Cohen, Taco S; Welling, Max
2016-01-01
It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks. In this paper we present Steerable Convolutional Neural Networks, an efficient and flexible class of equivariant convolutional networks. We show that steerable CNNs achieve state of the art results on the CIFAR image classification benchmark. The mathematical theory of steerable representations reveals a type system in which any steerable r...
Modelling lava flows by Cellular Nonlinear Networks (CNN: preliminary results
Directory of Open Access Journals (Sweden)
C. Del Negro
2005-01-01
Full Text Available The forecasting of lava flow paths is a complex problem in which temperature, rheology and flux-rate all vary with space and time. The problem is more difficult to solve when lava runs down a real topography, considering that the relations between characteristic parameters of flow are typically nonlinear. An alternative approach to this problem that does not use standard differential equation methods is Cellular Nonlinear Networks (CNNs. The CNN paradigm is a natural and flexible framework for describing locally interconnected, simple, dynamic systems that have a lattice-like structure. They consist of arrays of essentially simple, nonlinearly coupled dynamic circuits containing linear and non-linear elements able to process large amounts of information in real time. Two different approaches have been implemented in simulating some lava flows. Firstly, a typical technique of the CNNs to analyze spatio-temporal phenomena (as Autowaves in 2-D and in 3-D has been utilized. Secondly, the CNNs have been used as solvers of partial differential equations of the Navier-Stokes treatment of Newtonian flow.
Multiscale CNNs for Brain Tumor Segmentation and Diagnosis
Zhao, Liya; Jia, Kebin
2016-01-01
Early brain tumor detection and diagnosis are critical to clinics. Thus segmentation of focused tumor area needs to be accurate, efficient, and robust. In this paper, we propose an automatic brain tumor segmentation method based on Convolutional Neural Networks (CNNs). Traditional CNNs focus only on local features and ignore global region features, which are both important for pixel classification and recognition. Besides, brain tumor can appear in any place of the brain and be any size and shape in patients. We design a three-stream framework named as multiscale CNNs which could automatically detect the optimum top-three scales of the image sizes and combine information from different scales of the regions around that pixel. Datasets provided by Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized by MICCAI 2013 are utilized for both training and testing. The designed multiscale CNNs framework also combines multimodal features from T1, T1-enhanced, T2, and FLAIR MRI images. By comparison with traditional CNNs and the best two methods in BRATS 2012 and 2013, our framework shows advances in brain tumor segmentation accuracy and robustness. PMID:27069501
ON THE STABILITY OF THE CELLULAR NEURAL NETWORKS WITH TIME LAGS
Vladimir RASVAN; Daniela DANCIU
2004-01-01
Cellular neural networks (CNNs) are recurrent artificial neural networks. Due to their cyclic connections and to the neurons’ nonlinear activation functions, recurrent neural networks are nonlinear dynamic systems, which display stable and unstable fixed points, limit cycles and chaotic behavior. Since the field of neural networks is still a young one, improving the stability conditions for such systems is an obvious and quasipermanent task. This paper focuses on CNNs affected by time delays....
Semantic Segmentation of Aerial Images with AN Ensemble of Cnns
Marmanis, D.; Wegner, J. D.; Galliani, S.; Schindler, K.; Datcu, M.; Stilla, U.
2016-06-01
This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental principles is to gradually aggregate information over larger and larger image regions, making it hard to disentangle contributions from different pixels. Very recently two extensions of the CNN framework have made it possible to trace the semantic information back to a precise pixel position: deconvolutional network layers undo the spatial downsampling, and Fully Convolution Networks (FCNs) modify the fully connected classification layers of the network in such a way that the location of individual activations remains explicit. We design a FCN which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution. We discuss design choices and intricacies of such a network, and demonstrate that an ensemble of several networks achieves excellent results on challenging data such as the ISPRS semantic labeling benchmark, using only the raw data as input.
Memristor-based cellular nonlinear/neural network: design, analysis, and applications.
Duan, Shukai; Hu, Xiaofang; Dong, Zhekang; Wang, Lidan; Mazumder, Pinaki
2015-06-01
Cellular nonlinear/neural network (CNN) has been recognized as a powerful massively parallel architecture capable of solving complex engineering problems by performing trillions of analog operations per second. The memristor was theoretically predicted in the late seventies, but it garnered nascent research interest due to the recent much-acclaimed discovery of nanocrossbar memories by engineers at the Hewlett-Packard Laboratory. The memristor is expected to be co-integrated with nanoscale CMOS technology to revolutionize conventional von Neumann as well as neuromorphic computing. In this paper, a compact CNN model based on memristors is presented along with its performance analysis and applications. In the new CNN design, the memristor bridge circuit acts as the synaptic circuit element and substitutes the complex multiplication circuit used in traditional CNN architectures. In addition, the negative differential resistance and nonlinear current-voltage characteristics of the memristor have been leveraged to replace the linear resistor in conventional CNNs. The proposed CNN design has several merits, for example, high density, nonvolatility, and programmability of synaptic weights. The proposed memristor-based CNN design operations for implementing several image processing functions are illustrated through simulation and contrasted with conventional CNNs. Monte-Carlo simulation has been used to demonstrate the behavior of the proposed CNN due to the variations in memristor synaptic weights.
Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs
Tang, Youbao; Wu, Xiangqian
2016-01-01
This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convolutional neural network (called pixel-level CNN) is constructed by modifying the VGGNet architecture to perform multi-scale feature learning, based on which an image-to-image prediction is conducted to accomplish the pixel-level saliency detection. For region-level saliency estima...
Hervás, C; Toledo, R; Silva, M
2001-01-01
The suitability of pruned computational neural networks (CNNs) for resolving nonlinear multicomponent systems involving synergistic effects by use of oscillating chemical reaction-based methods implemented using the analyte pulse perturbation technique is demonstrated. The CNN input data used for this purpose are estimates provided by the Levenberg-Marquardt method in the form of a three-parameter Gaussian curve associated with the singular profile obtained when the oscillating system is perturbed by an analyte mixture. The performance of the proposed method was assessed by applying it to the resolution of mixtures of pyrogallol and gallic acid based on their perturbating effect on a classical oscillating chemical system, viz. the Belousov-Zhabotinskyi reaction. A straightforward network topology (3:3:2, with 18 connections after pruning) allowed the resolution of mixtures of the two analytes in concentration ratios from 1:7 to 6:2 with a standard error of prediction for the testing set of 4.01 and 8.98% for pyrogallol and gallic acid, respectively. The reduced dimensions of the selected CNN architecture allowed a mathematical transformation of the input vector into the output one that can be easily implemented via software. Finally, the suitability of response surface analysis as an alternative to CNNs was also tested. The results were poor (relative errors were high), which confirms that properly selected pruned CNNs are effective tools for solving the analytical problem addressed in this work.
Classifying objects in LWIR imagery via CNNs
Rodger, Iain; Connor, Barry; Robertson, Neil M.
2016-10-01
The aim of the presented work is to demonstrate enhanced target recognition and improved false alarm rates for a mid to long range detection system, utilising a Long Wave Infrared (LWIR) sensor. By exploiting high quality thermal image data and recent techniques in machine learning, the system can provide automatic target recognition capabilities. A Convolutional Neural Network (CNN) is trained and the classifier achieves an overall accuracy of > 95% for 6 object classes related to land defence. While the highly accurate CNN struggles to recognise long range target classes, due to low signal quality, robust target discrimination is achieved for challenging candidates. The overall performance of the methodology presented is assessed using human ground truth information, generating classifier evaluation metrics for thermal image sequences.
Neural Networks for Non-linear Control
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....
Neural Networks for Non-linear Control
DEFF Research Database (Denmark)
Sørensen, O.
1994-01-01
This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....
Sensor Network Design for Nonlinear Processes
Institute of Scientific and Technical Information of China (English)
李博; 陈丙珍
2003-01-01
This paper presents a method to design a cost-optimal nonredundant sensor network to observe all variables in a general nonlinear process. A mixed integer linear programming model was used to minimize the cost with data classification to check the observability of all unmeasured variables. This work is a starting point for designing sensor networks for general nonlinear processes based on various criteria, such as reliability and accuracy.
Network science, nonlinear science and infrastructure systems
2007-01-01
Network Science, Nonlinear Science and Infrastructure Systems has been written by leading scholars in these areas. Its express purpose is to develop common theoretical underpinnings to better solve modern infrastructural problems. It is felt by many who work in these fields that many modern communication problems, ranging from transportation networks to telecommunications, Internet, supply chains, etc., are fundamentally infrastructure problems. Moreover, these infrastructure problems would benefit greatly from a confluence of theoretical and methodological work done with the areas of Network Science, Dynamical Systems and Nonlinear Science. This book is dedicated to the formulation of infrastructural tools that will better solve these types of infrastructural problems. .
Nonlinear programming with feedforward neural networks.
Energy Technology Data Exchange (ETDEWEB)
Reifman, J.
1999-06-02
We provide a practical and effective method for solving constrained optimization problems by successively training a multilayer feedforward neural network in a coupled neural-network/objective-function representation. Nonlinear programming problems are easily mapped into this representation which has a simpler and more transparent method of solution than optimization performed with Hopfield-like networks and poses very mild requirements on the functions appearing in the problem. Simulation results are illustrated and compared with an off-the-shelf optimization tool.
Nonlinear Dynamics on Interconnected Networks
Arenas, Alex; De Domenico, Manlio
2016-06-01
Networks of dynamical interacting units can represent many complex systems, from the human brain to transportation systems and societies. The study of these complex networks, when accounting for different types of interactions has become a subject of interest in the last few years, especially because its representational power in the description of users' interactions in diverse online social platforms (Facebook, Twitter, Instagram, etc.) [1], or in representing different transportation modes in urban networks [2,3]. The general name coined for these networks is multilayer networks, where each layer accounts for a type of interaction (see Fig. 1).
Nonlinear System Control Using Neural Networks
Directory of Open Access Journals (Sweden)
Jaroslava Žilková
2006-10-01
Full Text Available The paper is focused especially on presenting possibilities of applying off-linetrained artificial neural networks at creating the system inverse models that are used atdesigning control algorithm for non-linear dynamic system. The ability of cascadefeedforward neural networks to model arbitrary non-linear functions and their inverses isexploited. This paper presents a quasi-inverse neural model, which works as a speedcontroller of an induction motor. The neural speed controller consists of two cascadefeedforward neural networks subsystems. The first subsystem provides desired statorcurrent components for control algorithm and the second subsystem providescorresponding voltage components for PWM converter. The availability of the proposedcontroller is verified through the MATLAB simulation. The effectiveness of the controller isdemonstrated for different operating conditions of the drive system.
Evolving Networks with Nonlinear Assignment of Weight
Institute of Scientific and Technical Information of China (English)
TANG Chao; TANG Yi
2006-01-01
We propose a weighted evolving network model in which the underlying topological structure is still driven by the degree according to the preferential attachment rule while the weight assigned to the newly established edges is dependent on the degree in a nonlinear form. By varying the parameter α that controls the function determining the assignment of weight, a wide variety of power-law behaviours of the total weight distributions as well as the diversity of the weight distributions of edges are displayed. Variation of correlation and heterogeneity in the network is illustrated as well.
Multilingual Text Detection with Nonlinear Neural Network
Directory of Open Access Journals (Sweden)
Lin Li
2015-01-01
Full Text Available Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work.
Identification of Nonlinear Systems Using Neurofuzzy Networks
Institute of Scientific and Technical Information of China (English)
LI Ying; JIAO Licheng
2001-01-01
This paper presents a compound neu-ral network model, I.e., adaptive neurofuzzy network(ANFN), which can be used for identifying the com-plicated nonlinear system. The proposed ANFN has asimple structure and exploits a hybrid algorithm com-bining supervised learning and unsupervised learning.In addition, ANFN is capable of overcoming the errorof system identification due to the existence of somechanging points and improving the accuracy of identi-fication of the whole system. The effectiveness of themodel and its algorithm are tested on the identifica-tion results of missile attacking area.
Cellular neural network implementation using a phase-only joint transform correlator
Zhang, Shuqun; Karim, Mohammad A.
1999-04-01
A phase-only joint transform correlator (JTC) is used to realize cellular neural networks (CNNs). The operation of summing cross-correlations of bipolar data in CNNs can be realized in parallel by phase-encoding bipolar data. Compared to other optical systems for implementing CNNs, the proposed method offers the advantages of easier implementation and robustness in terms of system alignment, and requires neither electronic precalculation nor data rearrangement. Simulation results of the proposed optical CNNs for edge detection are provided.
Energy Technology Data Exchange (ETDEWEB)
Zhang, G.M. [China Center of Advanced Science and Technology (CCAST), Beijing, BJ (China)]|[Suzhou Univ. (China). Dept. of Physics
1996-04-01
In this note we consider the geometrical effects of a percolating system on the nonlinear transport properties in a superconductor-normal conductor nonlinear resistor network. For realistic composites, the nonlinearity may play an important role in the electrical transport phenomena. A typical example consists of studying a nonlinear composite medium in which an inclusion with nonlinear current-field (J-E) characteristics is randomly embedded in a host with either linear or nonlinear J-E response. For such a system, substantial progress in studies of the effective nonlinear response has been made in the past few years. 24 refs.
Identification of Non-Linear Structures using Recurrent Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.
1995-01-01
Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure.......Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure....
Identification of Non-Linear Structures using Recurrent Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.
Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure.......Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure....
Identification of Non-Linear Structures using Recurrent Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.
1995-01-01
Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure.......Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure....
Nonlinear system identification and control based on modular neural networks.
Puscasu, Gheorghe; Codres, Bogdan
2011-08-01
A new approach for nonlinear system identification and control based on modular neural networks (MNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This is obtained using a partitioning algorithm. Each local nonlinear model is associated with a nonlinear controller. These are also implemented by neural networks. The switching between the neural controllers is done by a dynamical switcher, also implemented by neural networks, that tracks the different operating points. The proposed multiple modelling and control strategy has been successfully tested on simulated laboratory scale liquid-level system.
Robust receding horizon control for networked and distributed nonlinear systems
Li, Huiping
2017-01-01
This book offers a comprehensive, easy-to-understand overview of receding-horizon control for nonlinear networks. It presents novel general strategies that can simultaneously handle general nonlinear dynamics, system constraints, and disturbances arising in networked and large-scale systems and which can be widely applied. These receding-horizon-control-based strategies can achieve sub-optimal control performance while ensuring closed-loop stability: a feature attractive to engineers. The authors address the problems of networked and distributed control step-by-step, gradually increasing the level of challenge presented. The book first introduces the state-feedback control problems of nonlinear networked systems and then studies output feedback control problems. For large-scale nonlinear systems, disturbance is considered first, then communication delay separately, and lastly the simultaneous combination of delays and disturbances. Each chapter of this easy-to-follow book not only proposes and analyzes novel ...
The Life-Changing Magic of Nonlinearity in Network Control
Cornelius, Sean
The proper functioning and reliability of many man-made and natural systems is fundamentally tied to our ability to control them. Indeed, applications as diverse as ecosystem management, emergency response and cell reprogramming all, at their heart, require us to drive a system to--or keep it in--a desired state. This process is complicated by the nonlinear dynamics inherent to most real systems, which has traditionally been viewed as the principle obstacle to their control. In this talk, I will discuss two ways in which nonlinearity turns this view on its head, in fact representing an asset to the control of complex systems. First, I will show how nonlinearity in the form of multistability allows one to systematically design control interventions that can deliberately induce ``reverse cascading failures'', in which a network spontaneously evolves to a desirable (rather than a failed) state. Second, I will show that nonlinearity in the form of time-varying dynamics unexpectedly makes temporal networks easier to control than their static counterparts, with the former enjoying dramatic and simultaneous reductions in all costs of control. This is true despite the fact that temporality tends to fragment a network's structure, disrupting the paths that allow the directly-controlled or ``driver'' nodes to communicate with the rest of the network. Taken together, these studies shed new light on the crucial role of nonlinearity in network control, and provide support to the idea we can control nonlinearity, rather than letting nonlinearity control us.
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.
Prediction of visual saliency in video with deep CNNs
Chaabouni, Souad; Benois-Pineau, Jenny; Hadar, Ofer
2016-09-01
Prediction of visual saliency in images and video is a highly researched topic. Target applications include Quality assessment of multimedia services in mobile context, video compression techniques, recognition of objects in video streams, etc. In the framework of mobile and egocentric perspectives, visual saliency models cannot be founded only on bottom-up features, as suggested by feature integration theory. The central bias hypothesis, is not respected neither. In this case, the top-down component of human visual attention becomes prevalent. Visual saliency can be predicted on the basis of seen data. Deep Convolutional Neural Networks (CNN) have proven to be a powerful tool for prediction of salient areas in stills. In our work we also focus on sensitivity of human visual system to residual motion in a video. A Deep CNN architecture is designed, where we incorporate input primary maps as color values of pixels and magnitude of local residual motion. Complementary contrast maps allow for a slight increase of accuracy compared to the use of color and residual motion only. The experiments show that the choice of the input features for the Deep CNN depends on visual task:for th eintersts in dynamic content, the 4K model with residual motion is more efficient, and for object recognition in egocentric video the pure spatial input is more appropriate.
Hand veins feature extraction using DT-CNNS
Malki, Suleyman; Spaanenburg, Lambert
2007-05-01
As the identification process is based on the unique patterns of the users, biometrics technologies are expected to provide highly secure authentication systems. The existing systems using fingerprints or retina patterns are, however, very vulnerable. One's fingerprints are accessible as soon as the person touches a surface, while a high resolution camera easily captures the retina pattern. Thus, both patterns can easily be "stolen" and forged. Beside, technical considerations decrease the usability for these methods. Due to the direct contact with the finger, the sensor gets dirty, which decreases the authentication success ratio. Aligning the eye with a camera to capture the retina pattern gives uncomfortable feeling. On the other hand, vein patterns of either a palm of the hand or a single finger offer stable, unique and repeatable biometrics features. A fingerprint-based identification system using Cellular Neural Networks has already been proposed by Gao. His system covers all stages of a typical fingerprint verification procedure from Image Preprocessing to Feature Matching. This paper performs a critical review of the individual algorithmic steps. Notably, the operation of False Feature Elimination is applied only once instead of 3 times. Furthermore, the number of iterations is limited to 1 for all used templates. Hence, the computational need of the feedback contribution is removed. Consequently the computational effort is drastically reduced without a notable chance in quality. This allows a full integration of the detection mechanism. The system is prototyped on a Xilinx Virtex II Pro P30 FPGA.
Continuous speech recognition based on convolutional neural network
Zhang, Qing-qing; Liu, Yong; Pan, Jie-lin; Yan, Yong-hong
2015-07-01
Convolutional Neural Networks (CNNs), which showed success in achieving translation invariance for many image processing tasks, are investigated for continuous speech recognitions in the paper. Compared to Deep Neural Networks (DNNs), which have been proven to be successful in many speech recognition tasks nowadays, CNNs can reduce the NN model sizes significantly, and at the same time achieve even better recognition accuracies. Experiments on standard speech corpus TIMIT showed that CNNs outperformed DNNs in the term of the accuracy when CNNs had even smaller model size.
Robust stabilization for a class of nonlinear networked control systems
Institute of Scientific and Technical Information of China (English)
Jinfeng GAO; Hongye SU; Xiaofu JI; Jian CHU
2008-01-01
The problem of robust stabilization for a class of uncertain networked control systems(NCSs)with nonlinearities satisfying a given sector condition is investigated in this paper.By introducing a new model of NCSs with parameter uncertainty,network.induced delay,nonlinearity and data packet dropout in the transmission,a strict linear matrix inequality(LMI)criterion is proposed for robust stabilization of the uncenmn nonlinear NCSs based on the Lyapunov stability theory.The maximum allowable transfer interval(MATI)can be derived by solving the feasibility problem of the corresponding LMI.Some numerical examples are provided to demonstrate the applicability of the proposed algorithm.
Robust nonlinear variable selective control for networked systems
Rahmani, Behrooz
2016-10-01
This paper is concerned with the networked control of a class of uncertain nonlinear systems. In this way, Takagi-Sugeno (T-S) fuzzy modelling is used to extend the previously proposed variable selective control (VSC) methodology to nonlinear systems. This extension is based upon the decomposition of the nonlinear system to a set of fuzzy-blended locally linearised subsystems and further application of the VSC methodology to each subsystem. To increase the applicability of the T-S approach for uncertain nonlinear networked control systems, this study considers the asynchronous premise variables in the plant and the controller, and then introduces a robust stability analysis and control synthesis. The resulting optimal switching-fuzzy controller provides a minimum guaranteed cost on an H2 performance index. Simulation studies on three nonlinear benchmark problems demonstrate the effectiveness of the proposed method.
Implementation of neural network based non-linear predictive control
DEFF Research Database (Denmark)
Sørensen, Paul Haase; Nørgård, Peter Magnus; Ravn, Ole
1999-01-01
of non-linear systems. GPC is model based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model, a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis...
Consensus in Directed Networks of Agents With Nonlinear Dynamics
Yu, Wenwu; Chen, Guanrong; Cao, Ming; Qu, Z.
2011-01-01
This technical note studies the consensus problem for cooperative agents with nonlinear dynamics in a directed network. Both local and global consensus are defined and investigated. Techniques for studying the synchronization in such complex networks are exploited to establish various sufficient con
Frequency Response and Gap Tuning for Nonlinear Electrical Oscillator Networks
Bhat, Harish S.; Vaz, Garnet J.
2013-01-01
We study nonlinear electrical oscillator networks, the smallest example of which consists of a voltage-dependent capacitor, an inductor, and a resistor driven by a pure tone source. By allowing the network topology to be that of any connected graph, such circuits generalize spatially discrete nonlinear transmission lines/lattices that have proven useful in high-frequency analog devices. For such networks, we develop two algorithms to compute the steady-state response when a subset of nodes are driven at the same fixed frequency. The algorithms we devise are orders of magnitude more accurate and efficient than stepping towards the steady-state using a standard numerical integrator. We seek to enhance a given network's nonlinear behavior by altering the eigenvalues of the graph Laplacian, i.e., the resonances of the linearized system. We develop a Newton-type method that solves for the network inductances such that the graph Laplacian achieves a desired set of eigenvalues; this method enables one to move the eigenvalues while keeping the network topology fixed. Running numerical experiments using three different random graph models, we show that shrinking the gap between the graph Laplacian's first two eigenvalues dramatically improves a network's ability to (i) transfer energy to higher harmonics, and (ii) generate large-amplitude signals. Our results shed light on the relationship between a network's structure, encoded by the graph Laplacian, and its function, defined in this case by the presence of strongly nonlinear effects in the frequency response. PMID:24223751
Qualitative stability of nonlinear networked systems
Angulo, Marco Tulio; Slotine, Jean-Jacques
2016-01-01
In many large systems, such as those encountered in biology or economics, the dynamics are nonlinear and are only known very coarsely. It is often the case, however, that the signs (excitation or inhibition) of individual interactions are known. This paper extends to nonlinear systems the classical criteria of linear sign stability introduced in the 70's, yielding simple sufficient conditions to determine stability using only the sign patterns of the interactions.
An Adaptive Neural Network Model for Nonlinear Programming Problems
Institute of Scientific and Technical Information of China (English)
Xiang-sun Zhang; Xin-jian Zhuo; Zhu-jun Jing
2002-01-01
In this paper a canonical neural network with adaptively changing synaptic weights and activation function parameters is presented to solve general nonlinear programming problems. The basic part of the model is a sub-network used to find a solution of quadratic programming problems with simple upper and lower bounds. By sequentially activating the sub-network under the control of an external computer or a special analog or digital processor that adjusts the weights and parameters, one then solves general nonlinear programming problems. Convergence proof and numerical results are given.
Palazzo, S.; Murari, A.; Vagliasindi, G.; Arena, P.; Mazon, D.; de Maack, A.; Jet-Efda Contributors
2010-08-01
In the past years cameras have become increasingly common tools in scientific applications. They are now quite systematically used in magnetic confinement fusion, to the point that infrared imaging is starting to be used systematically for real-time machine protection in major devices. However, in order to guarantee that the control system can always react rapidly in case of critical situations, the time required for the processing of the images must be as predictable as possible. The approach described in this paper combines the new computational paradigm of cellular nonlinear networks (CNNs) with field-programmable gate arrays and has been tested in an application for the detection of hot spots on the plasma facing components in JET. The developed system is able to perform real-time hot spot recognition, by processing the image stream captured by JET wide angle infrared camera, with the guarantee that computational time is constant and deterministic. The statistical results obtained from a quite extensive set of examples show that this solution approximates very well an ad hoc serial software algorithm, with no false or missed alarms and an almost perfect overlapping of alarm intervals. The computational time can be reduced to a millisecond time scale for 8 bit 496×560-sized images. Moreover, in our implementation, the computational time, besides being deterministic, is practically independent of the number of iterations performed by the CNN—unlike software CNN implementations.
Interval standard neural network models for nonlinear systems
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
A neural-network-based robust control design is suggested for control of a class of nonlinear systems. The design approach employs a neural network, whose activation functions satisfy the sector conditions, to approximate the nonlinear system. To improve the approximation performance and to account for the parameter perturbations during operation, a novel neural network model termed standard neural network model (SNNM) is proposed. If the uncertainty is bounded, the SNNM is called an interval SNNM (ISNNM). A state-feedback control law is designed for the nonlinear system modelled by an ISNNM such that the closed-loop system is globally, robustly, and asymptotically stable. The control design equations are shown to be a set of linear matrix inequalities (LMIs) that can be easily solved by available convex optimization algorithms. An example is given to illustrate the control design procedure, and the performance of the proposed approach is compared with that of a related method reported in literature.
Mean Square Synchronization of Stochastic Nonlinear Delayed Coupled Complex Networks
Directory of Open Access Journals (Sweden)
Chengrong Xie
2013-01-01
Full Text Available We investigate the problem of adaptive mean square synchronization for nonlinear delayed coupled complex networks with stochastic perturbation. Based on the LaSalle invariance principle and the properties of the Weiner process, the controller and adaptive laws are designed to ensure achieving stochastic synchronization and topology identification of complex networks. Sufficient conditions are given to ensure the complex networks to be mean square synchronization. Furthermore, numerical simulations are also given to demonstrate the effectiveness of the proposed scheme.
Distributed Extreme Learning Machine for Nonlinear Learning over Network
Songyan Huang; Chunguang Li
2015-01-01
Distributed data collection and analysis over a network are ubiquitous, especially over a wireless sensor network (WSN). To our knowledge, the data model used in most of the distributed algorithms is linear. However, in real applications, the linearity of systems is not always guaranteed. In nonlinear cases, the single hidden layer feedforward neural network (SLFN) with radial basis function (RBF) hidden neurons has the ability to approximate any continuous functions and, thus, may be used as...
Nonlinear effective-medium theory of disordered spring networks.
Sheinman, M; Broedersz, C P; MacKintosh, F C
2012-02-01
Disordered soft materials, such as fibrous networks in biological contexts, exhibit a nonlinear elastic response. We study such nonlinear behavior with a minimal model for networks on lattice geometries with simple Hookian elements with disordered spring constant. By developing a mean-field approach to calculate the differential elastic bulk modulus for the macroscopic network response of such networks under large isotropic deformations, we provide insight into the origins of the strain stiffening and softening behavior of these systems. We find that the nonlinear mechanics depends only weakly on the lattice geometry and is governed by the average network connectivity. In particular, the nonlinear response is controlled by the isostatic connectivity, which depends strongly on the applied strain. Our predictions for the strain dependence of the isostatic point as well as the strain-dependent differential bulk modulus agree well with numerical results in both two and three dimensions. In addition, by using a mapping between the disordered network and a regular network with random forces, we calculate the nonaffine fluctuations of the deformation field and compare them to the numerical results. Finally, we discuss the limitations and implications of the developed theory.
A neural feedforward network with a polynomial nonlinearity
DEFF Research Database (Denmark)
Hoffmann, Nils
1992-01-01
A novel neural network based on the Wiener model is proposed. The network is composed of a hidden layer of preprocessing neurons followed by a polynomial nonlinearity and a linear output neuron. The author tries to solve the problem of finding an appropriate preprocessing method by using a modified...... backpropagation algorithm. It is shown by the use of calculation trees that the proposed approach is simple to implement, and that the computational complexity is not much larger than for the alternative method of using PCA to determine the weights in the preprocessing network. A simulation is given which...... indicates superior performance of the proposed network compared to the PCA network...
Adaptive Neural Network Based Control of Noncanonical Nonlinear Systems.
Zhang, Yanjun; Tao, Gang; Chen, Mou
2016-09-01
This paper presents a new study on the adaptive neural network-based control of a class of noncanonical nonlinear systems with large parametric uncertainties. Unlike commonly studied canonical form nonlinear systems whose neural network approximation system models have explicit relative degree structures, which can directly be used to derive parameterized controllers for adaptation, noncanonical form nonlinear systems usually do not have explicit relative degrees, and thus their approximation system models are also in noncanonical forms. It is well-known that the adaptive control of noncanonical form nonlinear systems involves the parameterization of system dynamics. As demonstrated in this paper, it is also the case for noncanonical neural network approximation system models. Effective control of such systems is an open research problem, especially in the presence of uncertain parameters. This paper shows that it is necessary to reparameterize such neural network system models for adaptive control design, and that such reparameterization can be realized using a relative degree formulation, a concept yet to be studied for general neural network system models. This paper then derives the parameterized controllers that guarantee closed-loop stability and asymptotic output tracking for noncanonical form neural network system models. An illustrative example is presented with the simulation results to demonstrate the control design procedure, and to verify the effectiveness of such a new design method.
A novel neural network for nonlinear convex programming.
Gao, Xing-Bao
2004-05-01
In this paper, we present a neural network for solving the nonlinear convex programming problem in real time by means of the projection method. The main idea is to convert the convex programming problem into a variational inequality problem. Then a dynamical system and a convex energy function are constructed for resulting variational inequality problem. It is shown that the proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem. Compared with the existing neural networks for solving the nonlinear convex programming problem, the proposed neural network has no Lipschitz condition, no adjustable parameter, and its structure is simple. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
A Recurrent Neural Network for Nonlinear Fractional Programming
Directory of Open Access Journals (Sweden)
Quan-Ju Zhang
2012-01-01
Full Text Available This paper presents a novel recurrent time continuous neural network model which performs nonlinear fractional optimization subject to interval constraints on each of the optimization variables. The network is proved to be complete in the sense that the set of optima of the objective function to be minimized with interval constraints coincides with the set of equilibria of the neural network. It is also shown that the network is primal and globally convergent in the sense that its trajectory cannot escape from the feasible region and will converge to an exact optimal solution for any initial point being chosen in the feasible interval region. Simulation results are given to demonstrate further the global convergence and good performance of the proposing neural network for nonlinear fractional programming problems with interval constraints.
Wavelet neural network based fault diagnosis in nonlinear analog circuits
Institute of Scientific and Technical Information of China (English)
Yin Shirong; Chen Guangju; Xie Yongle
2006-01-01
The theories of diagnosing nonlinear analog circuits by means of the transient response testing are studied. Wavelet analysis is made to extract the transient response signature of nonlinear circuits and compress the signature dada. The best wavelet function is selected based on the between-category total scatter of signature. The fault dictionary of nonlinear circuits is constructed based on improved back-propagation(BP) neural network. Experimental results demonstrate that the method proposed has high diagnostic sensitivity and fast fault identification and deducibility.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
Institute of Scientific and Technical Information of China (English)
ZHENGXin; CHENTian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear time series, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-means clustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from the local minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glass equation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting results are obtained.
Nonlinear Time Series Forecast Using Radial Basis Function Neural Networks
Institute of Scientific and Technical Information of China (English)
ZHENG Xin; CHEN Tian-Lun
2003-01-01
In the research of using Radial Basis Function Neural Network (RBF NN) forecasting nonlinear timeseries, we investigate how the different clusterings affect the process of learning and forecasting. We find that k-meansclustering is very suitable. In order to increase the precision we introduce a nonlinear feedback term to escape from thelocal minima of energy, then we use the model to forecast the nonlinear time series which are produced by Mackey-Glassequation and stocks. By selecting the k-means clustering and the suitable feedback term, much better forecasting resultsare obtained.
