance problem of an autonomous mobile robot in unknown environments. In the proposed strategy, two independent modules, namely, avoidance without considering the target and goal-seeking without considering obstacles, are first trained using the proposed random neural Q-learning algorithm to obtain their best control policies. Then, the two trained modules are combined based on a switching function to realize the obstacle avoidance in unknown environments. For the proposed random neural Q-learning algorithm, a single-hidden layer feedforward network is used to approximate the Q-function to estimate the Q-value. The parameters of the single-hidden layer feedforward network are modified using the recently proposed neural algorithm named the online sequential version of extreme learning machine, where the parameters of the hidden nodes are assigned randomly and the sample data can come one by one. However, different from the original online sequential version of extreme learning machine algorithm, the initial output weights are estimated subjected to quadratic inequality constraint to improve the convergence speed. Finally, the simulation results demonstrate that the proposed random neural Q-learning strategy can successfully solve the obstacle avoidance problem. Also, the higher learning efficiency and better generalization ability are achieved by the proposed random neural Q-learning algorithm compared with the Q-learning based on the back-propagation method.
Parameter estimation in space systems using recurrent neural networks
Parlos, Alexander G.; Atiya, Amir F.; Sunkel, John W.
1991-01-01
The identification of time-varying parameters encountered in space systems is addressed, using artificial neural systems. A hybrid feedforward/feedback neural network, namely a recurrent multilayer perception, is used as the model structure in the nonlinear system identification. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard back-propagation-learning algorithm is modified and it is used for both the off-line and on-line supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying parameters of nonlinear dynamic systems is investigated by estimating the mass properties of a representative large spacecraft. The changes in the spacecraft inertia are predicted using a trained neural network, during two configurations corresponding to the early and late stages of the spacecraft on-orbit assembly sequence. The proposed on-line mass properties estimation capability offers encouraging results, though, further research is warranted for training and testing the predictive capabilities of these networks beyond nominal spacecraft operations.
Nonlinear identification of process dynamics using neural networks
International Nuclear Information System (INIS)
Parlos, A.G.; Atiya, A.F.; Chong, K.T.
1992-01-01
In this paper the nonlinear identification of process dynamics encountered in nuclear power plant components is addressed, in an input-output sense, using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the model structure to be identified. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard backpropagation learning algorithm is modified, and it is used for the supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The response of representative steam generator is predicted using a neural network, and it is compared to the response obtained from a sophisticated computer model based on first principles. The transient responses compare well, although further research is warranted to determine the predictive capabilities of these networks during more severe operational transients and accident scenarios
Moving image compression and generalization capability of constructive neural networks
Ma, Liying; Khorasani, Khashayar
2001-03-01
To date numerous techniques have been proposed to compress digital images to ease their storage and transmission over communication channels. Recently, a number of image compression algorithms using Neural Networks NNs have been developed. Particularly, several constructive feed-forward neural networks FNNs have been proposed by researchers for image compression, and promising results have been reported. At the previous SPIE AeroSense conference 2000, we proposed to use a constructive One-Hidden-Layer Feedforward Neural Network OHL-FNN for compressing digital images. In this paper, we first investigate the generalization capability of the proposed OHL-FNN in the presence of additive noise for network training and/ or generalization. Extensive experimental results for different scenarios are presented. It is revealed that the constructive OHL-FNN is not as robust to additive noise in input image as expected. Next, the constructive OHL-FNN is applied to moving images, video sequences. The first, or other specified frame in a moving image sequence is used to train the network. The remaining moving images that follow are then generalized/compressed by this trained network. Three types of correlation-like criteria measuring the similarity of any two images are introduced. The relationship between the generalization capability of the constructed net and the similarity of images is investigated in some detail. It is shown that the constructive OHL-FNN is promising even for changing images such as those extracted from a football game.
Kumada, Hiroaki; Kurihara, Toshikazu; Yoshioka, Masakazu; Kobayashi, Hitoshi; Matsumoto, Hiroshi; Sugano, Tomei; Sakurai, Hideyuki; Sakae, Takeji; Matsumura, Akira
2015-12-01
The iBNCT project team with University of Tsukuba is developing an accelerator-based neutron source. Regarding neutron target material, our project has applied beryllium. To deal with large heat load and blistering of the target system, we developed a three-layer structure for the target system that includes a blistering mitigation material between the beryllium used as the neutron generator and the copper heat sink. The three materials were bonded through diffusion bonding using a hot isostatic pressing method. Based on several verifications, our project chose palladium as the intermediate layer. A prototype of the neutron target system was produced. We will verify that sufficient neutrons for BNCT treatment are generated by the device in the near future. Copyright © 2015 Elsevier Ltd. All rights reserved.
A Neural Network Approach for GMA Butt Joint Welding
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least...
Supervised learning of probability distributions by neural networks
Baum, Eric B.; Wilczek, Frank
1988-01-01
Supervised learning algorithms for feedforward neural networks are investigated analytically. The back-propagation algorithm described by Werbos (1974), Parker (1985), and Rumelhart et al. (1986) is generalized by redefining the values of the input and output neurons as probabilities. The synaptic weights are then varied to follow gradients in the logarithm of likelihood rather than in the error. This modification is shown to provide a more rigorous theoretical basis for the algorithm and to permit more accurate predictions. A typical application involving a medical-diagnosis expert system is discussed.
New approach to ECG's features recognition involving neural network
International Nuclear Information System (INIS)
Babloyantz, A.; Ivanov, V.V.; Zrelov, P.V.
2001-01-01
A new approach for the detection of slight changes in the form of the ECG signal is proposed. It is based on the approximation of raw ECG data inside each RR-interval by the expansion in polynomials of special type and on the classification of samples represented by sets of expansion coefficients using a layered feed-forward neural network. The transformation applied provides significantly simpler data structure, stability to noise and to other accidental factors. A by-product of the method is the compression of ECG data with factor 5
AIR POLLUITON INDEX PREDICTION USING MULTIPLE NEURAL NETWORKS
Zainal Ahmad; Nazira Anisa Rahim; Alireza Bahadori; Jie Zhang
2017-01-01
Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN) is shown to be able to predict the Air Pollution Index (API) with a Mean Squared Error (MSE) and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-rob...
A simple mechanical system for studying adaptive oscillatory neural networks
DEFF Research Database (Denmark)
Jouffroy, Guillaume; Jouffroy, Jerome
model, etc.) might be too complex to study. In this paper, we use a comparatively simple mechanical system, the nonholonomic vehicle referred to as the Roller-Racer, as a means towards testing different learning strategies for an Recurrent Neural Network-based (RNN) controller/guidance system. After...... a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component....
International Nuclear Information System (INIS)
Denby, Bruce; Lindsey, Clark; Lyons, Louis
1992-01-01
The 1980s saw a tremendous renewal of interest in 'neural' information processing systems, or 'artificial neural networks', among computer scientists and computational biologists studying cognition. Since then, the growth of interest in neural networks in high energy physics, fueled by the need for new information processing technologies for the next generation of high energy proton colliders, can only be described as explosive
NNSYSID and NNCTRL Tools for system identification and control with neural networks
DEFF Research Database (Denmark)
Nørgaard, Magnus; Ravn, Ole; Poulsen, Niels Kjølstad
2001-01-01
choose among several designs such as direct inverse control, internal model control, nonlinear feedforward, feedback linearisation, optimal control, gain scheduling based on instantaneous linearisation of neural network models and nonlinear model predictive control. This article gives an overview......Two toolsets for use with MATLAB have been developed: the neural network based system identification toolbox (NNSYSID) and the neural network based control system design toolkit (NNCTRL). The NNSYSID toolbox has been designed to assist identification of nonlinear dynamic systems. It contains...... a number of nonlinear model structures based on neural networks, effective training algorithms and tools for model validation and model structure selection. The NNCTRL toolkit is an add-on to NNSYSID and provides tools for design and simulation of control systems based on neural networks. The user can...
Hand-Eye Calibration and Inverse Kinematics of Robot Arm using Neural Network
DEFF Research Database (Denmark)
Wu, Haiyan; Tizzano, Walter; Andersen, Thomas Timm
2013-01-01
Traditional technologies for solving hand-eye calibration and inverse kinematics are cumbersome and time consuming due to the high nonlinearity in the models. An alternative to the traditional approaches is the articial neural network inspired by the remarkable abilities of the animals in dierent...... tasks. This paper describes the theory and implementation of neural networks for hand-eye calibration and inverse kinematics of a six degrees of freedom robot arm equipped with a stereo vision system. The feedforward neural network and the network training with error propagation algorithm are applied....... The proposed approaches are validated in experiments. The results indicate that the hand-eye calibration with simple neural network outperforms the conventional method. Meanwhile, the neural network exhibits a promising performance in solving inverse kinematics....
A neural network architecture for implementation of expert systems for real time monitoring
Ramamoorthy, P. A.
1991-01-01
Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.
NNSYSID and NNCTRL Tools for system identification and control with neural networks
DEFF Research Database (Denmark)
Nørgaard, Magnus; Ravn, Ole; Poulsen, Niels Kjølstad
2001-01-01
Two toolsets for use with MATLAB have been developed: the neural network based system identification toolbox (NNSYSID) and the neural network based control system design toolkit (NNCTRL). The NNSYSID toolbox has been designed to assist identification of nonlinear dynamic systems. It contains...... a number of nonlinear model structures based on neural networks, effective training algorithms and tools for model validation and model structure selection. The NNCTRL toolkit is an add-on to NNSYSID and provides tools for design and simulation of control systems based on neural networks. The user can...... choose among several designs such as direct inverse control, internal model control, nonlinear feedforward, feedback linearisation, optimal control, gain scheduling based on instantaneous linearisation of neural network models and nonlinear model predictive control. This article gives an overview...
Modelling and Prediction of Photovoltaic Power Output Using Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Aminmohammad Saberian
2014-01-01
Full Text Available This paper presents a solar power modelling method using artificial neural networks (ANNs. Two neural network structures, namely, general regression neural network (GRNN feedforward back propagation (FFBP, have been used to model a photovoltaic panel output power and approximate the generated power. Both neural networks have four inputs and one output. The inputs are maximum temperature, minimum temperature, mean temperature, and irradiance; the output is the power. The data used in this paper started from January 1, 2006, until December 31, 2010. The five years of data were split into two parts: 2006–2008 and 2009-2010; the first part was used for training and the second part was used for testing the neural networks. A mathematical equation is used to estimate the generated power. At the end, both of these networks have shown good modelling performance; however, FFBP has shown a better performance comparing with GRNN.
DEFF Research Database (Denmark)
Wang, Haojie; Han, Minxiao; Yan, Wenli
2016-01-01
for storage batteries in DC microgrids. The working principle of TIDC is analyzed, and the factors influencing the response rate based on the dual-loop constant voltage control for TIDC are discussed, and then the method of feed-forward control for TIDC is studied to improve the response rate for load...
Sub-Shot-Noise Transmission Measurement Enabled by Active Feed-Forward of Heralded Single Photons
Sabines-Chesterking, J.; Whittaker, R.; Joshi, S. K.; Birchall, P. M.; Moreau, P. A.; McMillan, A.; Cable, H. V.; O'Brien, J. L.; Rarity, J. G.; Matthews, J. C. F.
2017-07-01
Harnessing the unique properties of quantum mechanics offers the possibility of delivering alternative technologies that can fundamentally outperform their classical counterparts. These technologies deliver advantages only when components operate with performance beyond specific thresholds. For optical quantum metrology, the biggest challenge that impacts on performance thresholds is optical loss. Here, we demonstrate how including an optical delay and an optical switch in a feed-forward configuration with a stable and efficient correlated photon-pair source reduces the detector efficiency required to enable quantum-enhanced sensing down to the detection level of single photons and without postselection. When the switch is active, we observe a factor of improvement in precision of 1.27 for transmission measurement on a per-input-photon basis compared to the performance of a laser emitting an ideal coherent state and measured with the same detection efficiency as our setup. When the switch is inoperative, we observe no quantum advantage.
McDermott, Ashley F; Rose, Maya; Norris, Troy; Gordon, Eric
2016-01-28
This study tested a novel feed-forward modeling (FFM) system as a nonpharmacological intervention for the treatment of ADHD children and the training of cognitive skills that improve academic performance. This study implemented a randomized, controlled, parallel design comparing this FFM with a nonpharmacological community care intervention. Improvements were measured on parent- and clinician-rated scales of ADHD symptomatology and on academic performance tests completed by the participant. Participants were followed for 3 months after training. Participants in the FFM training group showed significant improvements in ADHD symptomatology and academic performance, while the control group did not. Improvements from FFM were sustained 3 months later. The FFM appeared to be an effective intervention for the treatment of ADHD and improving academic performance. This FFM training intervention shows promise as a first-line treatment for ADHD while improving academic performance. © The Author(s) 2016.
Directory of Open Access Journals (Sweden)
Youngseung Na
2015-09-01
Full Text Available Most of the R&D on fuel cells for portable applications concentrates on increasing efficiencies and energy densities to compete with other energy storage devices, especially batteries. To improve the efficiency of direct methanol fuel cell (DMFC systems, several modifications to system layouts and operating strategies are considered in this paper, rather than modifications to the fuel cell itself. Two modified DMFC systems are presented, one with an additional inline mixer and a further modification of it with a separate tank to recover condensed water. The set point for methanol concentration control in the solution is determined by fuel efficiency and varies with the current and other process variables. Feedforward concentration control enables variable concentration for dynamic loads. Simulation results were validated experimentally with fuel cell systems.
Soliton generation from a fundamentally mode-locked fiber laser with a feed-forward path
Wang, Ruixin; Dai, Yitang; Yin, Feifei; Xu, Kun; Li, Jianqiang; Lin, Jintong
2014-08-01
We demonstrate for the first time to our knowledge, the soliton generation from a mode-locked erbium-doped fiber laser using a novel saturable absorber (SA), which is realized by combining a dual-drive modulator and an intensity feed-forward path. The laser is fundamentally mode-locked under high-frequency RF signal modulation. Experimentally, the actively mode-locked laser produces a 16.7 MHz repetition rate pulse train with a 1.4 ps pulse width, and the spectrum bandwidth is 2.17 nm. The results demonstrate that the SA supports soliton pulse shaping in the cavity at the fundamental frequency.
Feedforward self-modeling enhances skill acquisition in children learning trampoline skills
Directory of Open Access Journals (Sweden)
Diane M. Ste-Marie
2011-07-01
Full Text Available The purpose of this research was to examine whether children would benefit from a feedforward self-modeling (FSM video and to explore possible explanatory mechanisms for the potential benefits, using a self-regulation framework. To this end, children were involved in learning two five-skill trampoline routines. For one of the routines, a FSM video was provided during acquisition, whereas only verbal instructions were provided for the alternate routine. The FSM involved editing video footage such that it showed the learner performing the trampoline routine at a higher skill level than their current capability. Analyses of the data showed that while physical performance benefits were observed for the routine that was learned with the FSM video, no differences were obtained in relation to the self-regulatory measures. Thus, the FSM video enhanced motor skill acquisition, but this could not be explained by changes to the varied self-regulatory processes examined.
Operating wind turbines in strong wind conditions by using feedforward-feedback control
International Nuclear Information System (INIS)
Feng, Ju; Sheng, Wen Zhong
2014-01-01
Due to the increasing penetration of wind energy into power systems, it becomes critical to reduce the impact of wind energy on the stability and reliability of the overall power system. In precedent works, Shen and his co-workers developed a re-designed operation schema to run wind turbines in strong wind conditions based on optimization method and standard PI feedback control, which can prevent the typical shutdowns of wind turbines when reaching the cut-out wind speed. In this paper, a new control strategy combing the standard PI feedback control with feedforward controls using the optimization results is investigated for the operation of variable-speed pitch-regulated wind turbines in strong wind conditions. It is shown that the developed control strategy is capable of smoothening the power output of wind turbine and avoiding its sudden showdown at high wind speeds without worsening the loads on rotor and blades
Increasing LIGO sensitivity by feedforward subtraction of auxiliary length control noise
International Nuclear Information System (INIS)
Meadors, Grant David; Riles, Keith; Kawabe, Keita
2014-01-01
LIGO, the Laser Interferometer Gravitational-wave Observatory, has been designed and constructed to measure gravitational wave strain via differential arm length. The LIGO 4 km Michelson arms with Fabry–Perot cavities have auxiliary length control servos for suppressing Michelson motion of the beam-splitter and arm cavity input mirrors, which degrades interferometer sensitivity. We demonstrate how a post facto pipeline improves a data sample from LIGO Science Run 6 with feedforward subtraction. Dividing data into 1024 s windows, we numerically fit filter functions representing the frequency-domain transfer functions from Michelson length channels into the gravitational-wave strain data channel for each window, then subtract the filtered Michelson channel noise (witness) from the strain channel (target). In this paper we describe the algorithm, assess achievable improvements in sensitivity to astrophysical sources, and consider relevance to future interferometry. (paper)
Arm Dominance Affects Feedforward Strategy more than Feedback Sensitivity during a Postural Task
Walker, Elise H. E.; Perreault, Eric J.
2015-01-01
Handedness is a feature of human motor control that is still not fully understood. Recent work has demonstrated that the dominant and nondominant arm each excel at different behaviors, and has proposed that this behavioral asymmetry arises from lateralization in the cerebral cortex: the dominant side specializes in predictive trajectory control, while the nondominant side is specialized for impedance control. Long-latency stretch reflexes are an automatic mechanism for regulating posture, and have been shown to contribute to limb impedance. To determine whether long-latency reflexes also contribute to asymmetric motor behavior in the upper limbs, we investigated the effect of arm dominance on stretch reflexes during a postural task that required varying degrees of impedance control. Our results demonstrated slightly but significantly larger reflex responses in the biarticular muscles of the nondominant arm, as would be consistent with increased impedance control. These differences were attributed solely to higher levels of voluntary background activity in the nondominant biarticular muscles, indicating that feedforward strategies for postural stability may differ between arms. Reflex sensitivity, which was defined as the magnitude of the reflex response for matched levels of background activity, was not significantly different between arms for a broad subject population ranging from 23–51 years of age. These results indicate that inter-arm differences in feedforward strategies are more influential during posture than differences in feedback sensitivity, in a broad subject population. Interestingly, restricting our analysis to subjects under 40 years of age revealed a small increase in long-latency reflex sensitivity in the nondominant arm relative to the dominant arm. Though our subject numbers were small for this secondary analysis, it suggests that further studies may be required to assess the influence of reflex lateralization throughout development. PMID
Deterministic quantum teleportation with feed-forward in a solid state system.
Steffen, L; Salathe, Y; Oppliger, M; Kurpiers, P; Baur, M; Lang, C; Eichler, C; Puebla-Hellmann, G; Fedorov, A; Wallraff, A
2013-08-15
Engineered macroscopic quantum systems based on superconducting electronic circuits are attractive for experimentally exploring diverse questions in quantum information science. At the current state of the art, quantum bits (qubits) are fabricated, initialized, controlled, read out and coupled to each other in simple circuits. This enables the realization of basic logic gates, the creation of complex entangled states and the demonstration of algorithms or error correction. Using different variants of low-noise parametric amplifiers, dispersive quantum non-demolition single-shot readout of single-qubit states with high fidelity has enabled continuous and discrete feedback control of single qubits. Here we realize full deterministic quantum teleportation with feed-forward in a chip-based superconducting circuit architecture. We use a set of two parametric amplifiers for both joint two-qubit and individual qubit single-shot readout, combined with flexible real-time digital electronics. Our device uses a crossed quantum bus technology that allows us to create complex networks with arbitrary connecting topology in a planar architecture. The deterministic teleportation process succeeds with order unit probability for any input state, as we prepare maximally entangled two-qubit states as a resource and distinguish all Bell states in a single two-qubit measurement with high efficiency and high fidelity. We teleport quantum states between two macroscopic systems separated by 6 mm at a rate of 10(4) s(-1), exceeding other reported implementations. The low transmission loss of superconducting waveguides is likely to enable the range of this and other schemes to be extended to significantly larger distances, enabling tests of non-locality and the realization of elements for quantum communication at microwave frequencies. The demonstrated feed-forward may also find application in error correction schemes.
Water demand prediction using artificial neural networks and support vector regression
CSIR Research Space (South Africa)
Msiza, IS
2008-11-01
Full Text Available the architecture of the two neural networks employed in this chapter. 1) The multi-layer perceptron (MLP): A multilayer perceptron can be defined as a feed-forward neural net- work model that approximates a relationship between sets of input data and a set... of appropriate output. Its foundation is the standard linear perceptron and it makes use of three or more layers of neurons (nodes) with non- linear activation functions, and is more powerful than the perceptron. This is because it can distinguish data...