Nonlinear Decoupling PID Control Using Neural Networks and Multiple Models
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential (PID) controller is proposed, which consists of a traditional PID controller, a decoupling compensator and a feedforward compensator for the unmodeled dynamics. The parameters of such controller is selected based on the generalized minimum variance control law. The unmodeled dynamics is estimated and compensated by neural networks, a switching mechanism is introduced to improve tracking performance, then a nonlinear decoupling PID control algorithm is proposed. All signals in such switching system are globally bounded and the tracking error is convergent. Simulations show effectiveness of the algorithm.
Nonlinear properties of the lattice network-based nonlinear CRLH transmission lines
Institute of Scientific and Technical Information of China (English)
王正斌; 吴昭质; 高超
2015-01-01
The nonlinear properties of lattice network-based (LNB) composite right-/left-handed transmission lines (CRLH TLs) with nonlinear capacitors are experimentally investigated. Harmonic generation, subharmonic generation, and parametric excitation are clearly observed in an unbalanced LNB CRLH TL separately. While the balanced design of the novel nonlinear TL shows that the subharmonic generation and parametric processes can be suppressed, and almost the same power level of the higher harmonics can be achieved over a wide bandwidth range, which are difficult to find in the conventional CRLH TLs.
Non-linear growth and condensation in multiplex networks
Nicosia, Vincenzo; Latora, Vito; Barthelemy, Marc
2013-01-01
Different types of interactions coexist and coevolve to shape the structure and function of a multiplex network. We propose here a general class of growth models in which the various layers of a multiplex network coevolve through a set of non-linear preferential attachment rules. We show, both numerically and analytically, that by tuning the level of non-linearity these models allow to reproduce either homogeneous or heterogeneous degree distributions, together with positive or negative degree correlations across layers. In particular, we derive the condition for the appearance of a condensed state in which a single node connects to nearly all other nodes of a layer.
Modeling of Nonlinear Signal Distortion in Fiber-Optical Networks
Johannisson, Pontus
2013-01-01
A low-complexity model for signal quality prediction in a nonlinear fiber-optical network is developed. The model, which builds on the Gaussian noise model, takes into account the signal degradation caused by a combination of chromatic dispersion, nonlinear signal distortion, and amplifier noise. The center frequencies, bandwidths, and transmit powers can be chosen independently for each channel, which makes the model suitable for analysis and optimization of resource allocation, routing, and scheduling in large-scale optical networks applying flexible-grid wavelength-division multiplexing.
Nonlinear Time Series Prediction Using Chaotic Neural Networks
Institute of Scientific and Technical Information of China (English)
LI KePing; CHEN TianLun
2001-01-01
A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm.``
A Comparison between Neural Networks and Wavelet Networks in Nonlinear System Identification
Directory of Open Access Journals (Sweden)
S. Ehsan Razavi
2012-01-01
Full Text Available In this study, identification of a nonlinear function will be presented by neural network and wavelet network methods. Behavior of a nonlinear system can be identified by intelligent methods. Two groups of the most common and at the same time the most effective of neural networks methods are multilayer perceptron and radial basis function that will be used for nonlinear system identification. The selected structure is series - parallel method that after network training by a series of training random data, the output is estimated and the nonlinear function is compared to a sinusoidal input. Then, wavelet network is used for identification and we will use Orthogonal Least Squares (OLS method for wavelet selection to reduce the volume of calculations and increase the convergence speed.
Application of dynamic recurrent neural networks in nonlinear system identification
Du, Yun; Wu, Xueli; Sun, Huiqin; Zhang, Suying; Tian, Qiang
2006-11-01
An adaptive identification method of simple dynamic recurrent neural network (SRNN) for nonlinear dynamic systems is presented in this paper. This method based on the theory that by using the inner-states feed-back of dynamic network to describe the nonlinear kinetic characteristics of system can reflect the dynamic characteristics more directly, deduces the recursive prediction error (RPE) learning algorithm of SRNN, and improves the algorithm by studying topological structure on recursion layer without the weight values. The simulation results indicate that this kind of neural network can be used in real-time control, due to its less weight values, simpler learning algorithm, higher identification speed, and higher precision of model. It solves the problems of intricate in training algorithm and slow rate in convergence caused by the complicate topological structure in usual dynamic recurrent neural network.
Quantized pressure control in large-scale nonlinear hydraulic networks
Persis, Claudio De; Kallesøe, Carsten Skovmose; Jensen, Tom Nørgaard
2010-01-01
It was shown previously that semi-global practical pressure regulation at designated points of a large-scale nonlinear hydraulic network is guaranteed by distributed proportional controllers. For a correct implementation of the control laws, each controller, which is located at these designated poin
Linear iterative technique for solution of nonlinear thermal network problems
Energy Technology Data Exchange (ETDEWEB)
Seabourn, C.M.
1976-11-01
A method for rapid and accurate solution of linear and/or nonlinear thermal network problems is described. It is a matrix iterative process that converges for nodal temperatures and variations of thermal conductivity with temperature. The method is computer oriented and can be changed easily for design studies.
Distributed Extreme Learning Machine for Nonlinear Learning over Network
Directory of Open Access Journals (Sweden)
Songyan Huang
2015-02-01
Full Text Available Distributed data collection and analysis over a network are ubiquitous, especially over a wireless sensor network (WSN. To our knowledge, the data model used in most of the distributed algorithms is linear. However, in real applications, the linearity of systems is not always guaranteed. In nonlinear cases, the single hidden layer feedforward neural network (SLFN with radial basis function (RBF hidden neurons has the ability to approximate any continuous functions and, thus, may be used as the nonlinear learning system. However, confined by the communication cost, using the distributed version of the conventional algorithms to train the neural network directly is usually prohibited. Fortunately, based on the theorems provided in the extreme learning machine (ELM literature, we only need to compute the output weights of the SLFN. Computing the output weights itself is a linear learning problem, although the input-output mapping of the overall SLFN is still nonlinear. Using the distributed algorithmto cooperatively compute the output weights of the SLFN, we obtain a distributed extreme learning machine (dELM for nonlinear learning in this paper. This dELM is applied to the regression problem and classification problem to demonstrate its effectiveness and advantages.
Characterization of nonlinear dynamic systems using artificial neural networks
Energy Technology Data Exchange (ETDEWEB)
Urbina, A. [Univ. of Texas, El Paso, TX (United States); Hunter, N.F. [Los Alamos National Lab., NM (United States). Engineering Science and Analysis Div.; Paez, T.L. [Sandia National Labs., Albuquerque, NM (United States). Experimental Structural Dynamics Dept.
1998-12-01
The efficient characterization of nonlinear systems is an important goal of vibration and model testing. The authors build a nonlinear system model based on the acceleration time series response of a single input, multiple output system. A series of local linear models are used as a template to train artificial neutral networks (ANNs). The trained ANNs map measured time series responses into states of a nonlinear system. Another NN propagates response states in time, and a third ANN inverts the original map, transforming states into acceleration predictions in the measurement domain. The technique is illustrated using a nonlinear oscillator, in which quadratic and cubic stiffness terms play a major part in the system`s response. Reasonable maps are obtained for the states, and accurate, long-term response predictions are made for data outside the training data set.
High yield, controlled synthesis of graphitic networks from dense micro emulsions
Negro, E.; Dieci, M.; Sordi, D.; Kowlgi, K.; Makkee, M.; Koper, G.J.M.
2014-01-01
We report on the production of Carbon Nano Networks (CNNs) from dense microemulsions in which catalyst nanoparticles have been synthesized. CNNs are 3D carbon networks, consisting of branches and junctions, and are mesoporous, graphitic, and conductive being suitable as electrode materials.
Nonlinear Time Series Analysis via Neural Networks
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Robust nonlinear system identification using neural-network models.
Lu, S; Basar, T
1998-01-01
We study the problem of identification for nonlinear systems in the presence of unknown driving noise, using both feedforward multilayer neural network and radial basis function network models. Our objective is to resolve the difficulty associated with the persistency of excitation condition inherent to the standard schemes in the neural identification literature. This difficulty is circumvented here by a novel formulation and by using a new class of identification algorithms recently obtained by Didinsky et al. We show how these algorithms can be exploited to successfully identify the nonlinearity in the system using neural-network models. By embedding the original problem in one with noise-perturbed state measurements, we present a class of identifiers (under L1 and L2 cost criteria) which secure a good approximant for the system nonlinearity provided that some global optimization technique is used. In this respect, many available learning algorithms in the current neural-network literature, e.g., the backpropagation scheme and the genetic algorithms-based scheme, with slight modifications, can ensure the identification of the system nonlinearity. Subsequently, we address the same problem under a third, worst case L(infinity) criterion for an RBF modeling. We present a neural-network version of an H(infinity)-based identification algorithm from Didinsky et al and show how, along with an appropriate choice of control input to enhance excitation, under both full-state-derivative information (FSDI) and noise-perturbed full-state-information (NPFSI), it leads to satisfaction of a relevant persistency of excitation condition, and thereby to robust identification of the nonlinearity. Results from several simulation studies have been included to demonstrate the effectiveness of these algorithms.
Synchronization in Complex Networks of Nonlinear Dynamical Systems
Wu, Chai Wah
2007-01-01
This book brings together two emerging research areas: synchronization in coupled nonlinear systems and complex networks, and study conditions under which a complex network of dynamical systems synchronizes. While there are many texts that study synchronization in chaotic systems or properties of complex networks, there are few texts that consider the intersection of these two very active and interdisciplinary research areas. The main theme of this book is that synchronization conditions can be related to graph theoretical properties of the underlying coupling topology. The book introduces ide
Information mining in weighted complex networks with nonlinear rating projection
Liao, Hao; Zeng, An; Zhou, Mingyang; Mao, Rui; Wang, Bing-Hong
2017-10-01
Weighted rating networks are commonly used by e-commerce providers nowadays. In order to generate an objective ranking of online items' quality according to users' ratings, many sophisticated algorithms have been proposed in the complex networks domain. In this paper, instead of proposing new algorithms we focus on a more fundamental problem: the nonlinear rating projection. The basic idea is that even though the rating values given by users are linearly separated, the real preference of users to items between the different given values is nonlinear. We thus design an approach to project the original ratings of users to more representative values. This approach can be regarded as a data pretreatment method. Simulation in both artificial and real networks shows that the performance of the ranking algorithms can be improved when the projected ratings are used.
Structure-based control of complex networks with nonlinear dynamics
Zañudo, Jorge G T; Albert, Réka
2016-01-01
Given the network of interactions underlying a complex system, what can we learn about controlling such a system solely from its structure? Over a century of research in control theory has given us tools to answer this question, which were widely applied in science and engineering. Yet the current tools do not always consider the inherently nonlinear dynamics of real systems and the naturally occurring system states in their definition of "control", a term whose interpretation varies across disciplines. Here we use a new mathematical framework for structure-based control of networks governed by a broad class of nonlinear dynamics that includes the major dynamic models of biological, technological, and social processes. This framework provides realizable node overrides that steer a system towards any of its natural long term dynamic behaviors and which are guaranteed to be effective regardless of the dynamic details and parameters of the underlying system. We use this framework on several real networks, compar...
Pairwise network information and nonlinear correlations
Martin, Elliot A.; Hlinka, Jaroslav; Davidsen, Jörn
2016-10-01
Reconstructing the structural connectivity between interacting units from observed activity is a challenge across many different disciplines. The fundamental first step is to establish whether or to what extent the interactions between the units can be considered pairwise and, thus, can be modeled as an interaction network with simple links corresponding to pairwise interactions. In principle, this can be determined by comparing the maximum entropy given the bivariate probability distributions to the true joint entropy. In many practical cases, this is not an option since the bivariate distributions needed may not be reliably estimated or the optimization is too computationally expensive. Here we present an approach that allows one to use mutual informations as a proxy for the bivariate probability distributions. This has the advantage of being less computationally expensive and easier to estimate. We achieve this by introducing a novel entropy maximization scheme that is based on conditioning on entropies and mutual informations. This renders our approach typically superior to other methods based on linear approximations. The advantages of the proposed method are documented using oscillator networks and a resting-state human brain network as generic relevant examples.
Geometrical Nonlinearity Analysis of the Steel Network Arch Bridges
Directory of Open Access Journals (Sweden)
Sigutė Žilėnaitė
2016-12-01
Full Text Available Arch bridges are one of the popular, oldest and graceful bridges which are being built in zones of the city and out of the city. However arches becomes especially sensitive to their buckling response due to dominated compressive force in the arch. In order to ensure stability conditions of the individual arch and arch bridges, it is estimated not just geometrical factor of arch, residual stress, work conditions, geometric imperfections but geometrical nonlinearity too. Geometric nonlinearity especially dominates in many times static indeterminable systems such as network arch bridges. However there are a few represents of estimation of geometric nonlinearity of the new construction form of the arch bridges created in a middle of 20th century. This paper represents estimation of geometric nonlinearity with numerical method of the steel arch bridges with vertical hangers and network arch bridges. There are determined stress-strain law and principal behavior of the steel network arch bridges under symmetric and asymmetric pedestrian loadings.
Nonlinear system identification based on internal recurrent neural networks.
Puscasu, Gheorghe; Codres, Bogdan; Stancu, Alexandru; Murariu, Gabriel
2009-04-01
A novel approach for nonlinear complex system identification based on internal recurrent neural networks (IRNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This approach employs internal state estimation when no measurements coming from the sensors are available for the system states. A modified backpropagation algorithm is introduced in order to train the IRNN for nonlinear system identification. The performance of the proposed design approach is proven on a car simulator case study.
Network-Based Practical Consensus of Heterogeneous Nonlinear Multiagent Systems.
Ding, Lei; Zheng, Wei Xing
2016-09-07
This paper studies network-based practical leader-following consensus problem of heterogeneous multiagent systems with Lipschitz nonlinear dynamics under both fixed and switching topologies. Considering the effect of network-induced delay, a network-based leader-following consensus protocol with heterogeneous gain matrix is proposed for each follower agent. By employing Lyapunov-Krasovskii method, a sufficient condition for designing the network-based consensus controller gain is derived such that the leader-following consensus error exponentially converges to a bounded region under a fixed topology. Correspondingly, the proposed design approach is then extended to the case of switching topology. Two numerical examples with networked Chua's circuits are given to show the efficiency of the design method proposed in this paper.
Strain-driven criticality underlies nonlinear mechanics of fibrous networks
Sharma, A; Rens, R; Vahabi, M; Jansen, K A; Koenderink, G H; MacKintosh, F C
2016-01-01
Networks with only central force interactions are floppy when their average connectivity is below an isostatic threshold. Although such networks are mechanically unstable, they can become rigid when strained. It was recently shown that the transition from floppy to rigid states as a function of simple shear strain is continuous, with hallmark signatures of criticality (Nat. Phys. 12, 584 (2016)). The nonlinear mechanical response of collagen networks was shown to be quantitatively described within the framework of such mechanical critical phenomenon. Here, we provide a more quantitative characterization of critical behavior in subisostatic networks. Using finite size scaling we demonstrate the divergence of strain fluctuations in the network at well-defined critical strain. We show that the characteristic strain corresponding to the onset of strain stiffening is distinct from but related to this critical strain in a way that depends on critical exponents. We confirm this prediction experimentally for collagen...
New cooperative projection neural network for nonlinearly constrained variational inequality
Institute of Scientific and Technical Information of China (English)
XIA YouSheng
2009-01-01
This paper proposes a new cooperative projection neural network (CPNN), which combines automat-ically three individual neural network models with a common projection term. As a special case, the proposed CPNN can include three recent recurrent neural networks for solving monotone variational in-equality problems with limit or linear constraints, respectively. Under the monotonicity condition of the corresponding Lagrangian mapping, the proposed CPNN is theoretically guaranteed to solve monotone variational inequality problems and a class of nonmonotone variational inequality problems with linear and nonlinear constraints. Unlike the extended projection neural network, the proposed CPNN has no limitation on the initial point for global convergence. Compared with other related cooperative neural networks and numerical optimization algorithms, the proposed CPNN has a low computational complex-ity and requires weak convergence conditions. An application in real-time grasping force optimization and examples demonstrate good performance of the proposed CPNN.
Directory of Open Access Journals (Sweden)
Alessandro Ferrarini
2016-06-01
Full Text Available Evolutionary Network Control (ENC has been first introduced in 2013 to effectively subdue network-like systems. ENC opposes the idea, very common in the scientific literature, that controllability of networks should be based on the identification of the set of driver nodes that can guide the system's dynamics, in other words on the choice of a subset of nodes that should be selected to be permanently controlled. ENC has proven to be effective in the global control (i.e. the focus is on mastery of the final state of network dynamics of linear and nonlinear networks, and in the local (i.e. the focus is on the step-by-step ascendancy of network dynamics control of linear networks. In this work, ENC is applied to the local control of nonlinear networks. Using the Lotka-Volterra model as a case study, I show here that ENC is capable of locally driving nonlinear networks as well, so that also intermediate steps (not only the final state are under our strict control. ENC can be readily applied to any kind of ecological, biological, economic and network-like system.
The mathematics of non-linear metrics for nested networks
Wu, Rui-Jie; Shi, Gui-Yuan; Zhang, Yi-Cheng; Mariani, Manuel Sebastian
2016-10-01
Numerical analysis of data from international trade and ecological networks has shown that the non-linear fitness-complexity metric is the best candidate to rank nodes by importance in bipartite networks that exhibit a nested structure. Despite its relevance for real networks, the mathematical properties of the metric and its variants remain largely unexplored. Here, we perform an analytic and numeric study of the fitness-complexity metric and a new variant, called minimal extremal metric. We rigorously derive exact expressions for node scores for perfectly nested networks and show that these expressions explain the non-trivial convergence properties of the metrics. A comparison between the fitness-complexity metric and the minimal extremal metric on real data reveals that the latter can produce improved rankings if the input data are reliable.
Nonlinear Time Series Model for Shape Classification Using Neural Networks
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
A complex nonlinear exponential autoregressive (CNEAR) model for invariant feature extraction is developed for recognizing arbitrary shapes on a plane. A neural network is used to calculate the CNEAR coefficients. The coefficients, which constitute the feature set, are proven to be invariant to boundary transformations such as translation, rotation, scale and choice of starting point in tracing the boundary. The feature set is then used as the input to a complex multilayer perceptron (C-MLP) network for learning and classification. Experimental results show that complicated shapes can be accurately recognized even with the low-order model and that the classification method has good fault tolerance when noise is present.
Non-linear feedback neural networks VLSI implementations and applications
Ansari, Mohd Samar
2014-01-01
This book aims to present a viable alternative to the Hopfield Neural Network (HNN) model for analog computation. It is well known that the standard HNN suffers from problems of convergence to local minima, and requirement of a large number of neurons and synaptic weights. Therefore, improved solutions are needed. The non-linear synapse neural network (NoSyNN) is one such possibility and is discussed in detail in this book. This book also discusses the applications in computationally intensive tasks like graph coloring, ranking, and linear as well as quadratic programming. The material in the book is useful to students, researchers and academician working in the area of analog computation.
Nonlinear programming strategies for source detection of municipal water networks.
Energy Technology Data Exchange (ETDEWEB)
van Bloemen Waanders, Bart Gustaaf; Biegler, Lorenz T. (Carnegie Mellon University, Pittsburgh, PA); Bartlett, Roscoe Ainsworth; Laird, Carl Damon (Carnegie Mellon University, Pittsburgh, PA)
2003-01-01
Increasing concerns for the security of the national infrastructure have led to a growing need for improved management and control of municipal water networks. To deal with this issue, optimization offers a general and extremely effective method to identify (possibly harmful) disturbances, assess the current state of the network, and determine operating decisions that meet network requirements and lead to optimal performance. This paper details an optimization strategy for the identification of source disturbances in the network. Here we consider the source inversion problem modeled as a nonlinear programming problem. Dynamic behavior of municipal water networks is simulated using EPANET. This approach allows for a widely accepted, general purpose user interface. For the source inversion problem, flows and concentrations of the network will be reconciled and unknown sources will be determined at network nodes. Moreover, intrusive optimization and sensitivity analysis techniques are identified to assess the influence of various parameters and models in the network in a computational efficient manner. A number of numerical comparisons are made to demonstrate the effectiveness of various optimization approaches.
Nonlinear network coding based on multiplication and exponentiation in GF(2m)
Institute of Scientific and Technical Information of China (English)
JIANG An-you; ZHU Jin-kang
2009-01-01
This article proposes a novel nonlinear network code in the GF(2m) finite field. Different from previous linear network codes that linearly mix multiple input flows, the proposed nonlinear network code mixes input flows through both multiplication and exponentiation in the GF(2m). Three relevant rules for selecting proper parameters for the proposed nonlinear network code are discussed, and the relationship between the power parameter and the coding coefficient K is explored. Further analysis shows that the proposed nonlinear network code is equivalent to a linear network code with deterministic coefficients.
Non-linear dimensionality reduction of signaling networks
Directory of Open Access Journals (Sweden)
Ivakhno Sergii
2007-06-01
Full Text Available Abstract Background Systems wide modeling and analysis of signaling networks is essential for understanding complex cellular behaviors, such as the biphasic responses to different combinations of cytokines and growth factors. For example, tumor necrosis factor (TNF can act as a proapoptotic or prosurvival factor depending on its concentration, the current state of signaling network and the presence of other cytokines. To understand combinatorial regulation in such systems, new computational approaches are required that can take into account non-linear interactions in signaling networks and provide tools for clustering, visualization and predictive modeling. Results Here we extended and applied an unsupervised non-linear dimensionality reduction approach, Isomap, to find clusters of similar treatment conditions in two cell signaling networks: (I apoptosis signaling network in human epithelial cancer cells treated with different combinations of TNF, epidermal growth factor (EGF and insulin and (II combination of signal transduction pathways stimulated by 21 different ligands based on AfCS double ligand screen data. For the analysis of the apoptosis signaling network we used the Cytokine compendium dataset where activity and concentration of 19 intracellular signaling molecules were measured to characterise apoptotic response to TNF, EGF and insulin. By projecting the original 19-dimensional space of intracellular signals into a low-dimensional space, Isomap was able to reconstruct clusters corresponding to different cytokine treatments that were identified with graph-based clustering. In comparison, Principal Component Analysis (PCA and Partial Least Squares – Discriminant analysis (PLS-DA were unable to find biologically meaningful clusters. We also showed that by using Isomap components for supervised classification with k-nearest neighbor (k-NN and quadratic discriminant analysis (QDA, apoptosis intensity can be predicted for different
Nonlinear Silicon Photonic Signal Processing Devices for Future Optical Networks
Directory of Open Access Journals (Sweden)
Cosimo Lacava
2017-01-01
Full Text Available In this paper, we present a review on silicon-based nonlinear devices for all optical nonlinear processing of complex telecommunication signals. We discuss some recent developments achieved by our research group, through extensive collaborations with academic partners across Europe, on optical signal processing using silicon-germanium and amorphous silicon based waveguides as well as novel materials such as silicon rich silicon nitride and tantalum pentoxide. We review the performance of four wave mixing wavelength conversion applied on complex signals such as Differential Phase Shift Keying (DPSK, Quadrature Phase Shift Keying (QPSK, 16-Quadrature Amplitude Modulation (QAM and 64-QAM that dramatically enhance the telecom signal spectral efficiency, paving the way to next generation terabit all-optical networks.
Circular Planar Resistor Networks with Nonlinear and Signed Conductors
Johnson, Will
2012-01-01
We consider the inverse boundary value problem in the case of discrete electrical networks containing nonlinear (non-ohmic) resistors. Generalizing work of Curtis, Ingerman, Morrow, Colin de Verdiere, Gitler, and Vertigan, we characterize the circular planar graphs for which the inverse boundary value problem has a solution in this generalized non-linear setting. The answer is the same as in the linear setting. Our method of proof never requires that the resistors behave in a continuous or monotone fashion; this allows us to recover signed conductances in many cases. We apply this to the problem of recovery in graphs that are not circular planar. We also use our results to make a frivolous knot-theoretic statement, and to slightly generalize a fact proved by Lam and Pylyavskyy about factorization schemes in their electrical linear group.
Evolutionary Network Control also holds for nonlinear networks: Ruling the Lotka-Volterra model
Directory of Open Access Journals (Sweden)
Alessandro Ferrarini
2015-09-01
Full Text Available The proof of our understanding of ecological and biological systems is measured by our skill to rule them, i.e. to channelize them towards a desired state. Control is a cardinal issue in most complex systems, but because a general theory to apply it in a quantitative manner has been absent so far, little was known about how we can rule weighted, directed networks that represent the most common configuration of real systems. To this purpose, Evolutionary Network Control (ENC has been developed as a theoretical and methodological framework aimed to the control of ecological and biological networks by coupling network dynamics and evolutionary modelling. ENC is a tools to address controllability for arbitrary network topologies and sizes. ENC has proven to cover several topics of network control, e.g. a the global control from inside and b from outside, c the local (step-by-step control, and the computation of: d control success, e feasibility, and f degree of uncertainty. Taken together, these results indicate that many aspects of controllability can be explored exactly and analytically for arbitrary networks, opening new avenues to deepening our understanding of complex systems. As yet, I have applied ENC only to linear ecological and biological networks. In this work, I show that ENC also holds for any kind of nonlinear networks, and provide an applicative example based on the nonlinear, widely-used, Lotka-Volterra model.
Artificial Neural Networks for Nonlinear Dynamic Response Simulation in Mechanical Systems
DEFF Research Database (Denmark)
Christiansen, Niels Hørbye; Høgsberg, Jan Becker; Winther, Ole
2011-01-01
It is shown how artificial neural networks can be trained to predict dynamic response of a simple nonlinear structure. Data generated using a nonlinear finite element model of a simplified wind turbine is used to train a one layer artificial neural network. When trained properly the network is able...
Neural network-based H∞ filtering for nonlinear systems with time-delays
Institute of Scientific and Technical Information of China (English)
无
2008-01-01
A novel H∞ design methodology for a neural network-based nonlinear filtering scheme is addressed.Firstly,neural networks are employed to approximate the nonlinearities.Next,the nonlinear dynamic system is represented by the mode-dependent linear difference inclusion (LDI).Finally,based on the LDI model,a neural network-based nonlinear filter (NNBNF) is developed to minimize the upper bound of H∞ gain index of the estimation error under some linear matrix inequality (LMI) constraints.Compared with the existing nonlinear filters,NNBNF is time-invariant and numerically tractable.The validity and applicability of the proposed approach are successfully demonstrated in an illustrative example.
Exponential synchronization of general chaotic delayed neural networks via hybrid feedback
Institute of Scientific and Technical Information of China (English)
无
2008-01-01
This paper investigates the exponential synchronization problem of some chaotic delayed neural networks based on the proposed general neural network model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, and covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, recurrent multilayer perceptrons (RMLPs). By virtue of LyapunovKrasovskii stability theory and linear matrix inequality (LMI) technique, some exponential synchronization criteria are derived.Using the drive-response concept, hybrid feedback controllers are designed to synchronize two identical chaotic neural networks based on those synchronization criteria. Finally, detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.
Nonlinear system modeling with random matrices: echo state networks revisited.
Zhang, Bai; Miller, David J; Wang, Yue
2012-01-01
Echo state networks (ESNs) are a novel form of recurrent neural networks (RNNs) that provide an efficient and powerful computational model approximating nonlinear dynamical systems. A unique feature of an ESN is that a large number of neurons (the "reservoir") are used, whose synaptic connections are generated randomly, with only the connections from the reservoir to the output modified by learning. Why a large randomly generated fixed RNN gives such excellent performance in approximating nonlinear systems is still not well understood. In this brief, we apply random matrix theory to examine the properties of random reservoirs in ESNs under different topologies (sparse or fully connected) and connection weights (Bernoulli or Gaussian). We quantify the asymptotic gap between the scaling factor bounds for the necessary and sufficient conditions previously proposed for the echo state property. We then show that the state transition mapping is contractive with high probability when only the necessary condition is satisfied, which corroborates and thus analytically explains the observation that in practice one obtains echo states when the spectral radius of the reservoir weight matrix is smaller than 1.
Cumulative signal transmission in nonlinear reaction-diffusion networks.
Directory of Open Access Journals (Sweden)
Diego A Oyarzún
Full Text Available Quantifying signal transmission in biochemical systems is key to uncover the mechanisms that cells use to control their responses to environmental stimuli. In this work we use the time-integral of chemical species as a measure of a network's ability to cumulatively transmit signals encoded in spatiotemporal concentrations. We identify a class of nonlinear reaction-diffusion networks in which the time-integrals of some species can be computed analytically. The derived time-integrals do not require knowledge of the solution of the reaction-diffusion equation, and we provide a simple graphical test to check if a given network belongs to the proposed class. The formulae for the time-integrals reveal how the kinetic parameters shape signal transmission in a network under spatiotemporal stimuli. We use these to show that a canonical complex-formation mechanism behaves as a spatial low-pass filter, the bandwidth of which is inversely proportional to the diffusion length of the ligand.
Approximating electrical distribution networks via mixed-integer nonlinear programming
Energy Technology Data Exchange (ETDEWEB)
Lakhera, Sanyogita [Citibank, New York City, NY (United States); Shanbhag, Uday V. [Department of Industrial and Enterprise Systems Engineering at the University of Illinois at Urbana-Champaign, 117 Transportation Building, 104 S. Mathews Ave., Urbana, IL 61801 (United States); McInerney, Michael K. [Construction Engineering Research Laboratory (CERL) (United States)
2011-02-15
Given urban data derived from a geographical information system (GIS), we consider the problem of constructing an estimate of the electrical distribution system of an urban area. We employ the image data to obtain an approximate electrical load distribution over a network of a prespecificed discretization. Together with partial information about existing substations, we determine the optimal placement of electrical substations to sustain such a load that minimizes the cost of capital and losses. This requires solving large-scale quadratic programs with discrete variables for which we present a novel penalization-smoothing scheme. The choice of locations allows one to determine the optimal flows in this network, as required by physical requirements which provide us with an approximation of the distribution network. Furthermore, the scheme allows for approximating systems in the presence of no-go areas, such as lakes and fields. We examine the performance of our algorithm on the solution of a set of location problems and observe that the scheme is capable of solving large-scale instances, well beyond the realm of existing mixed-integer nonlinear programming solvers. We conclude with a case study in which a stage-wise extension of this scheme is developed to reflect the temporal evolution of load. (author)
Nonlinear Non-convex Optimization of Hydraulic Networks
DEFF Research Database (Denmark)
Tahavori, Maryamsadat; Kallesøe, Carsten; Leth, John-Josef
2013-01-01
Pressure management in water supply systems is an effective way to reduce the leakage in a system. In this paper, the pressure management and the reduction of power consumption of a water supply system is formulated as an optimization problem. The problem is to minimize the power consumption...... in pumps and also to regulate the pressure at the end-user valves to a desired value. The optimization problem which is solved is a nonlinear and non-convex optimization. The barrier method is used to solve this problem. The modeling framework and the optimization technique which are used are general....... They can be used for a general hydraulic networks to optimize the leakage and energy consumption and to satisfy the demands at the end-users. The results in this paper show that the power consumption of the pumps is reduced....
Computational models of signalling networks for non-linear control.
Fuente, Luis A; Lones, Michael A; Turner, Alexander P; Stepney, Susan; Caves, Leo S; Tyrrell, Andy M
2013-05-01
Artificial signalling networks (ASNs) are a computational approach inspired by the signalling processes inside cells that decode outside environmental information. Using evolutionary algorithms to induce complex behaviours, we show how chaotic dynamics in a conservative dynamical system can be controlled. Such dynamics are of particular interest as they mimic the inherent complexity of non-linear physical systems in the real world. Considering the main biological interpretations of cellular signalling, in which complex behaviours and robust cellular responses emerge from the interaction of multiple pathways, we introduce two ASN representations: a stand-alone ASN and a coupled ASN. In particular we note how sophisticated cellular communication mechanisms can lead to effective controllers, where complicated problems can be divided into smaller and independent tasks.
MODELING NONLINEAR DYNAMICS OF CIRCULATING FLUIDIZED BEDS USING NEURAL NETWORKS
Institute of Scientific and Technical Information of China (English)
Wei; Chen; Atsushi; Tsutsumi; Haiyan; Lin; Kentaro; Otawara
2005-01-01
In the present work, artificial neural networks (ANNs) were proposed to model nonlinear dynamic behaviors of local voidage fluctuations induced by highly turbulent interactions between the gas and solid phases in circulating fluidized beds. The fluctuations of local voidage were measured by using an optical transmittance probe at various axial and radial positions in a circulating fluidized bed with a riser of 0.10 m in inner diameter and 10 m in height. The ANNs trained with experimental time series were applied to make short-term and long-term predictions of dynamic characteristics in the circulating fluidized bed. An early stop approach was adopted to enhance the long-term prediction capability of ANNs. The performance of the trained ANN was evaluated in terms of time-averaged characteristics, power spectra, cycle number and short-term predictability analysis of time series measured and predicted by the model.
Nonlinear electrokinetic transport in networks of microscale and nanoscale pores
Alizadeh, Shima; Andersen, Mathias B.; Mani, Ali
2012-11-01
The objective of this study is to develop the understanding of nonlinear electrohydrodynamic effects in a wide range of systems including lab-on-a-chip systems, electroosmotic pumps, and, in general, porous media with random or fabricated pore morphology. We present a continuum model in which these systems are described as massive networks of long and thin pores. The thickness of the pores can vary from nanoscale to microscale, corresponding to the highly overlapped electric double layers (EDL) to the thin double layer limit. Within each pore the transport in the wall-normal direction is assumed to be in equilibrium leading to a reduced order model for the axial transport of species in the form of a transient one-dimensional partial differential equation (PDE). PDEs from different pores are coupled through boundary conditions at the pore intersections by proper implementation of the conservation laws. We show that this model can capture important nonlinear dynamics, which are typically ignored in homogenized models. Specifically, our model captures concentration polarization shocks and flow recirculation zones respectively formed when micropores and nanopores are connected in series and in parallel. We present a comparison between our model and recent experiments in microfluidics, and will discuss applications in porous media modeling for energy storage and water purification systems.
Nonlinear modeling of PEMFC based on neural networks identification
Institute of Scientific and Technical Information of China (English)
SUN Tao; CAO Guang-yi; ZHU Xin-jian
2005-01-01
The proton exchange membrane generation technology is highly efficient and clean, and is considered as the most hopeful "green" power technology. The operating principles of proton exchange membrane fuel cell (PEMFC) system involve thermodynamics, electrochemistry, hydrodynamics and mass transfer theory, which comprise a complex nonlinear system, for which it is difficult to establish a mathematical model. This paper first simply analyzes the necessity of the PEMFC generation technology, then introduces the generating principle from four aspects: electrode, single cell, stack, system; and then uses the approach and self-study ability of artificial neural network to build the model of nonlinear system, and adapts the Levenberg-Marquardt BP (LMBP) to build the electric characteristic model of PEMFC. The model uses experimental data as training specimens, on the condition the system is provided enough hydrogen. Considering the flow velocity of air (or oxygen) and the cell operational temperature as inputs, the cell voltage and current density as the outputs and establishing the electric characteristic model of PEMFC according to the different cell temperatures. The voltage-current output curves of model has some guidance effect for improving the cell performance, and provide basic data for optimizing cell performance that have practical significance.
Hu, Jun; Gao, Huijun
2014-01-01
This monograph introduces methods for handling filtering and control problems in nonlinear stochastic systems arising from network-induced phenomena consequent on limited communication capacity. Such phenomena include communication delay, packet dropout, signal quantization or saturation, randomly occurring nonlinearities and randomly occurring uncertainties.The text is self-contained, beginning with an introduction to nonlinear stochastic systems, network-induced phenomena and filtering and control, moving through a collection of the latest research results which focuses on the three aspects
2013-01-01
A fault detection approach based on nonlinear robust observer is designed for the networked suspension control system of Maglev train with random induced time delay. First, considering random bounded time-delay and external disturbance, the nonlinear model of the networked suspension control system is established. Then, a nonlinear robust observer is designed using the input of the suspension gap. And the estimate error is proved to be bounded with arbitrary precision by adopting an appropria...
Compressive sensing reconstruction of feed-forward connectivity in pulse-coupled nonlinear networks
Barranca, Victor J.; Zhou, Douglas; Cai, David
2016-06-01
Utilizing the sparsity ubiquitous in real-world network connectivity, we develop a theoretical framework for efficiently reconstructing sparse feed-forward connections in a pulse-coupled nonlinear network through its output activities. Using only a small ensemble of random inputs, we solve this inverse problem through the compressive sensing theory based on a hidden linear structure intrinsic to the nonlinear network dynamics. The accuracy of the reconstruction is further verified by the fact that complex inputs can be well recovered using the reconstructed connectivity. We expect this Rapid Communication provides a new perspective for understanding the structure-function relationship as well as compressive sensing principle in nonlinear network dynamics.
Compressive sensing reconstruction of feed-forward connectivity in pulse-coupled nonlinear networks.
Barranca, Victor J; Zhou, Douglas; Cai, David
2016-06-01
Utilizing the sparsity ubiquitous in real-world network connectivity, we develop a theoretical framework for efficiently reconstructing sparse feed-forward connections in a pulse-coupled nonlinear network through its output activities. Using only a small ensemble of random inputs, we solve this inverse problem through the compressive sensing theory based on a hidden linear structure intrinsic to the nonlinear network dynamics. The accuracy of the reconstruction is further verified by the fact that complex inputs can be well recovered using the reconstructed connectivity. We expect this Rapid Communication provides a new perspective for understanding the structure-function relationship as well as compressive sensing principle in nonlinear network dynamics.
Prediction of municipal solid waste generation using nonlinear autoregressive network.
Younes, Mohammad K; Nopiah, Z M; Basri, N E Ahmad; Basri, H; Abushammala, Mohammed F M; Maulud, K N A
2015-12-01
Most of the developing countries have solid waste management problems. Solid waste strategic planning requires accurate prediction of the quality and quantity of the generated waste. In developing countries, such as Malaysia, the solid waste generation rate is increasing rapidly, due to population growth and new consumption trends that characterize society. This paper proposes an artificial neural network (ANN) approach using feedforward nonlinear autoregressive network with exogenous inputs (NARX) to predict annual solid waste generation in relation to demographic and economic variables like population number, gross domestic product, electricity demand per capita and employment and unemployment numbers. In addition, variable selection procedures are also developed to select a significant explanatory variable. The model evaluation was performed using coefficient of determination (R(2)) and mean square error (MSE). The optimum model that produced the lowest testing MSE (2.46) and the highest R(2) (0.97) had three inputs (gross domestic product, population and employment), eight neurons and one lag in the hidden layer, and used Fletcher-Powell's conjugate gradient as the training algorithm.
Convolutional neural networks for synthetic aperture radar classification
Profeta, Andrew; Rodriguez, Andres; Clouse, H. Scott
2016-05-01
For electro-optical object recognition, convolutional neural networks (CNNs) are the state-of-the-art. For large datasets, CNNs are able to learn meaningful features used for classification. However, their application to synthetic aperture radar (SAR) has been limited. In this work we experimented with various CNN architectures on the MSTAR SAR dataset. As the input to the CNN we used the magnitude and phase (2 channels) of the SAR imagery. We used the deep learning toolboxes CAFFE and Torch7. Our results show that we can achieve 93% accuracy on the MSTAR dataset using CNNs.
A geometrical approach to control and controllability of nonlinear dynamical networks.
Wang, Le-Zhi; Su, Ri-Qi; Huang, Zi-Gang; Wang, Xiao; Wang, Wen-Xu; Grebogi, Celso; Lai, Ying-Cheng
2016-04-14
In spite of the recent interest and advances in linear controllability of complex networks, controlling nonlinear network dynamics remains an outstanding problem. Here we develop an experimentally feasible control framework for nonlinear dynamical networks that exhibit multistability. The control objective is to apply parameter perturbation to drive the system from one attractor to another, assuming that the former is undesired and the latter is desired. To make our framework practically meaningful, we consider restricted parameter perturbation by imposing two constraints: it must be experimentally realizable and applied only temporarily. We introduce the concept of attractor network, which allows us to formulate a quantifiable controllability framework for nonlinear dynamical networks: a network is more controllable if the attractor network is more strongly connected. We test our control framework using examples from various models of experimental gene regulatory networks and demonstrate the beneficial role of noise in facilitating control.
Bifurcation-based adiabatic quantum computation with a nonlinear oscillator network.
Goto, Hayato
2016-02-22
The dynamics of nonlinear systems qualitatively change depending on their parameters, which is called bifurcation. A quantum-mechanical nonlinear oscillator can yield a quantum superposition of two oscillation states, known as a Schrödinger cat state, via quantum adiabatic evolution through its bifurcation point. Here we propose a quantum computer comprising such quantum nonlinear oscillators, instead of quantum bits, to solve hard combinatorial optimization problems. The nonlinear oscillator network finds optimal solutions via quantum adiabatic evolution, where nonlinear terms are increased slowly, in contrast to conventional adiabatic quantum computation or quantum annealing, where quantum fluctuation terms are decreased slowly. As a result of numerical simulations, it is concluded that quantum superposition and quantum fluctuation work effectively to find optimal solutions. It is also notable that the present computer is analogous to neural computers, which are also networks of nonlinear components. Thus, the present scheme will open new possibilities for quantum computation, nonlinear science, and artificial intelligence.
Bifurcation-based adiabatic quantum computation with a nonlinear oscillator network
Goto, Hayato
2016-02-01
The dynamics of nonlinear systems qualitatively change depending on their parameters, which is called bifurcation. A quantum-mechanical nonlinear oscillator can yield a quantum superposition of two oscillation states, known as a Schrödinger cat state, via quantum adiabatic evolution through its bifurcation point. Here we propose a quantum computer comprising such quantum nonlinear oscillators, instead of quantum bits, to solve hard combinatorial optimization problems. The nonlinear oscillator network finds optimal solutions via quantum adiabatic evolution, where nonlinear terms are increased slowly, in contrast to conventional adiabatic quantum computation or quantum annealing, where quantum fluctuation terms are decreased slowly. As a result of numerical simulations, it is concluded that quantum superposition and quantum fluctuation work effectively to find optimal solutions. It is also notable that the present computer is analogous to neural computers, which are also networks of nonlinear components. Thus, the present scheme will open new possibilities for quantum computation, nonlinear science, and artificial intelligence.
Donges, Jonathan F; Beronov, Boyan; Wiedermann, Marc; Runge, Jakob; Feng, Qing Yi; Tupikina, Liubov; Stolbova, Veronika; Donner, Reik V; Marwan, Norbert; Dijkstra, Henk A; Kurths, Jürgen
2015-01-01
We introduce the pyunicorn (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and nonlinear time series analysis. pyunicorn is a fully object-oriented and easily parallelizable package written in the language Python. It allows for the construction of functional networks such as climate networks in climatology or functional brain networks in neuroscience representing the structure of statistical interrelationships in large data sets of time series and, subsequently, investigating this structure using advanced methods of complex network theory such as measures and models for spatial networks, networks of interacting networks, node-weighted statistics or network surrogates. Additionally, pyunicorn provides insights into the nonlinear dynamics of complex systems as recorded in uni- and multivariate time series from a non-traditional perspective by means of recurrence qua...
Institute of Scientific and Technical Information of China (English)
顾成奎; 王正欧; 孙雅明
2003-01-01
A new method for identifying nonlinear time-varying systems with unknown structure is presented. The method extends the application area of basis sequence identification. The essential idea is to utilize the learning and nonlinear approximating ability of neural networks to model the non-linearity of the system, characterize time-varying dynamics of the system by the time-varying parametric vector of the network, then the parametric vector of the network is approximated by a weighted sum of known basis sequences. Because of black-box modeling ability of neural networks, the presented method can identify nonlinear time-varying systems with unknown structure. In order to improve the real-time capability of the algorithm, the neural network is trained by a simple fast learning algorithm based on local least squares presented by the authors. The effectiveness and the performance of the method are demonstrated by some simulation results.
Depict noise-driven nonlinear dynamic networks from output data by using high-order correlations
Chen, Yang; Chen, Tianyu; Wang, Shihong; Hu, Gang
2016-01-01
Many practical systems can be described by dynamic networks, for which modern technique can measure their output signals, and accumulate extremely rich data. Nevertheless, the network structures producing these data are often deeply hidden in these data. Depicting network structures by analysing the available data turns to be significant inverse problems. On one hand, dynamics are often driven by various unknown facts, called noises. On the other hand, network structures of practical systems are commonly nonlinear, and different nonlinearities can provide rich dynamic features and meaningful functions of realistic networks. So far, no method, both theoretically or numerically, has been found to systematically treat the both difficulties together. Here we propose to use high-order correlation computations (HOCC) to treat nonlinear dynamics; use two-time correlations to treat noise effects; and use suitable basis and correlator vectors to unifiedly depict all dynamic nonlinearities and topological interaction l...
Koyuncu, A.; Cigeroglu, E.; Özgüven, H. N.
2017-10-01
In this study, a new approach is proposed for identification of structural nonlinearities by employing cascaded optimization and neural networks. Linear finite element model of the system and frequency response functions measured at arbitrary locations of the system are used in this approach. Using the finite element model, a training data set is created, which appropriately spans the possible nonlinear configurations space of the system. A classification neural network trained on these data sets then localizes and determines the types of all nonlinearities associated with the nonlinear degrees of freedom in the system. A new training data set spanning the parametric space associated with the determined nonlinearities is created to facilitate parametric identification. Utilizing this data set, initially, a feed forward regression neural network is trained, which parametrically identifies the classified nonlinearities. Then, the results obtained are further improved by carrying out an optimization which uses network identified values as starting points. Unlike identification methods available in literature, the proposed approach does not require data collection from the degrees of freedoms where nonlinear elements are attached, and furthermore, it is sufficiently accurate even in the presence of measurement noise. The application of the proposed approach is demonstrated on an example system with nonlinear elements and on a real life experimental setup with a local nonlinearity.
Determining the input dimension of a neural network for nonlinear time series prediction
Institute of Scientific and Technical Information of China (English)
张胜; 刘红星; 高敦堂; 都思丹
2003-01-01
Determining the input dimension of a feed-forward neural network for nonlinear time series prediction plays an important role in the modelling.The paper first summarizes the current methods for determining the input dimension of the neural network.Then inspired by the fact that the correlation dimension of a nonlinear dynamic system is the mostimportant feature of it,the paper presents a new idea that the input dimension of the neural network for nonlinear time series prediction can be taken as an integer just greater than or equal to the correlation dimension.Finally,some wlidation examples and results are given.
Model algorithm control using neural networks for input delayed nonlinear control system
Institute of Scientific and Technical Information of China (English)
Yuanliang Zhang; Kil To Chong
2015-01-01
The performance of the model algorithm control method is partial y based on the accuracy of the system’s model. It is diffi-cult to obtain a good model of a nonlinear system, especial y when the nonlinearity is high. Neural networks have the ability to“learn”the characteristics of a system through nonlinear mapping to rep-resent nonlinear functions as wel as their inverse functions. This paper presents a model algorithm control method using neural net-works for nonlinear time delay systems. Two neural networks are used in the control scheme. One neural network is trained as the model of the nonlinear time delay system, and the other one pro-duces the control inputs. The neural networks are combined with the model algorithm control method to control the nonlinear time delay systems. Three examples are used to il ustrate the proposed control method. The simulation results show that the proposed control method has a good control performance for nonlinear time delay systems.
Nonlinear transport of soft droplets in pore networks
Vernerey, Franck; Benet Cerda, Eduard; Koo, Kanghyeon
A large number of biological and technological processes depend on the transport of soft colloidal particles through porous media; this includes the transport and separation of cells, viruses or drugs through tissues, membranes and microfluidic devices. In these systems, the interactions between soft particles, background fluid and the surrounding pore space yield complex, nonlinear behaviors such as non-Darcy flows, localization and jamming. We devise a computational strategy to investigate the transport of non-wetting and deformable water droplets in a microfluidic device made of a random distribution of cylindrical obstacles. We first derive scaling laws for the entry of the droplet in a single pore and discuss the role of surface tension, contact angle and size in this process. This information is then used to study the transport of multiple droplets in an obstacle network. We find that when the droplet size is close to the pore size, fluid flow and droplet trafficking strongly interact, leading to local redistributions in pressure fields, intermittent clogging and jamming. Importantly, it is found that the overall droplet and fluid transport display three different scaling regimes depending on the forcing pressure, and that these regimes can be related to droplet properties.
Institute of Scientific and Technical Information of China (English)
ZHANG Ying-Yue; YANG Qiu-Ying; CHEN Tian-Lun
2007-01-01
We introduce a modified small-world network adding new links with nonlinearly preferential connection instead of adding randomly, then we apply Bak-Sneppen (BS) evolution model on this network. We study several important structural properties of our network such as the distribution of link-degree, the maximum link-degree, and the length of the shortest path. We further argue several dynamical characteristics of the model such as the important critical value fc, the f0 avalanche, and the mutating condition, and find that those characteristics show particular behaviors.
Absolute stability of nonlinear systems with time delays and applications to neural networks
Directory of Open Access Journals (Sweden)
Xinzhi Liu
2001-01-01
Full Text Available In this paper, absolute stability of nonlinear systems with time delays is investigated. Sufficient conditions on absolute stability are derived by using the comparison principle and differential inequalities. These conditions are simple and easy to check. In addition, exponential stability conditions for some special cases of nonlinear delay systems are discussed. Applications of those results to cellular neural networks are presented.
A hyperstable neural network for the modelling and control of nonlinear systems
Indian Academy of Sciences (India)
K Warwick; Q M Zhu; Z Ma
2000-04-01
A multivariable hyperstable robust adaptive decoupling control algorithm based on a neural network is presented for the control of nonlinear multivariable coupled systems with unknown parameters and structure. The Popov theorem is used in the design of the controller. The modelling errors, coupling action and other uncertainties of the system are identified on-line by a neural network. The identified results are taken as compensation signals such that the robust adaptive control of nonlinear systems is realised. Simulation results are given.
Improved Stability Analysis of Nonlinear Networked Control Systems over Multiple Communication Links
Delavar, Rahim; Tavassoli, Babak; Beheshti, Mohammad Taghi Hamidi
2015-01-01
In this paper, we consider a nonlinear networked control system (NCS) in which controllers, sensors and actuators are connected via several communication links. In each link, networking effects such as the transmission delay, packet loss, sampling jitter and data packet miss-ordering are captured by time-varying delays. Stability analysis is carried out based on the Lyapunov Krasovskii method to obtain a condition for stability of the nonlinear NCS in the form of linear matrix inequality (LMI...
DEFF Research Database (Denmark)
Arlunno, Valeria; Zhang, Xu; Larsen, Knud J.
2011-01-01
We experimentally demonstrate that digital non-linear equalization allows for using independent tunable DFB lasers spaced at 12.5 GHz for ultradense WDM PM-QPSK flexible capacity channels for metro core networking.......We experimentally demonstrate that digital non-linear equalization allows for using independent tunable DFB lasers spaced at 12.5 GHz for ultradense WDM PM-QPSK flexible capacity channels for metro core networking....
Institute of Scientific and Technical Information of China (English)
无
2002-01-01
The nonlinear dynamical behaviors of artificial neural network (ANN) and their application to science and engineering were summarized. The mechanism of two kinds of dynamical processes, i.e. weight dynamics and activation dynamics in neural networks, and the stability of computing in structural analysis and design were stated briefly. It was successfully applied to nonlinear neural network to evaluate the stability of underground stope structure in a gold mine. With the application of BP network, it is proven that the neuro-computing is a practical and advanced tool for solving large-scale underground rock engineering problems.
Directory of Open Access Journals (Sweden)
Wu Huaiqin
2009-01-01
Full Text Available This paper considers a new class of additive neural networks where the neuron activations are modelled by discontinuous functions with nonlinear growth. By Leray-Schauder alternative theorem in differential inclusion theory, matrix theory, and generalized Lyapunov approach, a general result is derived which ensures the existence and global asymptotical stability of a unique periodic solution for such neural networks. The obtained results can be applied to neural networks with a broad range of activation functions assuming neither boundedness nor monotonicity, and also show that Forti's conjecture for discontinuous neural networks with nonlinear growth activations is true.
Discrete-time delayed standard neural network model and its application
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
A novel neural network model, termed the discrete-time delayed standard neural network model (DDSNNM), and similar to the nominal model in linear robust control theory, is suggested to facilitate the stability analysis of discrete-time recurrent neural networks (RNNs) and to ease the synthesis of controllers for discrete-time nonlinear systems. The model is composed of a discrete-time linear dynamic system and a bounded static delayed (or non-delayed) nonlinear operator. By combining various Lyapunov functionals with the S-procedure, sufficient conditions for the global asymptotic stability and global exponential stability of the DDSNNM are derived, which are formulated as linear or nonlinear matrix inequalities. Most discrete-time delayed or non-delayed RNNs, or discrete-time neural-network-based nonlinear control systems can be transformed into the DDSNNMs for stability analysis and controller synthesis in a unified way. Two application examples are given where the DDSNNMs are employed to analyze the stability of the discrete-time cellular neural networks (CNNs) and to synthesize the neuro-controllers for the discrete-time nonlinear systems, respectively. Through these examples, it is demonstrated that the DDSNNM not only makes the stability analysis of the RNNs much easier, but also provides a new approach to the synthesis of the controllers for the nonlinear systems.
Probabilistic Universal Learning Networks and their Applications to Nonlinear Control Systems
1998-01-01
Probabilistic Universal Learning Networks (PrULNs) are proposed, which are learning networks with a capability of dealing with stochastic signals. PrULNs are extensions of Universal Learning Networks (ULNs). ULNs form a superset of neural networks and were proposed to provide a universal framework for modeling and control of nonlinear large-scale complex systems. A generalized learning algorithm has been devised for ULNs which can also be used in a unified manner for almost all kinds of learn...
Deep Convolutional Neural Networks for large-scale speech tasks.
Sainath, Tara N; Kingsbury, Brian; Saon, George; Soltau, Hagen; Mohamed, Abdel-rahman; Dahl, George; Ramabhadran, Bhuvana
2015-04-01
Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. Since speech signals exhibit both of these properties, we hypothesize that CNNs are a more effective model for speech compared to Deep Neural Networks (DNNs). In this paper, we explore applying CNNs to large vocabulary continuous speech recognition (LVCSR) tasks. First, we determine the appropriate architecture to make CNNs effective compared to DNNs for LVCSR tasks. Specifically, we focus on how many convolutional layers are needed, what is an appropriate number of hidden units, what is the best pooling strategy. Second, investigate how to incorporate speaker-adapted features, which cannot directly be modeled by CNNs as they do not obey locality in frequency, into the CNN framework. Third, given the importance of sequence training for speech tasks, we introduce a strategy to use ReLU+dropout during Hessian-free sequence training of CNNs. Experiments on 3 LVCSR tasks indicate that a CNN with the proposed speaker-adapted and ReLU+dropout ideas allow for a 12%-14% relative improvement in WER over a strong DNN system, achieving state-of-the art results in these 3 tasks.
Synchronization of Nonlinear Oscillators Over Networks with Dynamic Links
De Persis, Claudio
2015-01-01
In this paper we investigate the problem of synchronization of homogeneous nonlinear oscillators coupled by dynamic links. The output of the nonlinear oscillators is the input to the dynamic links, while the output of these dynamics links is the quantity available to the distributed controllers at t
Representation of nonlinear random transformations by non-gaussian stochastic neural networks.
Turchetti, Claudio; Crippa, Paolo; Pirani, Massimiliano; Biagetti, Giorgio
2008-06-01
The learning capability of neural networks is equivalent to modeling physical events that occur in the real environment. Several early works have demonstrated that neural networks belonging to some classes are universal approximators of input-output deterministic functions. Recent works extend the ability of neural networks in approximating random functions using a class of networks named stochastic neural networks (SNN). In the language of system theory, the approximation of both deterministic and stochastic functions falls within the identification of nonlinear no-memory systems. However, all the results presented so far are restricted to the case of Gaussian stochastic processes (SPs) only, or to linear transformations that guarantee this property. This paper aims at investigating the ability of stochastic neural networks to approximate nonlinear input-output random transformations, thus widening the range of applicability of these networks to nonlinear systems with memory. In particular, this study shows that networks belonging to a class named non-Gaussian stochastic approximate identity neural networks (SAINNs) are capable of approximating the solutions of large classes of nonlinear random ordinary differential transformations. The effectiveness of this approach is demonstrated and discussed by some application examples.
Nonlinear System Identification Using Neural Networks Trained with Natural Gradient Descent
Directory of Open Access Journals (Sweden)
Ibnkahla Mohamed
2003-01-01
Full Text Available We use natural gradient (NG learning neural networks (NNs for modeling and identifying nonlinear systems with memory. The nonlinear system is comprised of a discrete-time linear filter followed by a zero-memory nonlinearity . The NN model is composed of a linear adaptive filter followed by a two-layer memoryless nonlinear NN. A Kalman filter-based technique and a search-and-converge method have been employed for the NG algorithm. It is shown that the NG descent learning significantly outperforms the ordinary gradient descent and the Levenberg-Marquardt (LM procedure in terms of convergence speed and mean squared error (MSE performance.
Institute of Scientific and Technical Information of China (English)
LIN Xiangguo; LIANG Yong
2005-01-01
The processing of nonlinear data was one of hot topics in surveying and mapping field in recent years.As a result, many linear methods and nonlinear methods have been developed.But the methods for processing generalized nonlinear surveying and mapping data, especially for different data types and including unknown parameters with random or nonrandom, are seldom noticed.A new algorithm model is presented in this paper for processing nonlinear dynamic multiple-period and multiple-accuracy data derived from deformation monitoring network.
A high-performance feedback neural network for solving convex nonlinear programming problems.
Leung, Yee; Chen, Kai-Zhou; Gao, Xing-Bao
2003-01-01
Based on a new idea of successive approximation, this paper proposes a high-performance feedback neural network model for solving convex nonlinear programming problems. Differing from existing neural network optimization models, no dual variables, penalty parameters, or Lagrange multipliers are involved in the proposed network. It has the least number of state variables and is very simple in structure. In particular, the proposed network has better asymptotic stability. For an arbitrarily given initial point, the trajectory of the network converges to an optimal solution of the convex nonlinear programming problem under no more than the standard assumptions. In addition, the network can also solve linear programming and convex quadratic programming problems, and the new idea of a feedback network may be used to solve other optimization problems. Feasibility and efficiency are also substantiated by simulation examples.
Directory of Open Access Journals (Sweden)
Yang Zhang
2013-01-01
Full Text Available We introduce a continuum modeling method to approximate a class of large wireless networks by nonlinear partial differential equations (PDEs. This method is based on the convergence of a sequence of underlying Markov chains of the network indexed by N, the number of nodes in the network. As N goes to infinity, the sequence converges to a continuum limit, which is the solution of a certain nonlinear PDE. We first describe PDE models for networks with uniformly located nodes and then generalize to networks with nonuniformly located, and possibly mobile, nodes. Based on the PDE models, we develop a method to control the transmissions in nonuniform networks so that the continuum limit is invariant under perturbations in node locations. This enables the networks to maintain stable global characteristics in the presence of varying node locations.
Wu, Li-Bing; Yang, Guang-Hong
2017-03-01
This paper investigates the problem of adaptive output neural network (NN) control for a class of stochastic nonaffine and nonlinear systems with actuator dead-zone inputs. First, based on the intermediate value theorem, a novel design scheme that converts the nonaffine system into the corresponding affine system is developed. In particular, the priori knowledge of the bound of the derivative of the nonaffine and nonlinear functions is removed; then, by employing NNs to approximate the appropriate nonlinear functions, the corresponding adaptive NN tracking controller with the adjustable parameter updated laws is designed through a backstepping technique. Furthermore, it is shown that all the closed-loop signals are bounded in probability, and the system output tracking error can converge to a small neighborhood in the sense of a mean quartic value. Finally, experimental simulations are provided to demonstrate the efficiency of the proposed adaptive NN tracking control method.
Pressure regulation in nonlinear hydraulic networks by positive controls
De Persis, Claudio; Skovmose Kallesøe, Carsten
2009-01-01
We report on our investigation of an industrial case study of a system distributed over a network, namely a large-scale hydraulic network which underlies a district heating system. The network comprises an arbitrarily large number of end-users and actuators distributed along the network. After intro
Institute of Scientific and Technical Information of China (English)
Xiao Huang; Jian Wang; Ling-zhi Zhang; Zhi-gang Cai; Zhao-xi Lianga
2001-01-01
Four phenoxysilicon networks for nonlinear optical (NLO) applications were designed and prepared by an extended sol-gel process without additional H20 and catalyst. All poled polymer network films possess high second-order nonlinear optical coefficients (d33) of 10-?～10-8 esu. The investigation of NLO temporal stability at room temperature and elevated temperature (120°C) indicated that these films exhibit high d33 stability because the orientation of the chromophores are locked in the phenoxysilicon organic/inorganic networks.
Application of BP neural networks in non-linearity correction of optical tweezers
Institute of Scientific and Technical Information of China (English)
Ziqiang WANG; Yinmei LI; Liren LOU; Henghua WEI; Zhong WANG
2008-01-01
The back-propagation (BP) neural network is proposed to correct nonlinearity and optimize the force measurement and calibration of an optical tweezer sys-tem. Considering the low convergence rate of the BP algo-rithm, the Levenberg-Marquardt (LM) algorithm is used to improve the BP network. The proposed method is experimentally studied for force calibration in a typical optical tweezer system using hydromechanics. The result shows that with the nonlinear correction using BP net-works, the range of force measurement of an optical tweezer system is enlarged by 30% and the precision is also improved compared with the polynomial fitting method. It is demonstrated that nonlinear correction by the neural network method effectively improves the per-formance of optical tweezers without adding or changing the measuring system.
Lukasiewicz-Topos Models of Neural Networks, Cell Genome and Interactome Nonlinear Dynamic Models
Baianu, I C
2004-01-01
A categorical and Lukasiewicz-Topos framework for Lukasiewicz Algebraic Logic models of nonlinear dynamics in complex functional systems such as neural networks, genomes and cell interactomes is proposed. Lukasiewicz Algebraic Logic models of genetic networks and signaling pathways in cells are formulated in terms of nonlinear dynamic systems with n-state components that allow for the generalization of previous logical models of both genetic activities and neural networks. An algebraic formulation of variable 'next-state functions' is extended to a Lukasiewicz Topos with an n-valued Lukasiewicz Algebraic Logic subobject classifier description that represents non-random and nonlinear network activities as well as their transformations in developmental processes and carcinogenesis.
Blind separation of sources in nonlinear convolved mixture based on a novel network
Institute of Scientific and Technical Information of China (English)
胡英; 杨杰; 沈利
2004-01-01
Blind separation of independent sources from their nonlinear convoluted mixtures is a more realistic problem than from linear ones. A solution to this problem based on the Entropy Maximization principle is presented. First we propose a novel two-layer network as the de-mixing system to separate sources in nonlinear convolved mixture. In output layer of our network we use feedback network architecture to cope with convoluted mixtures. Then we derive learning algorithms for the two-layer network by maximizing the information entropy. Based on the comparison of the computer simulation results, it can be concluded that the proposed algorithm has a better nonlinear convolved blind signal separation effect than the H.H. Y' s algorithm.
The Projection Neural Network for Solving Convex Nonlinear Programming
Yang, Yongqing; Xu, Xianyun
In this paper, a projection neural network for solving convex optimization is investigated. Using Lyapunov stability theory and LaSalle invariance principle, the proposed network is showed to be globally stable and converge to exact optimal solution. Two examples show the effectiveness of the proposed neural network model.
Dynamic Structure Neural Networks for Stable Adaptive Control of Nonlinear Systems
Fabri, S.; Kadirkamanathan, V.