Investigation of tt in the full hadronic final state at CDF with a neural network approach
Sidoti, A; Busetto, G; Castro, A; Dusini, S; Lazzizzera, I; Wyss, J
2001-01-01
In this work we present the results of a neural network (NN) approach to the measurement of the tt production cross-section and top mass in the all-hadronic channel, analyzing data collected at the Collider Detector at Fermilab (CDF) experiment. We have used a hardware implementation of a feedforward neural network, TOTEM, the product of a collaboration of INFN (Istituto Nazionale Fisica Nucleare)-IRST (Istituto per la Ricerca Scientifica e Tecnologica)-University of Trento, Italy. Particular attention has been paid to the evaluation of the systematics specifically related to the NN approach. The results are consistent with those obtained at CDF by conventional data selection techniques. (38 refs).
Recurrent neural networks for NO{sub x} prediction in fossil plants
Energy Technology Data Exchange (ETDEWEB)
Reifman, J.; Vitela, J.E.; Feldman, E.E.; Wei, T.Y.C.
1996-04-01
The authors discuss the application of recurrent (dynamic) neural networks for time-dependent modeling of NO{sub x} emissions in coal-fired fossil plants. They use plant data from one of ComEd`s plants to train and test the network model. Additional tests, parametric studies, and sensitivity analyses are performed to determine if the dynamic behavior of the model matches the expected behavior of the physical system. The results are also compared with feedforward (static) neural network models trained to represent temporal information.
Egg hatchability prediction by multiple linear regression and artificial neural networks
Directory of Open Access Journals (Sweden)
AC Bolzan
2008-06-01
Full Text Available An artificial neural network (ANN was compared with a multiple linear regression statistical method to predict hatchability in an artificial incubation process. A feedforward neural network architecture was applied. Network trainings were made by the backpropagation algorithm based on data obtained from industrial incubations. The ANN model was chosen as it produced data that fit better the experimental data as compared to the multiple linear regression model, which used coefficients determined by minimum square method. The proposed simulation results of these approaches indicate that this ANN can be used for incubation performance prediction.
International Nuclear Information System (INIS)
Seker, Serhat; Tuerkcan, Erdinc; Ayaz, Emine; Barutcu, Burak
2003-01-01
This paper addresses to the problem of utilisation of the artificial neural networks (ANNs) for detecting anomalies as well as physical parameters of a nuclear power plant during power operation in real time. Three different types of neural network algorithms were used namely, feed-forward neural network (back-propagation, BP) and two types of recurrent neural networks (RNN). The data used in this paper were gathered from the simulation of the power operation of the Japan's High Temperature Engineering Testing Reactor (HTTR). For the wide range of power operation, 56 signals were generated by the reactor dynamic simulation code for several hours of normal power operation at different power ramps between 30 and 100% nominal power. Paper will compare the outcomes of different neural networks and presents the neural network system and the determination of physical parameters from the simulated operating data
A neural network approach to cloud classification
Lee, Jonathan; Weger, Ronald C.; Sengupta, Sailes K.; Welch, Ronald M.
1990-01-01
It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach. A texture-based neural network classifier using only single-channel visible Landsat MSS imagery achieves an overall cloud identification accuracy of 93 percent. Cirrus can be distinguished from boundary layer cloudiness with an accuracy of 96 percent, without the use of an infrared channel. Stratocumulus is retrieved with an accuracy of 92 percent, cumulus at 90 percent. The use of the neural network does not improve cirrus classification accuracy. Rather, its main effect is in the improved separation between stratocumulus and cumulus cloudiness. While most cloud classification algorithms rely on linear parametric schemes, the present study is based on a nonlinear, nonparametric four-layer neural network approach. A three-layer neural network architecture, the nonparametric K-nearest neighbor approach, and the linear stepwise discriminant analysis procedure are compared. A significant finding is that significantly higher accuracies are attained with the nonparametric approaches using only 20 percent of the database as training data, compared to 67 percent of the database in the linear approach.
Neurale Netværk anvendt indenfor Proceskontrol. Neural Network for Process Control
DEFF Research Database (Denmark)
Madsen, Per Printz
Dette projekt omhandler anvendelsen af neurale netværksmodeller til proceskontrol. Neurale netværksmodeller er simple modeller af de processer, der forløber i det biologiske neurale netværk. Det biologiske neurale netværk er det netværk af nerveceller, der tilsammen danner centralnervesystemet hos...... at generere indlærings- og testdata. Af de tre valgte netværkstyper er der kun Multi-Layer Perceptron nette, der e ranvendeligt til prediction og simulering af dynamiske systemer ud fra de opstillede koncepter og metoder. I sidste kapitel, omhandlende regulering, er der således også anvendt Multi......-Layer Perceptron net. Der er opstillet koncepter/metoder til såvel feedforward regulering som feedback regulering. Multi-Layer Perceptronen er i stand til at regulere et ulineært, multivariabelt og dynamisk system, således at der opnås følgende: 1. Systemet lineariseres således, at der opnås ensartet steprespons i...
International Nuclear Information System (INIS)
Zuo Guomin; Li Xinxin
2011-01-01
This research is aimed at elucidating surface-energy (or interfacial energy) variation during the process of molecule-layer self-assembly on a solid surface. A quasi-quantitative plotting model is proposed and established to distinguish the surface-energy variation contributed by the three characteristic layers of a thiol-on-gold self-assembled monolayer (SAM), namely the assembly-medium correlative gold/head-group layer, the chain/chain interaction layer and the tail/medium layer, respectively. The data for building the model are experimentally extracted from a set of correlative thiol self-assemblies in different media. The variation in surface-energy during self-assembly is obtained by in situ recording of the self-assembly induced nanomechanical surface-stress using integrated micro-cantilever sensors. Based on the correlative self-assembly experiment, and by using the nanomechanically sensitive self-sensing cantilevers to monitor the self-assembly induced surface-stressin situ, the experimentally extracted separate contributions of the three layers to the overall surface-energy change aid a comprehensive understanding of the self-assembly mechanism. Moreover, the quasi-quantitative modeling method is helpful for optimal design, molecule synthesis and performance evaluation of molecule self-assembly for application-specific surface functionalization.
Park, Jaeyeong; Kim, Jung-Su; Kang, Minju; Sohn, Seok Su; Cho, Won Tae; Kim, Hyoung Seop; Lee, Sunghak
2017-01-09
TWIP-cored three-layer steel sheets were newly fabricated by hot rolling of TWIP steel sheet surrounded by low-carbon (LC) or interstitial-free (IF) steel sheets. TWIP/LC or TWIP/IF interfaces were well bonded without pores or voids, while a few pearlites were thinly formed along the interfaces. The strengths and elongation of the TWIP-cored sheets increased as the volume fraction of TWIP-cored region increased, and were also well matched with the ones calculated by a rule of mixtures based on volume fraction or force fraction. According to digital image correlation and electron back-scatter diffraction analyses, very high strain hardening effect in the initial deformation stage and active twin formation in the interfacial region beneficially affected the overall homogeneous deformation in the TWIP-cored sheets without any yield point phenomenon occurring in the LC sheet and serrations occurring in the TWIP sheet, respectively. These TWIP-cored sheets can cover a wide range of yield strength, tensile strength, and ductility levels, e.g., 320~498 MPa, 545~878 MPa, and 48~54%, respectively, by controlling the volume fraction of TWIP-cored region, and thus present new applications to multi-functional automotive steel sheets requiring excellent properties.
Kríz, Jaroslav; Plestil, Josef; Pospísil, Herman; Kadlec, Petr; Konák, Cestmír; Almásy, László; Kuklin, Alexander I
2004-12-07
Three-layer nanoparticles were prepared by radiation-induced polymerization of 1-10 g/L of methyl methacrylate dissolved in a 0.1 wt % D(2)O solution of polystyrene-poly(methacrylic acid) (PS-PMA) micelles. According to NMR and small-angle neutron scattering (SANS), most of the poly(methyl methacrylate) (PMMA) is adsorbed at the core-shell interface of the particles. A small fraction of shorter PMMA probably sticks to outer parts of the PMA chains. The absorption kinetics and equilibria of benzene and chloroform were studied by NMR and SANS time-resolved experiments. The diffusion front in the PS core is very narrow but quite broad in the PMMA sheet suggesting, thus, a less compact state of PMMA. According to SANS, the diffusion kinetics is almost independent of the PMMA sheet thickness. In contrast to it, the absorption capacity, reflected by both SANS and NMR, increases markedly with the PMMA content in the particle. The maximum amount of solubilized compound depends on its positive interaction with PMMA (expressed by the chi parameter) but is restricted by the growing interface tension between swollen PMMA and D(2)O. In accordance with this conclusion, a particle saturated with benzene can absorb chloroform only at the expense of a part of benzene expelled into the surrounding medium and vice versa. Starting with 10 g PMMA/L (10 times the weight of the original micelles), the particles become unstable when being swollen with a good solvent.
Pan, Wen-hao; Liu, Shi-he; Huang, Li
2018-02-01
This study developed a three-layer velocity model for turbulent flow over large-scale roughness. Through theoretical analysis, this model coupled both surface and subsurface flow. Flume experiments with flat cobble bed were conducted to examine the theoretical model. Results show that both the turbulent flow field and the total flow characteristics are quite different from that in the low gradient flow over microscale roughness. The velocity profile in a shallow stream converges to the logarithmic law away from the bed, while inflecting over the roughness layer to the non-zero subsurface flow. The velocity fluctuations close to a cobble bed are different from that of a sand bed, and it indicates no sufficiently large peak velocity. The total flow energy loss deviates significantly from the 1/7 power law equation when the relative flow depth is shallow. Both the coupled model and experiments indicate non-negligible subsurface flow that accounts for a considerable proportion of the total flow. By including the subsurface flow, the coupled model is able to predict a wider range of velocity profiles and total flow energy loss coefficients when compared with existing equations.
International Nuclear Information System (INIS)
Djurup, R.; Soendergaard, I.; Weeke, B.; University of Copenhagen, Denmark); Magnusson, C.G.M.
1984-01-01
We report the development of a three-layer immunoradiometric assay (TIRA) for measurement of IgG antibodies of all four subclasses in human sera. The first layer consists of diluted human serum, the second layer is monoclonal mouse antibodies to human IgG subclasses, and the third layer is 125 I-labelled rabbit anti-mouse IgG. Monoclonal anti-IgGI, anti-IgG3 and anti-IgG4 reacted only with their complementary IgG subclass, whereas the anti-IgG2 showed slight cross-reactivity to immunoglobins of other subclasses and classes and to light chain proteins. The observed cross-reactivity was found to be without importance, when the TIRA was applied to measurement of IgG subclass antibodies. Equipotency was established by use of appropriate dilutions of the monoclonal antibodies, and the assay was calibrated by use of human reference serum. The TIRA therefore permits reliable inter-individual and intra-individual comparisons of the IgG antibody response in all four subclasses. Non-specific binding obtained with pooled normal human serum was below 0.33%. Inter-assay coefficient of variation was between 18 and 27%. The TIRA was applied to measurement of IgG subclass antibodies to timothy grass pollen in sera from grass pollen allergies undergoing immunotherapy. (author)
Estimation of concrete compressive strength using artificial neural network
Directory of Open Access Journals (Sweden)
Kostić Srđan
2015-01-01
Full Text Available In present paper, concrete compressive strength is evaluated using back propagation feed-forward artificial neural network. Training of neural network is performed using Levenberg-Marquardt learning algorithm for four architectures of artificial neural networks, one, three, eight and twelve nodes in a hidden layer in order to avoid the occurrence of overfitting. Training, validation and testing of neural network is conducted for 75 concrete samples with distinct w/c ratio and amount of superplasticizer of melamine type. These specimens were exposed to different number of freeze/thaw cycles and their compressive strength was determined after 7, 20 and 32 days. The obtained results indicate that neural network with one hidden layer and twelve hidden nodes gives reasonable prediction accuracy in comparison to experimental results (R=0.965, MSE=0.005. These results of the performed analysis are further confirmed by calculating the standard statistical errors: the chosen architecture of neural network shows the smallest value of mean absolute percentage error (MAPE=, variance absolute relative error (VARE and median absolute error (MEDAE, and the highest value of variance accounted for (VAF.
Development of an Accurate Feed-Forward Temperature Control Tankless Water Heater
Energy Technology Data Exchange (ETDEWEB)
David Yuill
2008-06-30
The following document is the final report for DE-FC26-05NT42327: Development of an Accurate Feed-Forward Temperature Control Tankless Water Heater. This work was carried out under a cooperative agreement from the Department of Energy's National Energy Technology Laboratory, with additional funding from Keltech, Inc. The objective of the project was to improve the temperature control performance of an electric tankless water heater (TWH). The reason for doing this is to minimize or eliminate one of the barriers to wider adoption of the TWH. TWH use less energy than typical (storage) water heaters because of the elimination of standby losses, so wider adoption will lead to reduced energy consumption. The project was carried out by Building Solutions, Inc. (BSI), a small business based in Omaha, Nebraska. BSI partnered with Keltech, Inc., a manufacturer of electric tankless water heaters based in Delton, Michigan. Additional work was carried out by the University of Nebraska and Mike Coward. A background study revealed several advantages and disadvantages to TWH. Besides using less energy than storage heaters, TWH provide an endless supply of hot water, have a longer life, use less floor space, can be used at point-of-use, and are suitable as boosters to enable alternative water heating technologies, such as solar or heat-pump water heaters. Their disadvantages are their higher cost, large instantaneous power requirement, and poor temperature control. A test method was developed to quantify performance under a representative range of disturbances to flow rate and inlet temperature. A device capable of conducting this test was designed and built. Some heaters currently on the market were tested, and were found to perform quite poorly. A new controller was designed using model predictive control (MPC). This control method required an accurate dynamic model to be created and required significant tuning to the controller before good control was achieved. The MPC
Zhang, Zhuoyong; Wang, Yamin; Fan, Guoqiang; Harrington, Peter de B
2007-01-01
Artificial neural networks have gained much attention in recent years as fast and flexible methods for quality control in traditional medicine. Near-infrared (NIR) spectroscopy has become an accepted method for the qualitative and quantitative analyses of traditional Chinese medicine since it is simple, rapid, and non-destructive. The present paper describes a method by which to discriminate official and unofficial rhubarb samples using three layer perceptron neural networks applied to NIR data. Multilayer perceptron neural networks were trained with back propagation, delta-bar-delta and quick propagation algorithms. Results obtained using these methods were all satisfactory, but the best outcomes were obtained with the delta-bar-delta algorithm.
2013-01-01
Neural Engineering, 2nd Edition, contains reviews and discussions of contemporary and relevant topics by leading investigators in the field. It is intended to serve as a textbook at the graduate and advanced undergraduate level in a bioengineering curriculum. This principles and applications approach to neural engineering is essential reading for all academics, biomedical engineers, neuroscientists, neurophysiologists, and industry professionals wishing to take advantage of the latest and greatest in this emerging field.
Directory of Open Access Journals (Sweden)
Abdulaziz Alfadhli
2018-04-01
Full Text Available Active seat suspensions can be used to reduce the harmful vertical vibration of a vehicle’s seat by applying an external force using a closed loop controller. Many of the controllers found in the literature are difficult to implement practically, because they are based on using unavailable or difficult and costly measurements. This paper presents both simulation and experimental studies of five novel, simple, and cost-effective control strategies to be used for an active seat suspension in order to improve ride comfort at low frequencies below 20 Hz. These strategies use available and measurable feedforward (preview information states from the vehicle secondary suspension, as well as feedback states from the seat suspension, together with gains optimised to minimise the occupant vibration. The gains were optimised using a genetic algorithm (GA, with a fitness function based on the seat effective amplitude transmissibility (SEAT factor. Constraints on the control force and the seat suspension stroke were also included in the optimisation algorithm. Simulation and laboratory experimental tests were carried out to assess the performance of the proposed controllers according to the ISO 2631-1 standard, in both the frequency and time domains with a range of different road profiles. The experimental tests were performed using a multi-axis simulation table (MAST and a physical active seat suspension configured as a hardware-in-loop (HIL simulation with a virtual linear quarter vehicle model (QvM. The results demonstrate that the proposed controllers substantially attenuate the vertical vibration at the driver’s seat compared with both a passive and a proportional-integral-derivative (PID active seat suspension and thus improve ride comfort together with reducing vibration-linked health risks. Moreover, experimental results show that employing both feedforward information and feedback vehicle body and seat acceleration signals in the controller
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
DEFF Research Database (Denmark)
Kock, Anders Bredahl; Teräsvirta, Timo
In this paper we consider the forecasting performance of a well-defined class of flexible models, the so-called single hidden-layer feedforward neural network models. A major aim of our study is to find out whether they, due to their flexibility, are as useful tools in economic forecasting as some...... previous studies have indicated. When forecasting with neural network models one faces several problems, all of which influence the accuracy of the forecasts. First, neural networks are often hard to estimate due to their highly nonlinear structure. In fact, their parameters are not even globally...... on the linearisation idea: the Marginal Bridge Estimator and Autometrics. Second, one must decide whether forecasting should be carried out recursively or directly. Comparisons of these two methodss exist for linear models and here these comparisons are extended to neural networks. Finally, a nonlinear model...
Plett, Gregory; Doi, Takeshi; Torrieri, Don
1996-05-01
The detection and disposal of anti-personnel landmines is one of the most difficult and intractable problems faced in ground conflict. This paper first presents current detection methods which use a separated aperture microwave sensor and an artificial neural-network pattern classifier. Several data-specific pre-processing methods are developed to enhance neural-network learning. In addition, a generalized Karhunen-Loeve transform and the eigenspace separation transform are used to perform data reduction and reduce network complexity. Highly favorable results have been obtained using the above methods in conjunction with a feedforward neural network. Secondly, a very promising idea relating to future research is proposed that uses acoustic modulation of the microwave signal to provide an additional independent feature to the input of the neural network. The expectation is that near-perfect mine detection will be possible with this proposed system.
Identification of Complex Dynamical Systems with Neural Networks (2/2)
CERN. Geneva
2016-01-01
The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...
Identification of Complex Dynamical Systems with Neural Networks (1/2)
CERN. Geneva
2016-01-01
The identification and analysis of high dimensional nonlinear systems is obviously a challenging task. Neural networks have been proven to be universal approximators but this still leaves the identification task a hard one. To do it efficiently, we have to violate some of the rules of classical regression theory. Furthermore we should focus on the interpretation of the resulting model to overcome its black box character. First, we will discuss function approximation with 3 layer feedforward neural networks up to new developments in deep neural networks and deep learning. These nets are not only of interest in connection with image analysis but are a center point of the current artificial intelligence developments. Second, we will focus on the analysis of complex dynamical system in the form of state space models realized as recurrent neural networks. After the introduction of small open dynamical systems we will study dynamical systems on manifolds. Here manifold and dynamics have to be identified in parall...
Artificial neural networks for spatial distribution of fuel assemblies in reload of PWR reactors
International Nuclear Information System (INIS)
Oliveira, Edyene; Castro, Victor F.; Velásquez, Carlos E.; Pereira, Claubia
2017-01-01
An artificial neural network methodology is being developed in order to find an optimum spatial distribution of the fuel assemblies in a nuclear reactor core during reload. The main bounding parameter of the modelling was the neutron multiplication factor, k ef f . The characteristics of the network are defined by the nuclear parameters: cycle, burnup, enrichment, fuel type, and average power peak of each element. These parameters were obtained by the ORNL nuclear code package SCALE6.0. As for the artificial neural network, the ANN Feedforward Multi L ayer P erceptron with various layers and neurons were constructed. Three algorithms were used and tested: LM (Levenberg-Marquardt), SCG (Scaled Conjugate Gradient) and BayR (Bayesian Regularization). Artificial neural network have implemented using MATLAB 2015a version. As preliminary results, the spatial distribution of the fuel assemblies in the core using a neural network was slightly better than the standard core. (author)
A hybrid neural network model in handwritten word recognition.
Chiang, J H
1998-03-01
A hybrid neural network model is developed and applied to handwritten word recognition. The word recognition system requires a module that assigns character class confidence values to segments of images of handwritten words. The module must accurately represent ambiguities between character classes and assign low confidence values to a wide variety of non-character segments resulting from erroneous segmentations. The proposed hybrid neural model is a cascaded system. The first stage is a self-organizing feature map algorithm (SOFM). The second stage maps distances into allograph membership values using a gradient descent learning algorithm. The third stage is a multi-layer feedforward network (MLFN). The new system performs better than the baseline system. Experiments were performed on a standard test set from the SUNY/USPS Database.
Spiking neural network for recognizing spatiotemporal sequences of spikes
International Nuclear Information System (INIS)
Jin, Dezhe Z.
2004-01-01
Sensory neurons in many brain areas spike with precise timing to stimuli with temporal structures, and encode temporally complex stimuli into spatiotemporal spikes. How the downstream neurons read out such neural code is an important unsolved problem. In this paper, we describe a decoding scheme using a spiking recurrent neural network. The network consists of excitatory neurons that form a synfire chain, and two globally inhibitory interneurons of different types that provide delayed feedforward and fast feedback inhibition, respectively. The network signals recognition of a specific spatiotemporal sequence when the last excitatory neuron down the synfire chain spikes, which happens if and only if that sequence was present in the input spike stream. The recognition scheme is invariant to variations in the intervals between input spikes within some range. The computation of the network can be mapped into that of a finite state machine. Our network provides a simple way to decode spatiotemporal spikes with diverse types of neurons
Classification of data patterns using an autoassociative neural network topology
Dietz, W. E.; Kiech, E. L.; Ali, M.