1994-01-01
An adaptive control technique, using dynamic structure Gaussian radical basis function neural networks, that grow in time according to the location of the system's state in space is presented for the affine class of nonlinear systems having unknown or partially known dynamics. The method results in a network that is economic in terms of network size, for cases where the state spans only a small subset of state space, by utilising less basis functions than would have been the case if basis fun...
Adaptive synchronization of two nonlinearly coupled complex dynamical networks with delayed coupling
Zheng, Song; Wang, Shuguo; Dong, Gaogao; Bi, Qinsheng
2012-01-01
This paper investigates the adaptive synchronization between two nonlinearly delay-coupled complex networks with the bidirectional actions and nonidentical topological structures. Based on LaSalle's invariance principle, some criteria for the synchronization between two coupled complex networks are achieved via adaptive control. To validate the proposed methods, the unified chaotic system as the nodes of the networks are analyzed in detail, and numerical simulations are given to illustrate the theoretical results.
Nonlinear wind prediction using a fuzzy modular temporal neural network
Energy Technology Data Exchange (ETDEWEB)
Wu, G.G. [GeoControl Systems, Inc., Houston, TX (United States); Zhijie Dou [West Texas A& M Univ., Canyon, TX (United States)
1995-12-31
This paper introduces a new approach utilizing a fuzzy classifier and a modular temporal neural network to predict wind speed and direction for advanced wind turbine control systems. The fuzzy classifier estimates wind patterns and then assigns weights accordingly to each module of the temporal neural network. A temporal network with the finite-duration impulse response and multiple-layer structure is used to represent the underlying dynamics of physical phenomena. Using previous wind measurements and information given by the classifier, the modular network trained by a standard back-propagation algorithm predicts wind speed and direction effectively. Meanwhile, the feedback from the network helps auto-tuning the classifier.
Quasiperiodic AlGaAs superlattices for neuromorphic networks and nonlinear control systems
Energy Technology Data Exchange (ETDEWEB)
Malyshev, K. V., E-mail: malyshev@bmstu.ru [Electronics and Laser Technology Department, Bauman Moscow State Technical University, Moscow 105005 (Russian Federation)
2015-01-28
The application of quasiperiodic AlGaAs superlattices as a nonlinear element of the FitzHugh–Nagumo neuromorphic network is proposed and theoretically investigated on the example of Fibonacci and figurate superlattices. The sequences of symbols for the figurate superlattices were produced by decomposition of the Fibonacci superlattices' symbolic sequences. A length of each segment of the decomposition was equal to the corresponding figurate number. It is shown that a nonlinear network based upon Fibonacci and figurate superlattices provides better parallel filtration of a half-tone picture; then, a network based upon traditional diodes which have cubic voltage-current characteristics. It was found that the figurate superlattice F{sup 0}{sub 11}(1) as a nonlinear network's element provides the filtration error almost twice less than the conventional “cubic” diode. These advantages are explained by a wavelike shape of the decreasing part of the quasiperiodic superlattice's voltage-current characteristic, which leads to multistability of the network's cell. This multistability promises new interesting nonlinear dynamical phenomena. A variety of wavy forms of voltage-current characteristics opens up new interesting possibilities for quasiperiodic superlattices and especially for figurate superlattices in many areas—from nervous system modeling to nonlinear control systems development.
Quasiperiodic AlGaAs superlattices for neuromorphic networks and nonlinear control systems
Malyshev, K. V.
2015-01-01
The application of quasiperiodic AlGaAs superlattices as a nonlinear element of the FitzHugh-Nagumo neuromorphic network is proposed and theoretically investigated on the example of Fibonacci and figurate superlattices. The sequences of symbols for the figurate superlattices were produced by decomposition of the Fibonacci superlattices' symbolic sequences. A length of each segment of the decomposition was equal to the corresponding figurate number. It is shown that a nonlinear network based upon Fibonacci and figurate superlattices provides better parallel filtration of a half-tone picture; then, a network based upon traditional diodes which have cubic voltage-current characteristics. It was found that the figurate superlattice F011(1) as a nonlinear network's element provides the filtration error almost twice less than the conventional "cubic" diode. These advantages are explained by a wavelike shape of the decreasing part of the quasiperiodic superlattice's voltage-current characteristic, which leads to multistability of the network's cell. This multistability promises new interesting nonlinear dynamical phenomena. A variety of wavy forms of voltage-current characteristics opens up new interesting possibilities for quasiperiodic superlattices and especially for figurate superlattices in many areas—from nervous system modeling to nonlinear control systems development.
Nonlinear identification and control a neural network approach
Liu, G P
2001-01-01
The series Advances in Industrial Control aims to report and encourage technology transfer in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. New theory, new controllers, actuators, sensors, new industrial processes, computer methods, new applications, new philosophies . . . , new challenges. Much of this development work resides in industrial reports, feasibility study papers and the reports of advanced collaborative projects. The series otTers an opportunity for researchers to present an extended exposition of such new work in all aspects of industrial control for wider and rapid dissemination. The time for nonlinear control to enter routine application seems to be approaching. Nonlinear control has had a long gestation period but much ofthe past has been concerned with methods that involve formal nonlinear functional model representations. It seems more likely that the breakthough will come through the use of other more flexible and ame...
EXISTENCE OF PERIODIC SOLUTIONS FOR A DISCRETE-TIME MODEL OF TWO-CELL CNNS
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
We investigate a class of discrete-time model of two-cell cellular neural networks with symmetric template. By using the Lyapunov direct method, La-Salle's invariance principle, we discuss the existence and the stability of periodic solutions. The model considered has attractive 2-periodic and unstable 2-periodic solutions.
Tunnel Effect in CNNs: Image Reconstruction From Max-Switch Locations
DEFF Research Database (Denmark)
de La Roche Saint Andre, Matthieu; Rieger, Laura; Hannemose, Morten
2016-01-01
In this paper, we show that reconstruction of an image passed through a neural network is possible, using only the locations of the max pool activations. This was demonstrated with an architecture consisting of an encoder and a decoder. The decoder is a mirrored version of the encoder, where conv...
Passivation and control of partially known SISO nonlinear systems via dynamic neural networks
Reyes-Reyes J.; yu W.; Poznyak A. S.
2000-01-01
In this paper, an adaptive technique is suggested to provide the passivity property for a class of partially known SISO nonlinear systems. A simple Dynamic Neural Network (DNN), containing only two neurons and without any hidden-layers, is used to identify the unknown nonlinear system. By means of a Lyapunov-like analysis the new learning law for this DNN, guarantying both successful identification and passivation effects, is derived. Based on this adaptive DNN model, an adaptive feedback con...
Nonlinear neural network for hemodynamic model state and input estimation using fMRI data
Karam, Ayman M.
2014-11-01
Originally inspired by biological neural networks, artificial neural networks (ANNs) are powerful mathematical tools that can solve complex nonlinear problems such as filtering, classification, prediction and more. This paper demonstrates the first successful implementation of ANN, specifically nonlinear autoregressive with exogenous input (NARX) networks, to estimate the hemodynamic states and neural activity from simulated and measured real blood oxygenation level dependent (BOLD) signals. Blocked and event-related BOLD data are used to test the algorithm on real experiments. The proposed method is accurate and robust even in the presence of signal noise and it does not depend on sampling interval. Moreover, the structure of the NARX networks is optimized to yield the best estimate with minimal network architecture. The results of the estimated neural activity are also discussed in terms of their potential use.
Donges, Jonathan F; Heitzig, Jobst; Beronov, Boyan; Wiedermann, Marc; Runge, Jakob; Feng, Qing Yi; Tupikina, Liubov; Stolbova, Veronika; Donner, Reik V; Marwan, Norbert; Dijkstra, Henk A; Kurths, Jürgen
2015-11-01
We introduce the pyunicorn (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and nonlinear time series analysis. pyunicorn is a fully object-oriented and easily parallelizable package written in the language Python. It allows for the construction of functional networks such as climate networks in climatology or functional brain networks in neuroscience representing the structure of statistical interrelationships in large data sets of time series and, subsequently, investigating this structure using advanced methods of complex network theory such as measures and models for spatial networks, networks of interacting networks, node-weighted statistics, or network surrogates. Additionally, pyunicorn provides insights into the nonlinear dynamics of complex systems as recorded in uni- and multivariate time series from a non-traditional perspective by means of recurrence quantification analysis, recurrence networks, visibility graphs, and construction of surrogate time series. The range of possible applications of the library is outlined, drawing on several examples mainly from the field of climatology.
Neural-network-based approximate output regulation of discrete-time nonlinear systems.
Lan, Weiyao; Huang, Jie
2007-07-01
The existing approaches to the discrete-time nonlinear output regulation problem rely on the offline solution of a set of mixed nonlinear functional equations known as discrete regulator equations. For complex nonlinear systems, it is difficult to solve the discrete regulator equations even approximately. Moreover, for systems with uncertainty, these approaches cannot offer a reliable solution. By combining the approximation capability of the feedforward neural networks (NNs) with an online parameter optimization mechanism, we develop an approach to solving the discrete nonlinear output regulation problem without solving the discrete regulator equations explicitly. The approach of this paper can be viewed as a discrete counterpart of our previous paper on approximately solving the continuous-time nonlinear output regulation problem.
A Novel Method for Nonlinear Time Series Forecasting of Time-Delay Neural Network
Institute of Scientific and Technical Information of China (English)
JIANG Weijin; XU Yuhui
2006-01-01
Based on the idea of nonlinear prediction of phase space reconstruction, this paper presented a time delay BP neural network model, whose generalization capability was improved by Bayesian regularization.Furthermore, the model is applied to forecast the import and export trades in one industry.The results showed that the improved model has excellent generalization capabilities, which not only learned the historical curve, but efficiently predicted the trend of business.Comparing with common evaluation of forecasts, we put on a conclusion that nonlinear forecast can not only focus on data combination and precision improvement, it also can vividly reflect the nonlinear characteristic of the forecasting system.While analyzing the forecasting precision of the model, we give a model judgment by calculating the nonlinear characteristic value of the combined serial and original serial, proved that the forecasting model can reasonably catch' the dynamic characteristic of the nonlinear system which produced the origin serial.
Networked control of nonlinear systems under Denial-of-Service
De Persis, C.; Tesi, P.
2016-01-01
We investigate the analysis and design of a control strategy for nonlinear systems under Denial-of-Service attacks. Based on an ISS-Lyapunov function analysis, we provide a characterization of the maximal percentage of time that feedback information can be lost without resulting in instability of th
Solving Nonlinearly Separable Classifications in a Single-Layer Neural Network.
Conaway, Nolan; Kurtz, Kenneth J
2017-03-01
Since the work of Minsky and Papert ( 1969 ), it has been understood that single-layer neural networks cannot solve nonlinearly separable classifications (i.e., XOR). We describe and test a novel divergent autoassociative architecture capable of solving nonlinearly separable classifications with a single layer of weights. The proposed network consists of class-specific linear autoassociators. The power of the model comes from treating classification problems as within-class feature prediction rather than directly optimizing a discriminant function. We show unprecedented learning capabilities for a simple, single-layer network (i.e., solving XOR) and demonstrate that the famous limitation in acquiring nonlinearly separable problems is not just about the need for a hidden layer; it is about the choice between directly predicting classes or learning to classify indirectly by predicting features.
Tang, Ze; Park, Ju H.; Lee, Tae H.
2016-10-01
This paper is devoted to the cluster synchronization issue of nonlinearly coupled Lur'e networks under the distributed adaptive pinning control strategy. The time-varying delayed networks consisted of identical and nonidentical Lur'e systems are discussed respectively by applying the edge-based pinning control scheme. In each cluster, the edges belonging to the spanning tree are pinned. In view of the nonlinearly couplings of the networks, for the first time, an efficient distributed nonlinearly adaptive update law based on the local information of the dynamical behaviors of node is proposed. Sufficient criteria for the achievement of cluster synchronization are derived based on S-procedure, Kronecker product and Lyapunov stability theory. Additionally, some illustrative examples are provided to demonstrate the effectiveness of the theoretical results.
Noise Response Data Reveal Novel Controllability Gramian for Nonlinear Network Dynamics.
Kashima, Kenji
2016-06-06
Control of nonlinear large-scale dynamical networks, e.g., collective behavior of agents interacting via a scale-free connection topology, is a central problem in many scientific and engineering fields. For the linear version of this problem, the so-called controllability Gramian has played an important role to quantify how effectively the dynamical states are reachable by a suitable driving input. In this paper, we first extend the notion of the controllability Gramian to nonlinear dynamics in terms of the Gibbs distribution. Next, we show that, when the networks are open to environmental noise, the newly defined Gramian is equal to the covariance matrix associated with randomly excited, but uncontrolled, dynamical state trajectories. This fact theoretically justifies a simple Monte Carlo simulation that can extract effectively controllable subdynamics in nonlinear complex networks. In addition, the result provides a novel insight into the relationship between controllability and statistical mechanics.
Passivation and control of partially known SISO nonlinear systems via dynamic neural networks
Directory of Open Access Journals (Sweden)
Reyes-Reyes J.
2000-01-01
Full Text Available In this paper, an adaptive technique is suggested to provide the passivity property for a class of partially known SISO nonlinear systems. A simple Dynamic Neural Network (DNN, containing only two neurons and without any hidden-layers, is used to identify the unknown nonlinear system. By means of a Lyapunov-like analysis the new learning law for this DNN, guarantying both successful identification and passivation effects, is derived. Based on this adaptive DNN model, an adaptive feedback controller, serving for wide class of nonlinear systems with an a priori incomplete model description, is designed. Two typical examples illustrate the effectiveness of the suggested approach.
Multiple-model-and-neural-network-based nonlinear multivariable adaptive control
Institute of Scientific and Technical Information of China (English)
Yue FU; Tianyou CHAI
2007-01-01
A multivariable adaptive controller feasible for implementation on distributed computer systems (DCS) is presented for a class of uncertain nonlinear multivariable discrete time systems. The adaptive controller is composed of a linear adaptive controller, a neural network nonlinear adaptive controller and a switching mechanism. The linear controller can provide boundedness of the input and output signals, and the nonlinear controller can improve the performance of the system. The purpose of using the switching mechanism is to obtain the improved system performance and stability simultaneously. Theory analysis and simulation results are presented to show the effectiveness of the proposed method.
A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network.
Zhao, Haiquan; Zhang, Jiashu
2009-12-01
To enhance the performance and overcome the heavy computational complexity of recurrent neural networks (RNN), a novel nonlinear adaptive filter based on a pipelined second-order Volterra recurrent neural network (PSOVRNN) is proposed in this paper. A modified real-time recurrent learning (RTRL) algorithm of the proposed filter is derived in much more detail. The PSOVRNN comprises of a number of simple small-scale second-order Volterra recurrent neural network (SOVRNN) modules. In contrast to the standard RNN, these modules of a PSOVRNN can be performed simultaneously in a pipelined parallelism fashion, which can lead to a significant improvement in its total computational efficiency. Moreover, since each module of the PSOVRNN is a SOVRNN in which nonlinearity is introduced by the recursive second-order Volterra (RSOV) expansion, its performance can be further improved. Computer simulations have demonstrated that the PSOVRNN performs better than the pipelined recurrent neural network (PRNN) and RNN for nonlinear colored signals prediction and nonlinear channel equalization. However, the superiority of the PSOVRNN over the PRNN is at the cost of increasing computational complexity due to the introduced nonlinear expansion of each module.
THEORETICAL EVALUATION OF NONLINEAR EFFECTS ON OPTICAL WDM NETWORKS WITH VARIOUS FIBER TYPES
Directory of Open Access Journals (Sweden)
YASIN M. KARFAA
2010-09-01
Full Text Available A theoretical study is carried out to evaluate the performance of an opticalwavelength division multiplexing (WDM network transmission system in the presenceof crosstalk due to optical fiber nonlinearities. The most significant nonlinear effects inthe optical fiber which are Cross-Phase Modulation (XPM, Four-Wave Mixing (FWM,and Stimulated Raman Scattering (SRS are investigated. Four types of optical fiber areincluded in the analysis; these are: single-mode fiber (SMF, dispersion compensationfiber (DCF, non-zero dispersion fiber (NZDF, and non-zero dispersion shifted fiber(NZDSF. The results represent the standard deviation of nonlinearity induced crosstalknoise power due to FWM and SRS, XPM power penalty for SMF, DCF, NZDF, andNZDSF types of fiber, besides the Bit Error Rate (BER for the three nonlinear effectsusing standard fiber type (SMF. It is concluded that three significant fiber nonlinearitiesare making huge limitations against increasing the launched power which is desired,otherwise, lower values of launched power limit network expansion including length,distance, covered areas, and number of users accessing the WDM network, unlesssuitable precautions are taken to neutralize the nonlinear effects. Besides, various fibertypes are not behaving similarly towards network parameters.
Implementation of neural network based non-linear predictive
DEFF Research Database (Denmark)
Sørensen, Paul Haase; Nørgård, Peter Magnus; Ravn, Ole
1998-01-01
-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi...
Implementation of Wavelet Networks in Nonlinear System Identification
Institute of Scientific and Technical Information of China (English)
李德强; 黄莎白
2002-01-01
Orthogonal Least Squares (OLS) is a general and powerful algorithm for solving the output layer weights of a wavelet network. In this paper, the Recursive Orthogonal Least Squares (ROLS) method is used to orthogonalize the wavelet regressors. With the result of ROLS method, it is possible to compute which wavelets are important, and which are redundant and can be eliminated from the wavelet network. A structure identification algorithm is carried out based on OLS for the reduction of network. Akaike 's Information Criterion (AIC) is introduced in the process of structure identification to seek a compromise between network complexity and accuracy. The final network models obtain acceptable accuracy with a relatively small number of significant wavelets. Numerical example is given to illustrate the effectiveness of the method mentioned above.
Donges, Jonathan; Heitzig, Jobst; Beronov, Boyan; Wiedermann, Marc; Runge, Jakob; Feng, Qing Yi; Tupikina, Liubov; Stolbova, Veronika; Donner, Reik; Marwan, Norbert; Dijkstra, Henk; Kurths, Jürgen
2016-04-01
We introduce the pyunicorn (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and nonlinear time series analysis. pyunicorn is a fully object-oriented and easily parallelizable package written in the language Python. It allows for the construction of functional networks such as climate networks in climatology or functional brain networks in neuroscience representing the structure of statistical interrelationships in large data sets of time series and, subsequently, investigating this structure using advanced methods of complex network theory such as measures and models for spatial networks, networks of interacting networks, node-weighted statistics, or network surrogates. Additionally, pyunicorn provides insights into the nonlinear dynamics of complex systems as recorded in uni- and multivariate time series from a non-traditional perspective by means of recurrence quantification analysis, recurrence networks, visibility graphs, and construction of surrogate time series. The range of possible applications of the library is outlined, drawing on several examples mainly from the field of climatology. pyunicorn is available online at https://github.com/pik-copan/pyunicorn. Reference: J.F. Donges, J. Heitzig, B. Beronov, M. Wiedermann, J. Runge, Q.-Y. Feng, L. Tupikina, V. Stolbova, R.V. Donner, N. Marwan, H.A. Dijkstra, and J. Kurths, Unified functional network and nonlinear time series analysis for complex systems science: The pyunicorn package, Chaos 25, 113101 (2015), DOI: 10.1063/1.4934554, Preprint: arxiv.org:1507.01571 [physics.data-an].
Identification of Nonlinear Dynamic Systems Using Hammerstein-Type Neural Network
Directory of Open Access Journals (Sweden)
Hongshan Yu
2014-01-01
Full Text Available Hammerstein model has been popularly applied to identify the nonlinear systems. In this paper, a Hammerstein-type neural network (HTNN is derived to formulate the well-known Hammerstein model. The HTNN consists of a nonlinear static gain in cascade with a linear dynamic part. First, the Lipschitz criterion for order determination is derived. Second, the backpropagation algorithm for updating the network weights is presented, and the stability analysis is also drawn. Finally, simulation results show that HTNN identification approach demonstrated identification performances.
Stable Second-Order Nonlinear Optical Materials Based on Interpenetrating Polymer Networks
1994-03-17
0IJUN93 to 31MAY94 4. 1I1Lk ANDLSUBI1ILIE D. ?-UNUING NUMBERS •’• Stable Second-Order Nonlinear Optical Materials Based On C:N00014-90-J-1148...release and sale; its distribution is unlimited. I Stable Second-Order Nonlinear Optical Materials Based On Interpenetrating Polymer Networks S... Optical Materials Based On Interpenetrating Polymer Networks by S. Marturunkakul, J. I. Chen, L. Li, X. L. Jiang, R. J. Jeng, S. K. Sengupta, J. Kumar
A new method of thermal network modeling - A nonlinear programming approach
Adachi, M.; Miyaoka, S.; Muramatsu, A.; Funabashi, M.; Nakajima, T.
A new method for correcting thermal network model coefficients is described. This method sharply reduces discrepancies obtained by the nonlinear programming approach in the conductance coefficients and radiation coefficients for determining the heat balance of a spacecraft. The method consists of an experimental design and a nonlinear parameter identification. An experimental design for obtaining useful data for the thermal network model correction is discussed. A simulation study has shown that the standard deviation of the estimated temperature and estimation error of the parameters are reduced by 50 percent and 70 percent respectively.
Neural Network for Combining Linear and Non-Linear Modelling of Dynamic Systems
DEFF Research Database (Denmark)
Madsen, Per Printz
1994-01-01
The purpose of this paper is to develop a method to combine linear models with MLP networks. In other words to find a method to make a non-linear and multivariable model that performs at least as good as a linear model, when the training data lacks information.......The purpose of this paper is to develop a method to combine linear models with MLP networks. In other words to find a method to make a non-linear and multivariable model that performs at least as good as a linear model, when the training data lacks information....
Institute of Scientific and Technical Information of China (English)
Endong LIU; Yuanwei JING; Siying ZHANG
2005-01-01
Based on high order dynamic neural network,this paper presents the tracking problem for uncertain nonlinear composite system,which contains external disturbance,whose nonlinearities are assumed to be unknown.A smooth controller is designed to guarantee a uniform ultimate boundedness property for the tracking error and all other signals in the closed loop.Certain measures are utilized to test its performance.No a priori knowledge of an upper bound on the "optimal" weight and modeling error is required;the weights of neural networks are updated on-line.Numerical simulations performed on a simple example illustrate and clarify the approach.
Gorinevsky, D
1995-01-01
Considers radial basis function (RBF) network approximation of a multivariate nonlinear mapping as a linear parametric regression problem. Linear recursive identification algorithms applied to this problem are known to converge, provided the regressor vector sequence has the persistency of excitation (PE) property. The main contribution of this paper is formulation and proof of PE conditions on the input variables. In the RBF network identification, the regressor vector is a nonlinear function of these input variables. According to the formulated condition, the inputs provide PE, if they belong to domains around the network node centers. For a two-input network with Gaussian RBF that have typical width and are centered on a regular mesh, these domains cover about 25% of the input domain volume. The authors further generalize the proposed solution of the standard RBF network identification problem and study affine RBF network identification that is important for affine nonlinear system control. For the affine RBF network, the author formulates and proves a PE condition on both the system state parameters and control inputs.
2002-06-01
IEEE TRANSACTIONS ON AUTOMATIC CONTROL , VOL. 47, NO. 6, JUNE 2002 1033 Application of Optimization Techniques to a Nonlinear Problem of Communication... IEEE TRANSACTIONS ON AUTOMATIC CONTROL , VOL. 47, NO. 6, JUNE 2002 We consider J source-destination pairs, each of which is assigned a fixed multihop...blocking probabilities are at the maximum permitted value. IEEE TRANSACTIONS ON AUTOMATIC CONTROL , VOL. 47, NO. 6, JUNE
A high performance neural network for solving nonlinear programming problems with hybrid constraints
Tao, Qing; Cao, Jinde; Xue, Meisheng; Qiao, Hong
2001-09-01
A continuous neural network is proposed in this Letter for solving optimization problems. It not only can solve nonlinear programming problems with the constraints of equality and inequality, but also has a higher performance. The main advantage of the network is that it is an extension of Newton's gradient method for constrained problems, the dynamic behavior of the network under special constraints and the convergence rate can be investigated. Furthermore, the proposed network is simpler than the existing networks even for solving positive definite quadratic programming problems. The network considered is constrained by a projection operator on a convex set. The advanced performance of the proposed network is demonstrated by means of simulation of several numerical examples.
Nonlinear signaling on biological networks: The role of stochasticity and spectral clustering
Hernandez-Hernandez, Gonzalo; Myers, Jesse; Alvarez-Lacalle, Enrique; Shiferaw, Yohannes
2017-03-01
Signal transduction within biological cells is governed by networks of interacting proteins. Communication between these proteins is mediated by signaling molecules which bind to receptors and induce stochastic transitions between different conformational states. Signaling is typically a cooperative process which requires the occurrence of multiple binding events so that reaction rates have a nonlinear dependence on the amount of signaling molecule. It is this nonlinearity that endows biological signaling networks with robust switchlike properties which are critical to their biological function. In this study we investigate how the properties of these signaling systems depend on the network architecture. Our main result is that these nonlinear networks exhibit bistability where the network activity can switch between states that correspond to a low and high activity level. We show that this bistable regime emerges at a critical coupling strength that is determined by the spectral structure of the network. In particular, the set of nodes that correspond to large components of the leading eigenvector of the adjacency matrix determines the onset of bistability. Above this transition the eigenvectors of the adjacency matrix determine a hierarchy of clusters, defined by its spectral properties, which are activated sequentially with increasing network activity. We argue further that the onset of bistability occurs either continuously or discontinuously depending upon whether the leading eigenvector is localized or delocalized. Finally, we show that at low network coupling stochastic transitions to the active branch are also driven by the set of nodes that contribute more strongly to the leading eigenvector. However, at high coupling, transitions are insensitive to network structure since the network can be activated by stochastic transitions of a few nodes. Thus this work identifies important features of biological signaling networks that may underlie their biological
Tunnel Effect in CNNs: Image Reconstruction From Max-Switch Locations
DEFF Research Database (Denmark)
de La Roche Saint Andre, Matthieu; Rieger, Laura; Hannemose, Morten;
2016-01-01
In this paper, we show that reconstruction of an image passed through a neural network is possible, using only the locations of the max pool activations. This was demonstrated with an architecture consisting of an encoder and a decoder. The decoder is a mirrored version of the encoder, where...... convolutions are replaced with deconvolutions and poolings are replaced with unpooling layers. The locations of the max pool switches are transmitted to the corresponding unpooling layer. The reconstruction is computed only from these switches without the use of feature values. Using only the max switch...... location information of the pool layers, a surprisingly good image reconstruction can be achieved. We examine this effect in various architectures, as well as how the quality of the reconstruction is affected by the number of features. We also compare the reconstruction with an encoder with randomly...
NONLINEAR MODELING AND CONTROLLING OF ARTIFICIAL MUSCLE SYSTEM USING NEURAL NETWORKS
Institute of Scientific and Technical Information of China (English)
Tian Sheping; Ding Guoqing; Yan Detian; Lin Liangming
2004-01-01
The pneumatic artificial muscles are widely used in the fields of medical robots,etc.Neural networks are applied to modeling and controlling of artificial muscle system.A single-joint artificial muscle test system is designed.The recursive prediction error (RPE) algorithm which yields faster convergence than back propagation (BP) algorithm is applied to train the neural networks.The realization of RPE algorithm is given.The difference of modeling of artificial muscles using neural networks with different input nodes and different hidden layer nodes is discussed.On this basis the nonlinear control scheme using neural networks for artificial muscle system has been introduced.The experimental results show that the nonlinear control scheme yields faster response and higher control accuracy than the traditional linear control scheme.
Directory of Open Access Journals (Sweden)
Bahita Mohamed
2011-01-01
Full Text Available In this work, we introduce an adaptive neural network controller for a class of nonlinear systems. The approach uses two Radial Basis Functions, RBF networks. The first RBF network is used to approximate the ideal control law which cannot be implemented since the dynamics of the system are unknown. The second RBF network is used for on-line estimating the control gain which is a nonlinear and unknown function of the states. The updating laws for the combined estimator and controller are derived through Lyapunov analysis. Asymptotic stability is established with the tracking errors converging to a neighborhood of the origin. Finally, the proposed method is applied to control and stabilize the inverted pendulum system.
Advanced models of neural networks nonlinear dynamics and stochasticity in biological neurons
Rigatos, Gerasimos G
2015-01-01
This book provides a complete study on neural structures exhibiting nonlinear and stochastic dynamics, elaborating on neural dynamics by introducing advanced models of neural networks. It overviews the main findings in the modelling of neural dynamics in terms of electrical circuits and examines their stability properties with the use of dynamical systems theory. It is suitable for researchers and postgraduate students engaged with neural networks and dynamical systems theory.
Real-time person detection in low-resolution thermal infrared imagery with MSER and CNNs
Herrmann, Christian; Müller, Thomas; Willersinn, Dieter; Beyerer, Jürgen
2016-10-01
In many camera-based systems, person detection and localization is an important step for safety and security applications such as search and rescue, reconnaissance, surveillance, or driver assistance. Long-wave infrared (LWIR) imagery promises to simplify this task because it is less affected by background clutter or illumination changes. In contrast to a lot of related work, we make no assumptions about any movement of persons or the camera, i.e. persons may stand still and the camera may move or any combination thereof. Furthermore, persons may appear arbitrarily in near or far distances to the camera leading to low-resolution persons in far distances. To address this task, we propose a two-stage system, including a proposal generation method and a classifier to verify, if the detected proposals really are persons. In contradiction to use all possible proposals as with sliding window approaches, we apply Maximally Stable Extremal Regions (MSER) and classify the detected proposals afterwards with a Convolutional Neural Network (CNN). The MSER algorithm acts as a hot spot detector when applied to LWIR imagery. Because the body temperature of persons is usually higher than the background, they appear as hot spots in the image. However, the MSER algorithm is unable to distinguish between different kinds of hot spots. Thus, all further LWIR sources such as windows, animals or vehicles will be detected, too. Still by applying MSER, the number of proposals is reduced significantly in comparison to a sliding window approach which allows employing the high discriminative capabilities of deep neural networks classifiers that were recently shown in several applications such as face recognition or image content classification. We suggest using a CNN as classifier for the detected hot spots and train it to discriminate between person hot spots and all further hot spots. We specifically design a CNN that is suitable for the low-resolution person hot spots that are common with
Nonlinear Non-convex Optimization of Hydraulic Networks
DEFF Research Database (Denmark)
Tahavori, Maryamsadat; Kallesøe, Carsten; Leth, John-Josef
2013-01-01
Pressure management in water supply systems is an effective way to reduce the leakage in a system. In this paper, the pressure management and the reduction of power consumption of a water supply system is formulated as an optimization problem. The problem is to minimize the power consumption...... in pumps and also to regulate the pressure at the end-user valves to a desired value. The optimization problem which is solved is a nonlinear and non-convex optimization. The barrier method is used to solve this problem. The modeling framework and the optimization technique which are used are general...
Inferring gene regulatory networks via nonlinear state-space models and exploiting sparsity.
Noor, Amina; Serpedin, Erchin; Nounou, Mohamed; Nounou, Hazem N
2012-01-01
This paper considers the problem of learning the structure of gene regulatory networks from gene expression time series data. A more realistic scenario when the state space model representing a gene network evolves nonlinearly is considered while a linear model is assumed for the microarray data. To capture the nonlinearity, a particle filter-based state estimation algorithm is considered instead of the contemporary linear approximation-based approaches. The parameters characterizing the regulatory relations among various genes are estimated online using a Kalman filter. Since a particular gene interacts with a few other genes only, the parameter vector is expected to be sparse. The state estimates delivered by the particle filter and the observed microarray data are then subjected to a LASSO-based least squares regression operation which yields a parsimonious and efficient description of the regulatory network by setting the irrelevant coefficients to zero. The performance of the aforementioned algorithm is compared with the extended Kalman filter (EKF) and Unscented Kalman Filter (UKF) employing the Mean Square Error (MSE) as the fidelity criterion in recovering the parameters of gene regulatory networks from synthetic data and real biological data. Extensive computer simulations illustrate that the proposed particle filter-based network inference algorithm outperforms EKF and UKF, and therefore, it can serve as a natural framework for modeling gene regulatory networks with nonlinear and sparse structure.
Linear and nonlinear ARMA model parameter estimation using an artificial neural network
Chon, K. H.; Cohen, R. J.
1997-01-01
This paper addresses parametric system identification of linear and nonlinear dynamic systems by analysis of the input and output signals. Specifically, we investigate the relationship between estimation of the system using a feedforward neural network model and estimation of the system by use of linear and nonlinear autoregressive moving-average (ARMA) models. By utilizing a neural network model incorporating a polynomial activation function, we show the equivalence of the artificial neural network to the linear and nonlinear ARMA models. We compare the parameterization of the estimated system using the neural network and ARMA approaches by utilizing data generated by means of computer simulations. Specifically, we show that the parameters of a simulated ARMA system can be obtained from the neural network analysis of the simulated data or by conventional least squares ARMA analysis. The feasibility of applying neural networks with polynomial activation functions to the analysis of experimental data is explored by application to measurements of heart rate (HR) and instantaneous lung volume (ILV) fluctuations.
Directory of Open Access Journals (Sweden)
Yun Li
2013-01-01
Full Text Available A fault detection approach based on nonlinear robust observer is designed for the networked suspension control system of Maglev train with random induced time delay. First, considering random bounded time-delay and external disturbance, the nonlinear model of the networked suspension control system is established. Then, a nonlinear robust observer is designed using the input of the suspension gap. And the estimate error is proved to be bounded with arbitrary precision by adopting an appropriate parameter. When sensor faults happen, the residual between the real states and the observer outputs indicates which kind of sensor failures occurs. Finally, simulation results using the actual parameters of CMS-04 maglev train indicate that the proposed method is effective for maglev train.
CONTROL OF NONLINEAR PROCESS USING NEURAL NETWORK BASED MODEL PREDICTIVE CONTROL
Directory of Open Access Journals (Sweden)
Dr.A.TRIVEDI
2011-04-01
Full Text Available This paper presents a Neural Network based Model Predictive Control (NNMPC strategy to control nonlinear process. Multilayer Perceptron Neural Network (MLP is chosen to represent a Nonlinear Auto Regressive with eXogenous signal (NARX model of a nonlinear system. NARX dynamic model is based on feed-forward architecture and offers good approximation capabilities along with robustness and accuracy. Based on the identified neural model, a generalized predictive control (GPC algorithm is implemented to control the composition in acontinuous stirred tank reactor (CSTR, whose parameters are optimally determined by solving quadratic performance index using well known Levenberg-Marquardt and Quasi-Newton algorithm. NNMPC is tuned by selecting few horizon parameters and weighting factor. The tracking performance of the NNMPC is tested using different amplitude function as a reference signal on CSTR application. Also the robustness and performance is tested in the presence of disturbance on random reference signal.
H∞ output tracking control of discrete-time nonlinear systems via standard neural network models.
Liu, Meiqin; Zhang, Senlin; Chen, Haiyang; Sheng, Weihua
2014-10-01
This brief proposes an output tracking control for a class of discrete-time nonlinear systems with disturbances. A standard neural network model is used to represent discrete-time nonlinear systems whose nonlinearity satisfies the sector conditions. H∞ control performance for the closed-loop system including the standard neural network model, the reference model, and state feedback controller is analyzed using Lyapunov-Krasovskii stability theorem and linear matrix inequality (LMI) approach. The H∞ controller, of which the parameters are obtained by solving LMIs, guarantees that the output of the closed-loop system closely tracks the output of a given reference model well, and reduces the influence of disturbances on the tracking error. Three numerical examples are provided to show the effectiveness of the proposed H∞ output tracking design approach.
Directory of Open Access Journals (Sweden)
Oscar Castillo
2013-01-01
Full Text Available Neural networks (NNs, type-1 fuzzy logic systems (T1FLSs, and interval type-2 fuzzy logic systems (IT2FLSs have been shown to be universal approximators, which means that they can approximate any nonlinear continuous function. Recent research shows that embedding an IT2FLS on an NN can be very effective for a wide number of nonlinear complex systems, especially when handling imperfect or incomplete information. In this paper we show, based on the Stone-Weierstrass theorem, that an interval type-2 fuzzy neural network (IT2FNN is a universal approximator, which uses a set of rules and interval type-2 membership functions (IT2MFs for this purpose. Simulation results of nonlinear function identification using the IT2FNN for one and three variables and for the Mackey-Glass chaotic time series prediction are presented to illustrate the concept of universal approximation.
Institute of Scientific and Technical Information of China (English)
Wang Jun-Song; Yuan Jing; Li Qiang; Yuan Rui-Xi
2011-01-01
This paper uses a correlation dimension based nonlinear analysis approach to analyse the dynamics of network traffics with three different application protocols-HTTP, FTP and SMTP. First, the phase space is reconstructed and the embedding parameters are obtained by the mutual information method. Secondly, the correlation dimensions of three different traffics are calculated and the results of analysis have demonstrated that the dynamics of the three different application protocol traffics is different from each other in nature, i.e. HTTP and FTP traffics are chaotic,furthermore, the former is more complex than the later; on the other hand, SMTP traffic is stochastic. It is shown that correlation dimension approach is an efficient method to understand and to characterize the nonlinear dynamics of HTTP, FTP and SMTP protocol network traffics. This analysis provided insight into and a more accurate understanding of nonlinear dynamics of internet traffics which have a complex mixture of chaotic and stochastic components.
Minimal data rate stabilization of nonlinear systems over networks with large delays
Persis, Claudio De
2007-01-01
We consider the problem of designing encoders, decoders and controllers which stabilize feedforward nonlinear systems over a communication network with finite bandwidth and large delay. The control scheme guarantees minimal data-rate semi-global asymptotic and local exponential stabilizatioln of the
DEFF Research Database (Denmark)
Chon, K H; Holstein-Rathlou, N H; Marsh, D J
1998-01-01
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....
Pinning Synchronization of Delayed Neural Networks with Nonlinear Inner-Coupling
Directory of Open Access Journals (Sweden)
Yangling Wang
2011-01-01
Full Text Available Without assuming the symmetry and irreducibility of the outer-coupling weight configuration matrices, we investigate the pinning synchronization of delayed neural networks with nonlinear inner-coupling. Some delay-dependent controlled stability criteria in terms of linear matrix inequality (LMI are obtained. An example is presented to show the application of the criteria obtained in this paper.
Influence of the Laser Diode Nonlinearity in Fiber-Fed Microcellular Networks
Gameiro, A.
In this paper, the use of an optical fiber-based fixed infrastructure for code division multiple access (CDMA) mobile networks is considered. One of the major problems associated with optical subcarrier multiplexing (SCM) is the nonlinearity of the laser diodes (LD). The LD is modeled by a memoryless nonlinearity, and the effect of the nonlinearity on the SCM transmission of CDMA signals is evaluated. The behavior departs significantly from what happens in frequency division multiple access (FDMA), and depends critically on the nonlinearity being compressing or expanding. In the former case, significant performance degradation may occur, whereas for the latter this is usually not dramatic. When compared against FDMA, the major advantage of CDMA comes from the tight power control function that must be built in such systems, which means that situations of a weak signal corrupted by strong signals do not occur, unlike what happens in FDMA.
Nonlinear systems identification and control via dynamic multitime scales neural networks.
Fu, Zhi-Jun; Xie, Wen-Fang; Han, Xuan; Luo, Wei-Dong
2013-11-01
This paper deals with the adaptive nonlinear identification and trajectory tracking via dynamic multilayer neural network (NN) with different timescales. Two NN identifiers are proposed for nonlinear systems identification via dynamic NNs with different timescales including both fast and slow phenomenon. The first NN identifier uses the output signals from the actual system for the system identification. In the second NN identifier, all the output signals from nonlinear system are replaced with the state variables of the NNs. The online identification algorithms for both NN identifier parameters are proposed using Lyapunov function and singularly perturbed techniques. With the identified NN models, two indirect adaptive NN controllers for the nonlinear systems containing slow and fast dynamic processes are developed. For both developed adaptive NN controllers, the trajectory errors are analyzed and the stability of the systems is proved. Simulation results show that the controller based on the second identifier has better performance than that of the first identifier.
A Fuzzy-Neural Network Control of Nonlinear Dynamic Systems
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
In this paper,an adaptive dynamic control scheme based on a fuzzy neural network is presented,that presents utilizes both feed-forward and feedback controller elements.The former of the two elements comprises a neural network with both identification and control role,and the latter is a fuzzy neural algorithm,which is introduced to provide additional control enhancement.The feedforward controller provides only coarse control,whereas the feedback oontroller can generate on-line conditional proposition rule automatically to improve the overall control action.These properties make the design very versatile and applicable to a range of industrial applications.
Field theory of unification in nonlinear and linear network (I)——Theoretical grounds of field theory
Institute of Scientific and Technical Information of China (English)
陈燊年; 何煜光; 王建成
1995-01-01
A field theory has been proposed. The laws of conservation of charge and energy can be obtained from the Maxwell’s equations, which are placed in nonlinear network for simultaneous solution, and therefore the Kirchhoff’s law with its most fundamental integral formulae in nonlinear network can be obtained. Thus, it will strictly push forward the total basic equations from non-linear network to linear network as well as other important new relationships to provide the theoretical grounds for the field theory.
NONLINEAR EXTENSION OF ASYMMETRIC GARCH MODEL WITHIN NEURAL NETWORK FRAMEWORK
Directory of Open Access Journals (Sweden)
Josip Arnerić
2016-05-01
Full Text Available The importance of volatility for all market participants has led to the development and application of various econometric models. The most popular models in modelling volatility are GARCH type models because they can account excess kurtosis and asymmetric effects of financial time series. Since standard GARCH(1,1 model usually indicate high persistence in the conditional variance, the empirical researches turned to GJR-GARCH model and reveal its superiority in fitting the asymmetric heteroscedasticity in the data. In order to capture both asymmetry and nonlinearity in data, the goal of this paper is to develop a parsimonious NN model as an extension to GJR-GARCH model and to determine if GJR-GARCH-NN outperforms the GJR-GARCH model.
Sensor Fault Diagnosis for a Class of Time Delay Uncertain Nonlinear Systems Using Neural Network
Institute of Scientific and Technical Information of China (English)
Mou Chen; Chang-Sheng Jiang; Qing-Xian Wu
2008-01-01
In this paper, a sliding mode observer scheme of sensor fault diagnosis is proposed for a class of time delay nonlinear systems with input uncertainty based on neural network. The sensor fault and the system input uncertainty are assumed to be unknown but bounded. The radial basis function (RBF) neural network is used to approximate the sensor fault. Based on the output of the RBF neural network, the sliding mode observer is presented. Using the Lyapunov method, a criterion for stability is given in terms of matrix inequality. Finally, an example is given for illustrating the availability of the fault diagnosis based on the proposed sliding mode observer.
Model predictive control of non-linear systems over networks with data quantization and packet loss.
Yu, Jimin; Nan, Liangsheng; Tang, Xiaoming; Wang, Ping
2015-11-01
This paper studies the approach of model predictive control (MPC) for the non-linear systems under networked environment where both data quantization and packet loss may occur. The non-linear controlled plant in the networked control system (NCS) is represented by a Tagaki-Sugeno (T-S) model. The sensed data and control signal are quantized in both links and described as sector bound uncertainties by applying sector bound approach. Then, the quantized data are transmitted in the communication networks and may suffer from the effect of packet losses, which are modeled as Bernoulli process. A fuzzy predictive controller which guarantees the stability of the closed-loop system is obtained by solving a set of linear matrix inequalities (LMIs). A numerical example is given to illustrate the effectiveness of the proposed method.
An extensive weight-driven network with non-linear growth information
Wang, Lin; Qing Zhang, Gui; Lun Chen, Tian
2008-12-01
In many real-world networks such as the Internet, World Wide Web, etc., the number of edges grows in time in a nonlinear fashion. We consider growing weighted networks in which the number of outgoing edges is a nonlinear function of time and the evolution of the edges' weight is based on a mixed mechanism of weight-driven and inner selection dynamics. Moreover, two kinds of selection fashion of nodes (connected by newly established edges) have been investigated. In the common accelerating growth model, the network exhibits a wide-range power law distribution of node strengths. In the poverty alleviation model, node strength distribution can display transition from power law distribution to Poission-like distribution. The clustering coefficient, the weighted shortest path and the correlation property have been investigated simultaneously.
Directory of Open Access Journals (Sweden)
Luis Gonzaga Baca Ruiz
2016-08-01
Full Text Available This paper addresses the problem of energy consumption prediction using neural networks over a set of public buildings. Since energy consumption in the public sector comprises a substantial share of overall consumption, the prediction of such consumption represents a decisive issue in the achievement of energy savings. In our experiments, we use the data provided by an energy consumption monitoring system in a compound of faculties and research centers at the University of Granada, and provide a methodology to predict future energy consumption using nonlinear autoregressive (NAR and the nonlinear autoregressive neural network with exogenous inputs (NARX, respectively. Results reveal that NAR and NARX neural networks are both suitable for performing energy consumption prediction, but also that exogenous data may help to improve the accuracy of predictions.
Zhang, Honglu; Cheng, Jun; Wang, Hailing; Chen, Yiping; Xiang, Huili
2016-07-01
This paper investigates the problem of finite-time event-triggered H∞ boundedness for network-based Markovian jump nonlinear system. An improved model is introduced in terms of network-induced delay. By synthesizing the newly event-triggering conditions, the finite-time H∞ boundedness for networked Markovian jump nonlinear systems are guaranteed. At last, a numerical example is given to illustrate the effectiveness of proposed theoretical results.
Wu, Tsai-Chin; Anderson, Rae
We use active microrheology coupled to single-molecule fluorescence imaging to elucidate the microscale dynamics of entangled DNA. DNA naturally exists in a wide range of lengths and topologies, and is often confined in cell nucleui, forming highly concentrated and entangled biopolymer networks. Thus, DNA is the model polymer for understanding entangled polymer dynamics as well as the crowded environment of cells. These networks display complex viscoelastic properties that are not well understood, especially at the molecular-level and in response to nonlinear perturbations. Specifically, how microscopic stresses and strains propagate through entangled networks, and what molecular deformations lead to the network stress responses are unknown. To answer these important questions, we optically drive a microsphere through entangled DNA, perturbing the system far from equilibrium, while measuring the resistive force the DNA exerts on the bead during and after bead motion. We simultaneously image single fluorescent-labeled DNA molecules throughout the network to directly link the microscale stress response to molecular deformations. We characterize the deformation of the network from the molecular-level to the mesoscale, and map the stress propagation throughout the network. We further study the impact of DNA length (11 - 115 kbp) and topology (linear vs ring DNA) on deformation and propagation dynamics, exploring key nonlinear features such as tube dilation and power-law relaxation.
An integer optimization algorithm for robust identification of non-linear gene regulatory networks
Directory of Open Access Journals (Sweden)
Chemmangattuvalappil Nishanth
2012-09-01
Full Text Available Abstract Background Reverse engineering gene networks and identifying regulatory interactions are integral to understanding cellular decision making processes. Advancement in high throughput experimental techniques has initiated innovative data driven analysis of gene regulatory networks. However, inherent noise associated with biological systems requires numerous experimental replicates for reliable conclusions. Furthermore, evidence of robust algorithms directly exploiting basic biological traits are few. Such algorithms are expected to be efficient in their performance and robust in their prediction. Results We have developed a network identification algorithm to accurately infer both the topology and strength of regulatory interactions from time series gene expression data in the presence of significant experimental noise and non-linear behavior. In this novel formulism, we have addressed data variability in biological systems by integrating network identification with the bootstrap resampling technique, hence predicting robust interactions from limited experimental replicates subjected to noise. Furthermore, we have incorporated non-linearity in gene dynamics using the S-system formulation. The basic network identification formulation exploits the trait of sparsity of biological interactions. Towards that, the identification algorithm is formulated as an integer-programming problem by introducing binary variables for each network component. The objective function is targeted to minimize the network connections subjected to the constraint of maximal agreement between the experimental and predicted gene dynamics. The developed algorithm is validated using both in silico and experimental data-sets. These studies show that the algorithm can accurately predict the topology and connection strength of the in silico networks, as quantified by high precision and recall, and small discrepancy between the actual and predicted kinetic parameters
Sun, Xiaodian; Jin, Li; Xiong, Momiao
2008-01-01
It is system dynamics that determines the function of cells, tissues and organisms. To develop mathematical models and estimate their parameters are an essential issue for studying dynamic behaviors of biological systems which include metabolic networks, genetic regulatory networks and signal transduction pathways, under perturbation of external stimuli. In general, biological dynamic systems are partially observed. Therefore, a natural way to model dynamic biological systems is to employ nonlinear state-space equations. Although statistical methods for parameter estimation of linear models in biological dynamic systems have been developed intensively in the recent years, the estimation of both states and parameters of nonlinear dynamic systems remains a challenging task. In this report, we apply extended Kalman Filter (EKF) to the estimation of both states and parameters of nonlinear state-space models. To evaluate the performance of the EKF for parameter estimation, we apply the EKF to a simulation dataset and two real datasets: JAK-STAT signal transduction pathway and Ras/Raf/MEK/ERK signaling transduction pathways datasets. The preliminary results show that EKF can accurately estimate the parameters and predict states in nonlinear state-space equations for modeling dynamic biochemical networks.
Spatially Nonlinear Interdependence of Alpha-Oscillatory Neural Networks under Chan Meditation
Directory of Open Access Journals (Sweden)
Pei-Chen Lo
2013-01-01
Full Text Available This paper reports the results of our investigation of the effects of Chan meditation on brain electrophysiological behaviors from the viewpoint of spatially nonlinear interdependence among regional neural networks. Particular emphasis is laid on the alpha-dominated EEG (electroencephalograph. Continuous-time wavelet transform was adopted to detect the epochs containing substantial alpha activities. Nonlinear interdependence quantified by similarity index S(X∣Y, the influence of source signal Y on sink signal X, was applied to the nonlinear dynamical model in phase space reconstructed from multichannel EEG. Experimental group involved ten experienced Chan-Meditation practitioners, while control group included ten healthy subjects within the same age range, yet, without any meditation experience. Nonlinear interdependence among various cortical regions was explored for five local neural-network regions, frontal, posterior, right-temporal, left-temporal, and central regions. In the experimental group, the inter-regional interaction was evaluated for the brain dynamics under three different stages, at rest (stage R, pre-meditation background recording, in Chan meditation (stage M, and the unique Chakra-focusing practice (stage C. Experimental group exhibits stronger interactions among various local neural networks at stages M and C compared with those at stage R. The intergroup comparison demonstrates that Chan-meditation brain possesses better cortical inter-regional interactions than the resting brain of control group.
Distributed Synchronization in Networks of Agent Systems With Nonlinearities and Random Switchings.
Tang, Yang; Gao, Huijun; Zou, Wei; Kurths, Jürgen
2013-02-01
In this paper, the distributed synchronization problem of networks of agent systems with controllers and nonlinearities subject to Bernoulli switchings is investigated. Controllers and adaptive updating laws injected in each vertex of networks depend on the state information of its neighborhood. Three sets of Bernoulli stochastic variables are introduced to describe the occurrence probabilities of distributed adaptive controllers, updating laws and nonlinearities, respectively. By the Lyapunov functions method, we show that the distributed synchronization of networks composed of agent systems with multiple randomly occurring nonlinearities, multiple randomly occurring controllers, and multiple randomly occurring updating laws can be achieved in mean square under certain criteria. The conditions derived in this paper can be solved by semi-definite programming. Moreover, by mathematical analysis, we find that the coupling strength, the probabilities of the Bernoulli stochastic variables, and the form of nonlinearities have great impacts on the convergence speed and the terminal control strength. The synchronization criteria and the observed phenomena are demonstrated by several numerical simulation examples. In addition, the advantage of distributed adaptive controllers over conventional adaptive controllers is illustrated.
Application of Nonlinear Predictive Control Based on RBF Network Predictive Model in MCFC Plant
Institute of Scientific and Technical Information of China (English)
CHEN Yue-hua; CAO Guang-yi; ZHU Xin-jian
2007-01-01
This paper described a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). A detailed mechanism model of output voltage of a MCFC was presented at first. However, this model was too complicated to be used in a control system. Consequently, an off line radial basis function (RBF) network was introduced to build a nonlinear predictive model. And then, the optimal control sequences were obtained by applying golden mean method. The models and controller have been realized in the MATLAB environment. Simulation results indicate the proposed algorithm exhibits satisfying control effect even when the current densities vary largely.
Nonlinear model predictive control with guaraneed stability based on pesudolinear neural networks
Institute of Scientific and Technical Information of China (English)
WANG Yongji; WANG Hong
2004-01-01
A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor. It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.
Dynamic neural network-based robust observers for uncertain nonlinear systems.
Dinh, H T; Kamalapurkar, R; Bhasin, S; Dixon, W E
2014-12-01
A dynamic neural network (DNN) based robust observer for uncertain nonlinear systems is developed. The observer structure consists of a DNN to estimate the system dynamics on-line, a dynamic filter to estimate the unmeasurable state and a sliding mode feedback term to account for modeling errors and exogenous disturbances. The observed states are proven to asymptotically converge to the system states of high-order uncertain nonlinear systems through Lyapunov-based analysis. Simulations and experiments on a two-link robot manipulator are performed to show the effectiveness of the proposed method in comparison to several other state estimation methods.
Adaptive neural network tracking control for a class of unknown nonlinear time-delay systems
Institute of Scientific and Technical Information of China (English)
Chen Weisheng; Li Junmin
2006-01-01
For a class of unknown nonlinear time-delay systems, an adaptive neural network (NN) control design approach is proposed. Backstepping, domination and adaptive bounding design technique are combined to construct a robust memoryless adaptive NN tracking controller. Unknown time-delay functions are approximated by NNs, such that the requirement on the nonlinear time-delay functions is relaxed. Based on Lyapunov-Krasoviskii functional, the sem-global uniformly ultimately boundedness (UUB) of all the signals in the closed-loop system is proved. The arbitrary output tracking accuracy is achieved by tuning the design parameters. The feasibility is investigated by an illustrative simulation example.
Directory of Open Access Journals (Sweden)
Shuiqing Yu
2013-01-01
Full Text Available This paper investigates the dynamic output feedback control for nonlinear networked control systems with both random packet dropout and random delay. Random packet dropout and random delay are modeled as two independent random variables. An observer-based dynamic output feedback controller is designed based upon the Lyapunov theory. The quantitative relationship of the dropout rate, transition probability matrix, and nonlinear level is derived by solving a set of linear matrix inequalities. Finally, an example is presented to illustrate the effectiveness of the proposed method.
Qin, Jiahu; Gao, Huijun; Zheng, Wei Xing
2015-03-01
A unified approach to the analysis of synchronization for complex dynamical networks, i.e., networks of partial-state coupled linear systems and networks of full-state coupled nonlinear oscillators, is introduced. It is shown that the developed analysis can be used to describe the difference between the state of each node and the weighted sum of the states of those nodes playing the role of leaders in the networks, thus making it feasible to consider the error dynamics for the whole network system. Different from the other various methods given in the existing literature, the analysis employed in this paper is demonstrated successfully in not only providing the consistent convergence analysis with much simpler form, but also explicitly specifying the convergence rate.
A new neural network model for the feedback stabilization of nonlinear systems
Institute of Scientific and Technical Information of China (English)
Mei-qin LIU; Sen-lin ZHANG; Gang-long YAN
2008-01-01
A new neural network model termed 'standard neural network model' (SNNM) is presented,and a state-feedback control law is then designed for the SNNM to stabilize the closed-loop system.The control design constraints are shown to be a set of linear matrix inequalities (LMIs),which can be easily solved by the MATLAB LMI Control Toolbox to determine the control law.Most recurrent neural networks (including the chaotic neural network) and nonlinear systems modeled by neural networks or Takagi and Sugeno (T-S) fuzzy models can be transformed into the SNNMs to be stabilization controllers synthesized in the framework of a unified SNNM.Finally,three numerical examples are provided to illustrate the design developed in this paper.
Neural network-based nonlinear model predictive control vs. linear quadratic gaussian control
Cho, C.; Vance, R.; Mardi, N.; Qian, Z.; Prisbrey, K.
1997-01-01
One problem with the application of neural networks to the multivariable control of mineral and extractive processes is determining whether and how to use them. The objective of this investigation was to compare neural network control to more conventional strategies and to determine if there are any advantages in using neural network control in terms of set-point tracking, rise time, settling time, disturbance rejection and other criteria. The procedure involved developing neural network controllers using both historical plant data and simulation models. Various control patterns were tried, including both inverse and direct neural network plant models. These were compared to state space controllers that are, by nature, linear. For grinding and leaching circuits, a nonlinear neural network-based model predictive control strategy was superior to a state space-based linear quadratic gaussian controller. The investigation pointed out the importance of incorporating state space into neural networks by making them recurrent, i.e., feeding certain output state variables into input nodes in the neural network. It was concluded that neural network controllers can have better disturbance rejection, set-point tracking, rise time, settling time and lower set-point overshoot, and it was also concluded that neural network controllers can be more reliable and easy to implement in complex, multivariable plants.
Directory of Open Access Journals (Sweden)
Nahid Ardalani
2011-07-01
Full Text Available This article describes linear and nonlinear Artificial Neural Network(ANN-based predictors as Autoregressive Moving Average models with Auxiliary input (ARMAX process for Signal to Interference plus Noise Ratio (SINR prediction in Direct Sequence Code Division Multiple Access (DS/CDMA systems. The Multi Layer Perceptron (MLP neural network with nonlinear function is used as nonlinear neural network and Adaptive Linear (Adaline predictor is used as linear predictor. The problem of complexity of the MLP and Adaline structures is solved by using the Minimum Mean Squared Error (MMSE principle to select the optimal numbers of input and hidden nodes by try and error role. Simulation results show that both of MLP and Adaline optimal neural networks can track the effect of deep fading due to using a 1.8 GHZ carrier frequency at the urban mobile speeds of 10 km/h, 50 km/h and 120 km/h with tolerable estimation errors. Therefore, the neural networkbased predictor is well suitable SINR-based predictor in closedloop power control to combat multi path fading in CDMA systems.
Nonlinear Model Predictive Control Based on a Self-Organizing Recurrent Neural Network.
Han, Hong-Gui; Zhang, Lu; Hou, Ying; Qiao, Jun-Fei
2016-02-01
A nonlinear model predictive control (NMPC) scheme is developed in this paper based on a self-organizing recurrent radial basis function (SR-RBF) neural network, whose structure and parameters are adjusted concurrently in the training process. The proposed SR-RBF neural network is represented in a general nonlinear form for predicting the future dynamic behaviors of nonlinear systems. To improve the modeling accuracy, a spiking-based growing and pruning algorithm and an adaptive learning algorithm are developed to tune the structure and parameters of the SR-RBF neural network, respectively. Meanwhile, for the control problem, an improved gradient method is utilized for the solution of the optimization problem in NMPC. The stability of the resulting control system is proved based on the Lyapunov stability theory. Finally, the proposed SR-RBF neural network-based NMPC (SR-RBF-NMPC) is used to control the dissolved oxygen (DO) concentration in a wastewater treatment process (WWTP). Comparisons with other existing methods demonstrate that the SR-RBF-NMPC can achieve a considerably better model fitting for WWTP and a better control performance for DO concentration.
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.
TRANSIENT ANALYSIS OF NONUNIFORM TRANSMISSION LINES WITH NONLINEAR TERMINAL NETWORKS
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
A semi-analytical method in time domain is presented for analysis of the transient response of nonuniform transmission lines. In this method, the telegraph equations in time domain is differenced in space domain first, and is transformed into a set of first-order differential equations of voltage and current with respect to time. By integrating these differential equations with respect to time, and precise computation, the solution of these differential equations can be obtained. This method can solve the transient response of various kinds of transmission lines with arbitrary terminal networks. Particularly, it can analyze the nonuniform lines with initial conditions, for which there is no existing effective method to analyze the time response so far. The results obtained with this method are stable and accurate. Two examples are given to illustrate the application of this method.
Kiefel, Martin; Jampani, Varun; Gehler, Peter V.
2014-01-01
This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but of more general features (such as color values). The presented algorithm makes use of the permutohedral lattice data structure. The permutohedral lattice was introduced to efficiently implement a bilateral filter, a commonly used image processing operation....
Strain-controlled criticality governs the nonlinear mechanics of fibre networks
Sharma, A.; Licup, A. J.; Jansen, K. A.; Rens, R.; Sheinman, M.; Koenderink, G. H.; Mackintosh, F. C.
2016-06-01
Disordered fibrous networks are ubiquitous in nature as major structural components of living cells and tissues. The mechanical stability of networks generally depends on the degree of connectivity: only when the average number of connections between nodes exceeds the isostatic threshold are networks stable. On increasing the connectivity through this point, such networks undergo a mechanical phase transition from a floppy to a rigid phase. However, even sub-isostatic networks become rigid when subjected to sufficiently large deformations. To study this strain-controlled transition, we perform a combination of computational modelling of fibre networks and experiments on networks of type I collagen fibres, which are crucial for the integrity of biological tissues. We show theoretically that the development of rigidity is characterized by a strain-controlled continuous phase transition with signatures of criticality. Our experiments demonstrate mechanical properties consistent with our model, including the predicted critical exponents. We show that the nonlinear mechanics of collagen networks can be quantitatively captured by the predictions of scaling theory for the strain-controlled critical behaviour over a wide range of network concentrations and strains up to failure of the material.
An Improved Differential Evolution Trained Neural Network Scheme for Nonlinear System Identification
Institute of Scientific and Technical Information of China (English)
Bidyadhar Subudhi; Debashisha Jena
2009-01-01
This paper prescnts an improved nonlinear system identification scheme using differential evolution (DE), neural network (NN) and Levenberg Marquardt algorithm (LM). With a view to achieve better convergence of NN weights optimization during the training, the DE and LM are used in a combined framework to train the NN. We present the convergence analysis of the DE and demonstrate the efficacy of the proposed improved system identification algorithm by exploiting the combined DE and LM training of the NN and suitably implementing it together with other system identification methods, namely NN and DE+NN on a numbcr of examples including a practical case study. The identification rcsults obtained through a series of simulation studies of these methods on different nonlinear systems demonstrate that the proposed DE and LM trained NN approach to nonlinear system identification can yield better identification results in terms of time of convergence and less identification error.
Han, Honggui; Wu, Xiao-Long; Qiao, Jun-Fei
2014-04-01
In this paper, a self-organizing fuzzy-neural-network with adaptive computation algorithm (SOFNN-ACA) is proposed for modeling a class of nonlinear systems. This SOFNN-ACA is constructed online via simultaneous structure and parameter learning processes. In structure learning, a set of fuzzy rules can be self-designed using an information-theoretic methodology. The fuzzy rules with high spiking intensities (SI) are divided into new ones. And the fuzzy rules with a small relative mutual information (RMI) value will be pruned in order to simplify the FNN structure. In parameter learning, the consequent part parameters are learned through the use of an ACA that incorporates an adaptive learning rate strategy into the learning process to accelerate the convergence speed. Then, the convergence of SOFNN-ACA is analyzed. Finally, the proposed SOFNN-ACA is used to model nonlinear systems. The modeling results demonstrate that this proposed SOFNN-ACA can model nonlinear systems effectively.
Lai, Guanyu; Liu, Zhi; Zhang, Yun; Chen, Chun Lung Philip; Xie, Shengli
2015-12-24
This paper mainly aims at the problem of adaptive quantized control for a class of uncertain nonlinear systems preceded by asymmetric actuator backlash. One challenging problem that blocks the construction of our control scheme is that the real control signal is wrapped in the coupling of quantization effect and nonsmooth backlash nonlinearity. To resolve this challenge, this paper presents a two-stage separation approach established on two new technical components, which are the approximate asymmetric backlash model and the nonlinear decomposition of quantizer, respectively. Then the real control is successfully separated from the coupling dynamics. Furthermore, by employing the neural networks and adaptation method in control design, a quantized controller is developed to guarantee the asymptotic convergence of tracking error to an adjustable region of zero and uniform ultimate boundedness of all closed-loop signals. Eventually, simulations are conducted to support our theoretical results.