1989-01-01
A diagnostic expert system based on neural networks is developed and applied to the real-time diagnosis of jet and rocket engines. The expert system methodologies are based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. The approach addresses deficiencies inherent in many feedforward neural network models and greatly reduces the number of networks necessary to identify the existence of a fault condition and estimate the duration and severity of the identified fault. The network topology used in the present implementation of the diagnostic system is described, as well as the training regimen used and the response of the system to inputs representing both previously observed and unknown fault scenarios. Noise effects on the integrity of the diagnosis are also evaluated.
An Artificial Neural Network for Data Forecasting Purposes
Directory of Open Access Journals (Sweden)
Catalina Lucia COCIANU
2015-01-01
Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.
Neural Network Based Indexing and Recognition of Power Quality Disturbances
Directory of Open Access Journals (Sweden)
Ram Awtar Gupta
2011-08-01
Full Text Available Power quality (PQ analysis has become imperative for utilities as well as for consumers due to huge cost burden of poor power quality. Accurate recognition of PQ disturbances is still a challenging task, whereas methods for its indexing are not much investigated yet. This paper expounds a system, which includes generation of unique patterns called signatures of various PQ disturbances using continuous wavelet transform (CWT and recognition of these signatures using feed-forward neural network. It is also corroborated that the size of signatures of PQ disturbances are proportional to its magnitude, so this feature of the signature is used for indexing the level of PQ disturbance in three sub-classes viz. high, medium, and low. Further, the effect of number of neurons used by neural network on the performance of recognition is also analyzed. Almost 100% accuracy of recognition substantiates the effectiveness of the proposed system.
Synthesis of recurrent neural networks for dynamical system simulation.
Trischler, Adam P; D'Eleuterio, Gabriele M T
2016-08-01
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time. Copyright © 2016 Elsevier Ltd. All rights reserved.
Schmidt, Filipp; Weber, Andreas; Schmidt, Thomas
2014-08-21
Most objects can be recognized easily even when they are partly occluded. This also holds when several overlapping objects share the same surface features (self-splitting objects) which is an illustration of the grouping principle of Good Gestalt. We employed outline and filled contour stimuli in a primed flanker task to test whether the processing of self-splitting objects is in accordance with a simple feedforward model. We obtained priming effects in response time and response force for both types of stimuli, even when increasing the number of occluders up to three. The results for outline contours were in full accordance with a feedforward account. This was not the case for the results for filled contours (i.e., for self-splitting objects), especially under conditions of strong occlusion. We conclude that the implementation of the Good Gestalt principle is fast but still based on recurrent processing. © 2014 ARVO.
International Nuclear Information System (INIS)
Barr, D.S.
1994-01-01
It is possible to use feedforward predictive control for transverse position and trajectory-angle jitter correction. The control procedure is straightforward, but creation of the predictive filter is not as obvious. The two processes tested were the least mean squares (LMS) and Kalman inter methods. The controller parameters calculated offline are downloaded to a real-time analog correction system between macropulses. These techniques worked well for both interpulse (pulse-to-pulse) correction and intrapulse (within a pulse) correction with the Kalman filter method being the clear winner. A simulation based on interpulse data taken at the Stanford Linear Collider showed an improvement factor of almost three in the average rms jitter over standard feedback techniques for the Kalman filter. An improvement factor of over three was found for the Kalman filter on intrapulse data taken at the Los Alamos Meson Physics Facility. The feedforward systems also improved the correction bandwidth
DEFF Research Database (Denmark)
Mojallali, Hamed; Izadi-Zamanabadi, Roozbeh; Amini, Rouzbeh
Feed-forward active noise control (ANC) systems act as adaptive systems to control and cancel undesired signals and noises. If the delay in the noise canceling subsystems increases more than the delays in the primary path, non-causal condition will occur in these systems. In this paper, study...... of noise canceling performance of feed-forward fuzzy-based ANC systems for ducts under non-causal condition is presented. For this purpose, we use fuzzy filtered-x algorithm as an adaptive filter and the results are compared with classical filteredx algorithm which is employed under the same conditions....... Analysis shows that ANC systems using fuzzy algorithm has better efficiency for noise cancellation in non-causal condition....
Schlipf, David; Fleming, Paul; Haizmann, Florian; Scholbrock, Andrew; Hofsäß, Martin; Wright, Alan; Cheng, Po Wen
2014-12-01
This work presents the results from a field test of LIDAR assisted collective pitch control using a scanning LIDAR device installed on the nacelle of a mid-scale research turbine. A nonlinear feedforward controller is extended by an adaptive filter to remove all uncorrelated frequencies of the wind speed measurement to avoid unnecessary control action. Positive effects on the rotor speed regulation as well as on tower, blade and shaft loads have been observed in the case that the previous measured correlation and timing between the wind preview and the turbine reaction are accomplish. The feedforward controller had negative impact, when the LIDAR measurement was disturbed by obstacles in front of the turbine. This work proves, that LIDAR is valuable tool for wind turbine control not only in simulations but also under real conditions. Furthermore, the paper shows that further understanding of the relationship between the wind measurement and the turbine reaction is crucial to improve LIDAR assisted control of wind turbines.
International Nuclear Information System (INIS)
Schlipf, David; Haizmann, Florian; Hofsäß, Martin; Cheng, Po Wen; Fleming, Paul; Scholbrock, Andrew; Wright, Alan
2014-01-01
This work presents the results from a field test of LIDAR assisted collective pitch control using a scanning LIDAR device installed on the nacelle of a mid-scale research turbine. A nonlinear feedforward controller is extended by an adaptive filter to remove all uncorrelated frequencies of the wind speed measurement to avoid unnecessary control action. Positive effects on the rotor speed regulation as well as on tower, blade and shaft loads have been observed in the case that the previous measured correlation and timing between the wind preview and the turbine reaction are accomplish. The feedforward controller had negative impact, when the LIDAR measurement was disturbed by obstacles in front of the turbine. This work proves, that LIDAR is valuable tool for wind turbine control not only in simulations but also under real conditions. Furthermore, the paper shows that further understanding of the relationship between the wind measurement and the turbine reaction is crucial to improve LIDAR assisted control of wind turbines
Directory of Open Access Journals (Sweden)
Maruthai Suresh
2010-10-01
Full Text Available A nonlinear process, the heat exchanger whose parameters vary with respect to the process variable, is considered. The time constant and gain of the chosen process vary as a function of temperature. The limitations of the conventional feedback controller tuned using Ziegler-Nichols settings for the chosen process are brought out. The servo and regulatory responses through simulation and experimentation for various magnitudes of set-point changes and load changes at various operating points with the controller tuned only at a chosen nominal operating point are obtained and analyzed. Regulatory responses for output load changes are studied. The efficiency of feedforward controller and the effects of modeling error have been brought out. An IMC based system is presented to understand clearly how variations of system parameters affect the performance of the controller. The present work illustrates the effectiveness of Feedforward and IMC controller.
Simple, low-noise piezo driver with feed-forward for broad tuning of external cavity diode lasers
Doret, S. Charles
2018-02-01
We present an inexpensive, low-noise (diode lasers. This simple driver improves upon many commercially available drivers by incorporating circuitry to produce a "feed-forward" signal appropriate for making simultaneous adjustments to the piezo voltage and laser current, enabling dramatic improvements in a mode-hop-free laser frequency tuning range. We present the theory behind our driver's operation, characterize its output noise, and demonstrate its use in absorption spectroscopy on the rubidium D1 line.
Directory of Open Access Journals (Sweden)
Troy A Hackett
2014-04-01
Full Text Available Our working model of the primate auditory cortex recognizes three major regions (core, belt, parabelt, subdivided into thirteen areas. The connections between areas are topographically ordered in a manner consistent with information flow along two major anatomical axes: core-belt-parabelt and caudal-rostral. Remarkably, most of the connections supporting this model were revealed using retrograde tracing techniques. Little is known about laminar circuitry, as anterograde tracing of axon terminations has rarely been used. The purpose of the present study was to examine the laminar projections of three areas of auditory cortex, pursuant to analysis of all areas. The selected areas were: middle lateral belt (ML; caudomedial belt (CM; and caudal parabelt (CPB. Injections of anterograde tracers yielded data consistent with major features of our model, and also new findings that compel modifications. Results supporting the model were: 1 feedforward projection from ML and CM terminated in CPB; 2 feedforward projections from ML and CPB terminated in rostral areas of the belt and parabelt; and 3 feedback projections typified inputs to the core region from belt and parabelt. At odds with the model was the convergence of feedforward inputs into rostral medial belt from ML and CPB. This was unexpected since CPB is at a higher stage of the processing hierarchy, with mainly feedback projections to all other belt areas. Lastly, extending the model, feedforward projections from CM, ML, and CPB overlapped in the temporal parietal occipital area (TPO in the superior temporal sulcus, indicating significant auditory influence on sensory processing in this region. The combined results refine our working model and highlight the need to complete studies of the laminar inputs to all areas of auditory cortex. Their documentation is essential for developing informed hypotheses about the neurophysiological influences of inputs to each layer and area.
Feedforward model based arm weight compensation with the rehabilitation robot ARMin.
Just, Fabian; Ozen, Ozhan; Tortora, Stefano; Riener, Robert; Rauter, Georg
2017-07-01
Highly impaired stroke patients at early stages of recovery are unable to generate enough muscle force to lift the weight of their own arm. Accordingly, task-related training is strongly limited or even impossible. However, as soon as partial or full arm weight support is provided, patients are enabled to perform arm rehabilitation training again throughout an increased workspace. In the literature, the current solutions for providing arm weight support are mostly mechanical. These systems have components that restrict the freedom of movement or entail additional disturbances. A scalable weight compensation for upper and lower arm that is online adjustable as well as generalizable to any robotic system is necessary. In this paper, a model-based feedforward weight compensation of upper and lower arm fulfilling these requirements is introduced. The proposed method is tested with the upper extremity rehabilitation robot ARMin V, but can be applied in any other actuated exoskeleton system. Experimental results were verified using EMG measurements. These results revealed that the proposed weight compensation reduces the effort of the subjects to 26% on average and more importantly throughout the entire workspace of the robot.
Hybrid feedforward-feedback active noise reduction for hearing protection and communication.
Ray, Laura R; Solbeck, Jason A; Streeter, Alexander D; Collier, Robert D
2006-10-01
A hybrid active noise reduction (ANR) architecture is presented and validated for a circumaural earcup and a communication earplug. The hybrid system combines source-independent feedback ANR with a Lyapunov-tuned leaky LMS filter (LyLMS) improving gain stability margins over feedforward ANR alone. In flat plate testing, the earcup demonstrates an overall C-weighted total noise reduction of 40 dB and 30-32 dB, respectively, for 50-800 Hz sum-of-tones noise and for aircraft or helicopter cockpit noise, improving low frequency (control component acting individually. For the earplug, a filtered-X implementation of the LyLMS accommodates its nonconstant cancellation path gain. A fast time-domain identification method provides a high-fidelity, computationally efficient, infinite impulse response cancellation path model, which is used for both the filtered-X implementation and communication feedthrough. Insertion loss measurements made with a manikin show overall C-weighted total noise reduction provided by the ANR earplug of 46-48 dB for sum-of-tones 80-2000 Hz and 40-41 dB from 63 to 3000 Hz for UH-60 helicopter noise, with negligible degradation in attenuation during speech communication. For both hearing protectors, a stability metric improves by a factor of 2 to several orders of magnitude through hybrid ANR.
Embedding the dynamics of a single delay system into a feed-forward ring
Klinshov, Vladimir; Shchapin, Dmitry; Yanchuk, Serhiy; Wolfrum, Matthias; D'Huys, Otti; Nekorkin, Vladimir
2017-10-01
We investigate the relation between the dynamics of a single oscillator with delayed self-feedback and a feed-forward ring of such oscillators, where each unit is coupled to its next neighbor in the same way as in the self-feedback case. We show that periodic solutions of the delayed oscillator give rise to families of rotating waves with different wave numbers in the corresponding ring. In particular, if for the single oscillator the periodic solution is resonant to the delay, it can be embedded into a ring with instantaneous couplings. We discover several cases where the stability of a periodic solution for the single unit can be related to the stability of the corresponding rotating wave in the ring. As a specific example, we demonstrate how the complex bifurcation scenario of simultaneously emerging multijittering solutions can be transferred from a single oscillator with delayed pulse feedback to multijittering rotating waves in a sufficiently large ring of oscillators with instantaneous pulse coupling. Finally, we present an experimental realization of this dynamical phenomenon in a system of coupled electronic circuits of FitzHugh-Nagumo type.
Development of a Beam-based Phase Feedforward Demonstration at the CLIC Test Facility (CTF3)
AUTHOR|(CDS)2083344; Christian, Glenn
The Compact Linear Collider (CLIC) is a proposal for a future linear electron--positron collider that could achieve collision energies of up to 3~TeV. In the CLIC concept the main high energy beam is accelerated using RF power extracted from a high intensity drive beam, achieving an accelerating gradient of 100~MV/m. This scheme places strict tolerances on the drive beam phase stability, which must be better than $0.2^\\circ$ at 12~GHz. To achieve the required phase stability CLIC proposes a high bandwidth (${>}17.5$~MHz), low latency drive beam ``phase feedforward'' (PFF) system. In this system electromagnetic kickers, powered by 500~kW amplifiers, are installed in a chicane and used to correct the phase by deflecting the beam on to longer or shorter trajectories. A prototype PFF system has been installed at the CLIC Test Facility, CTF3; the design, operation and commissioning of which is the focus of this work. Two kickers have been installed in the pre-existing chicane in the TL2 transfer line at CTF3 for t...
Ordureau, Alban; Sarraf, Shireen A; Duda, David M; Heo, Jin-Mi; Jedrychowski, Mark P; Sviderskiy, Vladislav O; Olszewski, Jennifer L; Koerber, James T; Xie, Tiao; Beausoleil, Sean A; Wells, James A; Gygi, Steven P; Schulman, Brenda A; Harper, J Wade
2014-11-06
Phosphorylation is often used to promote protein ubiquitylation, yet we rarely understand quantitatively how ligase activation and ubiquitin (UB) chain assembly are integrated with phosphoregulation. Here we employ quantitative proteomics and live-cell imaging to dissect individual steps in the PINK1 kinase-PARKIN UB ligase mitochondrial control pathway disrupted in Parkinson's disease. PINK1 plays a dual role by phosphorylating PARKIN on its UB-like domain and poly-UB chains on mitochondria. PARKIN activation by PINK1 produces canonical and noncanonical UB chains on mitochondria, and PARKIN-dependent chain assembly is required for accumulation of poly-phospho-UB (poly-p-UB) on mitochondria. In vitro, PINK1 directly activates PARKIN's ability to assemble canonical and noncanonical UB chains and promotes association of PARKIN with both p-UB and poly-p-UB. Our data reveal a feedforward mechanism that explains how PINK1 phosphorylation of both PARKIN and poly-UB chains synthesized by PARKIN drives a program of PARKIN recruitment and mitochondrial ubiquitylation in response to mitochondrial damage. Copyright © 2014 Elsevier Inc. All rights reserved.
Yoneya, Akihiko; Watanabe, Akira
The full-digital audio amplifiers are advantageous with the points of its high power efficiency and its possibility of high fidelity due to the digital signal processing. With the full-digital amplifier, class-D amplifiers are used to drive the load with PWM signals produced from the source signal. Unfortunately, the signals are distorted when the PCM signals are converted to the PWM signals because the pulse-width modulation is a nonlinear conversion from the viewpoint of transient responses. This paper proposes a way to compensate the distortion caused by the pulse-width modulation. A feedforward compensation approach is used because of the simplicity of implementation. The distortion components are estimated with the source signals and its time-derivative signals and used to cancel out them by subtracting them from the source signals. A numerical example with two-tone test is performed to show the effectiveness of the proposed method. The distortion compensation scheme used here may be applicative to other applications.
Directory of Open Access Journals (Sweden)
João C. O. Marra
2016-01-01
Full Text Available Vibratory phenomena have always surrounded human life. The need for more knowledge and domain of such phenomena increases more and more, especially in the modern society where the human-machine integration becomes closer day after day. In that context, this work deals with the development and practical implementation of a hybrid (passive-active/adaptive vibration control system over a metallic beam excited by a broadband signal and under variable temperature, between 5 and 35°C. Since temperature variations affect directly and considerably the performance of the passive control system, composed of a viscoelastic dynamic vibration neutralizer (also called a viscoelastic dynamic vibration absorber, the associative strategy of using an active-adaptive vibration control system (based on a feedforward approach with the use of the FXLMS algorithm working together with the passive one has shown to be a good option to compensate the neutralizer loss of performance and generally maintain the extended overall level of vibration control. As an additional gain, the association of both vibration control systems (passive and active-adaptive has improved the attenuation of vibration levels. Some key steps matured over years of research on this experimental setup are presented in this paper.
Protection from feed-forward amplification in an amplified RNAi mechanism
Pak, Julia; Maniar, Jay Mahesh; Mello, Cecilia Cabral; Fire, Andrew
2012-01-01
SUMMARY The effectiveness of RNA interference (RNAi) in many organisms is potentiated through the signal-amplifying activity of a targeted RNA directed RNA polymerase (RdRP) system that can convert a small population of exogenously-encountered dsRNA fragments into an abundant internal pool of small interfering RNA (siRNA). As for any biological amplification system, we expect an underlying architecture that will limit the ability of a randomly encountered trigger to produce an uncontrolled and self-escalating response. Investigating such limits in C. elegans, we find that feed-forward amplification is limited by a critical biosynthetic and structural distinction at the RNA level between (i) triggers that can produce amplification and (ii) siRNA products of the amplification reaction. By assuring that initial (primary) siRNAs can act as triggers but not templates for activation, and that the resulting (secondary) siRNAs can enforce gene silencing on additional targets without unbridled trigger amplification, the system achieves substantial but fundamentally limited signal amplification. PMID:23141544
Yue, Ming; Jiang, Jue; Gao, Peng; Liu, Hudan; Qing, Guoliang
2017-12-26
Most tumor cells exhibit obligatory demands for essential amino acids (EAAs), but the regulatory mechanisms whereby tumor cells take up EAAs and EAAs promote malignant transformation remain to be determined. Here, we show that oncogenic MYC, solute carrier family (SLC) 7 member 5 (SLC7A5), and SLC43A1 constitute a feedforward activation loop to promote EAA transport and tumorigenesis. MYC selectively activates Slc7a5 and Slc43a1 transcription through direct binding to specific E box elements within both genes, enabling effective EAA import. Elevated EAAs, in turn, stimulate Myc mRNA translation, in part through attenuation of the GCN2-eIF2α-ATF4 amino acid stress response pathway, leading to MYC-dependent transcriptional amplification. SLC7A5/SLC43A1 depletion inhibits MYC expression, metabolic reprogramming, and tumor cell growth in vitro and in vivo. These findings thus reveal a MYC-SLC7A5/SLC43A1 signaling circuit that underlies EAA metabolism, MYC deregulation, and tumorigenesis. Copyright © 2017 The Author(s). Published by Elsevier Inc. All rights reserved.
International Nuclear Information System (INIS)
Yan, T H; Li, Q; Xu, C; Pu, H Y; Chen, X D
2010-01-01
The design, realization and control technologies of a high-performance hybrid microvibration isolator for ultra-high-precision high-speed moving X/Y tables are presented in this paper—the novel isolator with integrated passive–active high level of damping. The passive damping was implemented using air-springs in both vertical and horizontal directions, with parallel linear motors in two directions to realize the active damping and the positioning functions. It is an actual hybrid isolation system because its air-spring can also be controlled through the pneumatic loop. The isolation servo system also has fast positioning capability via the feedforward compensation for the moving tables. Compared with the conventional filtered reference type control algorithms that rely on the assumption for the adaptive filter and the controlled system, in which the disturbance is estimated from the residual signal, the feedforward compensation here shows high effectiveness of vibration isolation and high-precision positioning performance for its platform. The performance of feedforward compensation has been enhanced via an efficient state estimation adaptive algorithm, the fast Kalman filter. Finally, experimental demonstration has been shown for the prototype system and the results have verified the effectiveness of the proposed isolator system design and the adaptive control algorithm for substantially enhanced damping of the platform system with the moving X/Y tables
Yan, T. H.; Pu, H. Y.; Chen, X. D.; Li, Q.; Xu, C.