Stošovic, Miona V Andrejevic; Litovski, Vanco B
2013-11-01
Simulation is indispensable during the design of many biomedical prostheses that are based on fundamental electrical and electronic actions. However, simulation necessitates the use of adequate models. The main difficulties related to the modeling of such devices are their nonlinearity and dynamic behavior. Here we report the application of recurrent artificial neural networks for modeling of a nonlinear, two-terminal circuit equivalent to a specific implantable hearing device. The method is general in the sense that any nonlinear dynamic two-terminal device or circuit may be modeled in the same way. The model generated was successfully used for simulation and optimization of a driver (operational amplifier)-transducer ensemble. This confirms our claim that in addition to the proper design and optimization of the hearing actuator, optimization in the electronic domain, at the electronic driver circuit-to-actuator interface, should take place in order to achieve best performance of the complete hearing aid.
Convolution neural networks for ship type recognition
Rainey, Katie; Reeder, John D.; Corelli, Alexander G.
2016-05-01
Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.
Chen, Jie; Li, Jiahong; Yang, Shuanghua; Deng, Fang
2016-07-21
The identification of the nonlinearity and coupling is crucial in nonlinear target tracking problem in collaborative sensor networks. According to the adaptive Kalman filtering (KF) method, the nonlinearity and coupling can be regarded as the model noise covariance, and estimated by minimizing the innovation or residual errors of the states. However, the method requires large time window of data to achieve reliable covariance measurement, making it impractical for nonlinear systems which are rapidly changing. To deal with the problem, a weighted optimization-based distributed KF algorithm (WODKF) is proposed in this paper. The algorithm enlarges the data size of each sensor by the received measurements and state estimates from its connected sensors instead of the time window. A new cost function is set as the weighted sum of the bias and oscillation of the state to estimate the "best" estimate of the model noise covariance. The bias and oscillation of the state of each sensor are estimated by polynomial fitting a time window of state estimates and measurements of the sensor and its neighbors weighted by the measurement noise covariance. The best estimate of the model noise covariance is computed by minimizing the weighted cost function using the exhaustive method. The sensor selection method is in addition to the algorithm to decrease the computation load of the filter and increase the scalability of the sensor network. The existence, suboptimality and stability analysis of the algorithm are given. The local probability data association method is used in the proposed algorithm for the multitarget tracking case. The algorithm is demonstrated in simulations on tracking examples for a random signal, one nonlinear target, and four nonlinear targets. Results show the feasibility and superiority of WODKF against other filtering algorithms for a large class of systems.
Differential Neural Networks for Identification and Filtering in Nonlinear Dynamic Games
Directory of Open Access Journals (Sweden)
Emmanuel García
2014-01-01
Full Text Available This paper deals with the problem of identifying and filtering a class of continuous-time nonlinear dynamic games (nonlinear differential games subject to additive and undesired deterministic perturbations. Moreover, the mathematical model of this class is completely unknown with the exception of the control actions of each player, and even though the deterministic noises are known, their power (or their effect is not. Therefore, two differential neural networks are designed in order to obtain a feedback (perfect state information pattern for the mentioned class of games. In this way, the stability conditions for two state identification errors and for a filtering error are established, the upper bounds of these errors are obtained, and two new learning laws for each neural network are suggested. Finally, an illustrating example shows the applicability of this approach.
Robust Filtering for a Class of Networked Nonlinear Systems With Switching Communication Channels.
Zhang, Lixian; Yin, Xunyuan; Ning, Zepeng; Ye, Dong
2016-02-15
This paper is concerned with the problem of robust filter design for a class of discrete-time networked nonlinear systems. The Takagi-Sugeno fuzzy model is employed to represent the underlying nonlinear dynamics. A multi-channel communication scheme that involves a channel switching phenomenon described by a Markov chain is proposed for data transmission. Two typical communication imperfections, network-induced time-varying delays and packet dropouts are considered in each channel. The objective of this paper is to design an admissible filter such that the filter error system is stochastically stable and ensures a prescribed disturbance attenuation level bound. Based on the Lyapunov-Krasovskii functional method and matrix inequality techniques, sufficient conditions on the existence of the desired filter are obtained. A numerical example is provided to illustrate the effectiveness of the proposed design approach.
Observer-based fault-tolerant control for a class of nonlinear networked control systems
Mahmoud, M. S.; Memon, A. M.; Shi, Peng
2014-08-01
This paper presents a fault-tolerant control (FTC) scheme for nonlinear systems which are connected in a networked control system. The nonlinear system is first transformed into two subsystems such that the unobservable part is affected by a fault and the observable part is unaffected. An observer is then designed which gives state estimates using a Luenberger observer and also estimates unknown parameter of the system; this helps in fault estimation. The FTC is applied in the presence of sampling due to the presence of a network in the loop. The controller gain is obtained using linear-quadratic regulator technique. The methodology is applied on a mechatronic system and the results show satisfactory performance.
Elmaroud, Brahim; Faqihi, Ahmed; Aboutajdine, Driss
2017-01-01
In this paper, we study the performance of asynchronous and nonlinear FBMC-based multi-cellular networks. The considered system includes a reference mobile perfectly synchronized with its reference base station (BS) and K interfering BSs. Both synchronization errors and high-power amplifier (HPA) distortions will be considered and a theoretical analysis of the interference signal will be conducted. On the basis of this analysis, we will derive an accurate expression of signal-to-noise-plus-interference ratio (SINR) and bit error rate (BER) in the presence of a frequency-selective channel. In order to reduce the computational complexity of the BER expression, we applied an interesting lemma based on the moment generating function of the interference power. Finally, the proposed model is evaluated through computer simulations which show a high sensitivity of the asynchronous FBMC-based multi-cellular network to HPA nonlinear distortions.
Nonlinear Adaptive PID Control for Greenhouse Environment Based on RBF Network
Directory of Open Access Journals (Sweden)
Guanghui Li
2012-04-01
Full Text Available This paper presents a hybrid control strategy, combining Radial Basis Function (RBF network with conventional proportional, integral, and derivative (PID controllers, for the greenhouse climate control. A model of nonlinear conservation laws of enthalpy and matter between numerous system variables affecting the greenhouse climate is formulated. RBF network is used to tune and identify all PID gain parameters online and adaptively. The presented Neuro-PID control scheme is validated through simulations of set-point tracking and disturbance rejection. We compare the proposed adaptive online tuning method with the offline tuning scheme that employs Genetic Algorithm (GA to search the optimal gain parameters. The results show that the proposed strategy has good adaptability, strong robustness and real-time performance while achieving satisfactory control performance for the complex and nonlinear greenhouse climate control system, and it may provide a valuable reference to formulate environmental control strategies for actual application in greenhouse production.
Nonlinear adaptive PID control for greenhouse environment based on RBF network.
Zeng, Songwei; Hu, Haigen; Xu, Lihong; Li, Guanghui
2012-01-01
This paper presents a hybrid control strategy, combining Radial Basis Function (RBF) network with conventional proportional, integral, and derivative (PID) controllers, for the greenhouse climate control. A model of nonlinear conservation laws of enthalpy and matter between numerous system variables affecting the greenhouse climate is formulated. RBF network is used to tune and identify all PID gain parameters online and adaptively. The presented Neuro-PID control scheme is validated through simulations of set-point tracking and disturbance rejection. We compare the proposed adaptive online tuning method with the offline tuning scheme that employs Genetic Algorithm (GA) to search the optimal gain parameters. The results show that the proposed strategy has good adaptability, strong robustness and real-time performance while achieving satisfactory control performance for the complex and nonlinear greenhouse climate control system, and it may provide a valuable reference to formulate environmental control strategies for actual application in greenhouse production.
Design of asymptotic estimators: an approach based on neural networks and nonlinear programming.
Alessandri, Angelo; Cervellera, Cristiano; Sanguineti, Marcello
2007-01-01
A methodology to design state estimators for a class of nonlinear continuous-time dynamic systems that is based on neural networks and nonlinear programming is proposed. The estimator has the structure of a Luenberger observer with a linear gain and a parameterized (in general, nonlinear) function, whose argument is an innovation term representing the difference between the current measurement and its prediction. The problem of the estimator design consists in finding the values of the gain and of the parameters that guarantee the asymptotic stability of the estimation error. Toward this end, if a neural network is used to take on this function, the parameters (i.e., the neural weights) are chosen, together with the gain, by constraining the derivative of a quadratic Lyapunov function for the estimation error to be negative definite on a given compact set. It is proved that it is sufficient to impose the negative definiteness of such a derivative only on a suitably dense grid of sampling points. The gain is determined by solving a Lyapunov equation. The neural weights are searched for via nonlinear programming by minimizing a cost penalizing grid-point constraints that are not satisfied. Techniques based on low-discrepancy sequences are applied to deal with a small number of sampling points, and, hence, to reduce the computational burden required to optimize the parameters. Numerical results are reported and comparisons with those obtained by the extended Kalman filter are made.
Directory of Open Access Journals (Sweden)
Ebrahim Parcham
2014-07-01
Full Text Available Classifying similar images is one of the most interesting and essential image processing operations. Presented methods have some disadvantages like: low accuracy in analysis step and low speed in feature extraction process. In this paper, a new method for image classification is proposed in which similarity weight is revised by means of information in related and unrelated images. Based on researchers’ idea, most of real world similarity measurement systems are nonlinear. Thus, traditional linear methods are not capable of recognizing nonlinear relationship and correlation in such systems. Undoubtedly, Self Organizing Map neural networks are strongest networks for data mining and nonlinear analysis of sophisticated spaces purposes. In our proposed method, we obtain images with the most similarity measure by extracting features of our target image and comparing them with the features of other images. We took advantage of NLPCA algorithm for feature extraction which is a nonlinear algorithm that has the ability to recognize the smallest variations even in noisy images. Finally, we compare the run time and efficiency of our proposed method with previous proposed methods.
Directory of Open Access Journals (Sweden)
Laila Khalilzadeh Ganjali-khani
2013-01-01
Full Text Available One of the most effective strategies for steam generator efficiency enhancement is to improve the control system. For such an improvement, it is essential to have an accurate model for the steam generator of power plant. In this paper, an industrial steam generator is considered as a nonlinear multivariable system for identification. An important step in nonlinear system identification is the development of a nonlinear model. In recent years, artificial neural networks have been successfully used for identification of nonlinear systems in many researches. Wavelet neural networks (WNNs also are used as a powerful tool for nonlinear system identification. In this paper we present a time delay neural network model and a WNN model in order to identify an industrial steam generator. Simulation results show the effectiveness of the proposed models in the system identification and demonstrate that the WNN model is more precise to estimate the plant outputs.
AN EPOXY/(METHYL METHACRYLATE) INTERPENETRATING POLYMER NETWORK FOR NONLINEAR OPTICS
Institute of Scientific and Technical Information of China (English)
Ling-zhi Zhang; Zhi-gang Cai; Quan-dong Ying; Zhao-xi Liang
1999-01-01
An interpenetrating polymer networks (IPN) consisting of an epoxy-based polymer network and a polymethyl methacrylate network were synthesized and characterized. The IPN showed only one Ts, and hence a homogeneous-phase morphology was suggested. The second-order nonlinear optical coefficient (d33) of the IPN was measured to be 1.72×10-7 esu. The study of NLO temporal stability at room temperature and elevated temperature (100℃) indicated that the IPN exhibits a high stability in the dipole orientation due to the permanent entanglements of two component networks in the IPN system. Long-term stability of second harmonic coefficients was observed at room temperature for more than 1000 h.
On Exact Controllability of Networks of Nonlinear Elastic Strings in 3-Dimensional Space
Institute of Scientific and Technical Information of China (English)
Günter R. LEUGERING; E. J. P. Georg SCHMIDT
2012-01-01
This paper concerns a system of nonlinear wave equations describing the vibrations of a 3-dimensional network of elastic strings.The authors derive the equations and appropriate nodal conditions,determine equilibrium solutions,and,by using the methods of quasilinear hyperbolic systems,prove that for tree networks the natural initial,bound-ary value problem has classical solutions existing in neighborhoods of the "stretched" equilibrium solutions.Then the local controllability of such networks near such equilibrium configurations in a certain specified time interval is proved.Finally,it is proved that,given two different equilibrium states satisfying certain conditions,it is possible to control the network from states in a small enough neighborhood of one equilibrium to any state in a suitable neighborhood of the second equilibrium over a sufficiently large time interval.
Neural networks for modelling and control of a non-linear dynamic system
Murray-Smith, R.; Neumerkel, D.; Sbarbaro-Hofer, D.
1992-01-01
The authors describe the use of neural nets to model and control a nonlinear second-order electromechanical model of a drive system with varying time constants and saturation effects. A model predictive control structure is used. This is compared with a proportional-integral (PI) controller with regard to performance and robustness against disturbances. Two feedforward network types, the multilayer perceptron and radial-basis-function nets, are used to model the system. The problems involved ...
Institute of Scientific and Technical Information of China (English)
ZHANG Xue; YANG Qiu-Ying; ZHENG Tai-Yu; ZHANG Ying-Yue; ZHENG Li; ZHANG Gui-Qing; CHEN Tian-Lun
2008-01-01
In this paper, we investigate the effect due to the change of topology structure of network on the nonlinear dynamical behavior, by virtue of the OFC neuron evolution model with attack and repair strategy based on the small world. In particular, roles of various parameters relating to the dynamical behavior are carefully studied and analyzed. In addition, the avalanche and EEG-like wave activities with attack and repair strategy are also explored in detail in this work.
Impulsive Controller Design for Complex Nonlinear Singular Networked Systems with Packet Dropouts
Directory of Open Access Journals (Sweden)
Xian-Lin Zhao
2013-01-01
Full Text Available Globally exponential stability of Complex (with coupling Nonlinear Singular Impulsive Networked Control Systems (CNSINCS with packet dropouts and time-delay is investigated. Firstly, the mathematic model of CNSINCS is established. Then, by employing the method of Lyapunov functional, exponential stability criteria are obtained and the impulsive controller design method is given. Finally, some simulation results are provided to demonstrate the effectiveness of the proposed method.
Fabri, S.; Kadirkamanathan, V.
1996-01-01
The use of composite adaptive laws for control of the affine class of nonlinear systems having unknown dynamics is proposed. These dynamics are approximated by Gaussian radial basis function neural networks whose parameters are updated by a composite law that is driven by both tracking and estimation errors, combining techniques used in direct and indirect adaptive control. This is motivated by the need to improve the speed of convergence of the unknown parameters, hence resulting in a better...
Non-Minimum Phase Nonlinear System Predictive Control Based on Local Recurrent Neural Networks
Institute of Scientific and Technical Information of China (English)
张燕; 陈增强; 袁著祉
2003-01-01
After a recursive multi-step-ahead predictor for nonlinear systems based on local recurrent neural networks is introduced, an intelligent PID controller is adopted to correct the errors including identified model errors and accumulated errors produced in the recursive process. Characterized by predictive control, this method can achieve a good control accuracy and has good robustness. A simulation study shows that this control algorithm is very effective.
Esfandiari, Kasra; Abdollahi, Farzaneh; Talebi, Heidar Ali
2015-10-01
This paper presents a tracking control methodology for a class of uncertain nonlinear systems subject to input saturation constraint and external disturbances. Unlike most previous approaches on saturated systems, which assumed affine nonlinear systems, in this paper, tracking control problem is solved for uncertain nonaffine nonlinear systems with input saturation. To deal with the saturation constraint, an auxiliary system is constructed and a modified tracking error is defined. Then, by employing implicit function theorem, mean value theorem, and modified tracking error, updating rules are derived based on the well-known back-propagation (BP) algorithm, which has been proven to be the most relevant updating rule to control problems. However, most of the previous approaches on BP algorithm suffer from lack of stability analysis. By injecting a damping term to the standard BP algorithm, uniformly ultimately boundedness of all the signals of the closed-loop system is ensured via Lyapunov's direct method. Furthermore, the presented approach employs nonlinear in parameter neural networks. Hence, the proposed scheme is applicable to systems with higher degrees of nonlinearity. Using a high-gain observer to reconstruct the states of the system, an output feedback controller is also presented. Finally, the simulation results performed on a Duffing-Holmes chaotic system, a generalized pendulum-type system, and a numerical system are presented to demonstrate the effectiveness of the suggested state and output feedback control schemes.
Beigy, Hamid; Ahmad, Ashar; Masoudi-Nejad, Ali; Fröhlich, Holger
2017-01-01
Inferring the structure of molecular networks from time series protein or gene expression data provides valuable information about the complex biological processes of the cell. Causal network structure inference has been approached using different methods in the past. Most causal network inference techniques, such as Dynamic Bayesian Networks and ordinary differential equations, are limited by their computational complexity and thus make large scale inference infeasible. This is specifically true if a Bayesian framework is applied in order to deal with the unavoidable uncertainty about the correct model. We devise a novel Bayesian network reverse engineering approach using ordinary differential equations with the ability to include non-linearity. Besides modeling arbitrary, possibly combinatorial and time dependent perturbations with unknown targets, one of our main contributions is the use of Expectation Propagation, an algorithm for approximate Bayesian inference over large scale network structures in short computation time. We further explore the possibility of integrating prior knowledge into network inference. We evaluate the proposed model on DREAM4 and DREAM8 data and find it competitive against several state-of-the-art existing network inference methods. PMID:28166542
Zhang, Chao; Ren, Pinyi; Peng, Jingbo; Wei, Guo; Du, Qinghe; Wang, Yichen
2011-01-01
In this paper, we propose an optimal relay power allocation of an Amplify-and-Forward relay networks with non-linear power amplifiers. Based on Bussgang Linearization Theory, we depict the non-linear amplifying process into a linear system, which lets analyzing system performance easier. To obtain spatial diversity, we design a complete practical framework of a non-linear distortion aware receiver. Consider a total relay power constraint, we propose an optimal power allocation scheme to maxim...
Prescott, Aaron M.; Abel, Steven M.
2016-12-01
The rational design of network behavior is a central goal of synthetic biology. Here, we combine in silico evolution with nonlinear dimensionality reduction to redesign the responses of fixed-topology signaling networks and to characterize sets of kinetic parameters that underlie various input-output relations. We first consider the earliest part of the T cell receptor (TCR) signaling network and demonstrate that it can produce a variety of input-output relations (quantified as the level of TCR phosphorylation as a function of the characteristic TCR binding time). We utilize an evolutionary algorithm (EA) to identify sets of kinetic parameters that give rise to: (i) sigmoidal responses with the activation threshold varied over 6 orders of magnitude, (ii) a graded response, and (iii) an inverted response in which short TCR binding times lead to activation. We also consider a network with both positive and negative feedback and use the EA to evolve oscillatory responses with different periods in response to a change in input. For each targeted input-output relation, we conduct many independent runs of the EA and use nonlinear dimensionality reduction to embed the resulting data for each network in two dimensions. We then partition the results into groups and characterize constraints placed on the parameters by the different targeted response curves. Our approach provides a way (i) to guide the design of kinetic parameters of fixed-topology networks to generate novel input-output relations and (ii) to constrain ranges of biological parameters using experimental data. In the cases considered, the network topologies exhibit significant flexibility in generating alternative responses, with distinct patterns of kinetic rates emerging for different targeted responses.
Convolutional Neural Networks for SAR Image Segmentation
DEFF Research Database (Denmark)
Malmgren-Hansen, David; Nobel-Jørgensen, Morten
2015-01-01
Segmentation of Synthetic Aperture Radar (SAR) images has several uses, but it is a difficult task due to a number of properties related to SAR images. In this article we show how Convolutional Neural Networks (CNNs) can easily be trained for SAR image segmentation with good results. Besides...
Eppenhof, Koen A. J.; Pluim, Josien P. W.
2017-02-01
Error estimation in medical image registration is valuable when validating, comparing, or combining registration methods. To validate a nonlinear image registration method, ideally the registration error should be known for the entire image domain. We propose a supervised method for the estimation of a registration error map for nonlinear image registration. The method is based on a convolutional neural network that estimates the norm of the residual deformation from patches around each pixel in two registered images. This norm is interpreted as the registration error, and is defined for every pixel in the image domain. The network is trained using a set of artificially deformed images. Each training example is a pair of images: the original image, and a random deformation of that image. No manually labeled ground truth error is required. At test time, only the two registered images are required as input. We train and validate the network on registrations in a set of 2D digital subtraction angiography sequences, such that errors up to eight pixels can be estimated. We show that for this range of errors the convolutional network is able to learn the registration error in pairs of 2D registered images at subpixel precision. Finally, we present a proof of principle for the extension to 3D registration problems in chest CTs, showing that the method has the potential to estimate errors in 3D registration problems.
Institute of Scientific and Technical Information of China (English)
Tao CHENG; Frank L.LEWIS
2007-01-01
In this paper,neural networks are used to approximately solve the finite-horizon constrained input H-infiniy state feedback control problem.The method is based on solving a related Hamilton-Jacobi-Isaacs equation of the corresponding finite-horizon zero-sum game.The game value function is approximated by a neural network wlth timevarying weights.It is shown that the neural network approximation converges uniformly to the game-value function and the resulting almost optimal constrained feedback controller provides closed-loop stability and bounded L2 gain.The result is an almost optimal H-infinity feedback controller with time-varying coefficients that is solved a priori off-line.The effectiveness of the method is shown on the Rotational/Translational Actuator benchmark nonlinear control problem.
Liu, Wei; Huang, Jie
2017-01-11
This paper studies the cooperative global robust output regulation problem for a class of heterogeneous second-order nonlinear uncertain multiagent systems with jointly connected switching networks. The main contributions consist of the following three aspects. First, we generalize the result of the adaptive distributed observer from undirected jointly connected switching networks to directed jointly connected switching networks. Second, by performing a new coordinate and input transformation, we convert our problem into the cooperative global robust stabilization problem of a more complex augmented system via the distributed internal model principle. Third, we solve the stabilization problem by a distributed state feedback control law. Our result is illustrated by the leader-following consensus problem for a group of Van der Pol oscillators.
Cooperative tracking control of nonlinear multiagent systems using self-structuring neural networks.
Chen, Gang; Song, Yong-Duan
2014-08-01
This paper considers a cooperative tracking problem for a group of nonlinear multiagent systems under a directed graph that characterizes the interaction between the leader and the followers. All the networked systems can have different dynamics and all the dynamics are unknown. A neural network (NN) with flexible structure is used to approximate the unknown dynamics at each node. Considering that the leader is a neighbor of only a subset of the followers and the followers have only local interactions, we introduce a cooperative dynamic observer at each node to overcome the deficiency of the traditional tracking control strategies. An observer-based cooperative controller design framework is proposed with the aid of graph tools, Lyapunov-based design method, self-structuring NN, and separation principle. It is proved that each agent can follow the active leader only if the communication graph contains a spanning tree. Simulation results on networked robots are provided to show the effectiveness of the proposed control algorithms.
Directory of Open Access Journals (Sweden)
A. N. Bokhan
2009-01-01
Full Text Available One of the most efficient means of over-voltage reduction in arcing ground short-circuits is an application of a nonlinear over-voltage limiter. It is necessary to take into account dynamic properties of the nonlinear over-voltage limiter in order to ensure authentic simulation of over-voltage in the network A dynamic model of the non-linear over-voltage limiter which takes a time lag constant τ into account during transition of the nonlinear over-voltage limiter into conducting state has been developed in the paper.
Xu, Hao; Jagannathan, Sarangapani
2013-03-01
The stochastic optimal controller design for the nonlinear networked control system (NNCS) with uncertain system dynamics is a challenging problem due to the presence of both system nonlinearities and communication network imperfections, such as random delays and packet losses, which are not unknown a priori. In the recent literature, neuro dynamic programming (NDP) techniques, based on value and policy iterations, have been widely reported to solve the optimal control of general affine nonlinear systems. However, for realtime control, value and policy iterations-based methodology are not suitable and time-based NDP techniques are preferred. In addition, output feedback-based controller designs are preferred for implementation. Therefore, in this paper, a novel NNCS representation incorporating the system uncertainties and network imperfections is introduced first by using input and output measurements for facilitating output feedback. Then, an online neural network (NN) identifier is introduced to estimate the control coefficient matrix, which is subsequently utilized for the controller design. Subsequently, the critic and action NNs are employed along with the NN identifier to determine the forward-in-time, time-based stochastic optimal control of NNCS without using value and policy iterations. Here, the value function and control inputs are updated once a sampling instant. By using novel NN weight update laws, Lyapunov theory is used to show that all the closed-loop signals and NN weights are uniformly ultimately bounded in the mean while the approximated control input converges close to its target value with time. Simulation results are included to show the effectiveness of the proposed scheme.
Neural-network predictive control for nonlinear dynamic systems with time-delay.
Huang, Jin-Quan; Lewis, F L
2003-01-01
A new recurrent neural-network predictive feedback control structure for a class of uncertain nonlinear dynamic time-delay systems in canonical form is developed and analyzed. The dynamic system has constant input and feedback time delays due to a communications channel. The proposed control structure consists of a linearized subsystem local to the controlled plant and a remote predictive controller located at the master command station. In the local linearized subsystem, a recurrent neural network with on-line weight tuning algorithm is employed to approximate the dynamics of the time-delay-free nonlinear plant. No linearity in the unknown parameters is required. No preliminary off-line weight learning is needed. The remote controller is a modified Smith predictor that provides prediction and maintains the desired tracking performance; an extra robustifying term is needed to guarantee stability. Rigorous stability proofs are given using Lyapunov analysis. The result is an adaptive neural net compensation scheme for unknown nonlinear systems with time delays. A simulation example is provided to demonstrate the effectiveness of the proposed control strategy.
Chen, Mou; Tao, Gang; Jiang, Bin
2015-09-01
In this paper, a dynamic surface control (DSC) scheme is proposed for a class of uncertain strict-feedback nonlinear systems in the presence of input saturation and unknown external disturbance. The radial basis function neural network (RBFNN) is employed to approximate the unknown system function. To efficiently tackle the unknown external disturbance, a nonlinear disturbance observer (NDO) is developed. The developed NDO can relax the known boundary requirement of the unknown disturbance and can guarantee the disturbance estimation error converge to a bounded compact set. Using NDO and RBFNN, the DSC scheme is developed for uncertain nonlinear systems based on a backstepping method. Using a DSC technique, the problem of explosion of complexity inherent in the conventional backstepping method is avoided, which is specially important for designs using neural network approximations. Under the proposed DSC scheme, the ultimately bounded convergence of all closed-loop signals is guaranteed via Lyapunov analysis. Simulation results are given to show the effectiveness of the proposed DSC design using NDO and RBFNN.
Förner, K.; Polifke, W.
2017-10-01
The nonlinear acoustic behavior of Helmholtz resonators is characterized by a data-based reduced-order model, which is obtained by a combination of high-resolution CFD simulation and system identification. It is shown that even in the nonlinear regime, a linear model is capable of describing the reflection behavior at a particular amplitude with quantitative accuracy. This observation motivates to choose a local-linear model structure for this study, which consists of a network of parallel linear submodels. A so-called fuzzy-neuron layer distributes the input signal over the linear submodels, depending on the root mean square of the particle velocity at the resonator surface. The resulting model structure is referred to as an local-linear neuro-fuzzy network. System identification techniques are used to estimate the free parameters of this model from training data. The training data are generated by CFD simulations of the resonator, with persistent acoustic excitation over a wide range of frequencies and sound pressure levels. The estimated nonlinear, reduced-order models show good agreement with CFD and experimental data over a wide range of amplitudes for several test cases.
Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network.
Zhao, Haiquan; Zeng, Xiangping; He, Zhengyou
2011-09-01
To reduce the computational complexity of the bilinear recurrent neural network (BLRNN), a novel low-complexity nonlinear adaptive filter with a pipelined bilinear recurrent neural network (PBLRNN) is presented in this paper. The PBLRNN, inheriting the modular architectures of the pipelined RNN proposed by Haykin and Li, comprises a number of BLRNN modules that are cascaded in a chained form. Each module is implemented by a small-scale BLRNN with internal dynamics. Since those modules of the PBLRNN can be performed simultaneously in a pipelined parallelism fashion, it would result in a significant improvement of computational efficiency. Moreover, due to nesting module, the performance of the PBLRNN can be further improved. To suit for the modular architectures, a modified adaptive amplitude real-time recurrent learning algorithm is derived on the gradient descent approach. Extensive simulations are carried out to evaluate the performance of the PBLRNN on nonlinear system identification, nonlinear channel equalization, and chaotic time series prediction. Experimental results show that the PBLRNN provides considerably better performance compared to the single BLRNN and RNN models.
Lu, Bao-Liang; Ito, Koji
2003-09-01
In this paper we present a method for converting general nonlinear programming (NLP) problems into separable programming (SP) problems by using feedforward neural networks (FNNs). The basic idea behind the method is to use two useful features of FNNs: their ability to approximate arbitrary continuous nonlinear functions with a desired degree of accuracy and their ability to express nonlinear functions in terms of parameterized compositions of functions of single variables. According to these two features, any nonseparable objective functions and/or constraints in NLP problems can be approximately expressed as separable functions with FNNs. Therefore, any NLP problems can be converted into SP problems. The proposed method has three prominent features. (a) It is more general than existing transformation techniques; (b) it can be used to formulate optimization problems as SP problems even when their precise analytic objective function and/or constraints are unknown; (c) the SP problems obtained by the proposed method may highly facilitate the selection of grid points for piecewise linear approximation of nonlinear functions. We analyze the computational complexity of the proposed method and compare it with an existing transformation approach. We also present several examples to demonstrate the method and the performance of the simplex method with the restricted basis entry rule for solving SP problems.
Ibnkahla, Mohamed
2012-12-01
Neural network (NN) approaches have been widely applied for modeling and identification of nonlinear multiple-input multiple-output (MIMO) systems. This paper proposes a stochastic analysis of a class of these NN algorithms. The class of MIMO systems considered in this paper is composed of a set of single-input nonlinearities followed by a linear combiner. The NN model consists of a set of single-input memoryless NN blocks followed by a linear combiner. A gradient descent algorithm is used for the learning process. Here we give analytical expressions for the mean squared error (MSE), explore the stationary points of the algorithm, evaluate the misadjustment error due to weight fluctuations, and derive recursions for the mean weight transient behavior during the learning process. The paper shows that in the case of independent inputs, the adaptive linear combiner identifies the linear combining matrix of the MIMO system (to within a scaling diagonal matrix) and that each NN block identifies the corresponding unknown nonlinearity to within a scale factor. The paper also investigates the particular case of linear identification of the nonlinear MIMO system. It is shown in this case that, for independent inputs, the adaptive linear combiner identifies a scaled version of the unknown linear combining matrix. The paper is supported with computer simulations which confirm the theoretical results.
Dual-orthogonal radial basis function networks for nonlinear time series prediction.
Hong, X; Billings, Steve A.
1998-04-01
A new structure of Radial Basis Function (RBF) neural network called the Dual-orthogonal RBF Network (DRBF) is introduced for nonlinear time series prediction. The hidden nodes of a conventional RBF network compare the Euclidean distance between the network input vector and the centres, and the node responses are radially symmetrical. But in time series prediction where the system input vectors are lagged system outputs, which are usually highly correlated, the Euclidean distance measure may not be appropriate. The DRBF network modifies the distance metric by introducing a classification function which is based on the estimation data set. Training the DRBF networks consists of two stages. Learning the classification related basis functions and the important input nodes, followed by selecting the regressors and learning the weights of the hidden nodes. In both cases, a forward Orthogonal Least Squares (OLS) selection procedure is applied, initially to select the important input nodes and then to select the important centres. Simulation results of single-step and multi-step ahead predictions over a test data set are included to demonstrate the effectiveness of the new approach.
Nonlinear analysis of gas-water/oil-water two-phase flow in complex networks
Gao, Zhong-Ke; Wang, Wen-Xu
2014-01-01
Understanding the dynamics of multi-phase flows has been a challenge in the fields of nonlinear dynamics and fluid mechanics. This chapter reviews our work on two-phase flow dynamics in combination with complex network theory. We systematically carried out gas-water/oil-water two-phase flow experiments for measuring the time series of flow signals which is studied in terms of the mapping from time series to complex networks. Three network mapping methods were proposed for the analysis and identification of flow patterns, i.e. Flow Pattern Complex Network (FPCN), Fluid Dynamic Complex Network (FDCN) and Fluid Structure Complex Network (FSCN). Through detecting the community structure of FPCN based on K-means clustering, distinct flow patterns can be successfully distinguished and identified. A number of FDCN’s under different flow conditions were constructed in order to reveal the dynamical characteristics of two-phase flows. The FDCNs exhibit universal power-law degree distributions. The power-law exponent ...
Adaptive Backstepping Output Feedback Control for SISO Nonlinear System Using Fuzzy Neural Networks
Institute of Scientific and Technical Information of China (English)
Shao-Cheng Tong; Yong-Ming Li
2009-01-01
In this paper, a new fuzzy-neural adaptive control approach is developed for a class of single-input and single-output (SISO) nonlinear systems with unmeasured states. Using fuzzy neural networks to approximate the unknown nonlinear functions, a fuzzy-neural adaptive observer is introduced for state estimation as well as system identification. Under the framework of the backstepping design, fuzzy-neural adaptive output feedback control is constructed rccursively. It is proven that the proposed fuzzy adaptive control approach guarantees the global boundedness property for all the signals, driving the tracking error to a small neighbordhood of the origin. Simulation example is included to illustrate the effectiveness of the proposed approach.
Adaptive identifier for uncertain complex nonlinear systems based on continuous neural networks.
Alfaro-Ponce, Mariel; Cruz, Amadeo Argüelles; Chairez, Isaac
2014-03-01
This paper presents the design of a complex-valued differential neural network identifier for uncertain nonlinear systems defined in the complex domain. This design includes the construction of an adaptive algorithm to adjust the parameters included in the identifier. The algorithm is obtained based on a special class of controlled Lyapunov functions. The quality of the identification process is characterized using the practical stability framework. Indeed, the region where the identification error converges is derived by the same Lyapunov method. This zone is defined by the power of uncertainties and perturbations affecting the complex-valued uncertain dynamics. Moreover, this convergence zone is reduced to its lowest possible value using ideas related to the so-called ellipsoid methodology. Two simple but informative numerical examples are developed to show how the identifier proposed in this paper can be used to approximate uncertain nonlinear systems valued in the complex domain.
Nonlinear random resistor diode networks and fractal dimensions of directed percolation clusters.
Stenull, O; Janssen, H K
2001-07-01
We study nonlinear random resistor diode networks at the transition from the nonpercolating to the directed percolating phase. The resistor-like bonds and the diode-like bonds under forward bias voltage obey a generalized Ohm's law V approximately I(r). Based on general grounds such as symmetries and relevance we develop a field theoretic model. We focus on the average two-port resistance, which is governed at the transition by the resistance exponent straight phi(r). By employing renormalization group methods we calculate straight phi(r) for arbitrary r to one-loop order. Then we address the fractal dimensions characterizing directed percolation clusters. Via considering distinct values of the nonlinearity r, we determine the dimension of the red bonds, the chemical path, and the backbone to two-loop order.
Han, Seong-Ik; Lee, Jang-Myung
2014-01-01
This paper proposes a backstepping control system that uses a tracking error constraint and recurrent fuzzy neural networks (RFNNs) to achieve a prescribed tracking performance for a strict-feedback nonlinear dynamic system. A new constraint variable was defined to generate the virtual control that forces the tracking error to fall within prescribed boundaries. An adaptive RFNN was also used to obtain the required improvement on the approximation performances in order to avoid calculating the explosive number of terms generated by the recursive steps of traditional backstepping control. The boundedness and convergence of the closed-loop system was confirmed based on the Lyapunov stability theory. The prescribed performance of the proposed control scheme was validated by using it to control the prescribed error of a nonlinear system and a robot manipulator.
Non-Linear Behaviour Of Gelatin Networks Reveals A Hierarchical Structure
Yang, Zhi
2015-12-14
We investigate the strain hardening behaviour of various gelatin networks - namely physically-crosslinked gelatin gel, chemically-crosslinked gelatin gels, and a hybrid gels made of a combination of the former two - under large shear deformations using the pre-stress, strain ramp, and large amplitude oscillation shear protocols. Further, the internal structures of physically-crosslinked gelatin gel and chemically-crosslinked gelatin gels were characterized by small angle neutron scattering (SANS) to enable their internal structures to be correlated with their nonlinear rheology. The Kratky plots of SANS data demonstrate the presence of small cross-linked aggregates within the chemically-crosslinked network, whereas in the physically-crosslinked gels a relatively homogeneous structure is observed. Through model fitting to the scattering data, we were able to obtain structural parameters, such as correlation length (ξ), cross-sectional polymer chain radius (Rc), and the fractal dimension (df) of the gel networks. The fractal dimension df obtained from the SANS data of the physically-crosslinked and chemically crosslinked gels is 1.31 and 1.53, respectively. These values are in excellent agreement with the ones obtained from a generalized non-linear elastic theory we used to fit our stress-strain curves. The chemical crosslinking that generates coils and aggregates hinders the free stretching of the triple helices bundles in the physically-crosslinked gels.
Kumar, Rajesh; Srivastava, Smriti; Gupta, J R P
2017-03-01
In this paper adaptive control of nonlinear dynamical systems using diagonal recurrent neural network (DRNN) is proposed. The structure of DRNN is a modification of fully connected recurrent neural network (FCRNN). Presence of self-recurrent neurons in the hidden layer of DRNN gives it an ability to capture the dynamic behaviour of the nonlinear plant under consideration (to be controlled). To ensure stability, update rules are developed using lyapunov stability criterion. These rules are then used for adjusting the various parameters of DRNN. The responses of plants obtained with DRNN are compared with those obtained when multi-layer feed forward neural network (MLFFNN) is used as a controller. Also, in example 4, FCRNN is also investigated and compared with DRNN and MLFFNN. Robustness of the proposed control scheme is also tested against parameter variations and disturbance signals. Four simulation examples including one-link robotic manipulator and inverted pendulum are considered on which the proposed controller is applied. The results so obtained show the superiority of DRNN over MLFFNN as a controller. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Ramoni Marco F
2007-05-01
Full Text Available Abstract Background Reverse engineering cellular networks is currently one of the most challenging problems in systems biology. Dynamic Bayesian networks (DBNs seem to be particularly suitable for inferring relationships between cellular variables from the analysis of time series measurements of mRNA or protein concentrations. As evaluating inference results on a real dataset is controversial, the use of simulated data has been proposed. However, DBN approaches that use continuous variables, thus avoiding the information loss associated with discretization, have not yet been extensively assessed, and most of the proposed approaches have dealt with linear Gaussian models. Results We propose a generalization of dynamic Gaussian networks to accommodate nonlinear dependencies between variables. As a benchmark dataset to test the new approach, we used data from a mathematical model of cell cycle control in budding yeast that realistically reproduces the complexity of a cellular system. We evaluated the ability of the networks to describe the dynamics of cellular systems and their precision in reconstructing the true underlying causal relationships between variables. We also tested the robustness of the results by analyzing the effect of noise on the data, and the impact of a different sampling time. Conclusion The results confirmed that DBNs with Gaussian models can be effectively exploited for a first level analysis of data from complex cellular systems. The inferred models are parsimonious and have a satisfying goodness of fit. Furthermore, the networks not only offer a phenomenological description of the dynamics of cellular systems, but are also able to suggest hypotheses concerning the causal interactions between variables. The proposed nonlinear generalization of Gaussian models yielded models characterized by a slightly lower goodness of fit than the linear model, but a better ability to recover the true underlying connections between
A Comparative Study of Neural Networks and Fuzzy Systems in Modeling of a Nonlinear Dynamic System
Directory of Open Access Journals (Sweden)
Metin Demirtas
2011-07-01
Full Text Available The aim of this paper is to compare the neural networks and fuzzy modeling approaches on a nonlinear system. We have taken Permanent Magnet Brushless Direct Current (PMBDC motor data and have generated models using both approaches. The predictive performance of both methods was compared on the data set for model configurations. The paper describes the results of these tests and discusses the effects of changing model parameters on predictive and practical performance. Modeling sensitivity was used to compare for two methods.
PkANN I: Non-Linear Matter Power Spectrum Estimation through Artificial Neural Networks
Agarwal, Shankar; Feldman, Hume A; Lahav, Ofer; Thomas, Shaun A
2012-01-01
We investigate a new approach to confront small-scale non-linearities in the power spectrum of matter fluctuations. This ever-present and pernicious uncertainty is often the Achilles' heel in cosmological studies and must be reduced if we are to see the advent of precision cosmology in the late-time Universe. We show that an optimally trained Artificial Neural Network (ANN), when presented with a set of cosmological parameters ($\\Omega_{\\rm m} h^2, \\Omega_{\\rm b} h^2, n_s, w_0, \\sigma_8, \\sum m_\
Pre-Trained Neural Networks used for Non-Linear State Estimation
DEFF Research Database (Denmark)
Bayramoglu, Enis; Andersen, Nils Axel; Ravn, Ole
2011-01-01
The paper focuses on nonlinear state estimation assuming non-Gaussian distributions of the states and the disturbances. The posterior distribution and the aposteriori distribution is described by a chosen family of paramtric distributions. The state transformation then results in a transformation...... of the paramters in the distribution. This transformation is approximated by a neural network using offline training, which is based on monte carlo sampling. In the paper, there will also be presented a method to construct a flexible distributions well suited for covering the effect of the non...
Directory of Open Access Journals (Sweden)
Lijun Zhang
2014-01-01
Full Text Available An integral-differential model equation arising from neuronal networks with very general kernel functions is considered in this paper. The kernel functions we study here include pure excitations, lateral inhibition, lateral excitations, and more general synaptic couplings (e.g., oscillating kernel functions. The main goal of this paper is to prove the existence and uniqueness of the traveling wave front solutions. The main idea we apply here is to reduce the nonlinear integral-differential equation into a solvable differential equation and test whether the solution we get is really a wave front solution of the model equation.
Arlunno, Valeria; Zhang, Xu; Larsen, Knud J; Zibar, Darko; Monroy, Idelfonso Tafur
2011-12-12
An experimental demonstration of Ultradense WDM with advanced digital signal processing is presented. The scheme proposed allows the use of independent tunable DFB lasers spaced at 12.5 GHz for ultradense WDM PM-QPSK flexible capacity channels for metro core networking. To allocate extremely closed carriers, we demonstrate that a digital non-linear equalization allow to mitigate inter-channel interference and improve overall system performance in terms of OSNR. Evaluation of the algorithm and comparison with an ultradense WDM system with coherent carriers generated from a single laser are also reported. © 2011 Optical Society of America
DEFF Research Database (Denmark)
Arlunno, Valeria; Zhang, Xu; Larsen, Knud J.
2011-01-01
An experimental demonstration of Ultradense WDM with advanced digital signal processing is presented. The scheme proposed allows the use of independent tunable DFB lasers spaced at 12.5 GHz for ultradense WDM PM-QPSK flexible capacity channels for metro core networking. To allocate extremely closed...... carriers, we demonstrate that a digital non-linear equalization allow to mitigate inter-channel interference and improve overall system performance in terms of OSNR. Evaluation of the algorithm and comparison with an ultradense WDM system with coherent carriers generated from a single laser are also...
Nonlinear modelling of a SOFC stack by improved neural networks identification
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far, most existing models are based on conversion laws, which are too complicated to be applied to design a control system. To facilitate a valid control strategy design, this paper tries to avoid the internal complexities and presents a modelling study of SOFC performance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of modelling, the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations, whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore, it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model.
On the Calculation of System Entropy in Nonlinear Stochastic Biological Networks
Directory of Open Access Journals (Sweden)
Bor-Sen Chen
2015-10-01
Full Text Available Biological networks are open systems that can utilize nutrients and energy from their environment for use in their metabolic processes, and produce metabolic products. System entropy is defined as the difference between input and output signal entropy, i.e., the net signal entropy of the biological system. System entropy is an important indicator for living or non-living biological systems, as biological systems can maintain or decrease their system entropy. In this study, system entropy is determined for the first time for stochastic biological networks, and a computation method is proposed to measure the system entropy of nonlinear stochastic biological networks that are subject to intrinsic random fluctuations and environmental disturbances. We find that intrinsic random fluctuations could increase the system entropy, and that the system entropy is inversely proportional to the robustness and stability of the biological networks. It is also determined that adding feedback loops to shift all eigenvalues to the farther left-hand plane of the complex s-domain could decrease the system entropy of a biological network.
Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks
Jiang, Fei-Bo; Dai, Qian-Wei; Dong, Li
2016-06-01
Conventional artificial neural networks used to solve electrical resistivity imaging (ERI) inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network (PBNN) nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter α k , which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion.
Recurrence networks-a novel paradigm for nonlinear time series analysis
Energy Technology Data Exchange (ETDEWEB)
Donner, Reik V [Max Planck Institute for Physics of Complex Systems, Dresden (Germany); Zou Yong; Donges, Jonathan F; Marwan, Norbert; Kurths, Juergen [Potsdam Institute for Climate Impact Research, Potsdam (Germany)], E-mail: donner@vwi.tu-dresden.de
2010-03-15
This paper presents a new approach for analysing the structural properties of time series from complex systems. Starting from the concept of recurrences in phase space, the recurrence matrix of a time series is interpreted as the adjacency matrix of an associated complex network, which links different points in time if the considered states are closely neighboured in phase space. In comparison with similar network-based techniques the new approach has important conceptual advantages, and can be considered as a unifying framework for transforming time series into complex networks that also includes other existing methods as special cases. It has been demonstrated here that there are fundamental relationships between many topological properties of recurrence networks and different nontrivial statistical properties of the phase space density of the underlying dynamical system. Hence, this novel interpretation of the recurrence matrix yields new quantitative characteristics (such as average path length, clustering coefficient, or centrality measures of the recurrence network) related to the dynamical complexity of a time series, most of which are not yet provided by other existing methods of nonlinear time series analysis.
Ondra, V.; Sever, I. A.; Schwingshackl, C. W.
2017-01-01
This paper presents a method for detection and characterisation of structural non-linearities from a single frequency response function using the Hilbert transform in the frequency domain and artificial neural networks. A frequency response function is described based on its Hilbert transform using several common and newly introduced scalar parameters, termed non-linearity indexes, to create training data of the artificial neural network. This network is subsequently used to detect the existence of non-linearity and classify its type. The theoretical background of the method is given and its usage is demonstrated on different numerical test cases created by single degree of freedom non-linear systems and a lumped parameter multi degree of freedom system with a geometric non-linearity. The method is also applied to several experimentally measured frequency response functions obtained from a cantilever beam with a clearance non-linearity and an under-platform damper experimental rig with a complex friction contact interface. It is shown that the method is a fast and noise-robust means of detecting and characterising non-linear behaviour from a single frequency response function.
Institute of Scientific and Technical Information of China (English)
SHI Shi-liang; LIU Hai-bo; LIU Ai-hua
2004-01-01
Based on the integration analysis of goods and shortcomings of various methods used in safety assessment of coal mines, combining nonlinear feature of mine safety sub-system, this paper establishes the neural network assessment model of mine safety, analyzes the ability of artificial neural network to evaluate mine safety state, and lays the theoretical foundation of artificial neural network using in the systematic optimization of mine safety assessment and getting reasonable accurate safety assessment result.
Designing a Fresh Food Supply Chain Network: An Application of Nonlinear Programming
Directory of Open Access Journals (Sweden)
Yu-Chung Tsao
2013-01-01
Full Text Available In today’s business environment, many fresh food companies have complex supply networks to distribute their products. For example, agricultural products are distributed through a multiechelon supply chain which includes agricultural association, agricultural produce marketing corporations (APMCs, markets, and so forth. In this paper a fresh produce supply network model is designed to determine the optimal service area for APMCs, the replenishment cycle time of APMCs, and the freshness-keeping effort, while maximizing the total profit. The objective is to address the integrated facility location, inventory allocation, and freshness-keeping effort problems. This paper develops an algorithm to solve the nonlinear problem, provides numerical analysis to illustrate the proposed solution procedure, and discusses the effects of various system parameters on the decisions and total profits. A real case of an agricultural product supply chain in Taiwan is used to verify the model. Results of this study can serve as a reference for business managers and administrators.
Robust MPC for a non-linear system - a neural network approach
Luzar, Marcel; Witczak, Marcin
2014-12-01
The aim of the paper is to design a robust actuator fault-tolerant control for a non-linear discrete-time system. Considered system is described by the Linear Parameter-Varying (LPV) model obtained with recurrent neural network. The proposed solution starts with a discretetime quasi-LPV system identification using artificial neural network. Subsequently, the robust controller is proposed, which does not take into account actuator saturation level and deals with the previously estimated faults. To check if the compensation problem is feasible, the robust invariant set is employed, which takes into account actuator saturation level. When the current state does not belong to the set, then a predictive control is performed in order to make such set larger. This makes it possible to increase the domain of attraction, which makes the proposed methodology an efficient solution for the fault-tolerant control. The last part of the paper presents an experimental results regarding wind turbines.
A new cellular nonlinear network emulation on FPGA for EEG signal processing in epilepsy
Müller, Jens; Müller, Jan; Tetzlaff, Ronald
2011-05-01
For processing of EEG signals, we propose a new architecture for the hardware emulation of discrete-time Cellular Nonlinear Networks (DT-CNN). Our results show the importance of a high computational accuracy in EEG signal prediction that cannot be achieved with existing analogue VLSI circuits. The refined architecture of the processing elements and its resource schedule, the cellular network structure with local couplings, the FPGA-based embedded system containing the DT-CNN, and the data flow in the entire system will be discussed in detail. The proposed DT-CNN design has been implemented and tested on an Xilinx FPGA development platform. The embedded co-processor with a multi-threading kernel is utilised for control and pre-processing tasks and data exchange to the host via Ethernet. The performance of the implemented DT-CNN has been determined for a popular example and compared to that of a conventional computer.
Directory of Open Access Journals (Sweden)
Qihong Chen
2014-01-01
Full Text Available This paper presents a neural network predictive control strategy to optimize power distribution for a fuel cell/ultracapacitor hybrid power system of a robot. We model the nonlinear power system by employing time variant auto-regressive moving average with exogenous (ARMAX, and using recurrent neural network to represent the complicated coefficients of the ARMAX model. Because the dynamic of the system is viewed as operating- state- dependent time varying local linear behavior in this frame, a linear constrained model predictive control algorithm is developed to optimize the power splitting between the fuel cell and ultracapacitor. The proposed algorithm significantly simplifies implementation of the controller and can handle multiple constraints, such as limiting substantial fluctuation of fuel cell current. Experiment and simulation results demonstrate that the control strategy can optimally split power between the fuel cell and ultracapacitor, limit the change rate of the fuel cell current, and so as to extend the lifetime of the fuel cell.
Chen, Qihong; Long, Rong; Quan, Shuhai; Zhang, Liyan
2014-01-01
This paper presents a neural network predictive control strategy to optimize power distribution for a fuel cell/ultracapacitor hybrid power system of a robot. We model the nonlinear power system by employing time variant auto-regressive moving average with exogenous (ARMAX), and using recurrent neural network to represent the complicated coefficients of the ARMAX model. Because the dynamic of the system is viewed as operating- state- dependent time varying local linear behavior in this frame, a linear constrained model predictive control algorithm is developed to optimize the power splitting between the fuel cell and ultracapacitor. The proposed algorithm significantly simplifies implementation of the controller and can handle multiple constraints, such as limiting substantial fluctuation of fuel cell current. Experiment and simulation results demonstrate that the control strategy can optimally split power between the fuel cell and ultracapacitor, limit the change rate of the fuel cell current, and so as to extend the lifetime of the fuel cell.
The adaptive control using BP networks for a nonlinear servo-motor
Institute of Scientific and Technical Information of China (English)
Xinliang ZHANG; Yonghong TAN
2008-01-01
The servo-motor possesses a strongly nonlinear property due to the effect of the stimulating input voltageload-torque and environmental operating conditions.So it is rather diffcult to derive a traditional mathematical model which is capable of expressing both its dynamics and steady-state characteristics.A neural network-based adaptive control strategy is proposed in this paper.In this method,two neural networks have been adopted for system identification(NNI)and control(NNC),respectively.Then,the commonly-used specialized learning has been modified,by taking the NNI output as the approximation output of the servo-motor during the weights training to get sensitivity information.Moreover,the rule for choosing the learning rate is given on the basis of the analysis of Lyapunov stability.Finally,an example of applying the proposed control strategy on a servo-motor is presented to show its effectiveness.
Burioni, Raffaella; di Santo, Serena; di Volo, Matteo; Vezzani, Alessandro
2014-10-01
Self-organized quasiperiodicity is one of the most puzzling dynamical phases observed in systems of nonlinear coupled oscillators. The single dynamical units are not locked to the periodic mean field they produce, but they still feature a coherent behavior, through an unexplained complex form of correlation. We consider a class of leaky integrate-and-fire oscillators on random sparse and massive networks with dynamical synapses, featuring self-organized quasiperiodicity, and we show how complex collective oscillations arise from constructive interference of microscopic dynamics. In particular, we find a simple quantitative relationship between two relevant microscopic dynamical time scales and the macroscopic time scale of the global signal. We show that the proposed relation is a general property of collective oscillations, common to all the partially synchronous dynamical phases analyzed. We argue that an analogous mechanism could be at the origin of similar network dynamics.
A Decentralized Approach for Nonlinear Prediction of Time Series Data in Sensor Networks
Directory of Open Access Journals (Sweden)
Richard Cédric
2010-01-01
Full Text Available Wireless sensor networks rely on sensor devices deployed in an environment to support sensing and monitoring, including temperature, humidity, motion, and acoustic. Here, we propose a new approach to model physical phenomena and track their evolution by taking advantage of the recent developments of pattern recognition for nonlinear functional learning. These methods are, however, not suitable for distributed learning in sensor networks as the order of models scales linearly with the number of deployed sensors and measurements. In order to circumvent this drawback, we propose to design reduced order models by using an easy to compute sparsification criterion. We also propose a kernel-based least-mean-square algorithm for updating the model parameters using data collected by each sensor. The relevance of our approach is illustrated by two applications that consist of estimating a temperature distribution and tracking its evolution over time.
Nonlinearly Activated Neural Network for Solving Time-Varying Complex Sylvester Equation.
Li, Shuai; Li, Yangming
2013-10-28
The Sylvester equation is often encountered in mathematics and control theory. For the general time-invariant Sylvester equation problem, which is defined in the domain of complex numbers, the Bartels-Stewart algorithm and its extensions are effective and widely used with an O(n³) time complexity. When applied to solving the time-varying Sylvester equation, the computation burden increases intensively with the decrease of sampling period and cannot satisfy continuous realtime calculation requirements. For the special case of the general Sylvester equation problem defined in the domain of real numbers, gradient-based recurrent neural networks are able to solve the time-varying Sylvester equation in real time, but there always exists an estimation error while a recently proposed recurrent neural network by Zhang et al [this type of neural network is called Zhang neural network (ZNN)] converges to the solution ideally. The advancements in complex-valued neural networks cast light to extend the existing real-valued ZNN for solving the time-varying real-valued Sylvester equation to its counterpart in the domain of complex numbers. In this paper, a complex-valued ZNN for solving the complex-valued Sylvester equation problem is investigated and the global convergence of the neural network is proven with the proposed nonlinear complex-valued activation functions. Moreover, a special type of activation function with a core function, called sign-bi-power function, is proven to enable the ZNN to converge in finite time, which further enhances its advantage in online processing. In this case, the upper bound of the convergence time is also derived analytically. Simulations are performed to evaluate and compare the performance of the neural network with different parameters and activation functions. Both theoretical analysis and numerical simulations validate the effectiveness of the proposed method.
Dynamic learning from adaptive neural network control of a class of nonaffine nonlinear systems.
Dai, Shi-Lu; Wang, Cong; Wang, Min
2014-01-01
This paper studies the problem of learning from adaptive neural network (NN) control of a class of nonaffine nonlinear systems in uncertain dynamic environments. In the control design process, a stable adaptive NN tracking control design technique is proposed for the nonaffine nonlinear systems with a mild assumption by combining a filtered tracking error with the implicit function theorem, input-to-state stability, and the small-gain theorem. The proposed stable control design technique not only overcomes the difficulty in controlling nonaffine nonlinear systems but also relaxes constraint conditions of the considered systems. In the learning process, the partial persistent excitation (PE) condition of radial basis function NNs is satisfied during tracking control to a recurrent reference trajectory. Under the PE condition and an appropriate state transformation, the proposed adaptive NN control is shown to be capable of acquiring knowledge on the implicit desired control input dynamics in the stable control process and of storing the learned knowledge in memory. Subsequently, an NN learning control design technique that effectively exploits the learned knowledge without re-adapting to the controller parameters is proposed to achieve closed-loop stability and improved control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed design techniques.
Directory of Open Access Journals (Sweden)
Mohammad Reza Zakerzadeh
2011-01-01
Full Text Available Preisach model is a well-known hysteresis identification method in which the hysteresis is modeled by linear combination of hysteresis operators. Although Preisach model describes the main features of system with hysteresis behavior, due to its rigorous numerical nature, it is not convenient to use in real-time control applications. Here a novel neural network approach based on the Preisach model is addressed, provides accurate hysteresis nonlinearity modeling in comparison with the classical Preisach model and can be used for many applications such as hysteresis nonlinearity control and identification in SMA and Piezo actuators and performance evaluation in some physical systems such as magnetic materials. To evaluate the proposed approach, an experimental apparatus consisting one-dimensional flexible aluminum beam actuated with an SMA wire is used. It is shown that the proposed ANN-based Preisach model can identify hysteresis nonlinearity more accurately than the classical one. It also has powerful ability to precisely predict the higher-order hysteresis minor loops behavior even though only the first-order reversal data are in use. It is also shown that to get the same precise results in the classical Preisach model, many more data should be used, and this directly increases the experimental cost.
Distress Propagation in Complex Networks: The Case of Non-Linear DebtRank.
Bardoscia, Marco; Caccioli, Fabio; Perotti, Juan Ignacio; Vivaldo, Gianna; Caldarelli, Guido
2016-01-01
We consider a dynamical model of distress propagation on complex networks, which we apply to the study of financial contagion in networks of banks connected to each other by direct exposures. The model that we consider is an extension of the DebtRank algorithm, recently introduced in the literature. The mechanics of distress propagation is very simple: When a bank suffers a loss, distress propagates to its creditors, who in turn suffer losses, and so on. The original DebtRank assumes that losses are propagated linearly between connected banks. Here we relax this assumption and introduce a one-parameter family of non-linear propagation functions. As a case study, we apply this algorithm to a data-set of 183 European banks, and we study how the stability of the system depends on the non-linearity parameter under different stress-test scenarios. We find that the system is characterized by a transition between a regime where small shocks can be amplified and a regime where shocks do not propagate, and that the overall stability of the system increases between 2008 and 2013.
Fuzzy Wavelet Neural Network Using a Correntropy Criterion for Nonlinear System Identification
Directory of Open Access Journals (Sweden)
Leandro L. S. Linhares
2015-01-01
Full Text Available Recent researches have demonstrated that the Fuzzy Wavelet Neural Networks (FWNNs are an efficient tool to identify nonlinear systems. In these structures, features related to fuzzy logic, wavelet functions, and neural networks are combined in an architecture similar to the Adaptive Neurofuzzy Inference Systems (ANFIS. In practical applications, the experimental data set used in the identification task often contains unknown noise and outliers, which decrease the FWNN model reliability. In order to reduce the negative effects of these erroneous measurements, this work proposes the direct use of a similarity measure based on information theory in the FWNN learning procedure. The Mean Squared Error (MSE cost function is replaced by the Maximum Correntropy Criterion (MCC in the traditional error backpropagation (BP algorithm. The input-output maps of a real nonlinear system studied in this work are identified from an experimental data set corrupted by different outliers rates and additive white Gaussian noise. The results demonstrate the advantages of the proposed cost function using the MCC as compared to the MSE. This work also investigates the influence of the kernel size on the performance of the MCC in the BP algorithm, since it is the only free parameter of correntropy.
Miao, Zhiyong; Shi, Hongyang; Zhang, Yi; Xu, Fan
2017-10-01
In this paper, a new variational Bayesian adaptive cubature Kalman filter (VBACKF) is proposed for nonlinear state estimation. Although the conventional VBACKF performs better than cubature Kalman filtering (CKF) in solving nonlinear systems with time-varying measurement noise, its performance may degrade due to the uncertainty of the system model. To overcome this drawback, a multilayer feed-forward neural network (MFNN) is used to aid the conventional VBACKF, generalizing it to attain higher estimation accuracy and robustness. In the proposed neural-network-aided variational Bayesian adaptive cubature Kalman filter (NN-VBACKF), the MFNN is used to turn the state estimation of the VBACKF adaptively, and it is used for both state estimation and in the online training paradigm simultaneously. To evaluate the performance of the proposed method, it is compared with CKF and VBACKF via target tracking problems. The simulation results demonstrate that the estimation accuracy and robustness of the proposed method are better than those of the CKF and VBACKF.
Nonlinear model identification and adaptive model predictive control using neural networks.
Akpan, Vincent A; Hassapis, George D
2011-04-01
This paper presents two new adaptive model predictive control algorithms, both consisting of an on-line process identification part and a predictive control part. Both parts are executed at each sampling instant. The predictive control part of the first algorithm is the Nonlinear Model Predictive Control strategy and the control part of the second algorithm is the Generalized Predictive Control strategy. In the identification parts of both algorithms the process model is approximated by a series-parallel neural network structure which is trained by a recursive least squares (ARLS) method. The two control algorithms have been applied to: 1) the temperature control of a fluidized bed furnace reactor (FBFR) of a pilot plant and 2) the auto-pilot control of an F-16 aircraft. The training and validation data of the neural network are obtained from the open-loop simulation of the FBFR and the nonlinear F-16 aircraft models. The identification and control simulation results show that the first algorithm outperforms the second one at the expense of extra computation time.
Moradi, Hojjatullah; Majd, Vahid Johari
2016-05-01
In this paper, the problem of robust stability of nonlinear genetic regulatory networks (GRNs) is investigated. The developed method is an integral sliding mode control based redesign for a class of perturbed dissipative switched GRNs with time delays. The control law is redesigned by modifying the dissipativity-based control law that was designed for the unperturbed GRNs with time delays. The switched GRNs are switched from one mode to another based on time, state, etc. Although, the active subsystem is known in any instance, but the switching law and the transition probabilities are not known. The model for each mode is considered affine with matched and unmatched perturbations. The redesigned control law forces the GRN to always remain on the sliding surface and the dissipativity is maintained from the initial time in the presence of the norm-bounded perturbations. The global stability of the perturbed GRNs is maintained if the unperturbed model is globally dissipative. The designed control law for the perturbed GRNs guarantees robust exponential or asymptotic stability of the closed-loop network depending on the type of stability of the unperturbed model. The results are applied to a nonlinear switched GRN, and its convergence to the origin is verified by simulation.
Finite-horizon control-constrained nonlinear optimal control using single network adaptive critics.
Heydari, Ali; Balakrishnan, Sivasubramanya N
2013-01-01
To synthesize fixed-final-time control-constrained optimal controllers for discrete-time nonlinear control-affine systems, a single neural network (NN)-based controller called the Finite-horizon Single Network Adaptive Critic is developed in this paper. Inputs to the NN are the current system states and the time-to-go, and the network outputs are the costates that are used to compute optimal feedback control. Control constraints are handled through a nonquadratic cost function. Convergence proofs of: 1) the reinforcement learning-based training method to the optimal solution; 2) the training error; and 3) the network weights are provided. The resulting controller is shown to solve the associated time-varying Hamilton-Jacobi-Bellman equation and provide the fixed-final-time optimal solution. Performance of the new synthesis technique is demonstrated through different examples including an attitude control problem wherein a rigid spacecraft performs a finite-time attitude maneuver subject to control bounds. The new formulation has great potential for implementation since it consists of only one NN with single set of weights and it provides comprehensive feedback solutions online, though it is trained offline.