2010-06-01
The design, realization and control technologies of a high-performance hybrid microvibration isolator for ultra-high-precision high-speed moving X/Y tables are presented in this paper—the novel isolator with integrated passive-active high level of damping. The passive damping was implemented using air-springs in both vertical and horizontal directions, with parallel linear motors in two directions to realize the active damping and the positioning functions. It is an actual hybrid isolation system because its air-spring can also be controlled through the pneumatic loop. The isolation servo system also has fast positioning capability via the feedforward compensation for the moving tables. Compared with the conventional filtered reference type control algorithms that rely on the assumption for the adaptive filter and the controlled system, in which the disturbance is estimated from the residual signal, the feedforward compensation here shows high effectiveness of vibration isolation and high-precision positioning performance for its platform. The performance of feedforward compensation has been enhanced via an efficient state estimation adaptive algorithm, the fast Kalman filter. Finally, experimental demonstration has been shown for the prototype system and the results have verified the effectiveness of the proposed isolator system design and the adaptive control algorithm for substantially enhanced damping of the platform system with the moving X/Y tables.
Jiang, Ping; Chiba, Ryosuke; Takakusaki, Kaoru; Ota, Jun
2016-01-01
The development of a physiologically plausible computational model of a neural controller that can realize a human-like biped stance is important for a large number of potential applications, such as assisting device development and designing robotic control systems. In this paper, we develop a computational model of a neural controller that can maintain a musculoskeletal model in a standing position, while incorporating a 120-ms neurological time delay. Unlike previous studies that have used an inverted pendulum model, a musculoskeletal model with seven joints and 70 muscular-tendon actuators is adopted to represent the human anatomy. Our proposed neural controller is composed of both feed-forward and feedback controls. The feed-forward control corresponds to the constant activation input necessary for the musculoskeletal model to maintain a standing posture. This compensates for gravity and regulates stiffness. The developed neural controller model can replicate two salient features of the human biped stance: (1) physiologically plausible muscle activations for quiet standing; and (2) selection of a low active stiffness for low energy consumption. PMID:27655271
Energy Technology Data Exchange (ETDEWEB)
Datta, S.
1999-10-01
The effect of composition and controlled thermomechanical process parameters on the mechanical properties of HSLA steels is modelled using the Widrow-Hoff's concept of training a neural net with feed-forward topology by applying Rumelhart's back propagation type algorithm for supervised learning, using a Petri like net structure. The data used are from laboratory experiments as well as from the published literature. The results from the neural network are found to be consistent and in good agreement with the experimented results. (author)
Predictive zero-dimensional combustion model for DI diesel engine feed-forward control
International Nuclear Information System (INIS)
Catania, Andrea Emilio; Finesso, Roberto; Spessa, Ezio
2011-01-01
Highlights: → Zero-dimensional low-throughput combustion model for real-time control in diesel engine applications. → Feed-forward control of MFB50, p max and IMEP in both conventional and PCCI combustion modes. → Capability of resolving the contribution to HRR of each injection pulse in multiple injection schedule. → Ignition delay and model parameters estimated through physically consistent and easy-to-tune correlations. - Abstract: An innovative zero-dimensional predictive combustion model has been developed for the estimation of HRR (heat release rate) and in-cylinder pressure traces. This model has been assessed and applied to conventional and PCCI (premixed charge compression ignition) DI diesel engines for model-based feed-forward control purposes. The injection rate profile is calculated on the basis of the injected fuel quantities and on the injection parameters, such as SOI (start of injection), ET (energizing time), and DT (dwell time), taking the injector NOD (nozzle opening delay) and NCD (nozzle closure delay) into account. The injection rate profile in turn allows the released chemical energy Q ch to be estimated. The approach starts from the assumption that, at each time instant, the HRR is proportional to the energy associated with the accumulated fuel mass in the combustion chamber. The main novelties of the proposed approach consist of the method that is adopted to estimate the fuel ignition delay and of injection rate splitting for HRR estimation. The procedure allows an accurate calculation to be made of the different combustion parameters that are important for engine calibration, such as SOC (start of combustion) and MFB50 (50% of fuel mass fraction burned angle). On the basis of an estimation of the fuel released chemical energy, of the heat globally exchanged from the charge with the walls and of the energy associated with the fuel evaporation, the charge net energy is calculated, for a subsequent evaluation of the in
The role of incoherent microRNA-mediated feedforward loops in noise buffering.
Directory of Open Access Journals (Sweden)
Matteo Osella
2011-03-01
Full Text Available MicroRNAs are endogenous non-coding RNAs which negatively regulate the expression of protein-coding genes in plants and animals. They are known to play an important role in several biological processes and, together with transcription factors, form a complex and highly interconnected regulatory network. Looking at the structure of this network, it is possible to recognize a few overrepresented motifs which are expected to perform important elementary regulatory functions. Among them, a special role is played by the microRNA-mediated feedforward loop in which a master transcription factor regulates a microRNA and, together with it, a set of target genes. In this paper we show analytically and through simulations that the incoherent version of this motif can couple the fine-tuning of a target protein level with an efficient noise control, thus conferring precision and stability to the overall gene expression program, especially in the presence of fluctuations in upstream regulators. Among the other results, a nontrivial prediction of our model is that the optimal attenuation of fluctuations coincides with a modest repression of the target expression. This feature is coherent with the expected fine-tuning function and in agreement with experimental observations of the actual impact of a wide class of microRNAs on the protein output of their targets. Finally, we describe the impact on noise-buffering efficiency of the cross-talk between microRNA targets that can naturally arise if the microRNA-mediated circuit is not considered as isolated, but embedded in a larger network of regulations.
A TORC2-Akt feedforward topology underlies HER3 resiliency in HER2-amplified cancers
Amin, Dhara N.; Ahuja, Deepika; Yaswen, Paul; Moasser, Mark M.
2015-01-01
The requisite role of HER3 in HER2-amplified cancers is beyond what would be expected as a dimerization partner or effector substrate and it exhibits a substantial degree of resiliency that mitigates the effects of HER2-inhibitor therapies. To better understand the roots of this resiliency, we conducted an in-depth chemical-genetic interrogation of the signaling network downstream of HER3. A unique attribute of these tumors is the deregulation of TORC2. The upstream signals that ordinarily maintain TORC2 signaling are lost in these tumors, and instead TORC2 is driven by Akt. We find that in these cancers HER3 functions as a buffering arm of an Akt-TORC2 feed-forward loop that functions as a self-perpetuating module. This network topology alters the role of HER3 from a conditionally engaged ligand-driven upstream physiologic signaling input to an essential component of a concentric signaling throughput highly competent at preservation of homeostasis. The competence of this signaling topology is evident in its response to perturbation at any of its nodes. Thus a critical pathophysiological event in the evolution of HER2-amplified cancers is the loss of the input signals that normally drive TORC2 signaling, repositioning it under Akt dependency and fundamentally altering the role of HER3. This reprogramming of the downstream network topology is a key aspect in the pathogenesis of HER2-amplified cancers and constitutes a formidable barrier in the targeted therapy of these cancers. PMID:26438156
Multichannel feedforward control schemes with coupling compensation for active sound profiling
Mosquera-Sánchez, Jaime A.; Desmet, Wim; de Oliveira, Leopoldo P. R.
2017-05-01
Active sound profiling includes a number of control techniques that enables the equalization, rather than the mere reduction, of acoustic noise. Challenges may rise when trying to achieve distinct targeted sound profiles simultaneously at multiple locations, e.g., within a vehicle cabin. This paper introduces distributed multichannel control schemes for independently tailoring structural borne sound reaching a number of locations within a cavity. The proposed techniques address the cross interactions amongst feedforward active sound profiling units, which compensate for interferences of the primary sound at each location of interest by exchanging run-time data amongst the control units, while attaining the desired control targets. Computational complexity, convergence, and stability of the proposed multichannel schemes are examined in light of the physical system at which they are implemented. The tuning performance of the proposed algorithms is benchmarked with the centralized and pure-decentralized control schemes through computer simulations on a simplified numerical model, which has also been subjected to plant magnitude variations. Provided that the representation of the plant is accurate enough, the proposed multichannel control schemes have been shown as the only ones that properly deliver targeted active sound profiling tasks at each error sensor location. Experimental results in a 1:3-scaled vehicle mock-up further demonstrate that the proposed schemes are able to attain reductions of more than 60 dB upon periodic disturbances at a number of positions, while resolving cross-channel interferences. Moreover, when the sensor/actuator placement is found as defective at a given frequency, the inclusion of a regularization parameter in the cost function is seen to not hinder the proper operation of the proposed compensation schemes, at the time that it assures their stability, at the expense of losing control performance.
Anatomy of hierarchy: feedforward and feedback pathways in macaque visual cortex.
Markov, Nikola T; Vezoli, Julien; Chameau, Pascal; Falchier, Arnaud; Quilodran, René; Huissoud, Cyril; Lamy, Camille; Misery, Pierre; Giroud, Pascale; Ullman, Shimon; Barone, Pascal; Dehay, Colette; Knoblauch, Kenneth; Kennedy, Henry
2014-01-01
The laminar location of the cell bodies and terminals of interareal connections determines the hierarchical structural organization of the cortex and has been intensively studied. However, we still have only a rudimentary understanding of the connectional principles of feedforward (FF) and feedback (FB) pathways. Quantitative analysis of retrograde tracers was used to extend the notion that the laminar distribution of neurons interconnecting visual areas provides an index of hierarchical distance (percentage of supragranular labeled neurons [SLN]). We show that: 1) SLN values constrain models of cortical hierarchy, revealing previously unsuspected areal relations; 2) SLN reflects the operation of a combinatorial distance rule acting differentially on sets of connections between areas; 3) Supragranular layers contain highly segregated bottom-up and top-down streams, both of which exhibit point-to-point connectivity. This contrasts with the infragranular layers, which contain diffuse bottom-up and top-down streams; 4) Cell filling of the parent neurons of FF and FB pathways provides further evidence of compartmentalization; 5) FF pathways have higher weights, cross fewer hierarchical levels, and are less numerous than FB pathways. Taken together, the present results suggest that cortical hierarchies are built from supra- and infragranular counterstreams. This compartmentalized dual counterstream organization allows point-to-point connectivity in both bottom-up and top-down directions. Copyright © 2013 Wiley Periodicals, Inc. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Feedforward Object-Vision Models Only Tolerate Small Image Variations Compared to Human
Directory of Open Access Journals (Sweden)
Masoud eGhodrati
2014-07-01
Full Text Available Invariant object recognition is a remarkable ability of primates' visual system that its underlying mechanism has constantly been under intense investigations. Computational modelling is a valuable tool toward understanding the processes involved in invariant object recognition. Although recent computational models have shown outstanding performances on challenging image databases, they fail to perform well when images with more complex variations of the same object are applied to them. Studies have shown that making sparse representation of objects by extracting more informative visual features through a feedforward sweep can lead to higher recognition performances. Here, however, we show that when the complexity of image variations is high, even this approach results in poor performance compared to humans. To assess the performance of models and humans in invariant object recognition tasks, we built a parametrically controlled image database consisting of several object categories varied in different dimensions and levels, rendered from 3D planes. Comparing the performance of several object recognition models with human observers shows that only in low-level image variations the models perform similar to humans in categorization tasks. Furthermore, the results of our behavioral experiments demonstrate that, even under difficult experimental conditions (i.e. briefly presented masked stimuli with complex image variations, human observers performed outstandingly well, suggesting that the models are still far from resembling humans in invariant object recognition. Taken together, we suggest that learning sparse informative visual features, although desirable, is not a complete solution for future progresses in object-vision modelling. We show that this approach is not of significant help in solving the computational crux of object recognition (that is invariant object recognition when the identity-preserving image variations become more complex.
Flatness-based model inverse for feed-forward braking control
de Vries, Edwin; Fehn, Achim; Rixen, Daniel
2010-12-01
For modern cars an increasing number of driver assistance systems have been developed. Some of these systems interfere/assist with the braking of a car. Here, a brake actuation algorithm for each individual wheel that can respond to both driver inputs and artificial vehicle deceleration set points is developed. The algorithm consists of a feed-forward control that ensures, within the modelled system plant, the optimal behaviour of the vehicle. For the quarter-car model with LuGre-tyre behavioural model, an inverse model can be derived using v x as the 'flat output', that is, the input for the inverse model. A number of time derivatives of the flat output are required to calculate the model input, brake torque. Polynomial trajectory planning provides the needed time derivatives of the deceleration request. The transition time of the planning can be adjusted to meet actuator constraints. It is shown that the output of the trajectory planning would ripple and introduce a time delay when a gradual continuous increase of deceleration is requested by the driver. Derivative filters are then considered: the Bessel filter provides the best symmetry in its step response. A filter of same order and with negative real-poles is also used, exhibiting no overshoot nor ringing. For these reasons, the 'real-poles' filter would be preferred over the Bessel filter. The half-car model can be used to predict the change in normal load on the front and rear axle due to the pitching of the vehicle. The anticipated dynamic variation of the wheel load can be included in the inverse model, even though it is based on a quarter-car. Brake force distribution proportional to normal load is established. It provides more natural and simpler equations than a fixed force ratio strategy.
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)
An STDP training algorithm for a spiking neural network with dynamic threshold neurons.
Strain, T J; McDaid, L J; McGinnity, T M; Maguire, L P; Sayers, H M
2010-12-01
This paper proposes a supervised training algorithm for Spiking Neural Networks (SNNs) which modifies the Spike Timing Dependent Plasticity (STDP)learning rule to support both local and network level training with multiple synaptic connections and axonal delays. The training algorithm applies the rule to two and three layer SNNs, and is benchmarked using the Iris and Wisconsin Breast Cancer (WBC) data sets. The effectiveness of hidden layer dynamic threshold neurons is also investigated and results are presented.
Directory of Open Access Journals (Sweden)
Schwindling Jerome
2010-04-01
Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.
DEFF Research Database (Denmark)
Chon, K H; Holstein-Rathlou, N H; Marsh, D J
1998-01-01
In this paper, feedforward neural networks with two types of activation functions (sigmoidal and polynomial) are utilized for modeling the nonlinear dynamic relation between renal blood pressure and flow data, and their performance is compared to Volterra models obtained by use of the leading...... kernel estimation method based on Laguerre expansions. The results for the two types of artificial neural networks and the Volterra models are comparable in terms of normalized mean square error (NMSE) of the respective output prediction for independent testing data. However, the Volterra models obtained...... via the Laguerre expansion technique achieve this prediction NMSE with approximately half the number of free parameters relative to either neural-network model. However, both approaches are deemed effective in modeling nonlinear dynamic systems and their cooperative use is recommended in general....
Directory of Open Access Journals (Sweden)
Kazem Barkhordari
2015-12-01
Full Text Available This research intends to develop a method based on the Artificial Neural Network (ANN to predict permanent earthquake-induced deformation of the earth dams and embankments. For this purpose, data sets of observations from 152 published case histories on the performance of the earth dams and embankments, during the past earthquakes, was used. In order to predict earthquake-induced deformation of the earth dams and embankments a Multi-Layer Perceptron (MLP analysis was used. A four-layer, feed-forward, back-propagation neural network, with a topology of 7-9-7-1 was found to be optimum. The results showed that an appropriately trained neural network could reliably predict permanent earthquake-induced deformation of the earth dams and embankments.
DEFF Research Database (Denmark)
Lu, Minghui; Xin, Zhen; Wang, Xiongfei
2016-01-01
For the LCL-filtered grid-connected inverter, it has been reported that the digital time delays will narrow the stable region of current control loop when the inverter-side current is used for implementing the feedback control. A sufficient stable condition is that the filter resonance frequency....... Theoretical analysis is then provided to validate its feasibility and stability. Compared to other widely used active damping strategies, no extra sensors are needed because the filter capacitor voltage, which is used for voltage feedforward control, is also sampled for phase-locked loop in this paper...
Estimation of Solar Radiation using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Slamet Suprayogi
2004-01-01
Full Text Available The solar radiation is the most important fator affeccting evapotranspiration, the mechanism of transporting the vapor from the water surface has also a great effect. The main objectives of this study were to investigate the potential of using Artificial Neural Network (ANN to predict solar radiation related to temperature. The three-layer backpropagation were developed, trained, and tested to forecast solar radiation for Ciriung sub Cachment. Result revealed that the ANN were able to well learn the events they were trained to recognize. Moreover, they were capable of effecctively generalize their training by predicting solar radiation for sets unseen cases.
Wind Speed Preview Measurement and Estimation for Feedforward Control of Wind Turbines
Simley, Eric J.
Wind turbines typically rely on feedback controllers to maximize power capture in below-rated conditions and regulate rotor speed during above-rated operation. However, measurements of the approaching wind provided by Light Detection and Ranging (lidar) can be used as part of a preview-based, or feedforward, control system in order to improve rotor speed regulation and reduce structural loads. But the effectiveness of preview-based control depends on how accurately lidar can measure the wind that will interact with the turbine. In this thesis, lidar measurement error is determined using a statistical frequency-domain wind field model including wind evolution, or the change in turbulent wind speeds between the time they are measured and when they reach the turbine. Parameters of the National Renewable Energy Laboratory (NREL) 5-MW reference turbine model are used to determine measurement error for a hub-mounted circularly-scanning lidar scenario, based on commercially-available technology, designed to estimate rotor effective uniform and shear wind speed components. By combining the wind field model, lidar model, and turbine parameters, the optimal lidar scan radius and preview distance that yield the minimum mean square measurement error, as well as the resulting minimum achievable error, are found for a variety of wind conditions. With optimized scan scenarios, it is found that relatively low measurement error can be achieved, but the attainable measurement error largely depends on the wind conditions. In addition, the impact of the induction zone, the region upstream of the turbine where the approaching wind speeds are reduced, as well as turbine yaw error on measurement quality is analyzed. In order to minimize the mean square measurement error, an optimal measurement prefilter is employed, which depends on statistics of the correlation between the preview measurements and the wind that interacts with the turbine. However, because the wind speeds encountered by
Directory of Open Access Journals (Sweden)
Michel Joël Tchatchueng Kammegne
2017-04-01
wing for a specified flight condition. The feasibility and effectiveness of the developed control system by use of a proportional fuzzy feed-forward methodology are demonstrated experimentally through bench and wind tunnel tests of the morphing wing model.
Directory of Open Access Journals (Sweden)
José Fernando Moretti
2016-01-01
Full Text Available Currently, artificial neural networks are being widely used in various fields of science and engineering. Neural networks have the ability to learn through experience and existing examples, and then generate solutions and answers to new problems, involving even the effects of non-linearity in their variables. The aim of this study is to use a feed-forward neural network with back-propagation technique, to predict the values of compressive strength and modulus of elasticity, at 28 days, of different concrete mixtures prepared and tested in the laboratory. It demonstrates the ability of the neural networks to quantify the strength and the elastic modulus of concrete specimens prepared using different mix proportions.
Energy Technology Data Exchange (ETDEWEB)
Lobato, Justo; Canizares, Pablo; Rodrigo, Manuel A.; Linares, Jose J. [Chemical Engineering Department, University of Castilla-La Mancha, Campus Universitario s/n, 13004 Ciudad Real (Spain); Piuleac, Ciprian-George; Curteanu, Silvia [Faculty of Chemical Engineering and Environmental Protection, Department of Chemical Engineering, ' ' Gh. Asachi' ' Technical University Iasi Bd. D. Mangeron, No. 71A, 700050 IASI (Romania)
2010-08-15
This article shows the application of a very useful mathematical tool, artificial neural networks, to predict the fuel cells results (the value of the tortuosity and the cell voltage, at a given current density, and therefore, the power) on the basis of several properties that define a Gas Diffusion Layer: Teflon content, air permeability, porosity, mean pore size, hydrophobia level. Four neural networks types (multilayer perceptron, generalized feedforward network, modular neural network, and Jordan-Elman neural network) have been applied, with a good fitting between the predicted and the experimental values in the polarization curves. A simple feedforward neural network with one hidden layer proved to be an accurate model with good generalization capability (error about 1% in the validation phase). A procedure based on inverse neural network modelling was able to determine, with small errors, the initial conditions leading to imposed values for characteristics of the fuel cell. In addition, the use of this tool has been proved to be very attractive in order to predict the cell performance, and more interestingly, the influence of the properties of the gas diffusion layer on the cell performance, allowing possible enhancements of this material by changing some of its properties. (author)
Learning representations for the early detection of sepsis with deep neural networks.
Kam, Hye Jin; Kim, Ha Young
2017-10-01
Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.
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
FGF Signaling Transforms Non-neural Ectoderm into Neural Crest
Yardley, Nathan; García-Castro, Martín I.
2012-01-01
The neural crest arises at the border between the neural plate and the adjacent non-neural ectoderm. It has been suggested that both neural and non-neural ectoderm can contribute to the neural crest. Several studies have examined the molecular mechanisms that regulate neural crest induction in neuralized tissues or the neural plate border. Here, using the chick as a model system, we address the molecular mechanisms by which non-neural ectoderm generates neural crest. We report that in respons...
Directory of Open Access Journals (Sweden)
Asad Dehghani Samani
2017-07-01
Full Text Available Application of Artificial Neural Network (ANN in modeling of combined cycle power plant (CCPP with dry cooling tower (Heller tower has been investigated in this paper. Prediction of power plant output (megawatt under different working conditions was made using multi-layer feed-forward ANN and training was performed with operational data using back-propagation. Two ANN network was constructed for the steam turbine (ST and the main cooling system(MCS. Results indicate that the ANN model is effective in predicting the power plant output with good accuracy.
Gas metal arc welding of butt joint with varying gap width based on neural networks
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2005-01-01
This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters, has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least...
Optimal mapping of neural-network learning on message-passing multicomputers
Chu, Lon-Chan; Wah, Benjamin W.
1992-01-01
A minimization of learning-algorithm completion time is sought in the present optimal-mapping study of the learning process in multilayer feed-forward artificial neural networks (ANNs) for message-passing multicomputers. A novel approximation algorithm for mappings of this kind is derived from observations of the dominance of a parallel ANN algorithm over its communication time. Attention is given to both static and dynamic mapping schemes for systems with static and dynamic background workloads, as well as to experimental results obtained for simulated mappings on multicomputers with dynamic background workloads.
Hattori, Yusuke; Otsuka, Makoto
2017-05-30
In the pharmaceutical industry, the implementation of continuous manufacturing has been widely promoted in lieu of the traditional batch manufacturing approach. More specially, in recent years, the innovative concept of feed-forward control has been introduced in relation to process analytical technology. In the present study, we successfully developed a feed-forward control model for the tablet compression process by integrating data obtained from near-infrared (NIR) spectra and the physical properties of granules. In the pharmaceutical industry, batch manufacturing routinely allows for the preparation of granules with the desired properties through the manual control of process parameters. On the other hand, continuous manufacturing demands the automatic determination of these process parameters. Here, we proposed the development of a control model using the partial least squares regression (PLSR) method. The most significant feature of this method is the use of dataset integrating both the NIR spectra and the physical properties of the granules. Using our model, we determined that the properties of products, such as tablet weight and thickness, need to be included as independent variables in the PLSR analysis in order to predict unknown process parameters. Copyright © 2017 Elsevier B.V. All rights reserved.
Keck, Alexander; Pott, Jörg-Uwe; Sawodny, Oliver
2014-07-01
The amount of image motion caused by vibrations of the telescope structure increases with the size of the telescope. Compensating the effects of structural vibrations in the optical path will be a major design question for adaptive optics (AO) systems in future extremely large telescopes like the E-ELT. A promising control system architecture is the recently developed Dual-Loop-Approach, with a feedforward loop based on accelerometer measurements, compensating for the vibrations in addition to the classical AO feedback loop compensating for atmospheric turbulences. We present our efforts to develop sophisticated estimation and control algorithms for this feedforward loop. The major task from a control engineering point of view is reconstructing the position of the vibrating elements from accelerometer measurements highly deteriorated by low-frequency drift and highfrequency noise. The algorithms are evaluated and compared using a realistic Tip-Tilt-Vibration laboratory test setup. Position reconstruction for a realistic 8 Hz structural resonance with an error of only 4% is achieved. Our ultimate goal is to achieve longer and more sensitive wavefront sensor (WFS) integrations by permitting a smaller bandwidth of the AO feedback loop in the E-ELT/MICADO.
Directory of Open Access Journals (Sweden)
Thomas Walker
Full Text Available Induction of genes is rarely an isolated event; more typically occurring as part of a web of parallel interactions, or motifs, which act to refine and control gene expression. Here, we define an Incoherent Feed-forward Loop motif in which TNFα-induced NF-κB signalling activates expression of the TNFA gene itself and also controls synthesis of the negative regulator BCL-3. While sharing a common inductive signal, the two genes have distinct temporal expression profiles. Notably, while the TNFA gene promoter is primed to respond immediately to activated NF-κB in the nucleus, induction of BCL3 expression only occurs after a time delay of about 1h. We show that this time delay is defined by remodelling of the BCL3 gene promoter, which is required to activate gene expression, and characterise the chromatin delayed induction of BCL3 expression using mathematical models. The models show how a delay in inhibitor production effectively uncouples the rate of response to inflammatory cues from the final magnitude of inhibition. Hence, within this regulatory motif, a delayed (incoherent feed-forward loop together with differential rates of TNFA (fast and BCL3 (slow mRNA turnover provide robust, pulsatile expression of TNFα . We propose that the structure of the BCL-3-dependent regulatory motif has a beneficial role in modulating expression dynamics and the inflammatory response while minimising the risk of pathological hyper-inflammation.
DEFF Research Database (Denmark)
Guerrero Gonzalez, Neil; Zibar, Darko; Yu, Xianbin
2008-01-01
Maximum likelihood based feedforward RF carrier synchronization scheme is proposed for a coherently detected phase-modulated radio-over-fiber link. Error-free demodulation of 100 Mbit/s QPSK modulated signal is experimentally demonstrated after 25 km of fiber transmission.......Maximum likelihood based feedforward RF carrier synchronization scheme is proposed for a coherently detected phase-modulated radio-over-fiber link. Error-free demodulation of 100 Mbit/s QPSK modulated signal is experimentally demonstrated after 25 km of fiber transmission....
Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan
2018-02-01
Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.
Buiu, Cătălin; Putz, Mihai V.; Avram, Speranta
2016-01-01
The dependency between the primary structure of HIV envelope glycoproteins (ENV) and the neutralization data for given antibodies is very complicated and depends on a large number of factors, such as the binding affinity of a given antibody for a given ENV protein, and the intrinsic infection kinetics of the viral strain. This paper presents a first approach to learning these dependencies using an artificial feedforward neural network which is trained to learn from experimental data. The results presented here demonstrate that the trained neural network is able to generalize on new viral strains and to predict reliable values of neutralizing activities of given antibodies against HIV-1. PMID:27727189
Buiu, Cătălin; Putz, Mihai V; Avram, Speranta
2016-10-11
The dependency between the primary structure of HIV envelope glycoproteins (ENV) and the neutralization data for given antibodies is very complicated and depends on a large number of factors, such as the binding affinity of a given antibody for a given ENV protein, and the intrinsic infection kinetics of the viral strain. This paper presents a first approach to learning these dependencies using an artificial feedforward neural network which is trained to learn from experimental data. The results presented here demonstrate that the trained neural network is able to generalize on new viral strains and to predict reliable values of neutralizing activities of given antibodies against HIV-1.
Catic, Aida; Gurbeta, Lejla; Kurtovic-Kozaric, Amina; Mehmedbasic, Senad; Badnjevic, Almir
2018-02-13
The usage of Artificial Neural Networks (ANNs) for genome-enabled classifications and establishing genome-phenotype correlations have been investigated more extensively over the past few years. The reason for this is that ANNs are good approximates of complex functions, so classification can be performed without the need for explicitly defined input-output model. This engineering tool can be applied for optimization of existing methods for disease/syndrome classification. Cytogenetic and molecular analyses are the most frequent tests used in prenatal diagnostic for the early detection of Turner, Klinefelter, Patau, Edwards and Down syndrome. These procedures can be lengthy, repetitive; and often employ invasive techniques so a robust automated method for classifying and reporting prenatal diagnostics would greatly help the clinicians with their routine work. The database consisted of data collected from 2500 pregnant woman that came to the Institute of Gynecology, Infertility and Perinatology "Mehmedbasic" for routine antenatal care between January 2000 and December 2016. During first trimester all women were subject to screening test where values of maternal serum pregnancy-associated plasma protein A (PAPP-A) and free beta human chorionic gonadotropin (β-hCG) were measured. Also, fetal nuchal translucency thickness and the presence or absence of the nasal bone was observed using ultrasound. The architectures of linear feedforward and feedback neural networks were investigated for various training data distributions and number of neurons in hidden layer. Feedback neural network architecture out performed feedforward neural network architecture in predictive ability for all five aneuploidy prenatal syndrome classes. Feedforward neural network with 15 neurons in hidden layer achieved classification sensitivity of 92.00%. Classification sensitivity of feedback (Elman's) neural network was 99.00%. Average accuracy of feedforward neural network was 89.6% and for
The three-state layered neural network with finite dilution
Theumann, W. K.; Erichsen, R.
2004-10-01
The dynamics and the stationary states of an exactly solvable three-state layered feed-forward neural network model with asymmetric synaptic connections, finite dilution and low pattern activity are studied in extension of a recent work on a recurrent network. Detailed phase diagrams are obtained for the stationary states and for the time evolution of the retrieval overlap with a single pattern. It is shown that in spite of instabilities for low thresholds there is a gradual improvement in network performance with increasing threshold up to an optimal stage. The robustness to synaptic noise is checked and the effects of dilution and of variable threshold on the information content of the network are also established.
A Neural Network Approach for GMA Butt Joint Welding
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least......This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self...
DEFF Research Database (Denmark)
Chon, K H; Hoyer, D; Armoundas, A A
1999-01-01
In this study, we introduce a new approach for estimating linear and nonlinear stochastic autoregressive moving average (ARMA) model parameters, given a corrupt signal, using artificial recurrent neural networks. This new approach is a two-step approach in which the parameters of the deterministic...... part of the stochastic ARMA model are first estimated via a three-layer artificial neural network (deterministic estimation step) and then reestimated using the prediction error as one of the inputs to the artificial neural networks in an iterative algorithm (stochastic estimation step). The prediction...... of significant amounts of either dynamic or measurement noise in the output signal. The comparison between the deterministic and stochastic recurrent neural network approaches is furthered by applying both approaches to experimentally obtained renal blood pressure and flow signals....
Song, Mengmeng; Song, Haixia; Xiao, Shungen
2017-12-01
In this paper, rolling bearing fault diagnosis method is proposed based on wavelet packet threshold de-noising and improved BP neural network. It achieves the goal of signal de-noising by setting the appropriate threshold, and then the denoised signal is decomposed into three layers by wavelet packet. The energy characteristics of the 8 frequency bands are calculated respectively. Levenberg-Maquardt algorithm which is improved the traditional BP neural network to improve the diagnosis efficiency of BP neural network, is proposed. Taking the outer ring fault of rolling bearings as an example, the experimental results show that the wavelet packet threshold de-noising can effectively improve the signal-to-noise ratio. Compared with the traditional BP neural network, the improved BP neural network has better diagnosis efficiency.
Reading out olfactory receptors: Feedforward circuits detect odors in mixtures without demixing
Mathis, Alexander; Rokni, Dan; Kapoor, Vikrant; Bethge, Matthias; Murthy, Venkatesh N.
2016-01-01
The olfactory system, like other sensory systems, can detect specific stimuli of interest amidst complex, varying backgrounds. To gain insight into the neural mechanisms underlying this ability, we imaged responses of mouse olfactory bulb glomeruli to mixtures. We used this data to build a model of mixture responses that incorporated nonlinear interactions and trial-to-trial variability and explored potential decoding mechanisms that can mimic mouse performance when given glomerular responses as input. We find that a linear decoder with sparse weights could match mouse performance using just a small subset of the glomeruli (~15). However, when such a decoder is trained only with single odors, it generalizes poorly to mixture stimuli due to nonlinear mixture responses. We show that mice similarly fail to generalize, suggesting that they learn this segregation task discriminatively by adjusting task-specific decision boundaries without taking advantage of a demixed representation of odors. PMID:27593177
DEFF Research Database (Denmark)
Török, Lajos; Mathe, L.
2017-01-01
The purpose of this work was to investigate effect of the DC-link voltage feed-forward compensation on the stability of the three-phase-grid connected DC power supply, used for electrolysis application, equipped with small DC link capacitor. In case of weak grid condition, the system...
Adaptive Control of Nonlinear Discrete-Time Systems by Using OS-ELM Neural Networks
Directory of Open Access Journals (Sweden)
Xiao-Li Li
2014-01-01
Full Text Available As a kind of novel feedforward neural network with single hidden layer, ELM (extreme learning machine neural networks are studied for the identification and control of nonlinear dynamic systems. The property of simple structure and fast convergence of ELM can be shown clearly. In this paper, we are interested in adaptive control of nonlinear dynamic plants by using OS-ELM (online sequential extreme learning machine neural networks. Based on data scope division, the problem that training process of ELM neural network is sensitive to the initial training data is also solved. According to the output range of the controlled plant, the data corresponding to this range will be used to initialize ELM. Furthermore, due to the drawback of conventional adaptive control, when the OS-ELM neural network is used for adaptive control of the system with jumping parameters, the topological structure of the neural network can be adjusted dynamically by using multiple model switching strategy, and an MMAC (multiple model adaptive control will be used to improve the control performance. Simulation results are included to complement the theoretical results.
Peng, Jinzhu; Dubay, Rickey
2011-10-01
In this paper, an adaptive control approach based on the neural networks is presented to control a DC motor system with dead-zone characteristics (DZC), where two neural networks are proposed to formulate the traditional identification and control approaches. First, a Wiener-type neural network (WNN) is proposed to identify the motor DZC, which formulates the Wiener model with a linear dynamic block in cascade with a nonlinear static gain. Second, a feedforward neural network is proposed to formulate the traditional PID controller, termed as PID-type neural network (PIDNN), which is then used to control and compensate for the DZC. In this way, the DC motor system with DZC is identified by the WNN identifier, which provides model information to the PIDNN controller in order to make it adaptive. Back-propagation algorithms are used to train both neural networks. Also, stability and convergence analysis are conducted using the Lyapunov theorem. Finally, experiments on the DC motor system demonstrated accurate identification and good compensation for dead-zone with improved control performance over the conventional PID control. Copyright © 2011 ISA. Published by Elsevier Ltd. All rights reserved.
A neural network device for on-line particle identification in cosmic ray experiments
International Nuclear Information System (INIS)
Scrimaglio, R.; Finetti, N.; D'Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G.C.
2004-01-01
On-line particle identification is one of the main goals of many experiments in space both for rare event studies and for optimizing measurements along the orbital trajectory. Neural networks can be a useful tool for signal processing and real time data analysis in such experiments. In this document we report on the performances of a programmable neural device which was developed in VLSI analog/digital technology. Neurons and synapses were accomplished by making use of Operational Transconductance Amplifier (OTA) structures. In this paper we report on the results of measurements performed in order to verify the agreement of the characteristic curves of each elementary cell with simulations and on the device performances obtained by implementing simple neural structures on the VLSI chip. A feed-forward neural network (Multi-Layer Perceptron, MLP) was implemented on the VLSI chip and trained to identify particles by processing the signals of two-dimensional position-sensitive Si detectors. The radiation monitoring device consisted of three double-sided silicon strip detectors. From the analysis of a set of simulated data it was found that the MLP implemented on the neural device gave results comparable with those obtained with the standard method of analysis confirming that the implemented neural network could be employed for real time particle identification
Disk hernia and spondylolisthesis diagnosis using biomechanical features and neural network.
Oyedotun, Oyebade K; Olaniyi, Ebenezer O; Khashman, Adnan
2016-01-01
Artificial neural networks have found applications in various areas of medical diagnosis. The capability of neural networks to learn medical data, mining useful and complex relationships that exist between attributes has earned it a major domain in decision support systems. This paper proposes a fast automatic system for the diagnosis of disk hernia and spondylolisthesis using biomechanical features and neural network. Such systems as described within this work allow the diagnosis of new cases using trained neural networks; patients are classified as either having disk hernia, spondylolisthesis, or normal. Generally, both disk hernia and spondylolisthesis present similar symptoms; hence, diagnosis is prone to inter-misclassification error. This work is significant in that the proposed systems are capable of making fast decisions on such somewhat difficult diagnoses with reasonable accuracies. Feedforward neural network and radial basis function networks are trained on data obtained from a public database. The results obtained within this research are promising and show that neural networks can find applications as efficient and effective expert systems for the diagnosis of disk hernia and spondylolisthesis.
International Nuclear Information System (INIS)
Lipponen, Jukka A; Tarvainen, Mika P; Karjalainen, Pasi A; Laitinen, Tomi; Vanninen, Joonas; Laitinen, Tiina M; Koponen, Timo
2013-01-01
Continuous electrocardiogram, blood pressure and carotid artery ultrasound video were analyzed from 15 diabetics and 28 healthy controls. By using these measurements artery elasticity, overall baroreflex sensitivity (BRS) assessed between RR and systolic blood pressure variation, and neural BRS assessed between RR and artery diameter variation were estimated. In addition, BRS was estimated using traditional and causal methods which enable separation of feedforward and feedback variation. The aim of this study was to analyze overall and neural BRS in relation to artery stiffness and to validate the causal BRS estimation method in assessing these two types of BRS within the study population. The most significant difference between the healthy and diabetic groups (p < 0.0007) was found for the overall BRS estimated using the causal method. The difference between the groups was also significant for neural BRS (p < 0.0018). However neural BRS was normal in some old diabetics, which indicates normal functioning of autonomic nervous system (ANS), even though the elasticity in arteries of these subjects was reduced. The noncausal method overestimated neural BRS in low BRS values when compared to causal BRS. In conclusion, neural BRS estimated using the causal method is proposed as the best marker of ANS functioning. (paper)
Neural network application to aircraft control system design
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.
A continuous-time neural model for sequential action.
Kachergis, George; Wyatte, Dean; O'Reilly, Randall C; de Kleijn, Roy; Hommel, Bernhard
2014-11-05
Action selection, planning and execution are continuous processes that evolve over time, responding to perceptual feedback as well as evolving top-down constraints. Existing models of routine sequential action (e.g. coffee- or pancake-making) generally fall into one of two classes: hierarchical models that include hand-built task representations, or heterarchical models that must learn to represent hierarchy via temporal context, but thus far lack goal-orientedness. We present a biologically motivated model of the latter class that, because it is situated in the Leabra neural architecture, affords an opportunity to include both unsupervised and goal-directed learning mechanisms. Moreover, we embed this neurocomputational model in the theoretical framework of the theory of event coding (TEC), which posits that actions and perceptions share a common representation with bidirectional associations between the two. Thus, in this view, not only does perception select actions (along with task context), but actions are also used to generate perceptions (i.e. intended effects). We propose a neural model that implements TEC to carry out sequential action control in hierarchically structured tasks such as coffee-making. Unlike traditional feedforward discrete-time neural network models, which use static percepts to generate static outputs, our biological model accepts continuous-time inputs and likewise generates non-stationary outputs, making short-timescale dynamic predictions. © 2014 The Author(s) Published by the Royal Society. All rights reserved.
Aspects of the numerical analysis of neural networks
Ellacott, S. W.
This article starts with a brief introduction to neural networks for those unfamiliar with the basic concepts, together with a very brief overview of mathematical approaches to the subject. This is followed by a more detailed look at three areas of research which are of particular interest to numerical analysts.The first area is approximation theory. If K is a compact set in n, for some n, then it is proved that a semilinear feedforward network with one hidden layer can uniformly approximate any continuous function in C(K) to any required accuracy. A discussion of known results and open questions on the degree of approximation is included. We also consider the relevance of radial basis functions to neural networks.The second area considered is that of learning algorithms. A detailed analysis of one popular algorithm (the delta rule) will be given, indicating why one implementation leads to a stable numerical process, whereas an initially attractive variant (essentially a form of steepest descent) does not. Similar considerations apply to the backpropagation algorithm. The effect of filtering and other preprocessing of the input data will also be discussed systematically.Finally some applications of neural networks to numerical computation are considered.
Control of 12-Cylinder Camless Engine with Neural Networks
Directory of Open Access Journals (Sweden)
Ashhab Moh’d Sami
2017-01-01
Full Text Available The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s. The inputs to the net are the intake valve lift (IVL and intake valve closing timing (IVC whereas the output of the net is the cylinder air charge (CAC. The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and applied to the camless engine ANN model. As a consequence the overall 12-cyliner camless engine feedback controller is upgraded and the necessary changes are implemented in order to contain the adaptive neural network with the objective of tracking the cylinder air charge (driver’s torque demand while minimizing the pumping losses (increasing engine efficiency. All the needed measurements are extracted only from the two conventional and inexpensive sensors, namely, the mass air flow through the throttle body (MAF and the intake manifold absolute pressure (MAP sensors. The feedback controller’s capability is demonstrated through computer simulation.
Expert music performance: cognitive, neural, and developmental bases.
Brown, Rachel M; Zatorre, Robert J; Penhune, Virginia B
2015-01-01
In this chapter, we explore what happens in the brain of an expert musician during performance. Understanding expert music performance is interesting to cognitive neuroscientists not only because it tests the limits of human memory and movement, but also because studying expert musicianship can help us understand skilled human behavior in general. In this chapter, we outline important facets of our current understanding of the cognitive and neural basis for music performance, and developmental factors that may underlie musical ability. We address three main questions. (1) What is expert performance? (2) How do musicians achieve expert-level performance? (3) How does expert performance come about? We address the first question by describing musicians' ability to remember, plan, execute, and monitor their performances in order to perform music accurately and expressively. We address the second question by reviewing evidence for possible cognitive and neural mechanisms that may underlie or contribute to expert music performance, including the integration of sound and movement, feedforward and feedback motor control processes, expectancy, and imagery. We further discuss how neural circuits in auditory, motor, parietal, subcortical, and frontal cortex all contribute to different facets of musical expertise. Finally, we address the third question by reviewing evidence for the heritability of musical expertise and for how expertise develops through training and practice. We end by discussing outlooks for future work. © 2015 Elsevier B.V. All rights reserved.
Towards practical control design using neural computation
Troudet, Terry; Garg, Sanjay; Mattern, Duane; Merrill, Walter
1991-01-01
The objective is to develop neural network based control design techniques which address the issue of performance/control effort tradeoff. Additionally, the control design needs to address the important issue if achieving adequate performance in the presence of actuator nonlinearities such as position and rate limits. These issues are discussed using the example of aircraft flight control. Given a set of pilot input commands, a feedforward net is trained to control the vehicle within the constraints imposed by the actuators. This is achieved by minimizing an objective function which is the sum of the tracking errors, control input rates and control input deflections. A tradeoff between tracking performance and control smoothness is obtained by varying, adaptively, the weights of the objective function. The neurocontroller performance is evaluated in the presence of actuator dynamics using a simulation of the vehicle. Appropriate selection of the different weights in the objective function resulted in the good tracking of the pilot commands and smooth neurocontrol. An extension of the neurocontroller design approach is proposed to enhance its practicality.
Neural network classification of questionable EGRET events
Meetre, C. A.; Norris, J. P.
1992-01-01
High energy gamma rays (greater than 20 MeV) pair producing in the spark chamber of the Energetic Gamma Ray Telescope Experiment (EGRET) give rise to a characteristic but highly variable 3-D locus of spark sites, which must be processed to decide whether the event is to be included in the database. A significant fraction (about 15 percent or 10(exp 4) events/day) of the candidate events cannot be categorized (accept/reject) by an automated rule-based procedure; they are therefore tagged, and must be examined and classified manually by a team of expert analysts. We describe a feedforward, back-propagation neural network approach to the classification of the questionable events. The algorithm computes a set of coefficients using representative exemplars drawn from the preclassified set of questionable events. These coefficients map a given input event into a decision vector that, ideally, describes the correct disposition of the event. The net's accuracy is then tested using a different subset of preclassified events. Preliminary results demonstrate the net's ability to correctly classify a large proportion of the events for some categories of questionables. Current work includes the use of much larger training sets to improve the accuracy of the net.
Balanced Neural Architecture and the Idling Brain
Directory of Open Access Journals (Sweden)
Brent eDoiron
2014-05-01
Full Text Available A signature feature of cortical spike trains is their trial-to-trial variability. This variability is large in spontaneous conditions and is reduced when cortex is driven by a stimulus or task. Models of recurrent cortical networks with unstructured, yet balanced, excitation and inhibition generate variability consistent with evoked conditions. However, these models lack the long timescale fluctuations and large variability present in spontaneous conditions. We propose that global network architectures which support a large number of stable states (attractor networks allow balanced networks to capture key features of neural variability in both spontaneous and evoked conditions. We illustrate this using balanced spiking networks with clustered assembly, feedforward chain, and ring structures. By assuming that global network structure is related to stimulus preference, we show that signal correlations are related to the magnitude of correlations in the spontaneous state. In our models, the dynamics of spontaneous activity encompasses much of the possible evoked states, consistent with many experimental reports. Finally, we contrast the impact of stimulation on the trial-to-trial variability in attractor networks with that of strongly coupled spiking networks with chaotic firing rate instabilities, recently investigated by Ostojic (2014. We find that only attractor networks replicate an experimentally observed stimulus-induced quenching of trial-to-trial variability. In total, the comparison of the trial-variable dynamics of single neurons or neuron pairs during spontaneous and evoked activity can be a window into the global structure of balanced cortical networks.
Directory of Open Access Journals (Sweden)
Lukas Falat
2014-01-01
Full Text Available In this paper, authors apply feed-forward artificial neural network (ANN of RBF type into the process of modelling and forecasting the future value of USD/CAD time series. Authors test the customized version of the RBF and add the evolutionary approach into it. They also combine the standard algorithm for adapting weights in neural network with an unsupervised clustering algorithm called K-means. Finally, authors suggest the new hybrid model as a combination of a standard ANN and a moving average for error modeling that is used to enhance the outputs of the network using the error part of the original RBF. Using high-frequency data, they examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, authors perform the comparative out-of-sample analysis of the suggested hybrid model with statistical models and the standard neural network.
International Nuclear Information System (INIS)
Sabahi, Kamel; Teshnehlab, Mohammad; Shoorhedeli, Mahdi Aliyari
2009-01-01
In this study, a new adaptive controller based on modified feedback error learning (FEL) approaches is proposed for load frequency control (LFC) problem. The FEL strategy consists of intelligent and conventional controllers in feedforward and feedback paths, respectively. In this strategy, a conventional feedback controller (CFC), i.e. proportional, integral and derivative (PID) controller, is essential to guarantee global asymptotic stability of the overall system; and an intelligent feedforward controller (INFC) is adopted to learn the inverse of the controlled system. Therefore, when the INFC learns the inverse of controlled system, the tracking of reference signal is done properly. Generally, the CFC is designed at nominal operating conditions of the system and, therefore, fails to provide the best control performance as well as global stability over a wide range of changes in the operating conditions of the system. So, in this study a supervised controller (SC), a lookup table based controller, is addressed for tuning of the CFC. During abrupt changes of the power system parameters, the SC adjusts the PID parameters according to these operating conditions. Moreover, for improving the performance of overall system, a recurrent fuzzy neural network (RFNN) is adopted in INFC instead of the conventional neural network, which was used in past studies. The proposed FEL controller has been compared with the conventional feedback error learning controller (CFEL) and the PID controller through some performance indices
Kowalski, J
2003-01-01
In this paper, a very large scale integration chip of an analog image weighted-order statistic (WOS) filter based on cellular neural network (CNN) architecture for real-time applications is described. The chip has been implemented in CMOS AMS 0.8 /spl mu/m technology. CNN-based filter consists of feedforward nonlinear template B operating within the window of 3 /spl times/ 3 pixels around the central pixel being filtered. The feedforward nonlinear CNN coefficients have been realized using programmable nonlinear coupler circuits. The WOS filter chip allows for processing of images with 300 pixels horizontal resolution. The resolution can be increased by cascading of the chips. Experimental results of basic circuit building blocks measurements are presented. Functional tests of the chip have been performed using a special test setup for PAL composite video signal processing. Using the setup real images have been filtered by WOS filter chip under test.
International Nuclear Information System (INIS)
Avci, E.
2007-01-01
In this paper, an automatic system is presented for word recognition using real Turkish word signals. This paper especially deals with combination of the feature extraction and classification from real Turkish word signals. A Discrete Wavelet Neural Network (DWNN) model is used, which consists of two layers: discrete wavelet layer and multi-layer perceptron. The discrete wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of Discrete Wavelet Transform (DWT) and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the used system is evaluated by using noisy Turkish word signals. Test results showing the effectiveness of the proposed automatic system are presented in this paper. The rate of correct recognition is about 92.5% for the sample speech signals. (author)
International Nuclear Information System (INIS)
Erkaymaz, Hande; Ozer, Mahmut; Orak, İlhami Muharrem
2015-01-01
The electrooculogram signals are very important at extracting information about detection of directional eye movements. Therefore, in this study, we propose a new intelligent detection model involving an artificial neural network for the eye movements based on the electrooculogram signals. In addition to conventional eye movements, our model also involves the detection of tic and blinking of an eye. We extract only two features from the electrooculogram signals, and use them as inputs for a feed-forwarded artificial neural network. We develop a new approach to compute these two features, which we call it as a movement range. The results suggest that the proposed model have a potential to become a new tool to determine the directional eye movements accurately
Adaptive online inverse control of a shape memory alloy wire actuator using a dynamic neural network
International Nuclear Information System (INIS)
Mai, Huanhuan; Liao, Xiaofeng; Song, Gangbing
2013-01-01
Shape memory alloy (SMA) actuators exhibit severe hysteresis, a nonlinear behavior, which complicates control strategies and limits their applications. This paper presents a new approach to controlling an SMA actuator through an adaptive inverse model based controller that consists of a dynamic neural network (DNN) identifier, a copy dynamic neural network (CDNN) feedforward term and a proportional (P) feedback action. Unlike fixed hysteresis models used in most inverse controllers, the proposed one uses a DNN to identify online the relationship between the applied voltage to the actuator and the displacement (the inverse model). Even without a priori knowledge of the SMA hysteresis and without pre-training, the proposed controller can precisely control the SMA wire actuator in various tracking tasks by identifying online the inverse model of the SMA actuator. Experiments were conducted, and experimental results demonstrated real-time modeling capabilities of DNN and the performance of the adaptive inverse controller. (paper)
Expectation violation and attention to pain jointly modulate neural gain in somatosensory cortex
DEFF Research Database (Denmark)
Fardo, Francesca; Auksztulewicz, Ryszard; Allen, Micah
2017-01-01
The neural processing and experience of pain are influenced by both expectations and attention. For example, the amplitude of event-related pain responses is enhanced by both novel and unexpected pain, and by moving the focus of attention towards a painful stimulus. Under predictive coding, this ...... the influence of both expectation violation and attention on cortical processing and pain perception.......The neural processing and experience of pain are influenced by both expectations and attention. For example, the amplitude of event-related pain responses is enhanced by both novel and unexpected pain, and by moving the focus of attention towards a painful stimulus. Under predictive coding......, this congruence can be explained by appeal to a precision-weighting mechanism, which mediates bottom-up and top-down attentional processes by modulating the influence of feedforward and feedback signals throughout the cortical hierarchy. The influence of expectation and attention on pain processing can thus...
Approximating quantum many-body wave functions using artificial neural networks
Cai, Zi; Liu, Jinguo
2018-01-01
In this paper, we demonstrate the expressibility of artificial neural networks (ANNs) in quantum many-body physics by showing that a feed-forward neural network with a small number of hidden layers can be trained to approximate with high precision the ground states of some notable quantum many-body systems. We consider the one-dimensional free bosons and fermions, spinless fermions on a square lattice away from half-filling, as well as frustrated quantum magnetism with a rapidly oscillating ground-state characteristic function. In the latter case, an ANN with a standard architecture fails, while that with a slightly modified one successfully learns the frustration-induced complex sign rule in the ground state and approximates the ground states with high precisions. As an example of practical use of our method, we also perform the variational method to explore the ground state of an antiferromagnetic J1-J2 Heisenberg model.
Online Particle Detection by Neural Networks Based on Topologic Calorimetry Information
Ciodaro, T; The ATLAS collaboration; de Seixas, JM; Damazio, D
2011-01-01
The neural ringer is an alternative algorithm (for both feature extraction and hypothesis testing) for electron identification at the ATLAS L2 calorimetry trigger. The feature extraction consists on calculating concentric energetic rings at each calorimeter layer. For each layer, the first ring is the energy from the hottest cell, and the energy of the outer cells are summed up forming the second ring (and sequentially for the other rings). A feedforward MLP neural network operates over the extracted rings performing particle identification. This study shows the later resuls considering improvements on the HLT implementation and performance evaluation over pileup from Monte Carlo proton-proton collisions simulations of 14 TeV at 2e34 luminosity.
Manipulator inverse kinematics control based on particle swarm optimization neural network
Wen, Xiulan; Sheng, Danghong; Guo, Jing
2008-10-01
The inverse kinematics control of a robotic manipulator requires solving non-linear equations having transcendental functions and involving time-consuming calculations. Particle Swarm Optimization (PSO), which is based on the behaviour of insect swarms and exploits the solution space by taking into account the experience of the single particle as well as that of the entire swarm, is similar to the genetic algorithm (GA) in that it performs a structured randomized search of an unknown parameter space by manipulating a population of parameter estimates to converge on a suitable solution. In this paper, PSO is firstly proposed to optimize feed-forward neural network for manipulator inverse kinematics. Compared with the results of the fast back propagation learning algorithm (FBP), conventional GA genetic algorithm based elitist reservation (EGA), improved GA (IGA) and immune evolutionary computation (IEC), the simulation results verify the particle swarm optimization neural network (PSONN) is effective for manipulator inverse kinematics control.
Predicting the Survival of Gastric Cancer Patients Using Artificial and Bayesian Neural Networks
Korhani Kangi, Azam; Bahrampour, Abbas
2018-02-26
Introduction and purpose: In recent years the use of neural networks without any premises for investigation of prognosis in analyzing survival data has increased. Artificial neural networks (ANN) use small processors with a continuous network to solve problems inspired by the human brain. Bayesian neural networks (BNN) constitute a neural-based approach to modeling and non-linearization of complex issues using special algorithms and statistical methods. Gastric cancer incidence is the first and third ranking for men and women in Iran, respectively. The aim of the present study was to assess the value of an artificial neural network and a Bayesian neural network for modeling and predicting of probability of gastric cancer patient death. Materials and Methods: In this study, we used information on 339 patients aged from 20 to 90 years old with positive gastric cancer, referred to Afzalipoor and Shahid Bahonar Hospitals in Kerman City from 2001 to 2015. The three layers perceptron neural network (ANN) and the Bayesian neural network (BNN) were used for predicting the probability of mortality using the available data. To investigate differences between the models, sensitivity, specificity, accuracy and the area under receiver operating characteristic curves (AUROCs) were generated. Results: In this study, the sensitivity and specificity of the artificial neural network and Bayesian neural network models were 0.882, 0.903 and 0.954, 0.909, respectively. Prediction accuracy and the area under curve ROC for the two models were 0.891, 0.944 and 0.935, 0.961. The age at diagnosis of gastric cancer was most important for predicting survival, followed by tumor grade, morphology, gender, smoking history, opium consumption, receiving chemotherapy, presence of metastasis, tumor stage, receiving radiotherapy, and being resident in a village. Conclusion: The findings of the present study indicated that the Bayesian neural network is preferable to an artificial neural network for
UNMANNED AIR VEHICLE STABILIZATION BASED ON NEURAL NETWORK REGULATOR
Directory of Open Access Journals (Sweden)
S. S. Andropov
2016-09-01
Full Text Available A problem of stabilizing for the multirotor unmanned aerial vehicle in an environment with external disturbances is researched. A classic proportional-integral-derivative controller is analyzed, its flaws are outlined: inability to respond to changing of external conditions and the need for manual adjustment of coefficients. The paper presents an adaptive adjustment method for coefficients of the proportional-integral-derivative controller based on neural networks. A neural network structure, its input and output data are described. Neural networks with three layers are used to create an adaptive stabilization system for the multirotor unmanned aerial vehicle. Training of the networks is done with the back propagation method. Each neural network produces regulator coefficients for each angle of stabilization as its output. A method for network training is explained. Several graphs of transition process on different stages of learning, including processes with external disturbances, are presented. It is shown that the system meets stabilization requirements with sufficient number of iterations. Described adjustment method for coefficients can be used in remote control of unmanned aerial vehicles, operating in the changing environment.
Missing Data Estimation using Principle Component Analysis and Autoassociative Neural Networks
Directory of Open Access Journals (Sweden)
Tshilidzi Marwala
2009-06-01
Full Text Available Three new methods are used for estimating missing data in a database using Neural Networks, Principal Component Analysis and Genetic Algorithms are presented. The proposed methods are tested on a set of data obtained from the South African Antenatal Survey. The data is a collection of demographic properties of patients. The proposed methods use Principal Component Analysis to remove redundancies and reduce the dimensionality in the data. Variations of autoassociative Neural Networks are used to further reduce the dimensionality of the data. A Genetic Algorithm is then used to find the missing data by optimizing the error function of the three variants of the Autoencoder Neural Network. The proposed system was tested on data with 1 to 6 missing fields in a single record of data and the accuracy of the estimated values were calculated and recorded. All methods are as accurate as a conventional feedforward neural network structure however the use of the newly proposed methods employs neural network architectures that have fewer hidden nodes.
Hybrid digital signal processing and neural networks for automated diagnostics using NDE methods
International Nuclear Information System (INIS)
Upadhyaya, B.R.; Yan, W.
1993-11-01
The primary purpose of the current research was to develop an integrated approach by combining information compression methods and artificial neural networks for the monitoring of plant components using nondestructive examination data. Specifically, data from eddy current inspection of heat exchanger tubing were utilized to evaluate this technology. The focus of the research was to develop and test various data compression methods (for eddy current data) and the performance of different neural network paradigms for defect classification and defect parameter estimation. Feedforward, fully-connected neural networks, that use the back-propagation algorithm for network training, were implemented for defect classification and defect parameter estimation using a modular network architecture. A large eddy current tube inspection database was acquired from the Metals and Ceramics Division of ORNL. These data were used to study the performance of artificial neural networks for defect type classification and for estimating defect parameters. A PC-based data preprocessing and display program was also developed as part of an expert system for data management and decision making. The results of the analysis showed that for effective (low-error) defect classification and estimation of parameters, it is necessary to identify proper feature vectors using different data representation methods. The integration of data compression and artificial neural networks for information processing was established as an effective technique for automation of diagnostics using nondestructive examination methods
Directory of Open Access Journals (Sweden)
Mohammad S. Islam
2017-01-01
Full Text Available Decoding neural activities related to voluntary and involuntary movements is fundamental to understanding human brain motor circuits and neuromotor disorders and can lead to the development of neuromotor prosthetic devices for neurorehabilitation. This study explores using recorded deep brain local field potentials (LFPs for robust movement decoding of Parkinson’s disease (PD and Dystonia patients. The LFP data from voluntary movement activities such as left and right hand index finger clicking were recorded from patients who underwent surgeries for implantation of deep brain stimulation electrodes. Movement-related LFP signal features were extracted by computing instantaneous power related to motor response in different neural frequency bands. An innovative neural network ensemble classifier has been proposed and developed for accurate prediction of finger movement and its forthcoming laterality. The ensemble classifier contains three base neural network classifiers, namely, feedforward, radial basis, and probabilistic neural networks. The majority voting rule is used to fuse the decisions of the three base classifiers to generate the final decision of the ensemble classifier. The overall decoding performance reaches a level of agreement (kappa value at about 0.729±0.16 for decoding movement from the resting state and about 0.671±0.14 for decoding left and right visually cued movements.
A new method to estimate parameters of linear compartmental models using artificial neural networks
International Nuclear Information System (INIS)
Gambhir, Sanjiv S.; Keppenne, Christian L.; Phelps, Michael E.; Banerjee, Pranab K.
1998-01-01
At present, the preferred tool for parameter estimation in compartmental analysis is an iterative procedure; weighted nonlinear regression. For a large number of applications, observed data can be fitted to sums of exponentials whose parameters are directly related to the rate constants/coefficients of the compartmental models. Since weighted nonlinear regression often has to be repeated for many different data sets, the process of fitting data from compartmental systems can be very time consuming. Furthermore the minimization routine often converges to a local (as opposed to global) minimum. In this paper, we examine the possibility of using artificial neural networks instead of weighted nonlinear regression in order to estimate model parameters. We train simple feed-forward neural networks to produce as outputs the parameter values of a given model when kinetic data are fed to the networks' input layer. The artificial neural networks produce unbiased estimates and are orders of magnitude faster than regression algorithms. At noise levels typical of many real applications, the neural networks are found to produce lower variance estimates than weighted nonlinear regression in the estimation of parameters from mono- and biexponential models. These results are primarily due to the inability of weighted nonlinear regression to converge. These results establish that artificial neural networks are powerful tools for estimating parameters for simple compartmental models. (author)
Stability analysis and the stabilization of a class of discrete-time dynamic neural networks.
Patan, Krzysztof
2007-05-01
This paper deals with problems of stability and the stabilization of discrete-time neural networks. Neural structures under consideration belong to the class of the so-called locally recurrent globally feedforward networks. The single processing unit possesses dynamic behavior. It is realized by introducing into the neuron structure a linear dynamic system in the form of an infinite impulse response filter. In this way, a dynamic neural network is obtained. It is well known that the crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates stability conditions for the analyzed class of neural networks. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem two methods are proposed. The first one is based on a gradient projection (GP) and the second one on a minimum distance projection (MDP). It is worth noting that these methods can be easily introduced into the existing learning algorithm as an additional step, and suitable convergence conditions can be developed for them. The efficiency and usefulness of the proposed approaches are justified by using a number of experiments including numerical complexity analysis, stabilization effectiveness, and the identification of an industrial process.
SYNTHESIS OF NEURAL NETWORK MODEL REFERENCE CONTROLLER FOR AIMING AND STABILIZING SYSTEM
Directory of Open Access Journals (Sweden)
B.I. Kuznetsov
2015-11-01
Full Text Available The aim of this work is the synthesis of neural network reference model controller. The synthesis is performed in MATLAB for the problem of control of the aiming and stabilization system for the special equipment of moving objects. This paper presents the synthesis of the neural network reference model controller to meet the given performance characteristics of operation for the aiming and stabilization system for the special equipment of moving objects. Simulink tool in MATLAB is used to build the block diagram of double-loop neural network system of aiming and stabilization, where the reference model controller is put in the velocity loop and P-regulator is put in the position loop, with feedforward velocity control. Presented the method of synthesis of the neural network reference model controller that is implemented in the Neural Network Toolbox in MATLAB. System tests with the broad range of parameter values determined the key parameters defining the control quality. Optimal values of the key parameters were found to provide the highest control performance. System simulation and analysis of the obtained results is given.
Application of neural models as controllers in mobile robot velocity control loop
Cerkala, Jakub; Jadlovska, Anna
2017-01-01
This paper presents the application of an inverse neural models used as controllers in comparison to classical PI controllers for velocity tracking control task used in two-wheel, differentially driven mobile robot. The PI controller synthesis is based on linear approximation of actuators with equivalent load. In order to obtain relevant datasets for training of feed-forward multi-layer perceptron based neural network used as neural model, the mathematical model of mobile robot, that combines its kinematic and dynamic properties such as chassis dimensions, center of gravity offset, friction and actuator parameters is used. Neural models are trained off-line to act as an inverse dynamics of DC motors with particular load using data collected in simulation experiment for motor input voltage step changes within bounded operating area. The performances of PI controllers versus inverse neural models in mobile robot internal velocity control loops are demonstrated and compared in simulation experiment of navigation control task for line segment motion in plane.
Energy Technology Data Exchange (ETDEWEB)
Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)
1996-12-31
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
Neural tube defects are birth defects of the brain, spine, or spinal cord. They happen in the ... that she is pregnant. The two most common neural tube defects are spina bifida and anencephaly. In ...
Loss-efficiency model of single and variable-speed compressors using neural networks
Energy Technology Data Exchange (ETDEWEB)
Yang, Liang [Institute of Refrigeration and Cryogenics, Shanghai Jiaotong University, Shanghai 200240 (China); China R and D Center, Carrier Corporation, No.3239 Shen Jiang Road, Shanghai 201206 (China); Zhao, Ling-Xiao; Gu, Bo [Institute of Refrigeration and Cryogenics, Shanghai Jiaotong University, Shanghai 200240 (China); Zhang, Chun-Lu [China R and D Center, Carrier Corporation, No.3239 Shen Jiang Road, Shanghai 201206 (China)
2009-09-15
Compressor is the critical component to the performance of a vapor-compression refrigeration system. The loss-efficiency model including the volumetric efficiency and the isentropic efficiency is widely used for representing the compressor performance. A neural network loss-efficiency model is developed to simulate the performance of positive displacement compressors like the reciprocating, screw and scroll compressors. With one more input, frequency, it can be easily extended to the variable speed compressors. The three-layer polynomial perceptron network is developed because the polynomial transfer function is found very effective in training and free of over-learning. The selection of input parameters of neural networks is also found critical to the network prediction accuracy. The proposed neural networks give less than 0.4% standard deviations and {+-}1.3% maximum deviations against the manufacturer data. (author)
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.
Feeding patterns of pigs in the grow-finish phase have been investigated for use in management decisions, identifying sick animals, and determining genetic differences within a herd. Development of models to predict swine feeding behavior has been limited due the large number of potential environmen...
2014-03-27
Perl script created by Moore [22]. It is available for download from the University of Cambridge Computer Laboratory Downloads: BRASIL – Characterizing...December 2013]. 127 [58] " BRASIL Downloads," 2009. [Online]. Available: http://www.cl.cam.ac.uk/research/srg/netos/ brasil /downloads/. [Accessed 15
BIALEK, W; RIEKE, F; VANSTEVENINCK, RRD; WARLAND, D
1991-01-01
Traditional approaches to neural coding characterize the encoding of known stimuli in average neural responses. Organisms face nearly the opposite task - extracting information about an unknown time-dependent stimulus from short segments of a spike train. Here the neural code was characterized from
artificial neural network (ann)
African Journals Online (AJOL)
2004-08-18
Aug 18, 2004 ... forecasting models and artificial intelligence techniques and have become one of the major research fields (Kher and Joshin, 2003). (a) Artificial Neural Network and Electrical Load. Prediction. Neural network analysis is an Artificial Intelligence. (AI) approach to mathematical modeling. Neural. Networks ...
Beisel, Chase L; Storz, Gisela
2011-02-04
Bacteria selectively consume some carbon sources over others through a regulatory mechanism termed catabolite repression. Here, we show that the base-pairing RNA Spot 42 plays a broad role in catabolite repression in Escherichia coli by directly repressing genes involved in central and secondary metabolism, redox balancing, and the consumption of diverse nonpreferred carbon sources. Many of the genes repressed by Spot 42 are transcriptionally activated by the global regulator CRP. Since CRP represses Spot 42, these regulators participate in a specific regulatory circuit called a multioutput feedforward loop. We found that this loop can reduce leaky expression of target genes in the presence of glucose and can maintain repression of target genes under changing nutrient conditions. Our results suggest that base-pairing RNAs in feedforward loops can help shape the steady-state levels and dynamics of gene expression. Copyright © 2011 Elsevier Inc. All rights reserved.
International Nuclear Information System (INIS)
Leon, Andres E.; Solsona, Jorge A.; Busada, Claudio; Chiacchiarini, Hector; Valla, Maria Ines
2009-01-01
In this paper a new control strategy for voltage-source converters (VSC) is introduced. The proposed strategy consists of a nonlinear feedback controller based on feedback linearization plus a feedforward compensation of the estimated load current. In our proposal an energy function and the direct-axis current are considered as outputs, in order to avoid the internal dynamics. In this way, a full linearization is obtained via nonlinear transformation and feedback. An estimate of the load current is feedforwarded to improve the performance of the whole system and to diminish the capacitor size. This estimation allows to obtain a more rugged and cheaper implementation. The estimate is calculated by using a nonlinear reduced-order observer. The proposal is validated through different tests. These tests include performance in presence of switching frequency, measurement filters delays, parameters uncertainties and disturbances in the input voltage.
Energy Technology Data Exchange (ETDEWEB)
Leon, Andres E.; Solsona, Jorge A.; Busada, Claudio; Chiacchiarini, Hector [Instituto de Investigaciones en Ingenieria Electrica (IIIE) UNS-CONICET, Universidad Nacional del Sur, Av. Alem 1253, Bahia Blanca 8000 (Argentina); Valla, Maria Ines [Laboratorio de Electronica Industrial, Control e Instrumentacion (LEICI) and CONICET, Facultad de Ingenieria, Universidad Nacional de La Plata, La Plata 1900 (Argentina)
2009-08-15
In this paper a new control strategy for voltage-source converters (VSC) is introduced. The proposed strategy consists of a nonlinear feedback controller based on feedback linearization plus a feedforward compensation of the estimated load current. In our proposal an energy function and the direct-axis current are considered as outputs, in order to avoid the internal dynamics. In this way, a full linearization is obtained via nonlinear transformation and feedback. An estimate of the load current is feedforwarded to improve the performance of the whole system and to diminish the capacitor size. This estimation allows to obtain a more rugged and cheaper implementation. The estimate is calculated by using a nonlinear reduced-order observer. The proposal is validated through different tests. These tests include performance in presence of switching frequency, measurement filters delays, parameters uncertainties and disturbances in the input voltage. (author)
Model-Trained Neural Networks and Electronic Holography Demonstrated to Detect Damage in Blades
Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.
1998-01-01
Detect Damage in Blades Electronic holography can show damaged regions in fan blades at 30 frames/sec. The electronic holograms are transformed by finite-element-model-trained artificial neural networks to visualize the damage. The trained neural networks are linked with video and graphics to visualize the bending-induced strain distribution, which is very sensitive to damage. By contrast, it is very difficult to detect damage by viewing the raw, speckled, characteristic fringe patterns. For neural-network visualization of damage, 2 frames or 2 fields are used, rather than the 12 frames normally used to compute the displacement distribution from electronic holograms. At the NASA Lewis Research Center, finite element models are used to compute displacement and strain distributions for the vibration modes of undamaged and cracked blades. A model of electronic time-averaged holography is used to transform the displacement distributions into finite-element-resolution characteristic fringe patterns. Then, a feedforward neural network is trained with the fringe-pattern/strain-pattern pairs, and the neural network, electronic holography, and video are implemented on a workstation. Now that the neural networks have been tested successfully at 30 frames/sec on undamaged and cracked cantilevers, the electronic holography and neural-network processing are being adapted for onsite damage inspection of twisted fan blades and rotormounted blades. Our conclusion is that model-trained neural nets are effective when they are trained with good models whose application is well understood. This work supports the aeromechanical testing portion of the Advanced Subsonic Technology Project.
Prediction of dose to the relatives of patients treated with radioiodine-131 using neural networks.
Ebrahimi, Marzieh; Kardan, Mohammad Reza; Changizi, Vahid; Hosseini Pooya, Seyed Mahdi; Geramifar, Parham
2017-11-20
In this study, the effective dose to family members and caregivers of 52 thyroid cancer patients who had been treated with radioiodine I-131 was measured to investigate the ability of neural network for predicting the doses to the relatives. Effectiveness of this method to define the relatives who will receive doses more than 1 mSv was evaluated. The effective doses were measured by TLD. The inputs of neural network were 13 different parameters that potentially could affect the dose and the output was dose to the family members. The neural networks in this study were feed-forward with sigmoid activation function and one hidden layer. The mean and median of measured doses were 0.45 and 0.28 mSv and its range was 0.1 - 3.64mSv. The mean square error of predicted doses by the neural network and measured doses by TLD (Mean Squared Error) for 99 individuals was 0.142. The optimum neural network was able to predict all relatives who receive doses more than 1 mSv. The area under the Receiver Operating Characteristic (ROC) Curve for the trained Neural Network was 0.957 that showed the ability of the trained Neural Network in distinguishing these groups. Prediction of dose to the patient's relatives before the release is a helpful and future based strategy for optimization. Neural network is a promising method for predicting dose to the family members and defining high risk patients and relatives. Patient specific criteria for release and patient specific advice and consultation can be used for reducing the dose to family member. © 2017 IOP Publishing Ltd.
Asiah, Neng
2014-01-01
The purpose of this study are to determine the effect of feedback control, feed-forward control on the market orientation and entrepreneurship, the effect of market orientation on organizational capabilities and influence the ability of entrepreneurship performance to organizational performance.The population of this study are all managers of manufacturing companies in the City and County of Bekasi. The sampling technique used was purposive sampling. The respondents of this study are middle m...
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.
Neural dynamics of phonological processing in the dorsal auditory stream.
Liebenthal, Einat; Sabri, Merav; Beardsley, Scott A; Mangalathu-Arumana, Jain; Desai, Anjali
2013-09-25
Neuroanatomical models hypothesize a role for the dorsal auditory pathway in phonological processing as a feedforward efferent system (Davis and Johnsrude, 2007; Rauschecker and Scott, 2009; Hickok et al., 2011). But the functional organization of the pathway, in terms of time course of interactions between auditory, somatosensory, and motor regions, and the hemispheric lateralization pattern is largely unknown. Here, ambiguous duplex syllables, with elements presented dichotically at varying interaural asynchronies, were used to parametrically modulate phonological processing and associated neural activity in the human dorsal auditory stream. Subjects performed syllable and chirp identification tasks, while event-related potentials and functional magnetic resonance images were concurrently collected. Joint independent component analysis was applied to fuse the neuroimaging data and study the neural dynamics of brain regions involved in phonological processing with high spatiotemporal resolution. Results revealed a highly interactive neural network associated with phonological processing, composed of functional fields in posterior temporal gyrus (pSTG), inferior parietal lobule (IPL), and ventral central sulcus (vCS) that were engaged early and almost simultaneously (at 80-100 ms), consistent with a direct influence of articulatory somatomotor areas on phonemic perception. Left hemispheric lateralization was observed 250 ms earlier in IPL and vCS than pSTG, suggesting that functional specialization of somatomotor (and not auditory) areas determined lateralization in the dorsal auditory pathway. The temporal dynamics of the dorsal auditory pathway described here offer a new understanding of its functional organization and demonstrate that temporal information is essential to resolve neural circuits underlying complex behaviors.
Cohen, Dror; van Swinderen, Bruno; Tsuchiya, Naotsugu
2018-01-01
Hierarchically organized brains communicate through feedforward (FF) and feedback (FB) pathways. In mammals, FF and FB are mediated by higher and lower frequencies during wakefulness. FB is preferentially impaired by general anesthetics in multiple mammalian species. This suggests FB serves critical functions in waking brains. The brain of Drosophila melanogaster (fruit fly) is also hierarchically organized, but the presence of FB in these brains is not established. Here, we studied FB in the fly brain, by simultaneously recording local field potentials (LFPs) from low-order peripheral structures and higher-order central structures. We analyzed the data using Granger causality (GC), the first application of this analysis technique to recordings from the insect brain. Our analysis revealed that low frequencies (0.1-5 Hz) mediated FB from the center to the periphery, while higher frequencies (10-45 Hz) mediated FF in the opposite direction. Further, isoflurane anesthesia preferentially reduced FB. Our results imply that the spectral characteristics of FF and FB may be a signature of hierarchically organized brains that is conserved from insects to mammals. We speculate that general anesthetics may induce unresponsiveness across species by targeting the mechanisms that support FB.
Tungpataratanawong, Somsawas; Ohishi, Kiyoshi; Miyazaki, Toshimasa
In control application of industrial robot manipulator, a two-inertia resonant system is normally represented as the basic plant model for various control schemes. Various control techniques with partially feedback linearization have been proposed to achieve high performance motion control. The design of such controllers basically relies on system mechanical parameters. The proper parameters of the model cannot be obtained by the parameter identification based on only manipulator force and motion measurements. In this paper, the open-loop resonant frequency characteristic of the flexible joint is employed to identify the proper mechanical parameters of the two-inertia model. The nominal link inertia and spring constant of gear drive can be readily measured by this novel identification method. The identified parameters are used in independent-joint controller design for conventional PD control scheme and robust control scheme to verify the effectiveness of the proposed identification method. Moreover, the accuracy improvement of the proposed robust control scheme based on feedforward inverse dynamic compensation and D-PD position control gives support the validity of the proposed identification method.
International Nuclear Information System (INIS)
Zhao, Y.; Edwards, R.M.; Lee, K.Y.
1997-01-01
In this paper, a simplified model with a lower order is first developed for a nuclear steam generator system and verified against some realistic environments. Based on this simplified model, a hybrid multi-input and multi-out (MIMO) control system, consisting of feedforward control (FFC) and feedback control (FBC), is designed for wide range conditions by using the genetic algorithm (GA) technique. The FFC control, obtained by the GA optimization method, injects an a priori command input into the system to achieve an optimal performance for the designed system, while the GA-based FBC control provides the necessary compensation for any disturbances or uncertainties in a real steam generator. The FBC control is an optimal design of a PI-based control system which would be more acceptable for industrial practices and power plant control system upgrades. The designed hybrid MIMO FFC/FBC control system is first applied to the simplified model and then to a more complicated model with a higher order which is used as a substitute of the real system to test the efficacy of the designed control system. Results from computer simulations show that the designed GA-based hybrid MIMO FFC/FBC control can achieve good responses and robust performances. Hence, it can be considered as a viable alternative to the current control system upgrade
Directory of Open Access Journals (Sweden)
Shiying Zhou
2017-05-01
Full Text Available Three-phase active damping LCL-type grid-connected converters are usually used in distributed power generation systems. However, serious inrush current will be aroused when the grid-connected converter starts, especially in rectifier mode, if no effective control method is taken. The point of common coupling (PCC voltage feedforward is usually used to suppress start-up inrush current. Unfortunately, it will introduce a positive feedback loop related to the grid current and grid impedance under weak grid conditions, and therefore, the grid current will be distorted and the system stability margin will be significantly reduced. To solve the above problems, this paper proposes a simple method based on a d-axis fundamental positive-sequence component of filter capacitor voltage feedforward, without extra sensors and software resources. With the proposed method, it is possible to suppress the start-up inrush current and maintain the grid current quality and system stability under weak grid conditions. The mechanism of start-up inrush current and the effectiveness of the method for inrush current suppression are analyzed in detail. Then, the influences of different feedforward methods on system stability are analyzed under weak grid conditions by the impedance model of grid-connected converter. Finally, experimental results verify the validity of the proposed method.
Neural networks and particle physics
Peterson, Carsten
1993-01-01
1. Introduction : Structure of the Central Nervous System Generics2. Feed-forward networks, Perceptions, Function approximators3. Self-organisation, Feature Maps4. Feed-back Networks, The Hopfield model, Optimization problems, Feed-back, Networks, Deformable templates, Graph bisection
Neural electrical activity and neural network growth.
Gafarov, F M
2018-02-09
The development of central and peripheral neural system depends in part on the emergence of the correct functional connectivity in its input and output pathways. Now it is generally accepted that molecular factors guide neurons to establish a primary scaffold that undergoes activity-dependent refinement for building a fully functional circuit. However, a number of experimental results obtained recently shows that the neuronal electrical activity plays an important role in the establishing of initial interneuronal connections. Nevertheless, these processes are rather difficult to study experimentally, due to the absence of theoretical description and quantitative parameters for estimation of the neuronal activity influence on growth in neural networks. In this work we propose a general framework for a theoretical description of the activity-dependent neural network growth. The theoretical description incorporates a closed-loop growth model in which the neural activity can affect neurite outgrowth, which in turn can affect neural activity. We carried out the detailed quantitative analysis of spatiotemporal activity patterns and studied the relationship between individual cells and the network as a whole to explore the relationship between developing connectivity and activity patterns. The model, developed in this work will allow us to develop new experimental techniques for studying and quantifying the influence of the neuronal activity on growth processes in neural networks and may lead to a novel techniques for constructing large-scale neural networks by self-organization. Copyright © 2018 Elsevier Ltd. All rights reserved.
Artificial neural networks for solving ordinary and partial differential equations.
Lagaris, I E; Likas, A; Fotiadis, D I
1998-01-01
We present a method to solve initial and boundary value problems using artificial neural networks. A trial solution of the differential equation is written as a sum of two parts. The first part satisfies the initial/boundary conditions and contains no adjustable parameters. The second part is constructed so as not to affect the initial/boundary conditions. This part involves a feedforward neural network containing adjustable parameters (the weights). Hence by construction the initial/boundary conditions are satisfied and the network is trained to satisfy the differential equation. The applicability of this approach ranges from single ordinary differential equations (ODE's), to systems of coupled ODE's and also to partial differential equations (PDE's). In this article, we illustrate the method by solving a variety of model problems and present comparisons with solutions obtained using the Galekrkin finite element method for several cases of partial differential equations. With the advent of neuroprocessors and digital signal processors the method becomes particularly interesting due to the expected essential gains in the execution speed.
Neural network stochastic simulation applied for quantifying uncertainties
Directory of Open Access Journals (Sweden)
N Foudil-Bey
2016-09-01
Full Text Available Generally the geostatistical simulation methods are used to generate several realizations of physical properties in the sub-surface, these methods are based on the variogram analysis and limited to measures correlation between variables at two locations only. In this paper, we propose a simulation of properties based on supervised Neural network training at the existing drilling data set. The major advantage is that this method does not require a preliminary geostatistical study and takes into account several points. As a result, the geological information and the diverse geophysical data can be combined easily. To do this, we used a neural network with multi-layer perceptron architecture like feed-forward, then we used the back-propagation algorithm with conjugate gradient technique to minimize the error of the network output. The learning process can create links between different variables, this relationship can be used for interpolation of the properties on the one hand, or to generate several possible distribution of physical properties on the other hand, changing at each time and a random value of the input neurons, which was kept constant until the period of learning. This method was tested on real data to simulate multiple realizations of the density and the magnetic susceptibility in three-dimensions at the mining camp of Val d'Or, Québec (Canada.
Gap Filling of Daily Sea Levels by Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Lyubka Pashova
2013-06-01
Full Text Available In the recent years, intelligent methods as artificial neural networks are successfully applied for data analysis from different fields of the geosciences. One of the encountered practical problems is the availability of gaps in the time series that prevent their comprehensive usage for the scientific and practical purposes. The article briefly describes two types of the artificial neural network (ANN architectures - Feed-Forward Backpropagation (FFBP and recurrent Echo state network (ESN. In some cases, the ANN can be used as an alternative on the traditional methods, to fill in missing values in the time series. We have been conducted several experiments to fill the missing values of daily sea levels spanning a 5-years period using both ANN architectures. A multiple linear regression for the same purpose has been also applied. The sea level data are derived from the records of the tide gauge Burgas, which is located on the western Black Sea coast. The achieved results have shown that the performance of ANN models is better than that of the classical one and they are very promising for the real-time interpolation of missing data in the time series.
A neural network model for predicting weighted mean temperature
Ding, Maohua
2018-02-01
Water vapor is an important element of the Earth's atmosphere, and most of it concentrates at the bottom of the troposphere. Knowledge of the water vapor measured by Global Navigation Satellite Systems (GNSS) is an important direction of GNSS research. In particular, when the zenith wet delay is converted to precipitable water vapor, the weighted mean temperature T_m is a variable parameter to be determined in this conversion. The purpose of the study is getting a more accurate T_m model for global users by a combination of two different characteristics of T_m (i.e., the T_m seasonal variations and the relationships between T_m and surface meteorological elements). The modeling process was carried out by using the neural network technology. A multilayer feedforward neural network model (the NN) was established. The NN model is used with measurements of only surface temperature T_S . The NN was validated and compared with four other published global T_m models. The results show that the NN performed better than any of the four compared models on the global scale.
Stellar Image Interpretation System Using Artificial Neural Networks:
Directory of Open Access Journals (Sweden)
A. El-Bassuny Alawy
2004-01-01
Full Text Available A supervised Artificial Neural Network (ANN based system is being developed employing the Bi-polar function for identifying stellar images in CCD frames. It is based on feed-forward artificial neural networks with error back-propagation learning. It has been coded in C language. The learning process was performed on a 341 input pattern set, while a similar set was used for testing. The present approach has been applied on a CCD frame of the open star cluster M67. The results obtained have been discussed and compared with those derived in our previous work employing the Uni-polar function and by a package known in the astronomical community (DAOPHOT-II. Full agreement was found between the present approach, that of Elnagahy et al, and the standard astronomical data for the cluster. It has been shown that the developed technique resembles that of the Uni-Polar function, possessing a simple, much faster yet reliable approach. Moreover, neither prior knowledge on, nor initial data from, the frame to be analysed is required, as it is for DAOPHOT-II.
Directory of Open Access Journals (Sweden)
Ana IGLESIAS RODRÍGUEZ
2012-03-01
Full Text Available 0 0 1 266 1465 Instituto Universitario de Ciencias de la Educación 12 3 1728 14.0 Normal 0 21 false false false ES JA X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Tabla normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:Calibri; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-ansi-language:ES; mso-fareast-language:EN-US;} En este artículo presentamos una experiencia basada en el uso de la actividad foro de Moodle (Studium para la realización, no sólo de tutorías online, sino para generar un espacio de comunicación que contribuya al desarrollo de un aprendizaje colaborativo. Comenzaremos con unas consideraciones muy generales sobre el sentido de los foros en un contexto de aprendizaje colaborativo en un curso online de formación dentro de los cursos virtuales realizados con la plataforma Moodle. Estas consideraciones servirán de marco de referencia para la descripción en detalle, tanto de los objetivos como del desarrollo de la experiencia. Finalizaremos con una exposición de las posibilidades del foro como herramienta que permite compartir entre todos los participantes sus reflexiones, búsquedas y contribuciones y generar así aprendizaje colaborativo a través de una revisión retrospectiva de las actuaciones llevadas a cabo (feedback en el transcurso de la búsqueda de soluciones múltiples a las diferentes situaciones-problema presentadas; al mismo tiempo que aprenden cómo mejorar para que puedan alcanzar los objetivos o las metas a las que aspiran (feedforward. This article aims at sharing an experience based on a USAL
Fiyadh, Seef Saadi; AlSaadi, Mohammed Abdulhakim; AlOmar, Mohamed Khalid; Fayaed, Sabah Saadi; Hama, Ako R; Bee, Sharifah; El-Shafie, Ahmed
2017-11-01
The main challenge in the lead removal simulation is the behaviour of non-linearity relationships between the process parameters. The conventional modelling technique usually deals with this problem by a linear method. The substitute modelling technique is an artificial neural network (ANN) system, and it is selected to reflect the non-linearity in the interaction among the variables in the function. Herein, synthesized deep eutectic solvents were used as a functionalized agent with carbon nanotubes as adsorbents of Pb 2+ . Different parameters were used in the adsorption study including pH (2.7 to 7), adsorbent dosage (5 to 20 mg), contact time (3 to 900 min) and Pb 2+ initial concentration (3 to 60 mg/l). The number of experimental trials to feed and train the system was 158 runs conveyed in laboratory scale. Two ANN types were designed in this work, the feed-forward back-propagation and layer recurrent; both methods are compared based on their predictive proficiency in terms of the mean square error (MSE), root mean square error, relative root mean square error, mean absolute percentage error and determination coefficient (R 2 ) based on the testing dataset. The ANN model of lead removal was subjected to accuracy determination and the results showed R 2 of 0.9956 with MSE of 1.66 × 10 -4 . The maximum relative error is 14.93% for the feed-forward back-propagation neural network model.
Evolvable Neural Software System
Curtis, Steven A.
2009-01-01
The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.
Neural Networks For Electrohydrodynamic Effect Modelling
Directory of Open Access Journals (Sweden)
Wiesław Wajs
2004-01-01
Full Text Available This paper presents currently achieved results concerning methods of electrohydrodynamiceffect used in geophysics simulated with feedforward networks trained with backpropagation algorithm, radial basis function networks and generalized regression networks.
An artificial neural network model for periodic trajectory generation
Shankar, S.; Gander, R. E.; Wood, H. C.
A neural network model based on biological systems was developed for potential robotic application. The model consists of three interconnected layers of artificial neurons or units: an input layer subdivided into state and plan units, an output layer, and a hidden layer between the two outer layers which serves to implement nonlinear mappings between the input and output activation vectors. Weighted connections are created between the three layers, and learning is effected by modifying these weights. Feedback connections between the output and the input state serve to make the network operate as a finite state machine. The activation vector of the plan units of the input layer emulates the supraspinal commands in biological central pattern generators in that different plan activation vectors correspond to different sequences or trajectories being recalled, even with different frequencies. Three trajectories were chosen for implementation, and learning was accomplished in 10,000 trials. The fault tolerant behavior, adaptiveness, and phase maintenance of the implemented network are discussed.
On-line validation of feedwater flow rate in nuclear power plants using neural networks
International Nuclear Information System (INIS)
Khadem, M.; Ipakchi, A.; Alexandro, F.J.; Colley, R.W.
1994-01-01
On-line calibration of feedwater flow rate measurement in nuclear power plants provides a continuous realistic value of feedwater flow rate. It also reduces the manpower required for periodic calibration needed due to the fouling and defouling of the venturi meter surface condition. This paper presents a method for on-line validation of feedwater flow rate in nuclear power plants. The method is an improvement of the previously developed method which is based on the use of a set of process variables dynamically related to the feedwater flow rate. The online measurements of this set of variables are used as inputs to a neural network to obtain an estimate of the feedwater flow rate reading. The difference between the on-line feedwater flow rate reading, and the neural network estimate establishes whether there is a need to apply a correction factor to the feedwater flow rate measurement for calculation of the actual reactor power. The method was applied to the feedwater flow meters in the two feedwater flow loops of the TMI-1 nuclear power plant. The venturi meters used for flow measurements are susceptible to frequent fouling that degrades their measurement accuracy. The fouling effects can cause an inaccuracy of up to 3% relative error in feedwater flow rate reading. A neural network, whose inputs were the readings of a set of reference instruments, was designed to predict both feedwater flow rates simultaneously. A multi-layer feedforward neural network employing the backpropagation algorithm was used. A number of neural network training tests were performed to obtain an optimum filtering technique of the input/output data of the neural networks. The result of the selection of the filtering technique was confirmed by numerous Fast Fourier Transform (FFT) tests. Training and testing were done on data from TMI-1 nuclear power plant. The results show that the neural network can predict the correct flow rates with an absolute relative error of less than 2%
NEURAL NETWORK ALGORITHM SAFE OVERFLIGHT AERIAL OBSTACLES AND PROHIBITED LAND AREAS
Directory of Open Access Journals (Sweden)
Denis A. Mikhaylin
2017-01-01
Full Text Available The article presents the algorithm of safe flying around obstacles when making en route flight of manned and unmanned aircraft. The analysis of obstacles in the path of the aircraft is carried out. It is shown that the application of neural networks for this problem solving allows to increase the control system performance and total flight safety. It is proved by modelling. The multilayer network consistent distribution is proposed to be used as neural network structure. In this work a neural network with three layers is used. To solve the problem the aircraft movement in plan is considered. It is important to have data on the Z coordinates of the obstacles vertices. Finally the number of neural network inputs was determined to be four. The number of alternatives, determining the number of neural network outputs is respectively five. As the continuing of the aircraft flight along the original route is possible, as a result, a training sample is in the form of a chart. After training the neural network simulations of its work were made. Obstacles have been formed in advance.
A TORC2-Akt Feed-Forward Topology Underlies HER3 Resiliency in HER2-Amplified Cancers.
Amin, Dhara N; Ahuja, Deepika; Yaswen, Paul; Moasser, Mark M
2015-12-01
The requisite role of HER3 in HER2-amplified cancers is beyond what would be expected as a dimerization partner or effector substrate and it exhibits a substantial degree of resiliency that mitigates the effects of HER2-inhibitor therapies. To better understand the roots of this resiliency, we conducted an in-depth chemical-genetic interrogation of the signaling network downstream of HER3. A unique attribute of these tumors is the deregulation of TORC2. The upstream signals that ordinarily maintain TORC2 signaling are lost in these tumors, and instead TORC2 is driven by Akt. We find that in these cancers HER3 functions as a buffering arm of an Akt-TORC2 feed-forward loop that functions as a self-perpetuating module. This network topology alters the role of HER3 from a conditionally engaged ligand-driven upstream physiologic signaling input to an essential component of a concentric signaling throughput highly competent at preservation of homeostasis. The competence of this signaling topology is evident in its response to perturbation at any of its nodes. Thus, a critical pathophysiologic event in the evolution of HER2-amplified cancers is the loss of the input signals that normally drive TORC2 signaling, repositioning it under Akt dependency, and fundamentally altering the role of HER3. This reprogramming of the downstream network topology is a key aspect in the pathogenesis of HER2-amplified cancers and constitutes a formidable barrier in the targeted therapy of these cancers. ©2015 American Association for Cancer Research.
Morsy-Osman, Mohamed; Zhuge, Qunbi; Chen, Lawrence R; Plant, David V
2011-11-21
We exploit pilot-aided (PA) transmission enabled by single-sideband (SSB) subcarrier modulation of both quadrature signals in the DSP domain to achieve fully feedforward carrier recovery (FFCR) in single-carrier (SC) coherent systems with arbitrary M-QAM constellations. A thorough mathematical description of the proposed PA-FFCR is presented, its linewidth tolerance is assessed by simulations and compared to other FFCR schemes in literature. Also, implementation and complexity issues of PA-FFCR are presented and briefly compared with other CR schemes. Simulation results show that PA-FFCR performs close to the best known CR technique in the literature with less computation complexity. Quantitatively, for 1 dB optical-signal-to-noise-ratio (OSNR) penalty at BER = 3.8 × 10(-3), PA-FFCR tolerates linewidth-symbol-duration products (Δf.Ts) of 1.5 × 10(-4) (4-QAM), 4 × 10(-5) (16-QAM) and 1 × 10(-5) (64-QAM). Finally, we propose the use of maximum likelihood (ML) phase estimation next to pilot phase compensation. This significantly improves tolerable Δf.Ts values to 7.5 × 10(-4) (4-QAM), 1.8 × 10(-4) (16-QAM) and 3.5 × 10(-5) (64-QAM). It turns out that PA-FFCR with ML always performs better or at least the same compared to other CR techniques known in literature with lower complexity in addition to the fact that pilot information can be as well exploited for tasks other than CR e.g., fiber nonlinearity compensation, with no extra complexity. © 2011 Optical Society of America
Feed-Forward Control Strategy for the VSC of DVR for Smooth and Clean Power Flow to Load
Directory of Open Access Journals (Sweden)
Aamir Hanif
2012-04-01
Full Text Available VSC (Voltage Source Converter feed-forward control strategy of DVR (Dynamic Voltage Restorer for an in-phase voltage injection scheme is proposed in this paper to tackle not only voltage sags and swells in the utility supply but also phase jumps as well. The proposed strategy utilizes a time based ramp at a clock rate of 50Hz to obtain a 3-phase reference signal that is compared with actual 3-phase utility voltage to obtain an error signal. If the error in each phase of the utility voltage is greater than zero then appropriate control signals are generated. The switching devices in VSC are switched accordingly to compensate voltage sags, swells and phase jumps in the utility voltage that propagates to load. For the mitigation of voltage sags, swells and phase jumps, the unipolar SPWM control is used. The proposed control system response time to compensate voltage sag, swell and phase jump through switching of VSC devices is less than 10ms whereas ITIC curve and SEMI-F-47 standard suggest a target of 20ms. Load voltage THD is below 5% as per IEEE Std. 519-1992. These results show that employed control strategy has an excellent capability of voltage restoration with acceptable harmonic distortion, within specified time frame for smooth and clean power flow to load. MATLAB/Simulink SimpowerSystem tool box has been used to obtain simulation results to verify the effectiveness and validity of the proposed control strategy to improve the quality of the power delivered to the load.
El feedback y el feedforward en la evaluación de las competencias de estudiantes universitarios
Directory of Open Access Journals (Sweden)
Georgeta Ion
2013-01-01
Full Text Available Las universidades españolas están inmersas en la implementación del Espacio Europeo de Educación Superior. Este proceso implica el uso más efectivo de diseños y metodologías que favorezcan un aprendizaje más profundo, que aumenten la implicación de los estudiantes en su propio desarrollo y más autonomía en la construcción de su desarrollo personal y profesional. Las nuevas tecnologías representan herramientas útiles para conseguir estos propósitos. Las TIC constituyen una herramienta eficiente para dar respuesta a las exigencias de la creación del Espacio Europeo de Educación Superior. En este artículo presentamos los resultados de una investigación sobre la implementación de la plataforma CAT (Competences Assessment Tool destinada a facilitar la evaluación basada en competencias. Hemos empleado una metodología mixta basada en la administración de una encuesta que ha permitido a los participantes expresar su opinión en términos de satisfacción con la experiencia y el análisis de los contenidos del feedback proporcionado a los alumnos. De entre los resultados se destaca la importancia de los procesos de devolución por parte del profesorado en términos de calidad del feedback y el feedforward como estrategias de aprendizaje y se valora la posibilidad que ofrecen para ayudar en el desarrollo de competencias específicas y transversales.
Feed-forward regulation of bile acid detoxification by CYP3A4: studies in humanized transgenic mice.
Stedman, Catherine; Robertson, Graham; Coulter, Sally; Liddle, Christopher
2004-03-19
Bile acids are potentially toxic end products of cholesterol metabolism and their concentrations must be tightly regulated. Homeostasis is maintained by both feed-forward regulation and feedback regulation. We used humanized transgenic mice incorporating 13 kb of the 5' regulatory flanking sequence of CYP3A4 linked to a lacZ reporter gene to explore the in vivo relationship between bile acids and physiological adaptive CYP3A gene regulation in acute cholestasis after bile duct ligation (BDL). Male transgenic mice were subjected to BDL or sham surgery prior to sacrifice on days 3, 6, and 10, and others were injected with intraperitoneal lithocholic acid (LCA) or vehicle alone. BDL resulted in marked hepatic activation of the CYP3A4/lacZ transgene in pericentral hepatocytes, with an 80-fold increase in transgene activation by day 10. Individual bile acids were quantified by liquid chromatography/mass spectrometry. Serum 6beta-hydroxylated bile acids were increased following BDL, confirming the physiological relevance of endogenous Cyp3a induction to bile acid detoxification. Although concentrations of conjugated primary bile acids increased after BDL, there was no increase in LCA, a putative PXR ligand, indicating that this cannot be the only endogenous bile acid mediating this protective response. Moreover, in LCA-treated animals, 5-bromo-4-chloro-3-indolyl-beta-d-galactopyranoside staining showed hepatic activation of the CYP3A4 transgene only on the liver capsular surface, and minimal parenchymal induction, despite significant liver injury. This study demonstrates that CYP3A up-regulation is a significant in vivo adaptive response to cholestasis. However, this up-regulation is not dependent on increases in circulating LCA and the role of other bile acids as regulatory molecules requires further exploration.
Choi, W.; La Haye, R. J.; Lanctot, M. J.; Olofsson, K. E. J.; Strait, E. J.; Sweeney, R.; Volpe, F. A.; The DIII-D Team
2018-03-01
The toroidal phase and rotation of otherwise locked magnetic islands of toroidal mode number n = 1 are controlled in the DIII-D tokamak by means of applied magnetic perturbations of n = 1. Pre-emptive perturbations were applied in feedforward to ‘catch’ the mode as it slowed down and entrain it to the rotating field before complete locking, thus avoiding the associated major confinement degradation. Additionally, for the first time, the phase of the perturbation was optimized in real-time, in feedback with magnetic measurements, in order for the mode’s phase to closely match a prescribed phase, as a function of time. Experimental results confirm the capability to hold the mode in a given fixed-phase or to rotate it at up to 20 Hz with good uniformity. The control-coil currents utilized in the experiments agree with the requirements estimated by an electromechanical model. Moreover, controlled rotation at 20 Hz was combined with electron cyclotron current drive (ECCD) modulated at the same frequency. This is simpler than regulating the ECCD modulation in feedback with spontaneous mode rotation, and enables repetitive, reproducible ECCD deposition at or near the island O-point, X-point and locations in between, for careful studies of how this affects the island stability. Current drive was found to be radially misaligned relative to the island, and resulting growth and shrinkage of islands matched expectations of the modified Rutherford equation for some discharges presented here. Finally, simulations predict the as designed ITER 3D coils can entrain a small island at sub-10 Hz frequencies.
International Nuclear Information System (INIS)
Dmitrievskij, S.G.; Gornushkin, Yu.A.; Ososkov, G.A.
2005-01-01
A neural-network (NN) approach for neutrino interaction vertex reconstruction in the OPERA experiment with the help of the Target Tracker (TT) detector is described. A feed-forward NN with the standard back propagation option is used. The energy functional minimization of the network is performed by the method of conjugate gradients. Data preprocessing by means of cellular automaton algorithm is performed. The Hough transform is applied for muon track determination and the robust fitting method is used for shower axis reconstruction. A comparison of the proposed approach with earlier studies, based on the use of the neural network package SNNS, shows their similar performance. The further development of the approach is underway
Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor
2012-01-01
A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method. PMID:22919371
Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor
2012-01-01
A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method.
Directory of Open Access Journals (Sweden)
Mahmoud Akbarian
2015-07-01
Results: Twelve features with P<0.05 and four features with P<0.1 were identified by using binary logistic regression as effective features. These sixteen features were used as input variables in artificial neural networks. The accuracy, sensitivity and specificity of the test data for the MLP network were 90.9%, 80.0%, and 94.1% respectively and for the total data were 97.3%, 93.5%, and 99.0% respectively. Conclusion: According to the results, we concluded that feed-forward Multi-Layer Perceptron (MLP neural network with scaled conjugate gradient (trainscg back propagation learning algorithm can help physicians to predict the pregnancy outcomes (spontaneous abortion and live birth among pregnant women with lupus by using identified effective variables.
Artificial neural networks for spatial distribution of fuel assemblies in reload of PWR reactors
Energy Technology Data Exchange (ETDEWEB)
Oliveira, Edyene; Castro, Victor F.; Velásquez, Carlos E.; Pereira, Claubia, E-mail: claubia@nuclear.ufmg.br [Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG (Brazil). Programa de Pós-Graduação em Ciências e Técnicas Nucleares
2017-07-01
An artificial neural network methodology is being developed in order to find an optimum spatial distribution of the fuel assemblies in a nuclear reactor core during reload. The main bounding parameter of the modelling was the neutron multiplication factor, k{sub ef{sub f}}. The characteristics of the network are defined by the nuclear parameters: cycle, burnup, enrichment, fuel type, and average power peak of each element. These parameters were obtained by the ORNL nuclear code package SCALE6.0. As for the artificial neural network, the ANN Feedforward Multi{sub L}ayer{sub P}erceptron with various layers and neurons were constructed. Three algorithms were used and tested: LM (Levenberg-Marquardt), SCG (Scaled Conjugate Gradient) and BayR (Bayesian Regularization). Artificial neural network have implemented using MATLAB 2015a version. As preliminary results, the spatial distribution of the fuel assemblies in the core using a neural network was slightly better than the standard core. (author)
Maximum entropy methods for extracting the learned features of deep neural networks.
Finnegan, Alex; Song, Jun S
2017-10-01
New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.
Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control
Hageman, Jacob J.; Smith, Mark S.; Stachowiak, Susan
2003-01-01
An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.
Neural networks-based modeling applied to a process of heavy metals removal from wastewaters.
Suditu, Gabriel D; Curteanu, Silvia; Bulgariu, Laura
2013-01-01
This article approaches the problem of environment pollution with heavy metals from disposal of industrial wastewaters, namely removal of these metals by means of biosorbents, particularly with Romanian peat (from Poiana Stampei). The study is carried out by simulation using feed-forward and modular neural networks with one or two hidden layers, pursuing the influence of certain operating parameters (metal nature, sorbent dose, pH, temperature, initial concentration of metal ion, contact time) on the amount of metal ions retained on the unit mass of sorbent. In neural network modeling, a consistent data set was used, including five metals: lead, mercury, cadmium, nickel and cobalt, the quantification of the metal nature being done by its electronegativity. Even if based on successive trials, the method of designing neural models was systematically conducted, recording and comparing the errors obtained with different types of neural networks, having various numbers of hidden layers and neurons, number of training epochs, or using various learning methods. The errors with values under 5% make clear the efficiency of the applied method.