2016-01-01
Photovoltaic (PV) systems have non-linear characteristics that generate maximum power at one particular operating point. Environmental factors such as irradiance and temperature variations greatly affect the maximum power point (MPP). Diverse offline and online techniques have been introduced for tracking the MPP. Here, to track the MPP, an augmented-state feedback linearized (AFL) non-linear controller combined with an artificial neural network (ANN) is proposed. This approach linearizes the...
Video-based convolutional neural networks for activity recognition from robot-centric videos
Ryoo, M. S.; Matthies, Larry
2016-05-01
In this evaluation paper, we discuss convolutional neural network (CNN)-based approaches for human activity recognition. In particular, we investigate CNN architectures designed to capture temporal information in videos and their applications to the human activity recognition problem. There have been multiple previous works to use CNN-features for videos. These include CNNs using 3-D XYT convolutional filters, CNNs using pooling operations on top of per-frame image-based CNN descriptors, and recurrent neural networks to learn temporal changes in per-frame CNN descriptors. We experimentally compare some of these different representatives CNNs while using first-person human activity videos. We especially focus on videos from a robots viewpoint, captured during its operations and human-robot interactions.
Institute of Scientific and Technical Information of China (English)
CHENMou; JIANGChang-sheng; CHENWen-hua
2004-01-01
A new decentralized robust control method is discussed for a class of nonlinear interconnected largescale system with unknown bounded disturbance and unknown nonlinear function term. A decentralized control law is proposed which combines the approximation method of neural network with sliding mode control. The decentralized controller consists of an equivalent controller and an adaptive sliding mode controller. The sliding mode controller is a robust controller used to reduce the track error of the control system. The neural networks are used to approximate the unknown nonlinear functions, meanwhile the approximation errors of the neural networks are applied to the weight value updated law to improve performance of the system. Finally, an example demonstrates the availability of the decentralized control method.
Zhang, Bo
The past decade has witnessed astounding boom in telecommunication network traffic. With the emergence of multimedia over Internet, the high-capacity optical transport systems have started to shift focus from the core network towards the end users. This trend leads to diverse optical networks with transparency and reconfigurability requirement. As single channel data rate continues to increase and channel spacing continues to shrink for high capacity, high spectral efficiency, the workload on conventional electronic signal processing elements in the router nodes continues to build up. Performing signal processing functions in the optical domain can potentially alleviate the speed bottleneck if the unique optical properties are efficiently leveraged to assist electronic processing methodologies. Ultra-high bandwidth capability along with the promise for multi-channel and format-transparent operation make optical signal processing an attractive technology which is expected to have great impact on future optical networks. For optical signal processing applications in fiber-optic network and systems, a laudable goal would be to explore the unique nonlinear optical processes in novel photonic devices. This dissertation investigates novel optical signal processing techniques through simulations and experimental demonstrations, analyzes limitations of these nonlinear processing elements and proposes techniques to enhance the system performance or designs for functional photonic modules. Two key signal-processing building blocks for future optical networks, namely slow-light-based tunable optical delay lines and SOA-based high-speed wavelength converters, are presented in the first part of the dissertation. Phase preserving and spectrally efficient slow light are experimentally demonstrated using advanced modulation formats. Functional and novel photonic modules, such as multi-channel synchronizer and variable-bit-rate optical time division multiplexer are designed and
Directory of Open Access Journals (Sweden)
Fei Chen
2013-01-01
Full Text Available This paper deals with the finite-time stabilization problem for discrete-time Markov jump nonlinear systems with time delays and norm-bounded exogenous disturbance. The nonlinearities in different jump modes are parameterized by neural networks. Subsequently, a linear difference inclusion state space representation for a class of neural networks is established. Based on this, sufficient conditions are derived in terms of linear matrix inequalities to guarantee stochastic finite-time boundedness and stochastic finite-time stabilization of the closed-loop system. A numerical example is illustrated to verify the efficiency of the proposed technique.
Bouchard, M
2001-01-01
In recent years, a few articles describing the use of neural networks for nonlinear active control of sound and vibration were published. Using a control structure with two multilayer feedforward neural networks (one as a nonlinear controller and one as a nonlinear plant model), steepest descent algorithms based on two distinct gradient approaches were introduced for the training of the controller network. The two gradient approaches were sometimes called the filtered-x approach and the adjoint approach. Some recursive-least-squares algorithms were also introduced, using the adjoint approach. In this paper, an heuristic procedure is introduced for the development of recursive-least-squares algorithms based on the filtered-x and the adjoint gradient approaches. This leads to the development of new recursive-least-squares algorithms for the training of the controller neural network in the two networks structure. These new algorithms produce a better convergence performance than previously published algorithms. Differences in the performance of algorithms using the filtered-x and the adjoint gradient approaches are discussed in the paper. The computational load of the algorithms discussed in the paper is evaluated for multichannel systems of nonlinear active control. Simulation results are presented to compare the convergence performance of the algorithms, showing the convergence gain provided by the new algorithms.
Santosa, H.; Hobara, Y.
2017-01-01
The electric field amplitude of very low frequency (VLF) transmitter from Hawaii (NPM) has been continuously recorded at Chofu (CHF), Tokyo, Japan. The VLF amplitude variability indicates lower ionospheric perturbation in the D region (60-90 km altitude range) around the NPM-CHF propagation path. We carried out the prediction of daily nighttime mean VLF amplitude by using Nonlinear Autoregressive with Exogenous Input Neural Network (NARX NN). The NARX NN model, which was built based on the daily input variables of various physical parameters such as stratospheric temperature, total column ozone, cosmic rays, Dst, and Kp indices possess good accuracy during the model building. The fitted model was constructed within the training period from 1 January 2011 to 4 February 2013 by using three algorithms, namely, Bayesian Neural Network (BRANN), Levenberg Marquardt Neural Network (LMANN), and Scaled Conjugate Gradient (SCG). The LMANN has the largest Pearson correlation coefficient (r) of 0.94 and smallest root-mean-square error (RMSE) of 1.19 dB. The constructed models by using LMANN were applied to predict the VLF amplitude from 5 February 2013 to 31 December 2013. As a result the one step (1 day) ahead predicted nighttime VLF amplitude has the r of 0.93 and RMSE of 2.25 dB. We conclude that the model built according to the proposed methodology provides good predictions of the electric field amplitude of VLF waves for NPM-CHF (midlatitude) propagation path.
Men, Zhongxian; Yee, Eugene; Lien, Fue-Sang; Yang, Zhiling; Liu, Yongqian
2014-01-01
Short-term wind speed and wind power forecasts (for a 72 h period) are obtained using a nonlinear autoregressive exogenous artificial neural network (ANN) methodology which incorporates either numerical weather prediction or high-resolution computational fluid dynamics wind field information as an exogenous input. An ensemble approach is used to combine the predictions from many candidate ANNs in order to provide improved forecasts for wind speed and power, along with the associated uncertainties in these forecasts. More specifically, the ensemble ANN is used to quantify the uncertainties arising from the network weight initialization and from the unknown structure of the ANN. All members forming the ensemble of neural networks were trained using an efficient particle swarm optimization algorithm. The results of the proposed methodology are validated using wind speed and wind power data obtained from an operational wind farm located in Northern China. The assessment demonstrates that this methodology for wind speed and power forecasting generally provides an improvement in predictive skills when compared to the practice of using an "optimal" weight vector from a single ANN while providing additional information in the form of prediction uncertainty bounds.
Sahoo, Avimanyu; Jagannathan, Sarangapani
2017-02-01
In this paper, an event-driven stochastic adaptive dynamic programming (ADP)-based technique is introduced for nonlinear systems with a communication network within its feedback loop. A near optimal control policy is designed using an actor-critic framework and ADP with event sampled state vector. First, the system dynamics are approximated by using a novel neural network (NN) identifier with event sampled state vector. The optimal control policy is generated via an actor NN by using the NN identifier and value function approximated by a critic NN through ADP. The stochastic NN identifier, actor, and critic NN weights are tuned at the event sampled instants leading to aperiodic weight tuning laws. Above all, an adaptive event sampling condition based on estimated NN weights is designed by using the Lyapunov technique to ensure ultimate boundedness of all the closed-loop signals along with the approximation accuracy. The net result is event-driven stochastic ADP technique that can significantly reduce the computation and network transmissions. Finally, the analytical design is substantiated with simulation results.
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
A new type controller, BP neural-networks-based sliding mode controller is developed for a class of large-scale nonlinear systems with unknown bounds of high-order interconnections in this paper. It is shown that decentralized BP neural networks are used to adaptively learn the uncertainty bounds of interconnected subsystems in the Lyapunov sense, and the outputs of the decentralized BP neural networks are then used as the parameters of the sliding mode controller to compensate for the effects of subsystems uncertainties. Using this scheme, not only strong robustness with respect to uncertainty dynamics and nonlinearities can be obtained, but also the output tracking error between the actual output of each subsystem and the corresponding desired reference output can asymptotically converge to zero. A simulation example is presented to support the validity of the proposed BP neural-networks-based sliding mode controller.
A Neural-Network-Based Nonlinear Adaptive State-Observer for Pressurized Water Reactors
Directory of Open Access Journals (Sweden)
Zhe Dong
2013-10-01
Full Text Available Although there have been some severe nuclear accidents such as Three Mile Island (USA, Chernobyl (Ukraine and Fukushima (Japan, nuclear fission energy is still a source of clean energy that can substitute for fossil fuels in a centralized way and in a great amount with commercial availability and economic competitiveness. Since the pressurized water reactor (PWR is the most widely used nuclear fission reactor, its safe, stable and efficient operation is meaningful to the current rebirth of the nuclear fission energy industry. Power-level regulation is an important technique which can deeply affect the operation stability and efficiency of PWRs. Compared with the classical power-level controllers, the advanced power-level regulators could strengthen both the closed-loop stability and control performance by feeding back the internal state-variables. However, not all of the internal state variables of a PWR can be obtained directly by measurements. To implement advanced PWR power-level control law, it is necessary to develop a state-observer to reconstruct the unmeasurable state-variables. Since a PWR is naturally a complex nonlinear system with parameters varying with power-level, fuel burnup, xenon isotope production, control rod worth and etc., it is meaningful to design a nonlinear observer for the PWR with adaptability to system uncertainties. Due to this and the strong learning capability of the multi-layer perceptron (MLP neural network, an MLP-based nonlinear adaptive observer is given for PWRs. Based upon Lyapunov stability theory, it is proved theoretically that this newly-built observer can provide bounded and convergent state-observation. This observer is then applied to the state-observation of a special PWR, i.e., the nuclear heating reactor (NHR, and numerical simulation results not only verify its feasibility but also give the relationship between the observation performance and observer parameters.
A Neural Network Based Hybrid Mixture Model to Extract Information from Non-linear Mixed Pixels
Directory of Open Access Journals (Sweden)
Uttam Kumar
2012-09-01
Full Text Available Signals acquired by sensors in the real world are non-linear combinations, requiring non-linear mixture models to describe the resultant mixture spectra for the endmember’s (pure pixel’s distribution. This communication discusses inferring class fraction through a novel hybrid mixture model (HMM. HMM is a three-step process, where the endmembers are first derived from the images themselves using the N-FINDR algorithm. These endmembers are used by the linear mixture model (LMM in the second step that provides an abundance estimation in a linear fashion. Finally, the abundance values along with the training samples representing the actual ground proportions are fed into neural network based multi-layer perceptron (MLP architecture as input to train the neurons. The neural output further refines the abundance estimates to account for the non-linear nature of the mixing classes of interest. HMM is first implemented and validated on simulated hyper spectral data of 200 bands and subsequently on real time MODIS data with a spatial resolution of 250 m. The results on computer simulated data show that the method gives acceptable results for unmixing pixels with an overall RMSE of 0.0089 ± 0.0022 with LMM and 0.0030 ± 0.0001 with the HMM when compared to actual class proportions. The unmixed MODIS images showed overall RMSE with HMM as 0.0191 ± 0.022 as compared to the LMM output considered alone that had an overall RMSE of 0.2005 ± 0.41, indicating that individual class abundances obtained from HMM are very close to the real observations.
Modeling and Stability Analysis for Non-linear Network Control System Based on T-S Fuzzy Model
Institute of Scientific and Technical Information of China (English)
ZHANG Hong; FANG Huajing
2007-01-01
Based on the T-S fuzzy model, this paper presents a new model of non-linear network control system with stochastic transfer delay. Sufficient criterion is proposed to guarantee globally asymptotically stability of this two-levels T-S fuzzy model. Also a T-S fuzzy observer of NCS is designed base on this two-levels T-S fuzzy model. All these results present a new approach for networked control system analysis and design.
Neural networks for emulation variational method for data assimilation in nonlinear dynamics
Energy Technology Data Exchange (ETDEWEB)
Morais Furtado, Helaine Cristina; Fraga de Campos Velho, Haroldo; Macau, Elbert E N, E-mail: helaine.furtado@lac.inpe.br, E-mail: haroldo@lac.inpe.br, E-mail: elbert@lac.inpe.br [Laboratorio Associado de Computacao e Matematica Aplicada, Sao Jose dos Campos (Brazil)
2011-03-01
Description of a physical phenomenon through differential equations has errors involved, since the mathematical model is always an approximation of reality. For an operational prediction system, one strategy to improve the prediction is to add some information from the real dynamics into mathematical model. This additional information consists of observations on the phenomenon. However, the observational data insertion should be done carefully, for avoiding a worse performance of the prediction. Technical data assimilation are tools to combine data from physical-mathematics model with observational data to obtain a better forecast. The goal of this work is to present the performance of the Neural Network Multilayer Perceptrons trained to emulate a Variational method in context of data assimilation. Techniques for data assimilation are applied for the Lorenz systems; which presents a strong nonlinearity and chaotic nature.
Karabiber, Fethullah; Vecchio, Pietro; Grassi, Giuseppe
2011-12-01
The Bio-inspired (Bi-i) Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN) paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Linear and Nonlinear Electrical Models of Neurons for Hopfield Neural Network
Sarwar, Farah; Iqbal, Shaukat; Hussain, Muhammad Waqar
2016-11-01
A novel electrical model of neuron is proposed in this presentation. The suggested neural network model has linear/nonlinear input-output characteristics. This new deterministic model has joint biological properties in excellent agreement with the earlier deterministic neuron model of Hopfield and Tank and to the stochastic neuron model of McCulloch and Pitts. It is an accurate portrayal of differential equation presented by Hopfield and Tank to mimic neurons. Operational amplifiers, resistances, capacitor, and diodes are used to design this system. The presented biological model of neurons remains to be advantageous for simulations. Impulse response is studied and conferred to certify the stability and strength of this innovative model. A simple illustration is mapped to demonstrate the exactness of the intended system. Precisely mapped illustration exhibits 100 % accurate results.
Optimal Control of Nonlinear Hydraulic Networks in the Presence of Disturbance
DEFF Research Database (Denmark)
Tahavori, Maryamsadat; Leth, John-Josef; Kallesøe, Carsten;
2014-01-01
Water leakage is an important component of water loss. Many methods have emerged from urban water supply systems for leakage control, but it still remains a challenge in many countries. Pressure management is an effective way to reduce the leakage in a system. It can also reduce the power consump...... control problem is the interior point method. The method which is used in this paper can be used for a general hydraulic networks to optimize the leakage and energy consumption and to satisfy the demands at the end-users....... consumption. To this end, an optimal control strategy is proposed in this paper. In the water supply system model, the hydraulic resistance of the valve is estimated by the real data from a water supply system and it is considered to be a disturbance. The method which is used to solve the nonlinear optimal...
Adaptive output feedback control for nonlinear time-delay systems using neural network
Institute of Scientific and Technical Information of China (English)
Weisheng CHEN; Junmin LI
2006-01-01
This paper extends the adaptive neural network (NN) control approaches to a class of unknown output feedback nonlinear time-delay systems. An adaptive output feedback NN tracking controller is designed by backstepping technique. NNs are used to approximate unknown functions dependent on time delay. Delay-dependent filters are introduced for state estimation. The domination method is used to deal with the smooth time-delay basis functions. The adaptive bounding technique is employed to estimate the upper bound of the NN approximation errors. Based on LyapunovKrasovskii functional, the semi-global uniform ultimate boundedness of all the signals in the closed-loop system is proved.The feasibility is investigated by two illustrative simulation examples.
Active control and parameter updating techniques for nonlinear thermal network models
Papalexandris, M. V.; Milman, M. H.
The present article reports on active control and parameter updating techniques for thermal models based on the network approach. Emphasis is placed on applications where radiation plays a dominant role. Examples of such applications are the thermal design and modeling of spacecrafts and space-based science instruments. Active thermal control of a system aims to approximate a desired temperature distribution or to minimize a suitably defined temperature-dependent functional. Similarly, parameter updating aims to update the values of certain parameters of the thermal model so that the output approximates a distribution obtained through direct measurements. Both problems are formulated as nonlinear, least-square optimization problems. The proposed strategies for their solution are explained in detail and their efficiency is demonstrated through numerical tests. Finally, certain theoretical results pertaining to the characterization of solutions of the problems of interest are also presented.
Networked iterative learning control approach for nonlinear systems with random communication delay
Liu, Jian; Ruan, Xiaoe
2016-12-01
This paper constructs a proportional-type networked iterative learning control (NILC) scheme for a class of discrete-time nonlinear systems with the stochastic data communication delay within one operation duration and being subject to Bernoulli-type distribution. In the scheme, the communication delayed data is replaced by successfully captured one at the concurrent sampling moment of the latest iteration. The tracking performance of the addressed NILC algorithm is analysed by statistic technique in virtue of mathematical expectation. The analysis shows that, under certain conditions, the expectation of the tracking error measured in the form of 1-norm is asymptotically convergent to zero. Numerical experiments are carried out to illustrate the validity and effectiveness.
Directory of Open Access Journals (Sweden)
Vecchio Pietro
2011-01-01
Full Text Available Abstract The Bio-inspired (Bi-i Cellular Vision System is a computing platform consisting of sensing, array sensing-processing, and digital signal processing. The platform is based on the Cellular Neural/Nonlinear Network (CNN paradigm. This article presents the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. Each part of the algorithm, along with the corresponding implementation on the hardware platform, is carefully described through the article. The experimental results, carried out for Foreman and Car-phone video sequences, highlight the feasibility of the approach, which provides a frame rate of about 26 frames/s. Comparisons with existing CNN-based methods show that the conceived approach is more accurate, thus representing a good trade-off between real-time requirements and accuracy.
Liu, Yan-Jun; Li, Jing; Tong, Shaocheng; Chen, C L Philip
2016-07-01
In order to stabilize a class of uncertain nonlinear strict-feedback systems with full-state constraints, an adaptive neural network control method is investigated in this paper. The state constraints are frequently emerged in the real-life plants and how to avoid the violation of state constraints is an important task. By introducing a barrier Lyapunov function (BLF) to every step in a backstepping procedure, a novel adaptive backstepping design is well developed to ensure that the full-state constraints are not violated. At the same time, one remarkable feature is that the minimal learning parameters are employed in BLF backstepping design. By making use of Lyapunov analysis, we can prove that all the signals in the closed-loop system are semiglobal uniformly ultimately bounded and the output is well driven to follow the desired output. Finally, a simulation is given to verify the effectiveness of the method.
Adaptive Output-feedback Regulation for Nonlinear Delayed Systems Using Neural Network
Institute of Scientific and Technical Information of China (English)
无
2008-01-01
A novel adaptive neural network (NN) output-feedback regulation algorithm for a class of nonlinear time-varying time-delay systems is proposed. Both the designed observer and controller are independent of time delay. Different from the existing results,where the upper bounding functions of time-delay terms are assumed to be known, we only use an NN to compensate for all unknown upper bounding functions without that assumption. The proposed design method is proved to be able to guarantee semi-global uniform ultimate boundedness of all the signals in the closed system, and the system output is proved to converge to a small neighborhood of the origin. The simulation results verify the effectiveness of the control scheme.
Directory of Open Access Journals (Sweden)
Elaheh Saeedi
2014-07-01
Full Text Available In this paper, a decentralized adaptive controller with using wavelet neural network is used for a class of large-scale nonlinear systems with time- delay unknown nonlinear non- affine subsystems. The entered interruptions in subsystems are considered nonlinear with time delay, this is closer the reality, compared with the case in which the delay is not considered for interruptions. In this paper, the output weights of wavelet neural network and the other parameters of wavelet are adjusted online. The stability of close loop system is guaranteed with using the Lyapanov- Krasovskii method. Moreover the stability of close loop systems, guaranteed tracking error is converging to neighborhood zero and also all of the signals in the close loop system are bounded. Finally, the proposed method, simulated and applied for the control of two inverted pendulums that connected by a spring and the computer results, show that the efficiency of suggested method in this paper.
Doulamis, A D; Doulamis, N D; Kollias, S D
2003-01-01
Multimedia services and especially digital video is expected to be the major traffic component transmitted over communication networks [such as internet protocol (IP)-based networks]. For this reason, traffic characterization and modeling of such services are required for an efficient network operation. The generated models can be used as traffic rate predictors, during the network operation phase (online traffic modeling), or as video generators for estimating the network resources, during the network design phase (offline traffic modeling). In this paper, an adaptable neural-network architecture is proposed covering both cases. The scheme is based on an efficient recursive weight estimation algorithm, which adapts the network response to current conditions. In particular, the algorithm updates the network weights so that 1) the network output, after the adaptation, is approximately equal to current bit rates (current traffic statistics) and 2) a minimal degradation over the obtained network knowledge is provided. It can be shown that the proposed adaptable neural-network architecture simulates a recursive nonlinear autoregressive model (RNAR) similar to the notation used in the linear case. The algorithm presents low computational complexity and high efficiency in tracking traffic rates in contrast to conventional retraining schemes. Furthermore, for the problem of offline traffic modeling, a novel correlation mechanism is proposed for capturing the burstness of the actual MPEG video traffic. The performance of the model is evaluated using several real-life MPEG coded video sources of long duration and compared with other linear/nonlinear techniques used for both cases. The results indicate that the proposed adaptable neural-network architecture presents better performance than other examined techniques.
Non-linear regression techniques are used widely to fit weed field emergence patterns to soil microclimatic indices using S-type functions. Artificial neural networks present interesting and alternative features for such modeling purposes. In this work, a univariate hydrothermal-time based Weibull m...
Directory of Open Access Journals (Sweden)
Fengxia Xu
2014-01-01
Full Text Available U-model can approximate a large class of smooth nonlinear time-varying delay system to any accuracy by using time-varying delay parameters polynomial. This paper proposes a new approach, namely, U-model approach, to solving the problems of analysis and synthesis for nonlinear systems. Based on the idea of discrete-time U-model with time-varying delay, the identification algorithm of adaptive neural network is given for the nonlinear model. Then, the controller is designed by using the Newton-Raphson formula and the stability analysis is given for the closed-loop nonlinear systems. Finally, illustrative examples are given to show the validity and applicability of the obtained results.
Zhang, Ridong; Tao, Jili; Lu, Renquan; Jin, Qibing
2016-12-08
Modeling of distributed parameter systems is difficult because of their nonlinearity and infinite-dimensional characteristics. Based on principal component analysis (PCA), a hybrid modeling strategy that consists of a decoupled linear autoregressive exogenous (ARX) model and a nonlinear radial basis function (RBF) neural network model are proposed. The spatial-temporal output is first divided into a few dominant spatial basis functions and finite-dimensional temporal series by PCA. Then, a decoupled ARX model is designed to model the linear dynamics of the dominant modes of the time series. The nonlinear residual part is subsequently parameterized by RBFs, where genetic algorithm is utilized to optimize their hidden layer structure and the parameters. Finally, the nonlinear spatial-temporal dynamic system is obtained after the time/space reconstruction. Simulation results of a catalytic rod and a heat conduction equation demonstrate the effectiveness of the proposed strategy compared to several other methods.
Extended LaSalle's Invariance Principle for Full-Range Cellular Neural Networks
Di Marco, Mauro; Forti, Mauro; Grazzini, Massimo; Pancioni, Luca
2009-12-01
In several relevant applications to the solution of signal processing tasks in real time, a cellular neural network (CNN) is required to be convergent, that is, each solution should tend toward some equilibrium point. The paper develops a Lyapunov method, which is based on a generalized version of LaSalle's invariance principle, for studying convergence and stability of the differential inclusions modeling the dynamics of the full-range (FR) model of CNNs. The applicability of the method is demonstrated by obtaining a rigorous proof of convergence for symmetric FR-CNNs. The proof, which is a direct consequence of the fact that a symmetric FR-CNN admits a strict Lyapunov function, is much more simple than the corresponding proof of convergence for symmetric standard CNNs.
Extended LaSalle's Invariance Principle for Full-Range Cellular Neural Networks
Directory of Open Access Journals (Sweden)
Mauro Di Marco
2009-01-01
Full Text Available In several relevant applications to the solution of signal processing tasks in real time, a cellular neural network (CNN is required to be convergent, that is, each solution should tend toward some equilibrium point. The paper develops a Lyapunov method, which is based on a generalized version of LaSalle's invariance principle, for studying convergence and stability of the differential inclusions modeling the dynamics of the full-range (FR model of CNNs. The applicability of the method is demonstrated by obtaining a rigorous proof of convergence for symmetric FR-CNNs. The proof, which is a direct consequence of the fact that a symmetric FR-CNN admits a strict Lyapunov function, is much more simple than the corresponding proof of convergence for symmetric standard CNNs.
Deep convolutional neural networks for multi-modality isointense infant brain image segmentation.
Zhang, Wenlu; Li, Rongjian; Deng, Houtao; Wang, Li; Lin, Weili; Ji, Shuiwang; Shen, Dinggang
2015-03-01
The segmentation of infant brain tissue images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) plays an important role in studying early brain development in health and disease. In the isointense stage (approximately 6-8 months of age), WM and GM exhibit similar levels of intensity in both T1 and T2 MR images, making the tissue segmentation very challenging. Only a small number of existing methods have been designed for tissue segmentation in this isointense stage; however, they only used a single T1 or T2 images, or the combination of T1 and T2 images. In this paper, we propose to use deep convolutional neural networks (CNNs) for segmenting isointense stage brain tissues using multi-modality MR images. CNNs are a type of deep models in which trainable filters and local neighborhood pooling operations are applied alternatingly on the raw input images, resulting in a hierarchy of increasingly complex features. Specifically, we used multi-modality information from T1, T2, and fractional anisotropy (FA) images as inputs and then generated the segmentation maps as outputs. The multiple intermediate layers applied convolution, pooling, normalization, and other operations to capture the highly nonlinear mappings between inputs and outputs. We compared the performance of our approach with that of the commonly used segmentation methods on a set of manually segmented isointense stage brain images. Results showed that our proposed model significantly outperformed prior methods on infant brain tissue segmentation. In addition, our results indicated that integration of multi-modality images led to significant performance improvement. Copyright © 2014 Elsevier Inc. All rights reserved.
Partial synchronization in networks of non-linearly coupled oscillators: The Deserter Hubs Model
Energy Technology Data Exchange (ETDEWEB)
Freitas, Celso, E-mail: cbnfreitas@gmail.com; Macau, Elbert, E-mail: elbert.macau@inpe.br [Associate Laboratory for Computing and Applied Mathematics - LAC, Brazilian National Institute for Space Research - INPE (Brazil); Pikovsky, Arkady, E-mail: pikovsky@uni-potsdam.de [Department of Physics and Astronomy, University of Potsdam, Germany and Department of Control Theory, Nizhni Novgorod State University, Gagarin Av. 23, 606950, Nizhni Novgorod (Russian Federation)
2015-04-15
We study the Deserter Hubs Model: a Kuramoto-like model of coupled identical phase oscillators on a network, where attractive and repulsive couplings are balanced dynamically due to nonlinearity of interactions. Under weak force, an oscillator tends to follow the phase of its neighbors, but if an oscillator is compelled to follow its peers by a sufficient large number of cohesive neighbors, then it actually starts to act in the opposite manner, i.e., in anti-phase with the majority. Analytic results yield that if the repulsion parameter is small enough in comparison with the degree of the maximum hub, then the full synchronization state is locally stable. Numerical experiments are performed to explore the model beyond this threshold, where the overall cohesion is lost. We report in detail partially synchronous dynamical regimes, like stationary phase-locking, multistability, periodic and chaotic states. Via statistical analysis of different network organizations like tree, scale-free, and random ones, we found a measure allowing one to predict relative abundance of partially synchronous stationary states in comparison to time-dependent ones.
Shimelevich, M. I.; Obornev, E. A.; Obornev, I. E.; Rodionov, E. A.
2017-07-01
The iterative approximation neural network method for solving conditionally well-posed nonlinear inverse problems of geophysics is presented. The method is based on the neural network approximation of the inverse operator. The inverse problem is solved in the class of grid (block) models of the medium on a regularized parameterization grid. The construction principle of this grid relies on using the calculated values of the continuity modulus of the inverse operator and its modifications determining the degree of ambiguity of the solutions. The method provides approximate solutions of inverse problems with the maximal degree of detail given the specified degree of ambiguity with the total number of the sought parameters n × 103 of the medium. The a priori and a posteriori estimates of the degree of ambiguity of the approximated solutions are calculated. The work of the method is illustrated by the example of the three-dimensional (3D) inversion of the synthesized 2D areal geoelectrical (audio magnetotelluric sounding, AMTS) data corresponding to the schematic model of a kimberlite pipe.
A new method for the re-implementation of threshold logic functions with cellular neural networks.
Bénédic, Y; Wira, P; Mercklé, J
2008-08-01
A new strategy is presented for the implementation of threshold logic functions with binary-output Cellular Neural Networks (CNNs). The objective is to optimize the CNNs weights to develop a robust implementation. Hence, the concept of generative set is introduced as a convenient representation of any linearly separable Boolean function. Our analysis of threshold logic functions leads to a complete algorithm that automatically provides an optimized generative set. New weights are deduced and a more robust CNN template assuming the same function can thus be implemented. The strategy is illustrated by a detailed example.
Quach, Minh; Brunel, Nicolas; d'Alché-Buc, Florence
2007-12-01
Statistical inference of biological networks such as gene regulatory networks, signaling pathways and metabolic networks can contribute to build a picture of complex interactions that take place in the cell. However, biological systems considered as dynamical, non-linear and generally partially observed processes may be difficult to estimate even if the structure of interactions is given. Using the same approach as Sitz et al. proposed in another context, we derive non-linear state-space models from ODEs describing biological networks. In this framework, we apply Unscented Kalman Filtering (UKF) to the estimation of both parameters and hidden variables of non-linear state-space models. We instantiate the method on a transcriptional regulatory model based on Hill kinetics and a signaling pathway model based on mass action kinetics. We successfully use synthetic data and experimental data to test our approach. This approach covers a large set of biological networks models and gives rise to simple and fast estimation algorithms. Moreover, the Bayesian tool used here directly provides uncertainty estimates on parameters and hidden states. Let us also emphasize that it can be coupled with structure inference methods used in Graphical Probabilistic Models. Matlab code available on demand.
Mei, Jie; Ren, Wei; Li, Bing; Ma, Guangfu
2015-09-01
In this paper, we consider the distributed containment control problem for multiagent systems with unknown nonlinear dynamics. More specifically, we focus on multiple second-order nonlinear systems and networked Lagrangian systems. We first study the distributed containment control problem for multiple second-order nonlinear systems with multiple dynamic leaders in the presence of unknown nonlinearities and external disturbances under a general directed graph that characterizes the interaction among the leaders and the followers. A distributed adaptive control algorithm with an adaptive gain design based on the approximation capability of neural networks is proposed. We present a necessary and sufficient condition on the directed graph such that the containment error can be reduced as small as desired. As a byproduct, the leaderless consensus problem is solved with asymptotical convergence. Because relative velocity measurements between neighbors are generally more difficult to obtain than relative position measurements, we then propose a distributed containment control algorithm without using neighbors' velocity information. A two-step Lyapunov-based method is used to study the convergence of the closed-loop system. Next, we apply the ideas to deal with the containment control problem for networked unknown Lagrangian systems under a general directed graph. All the proposed algorithms are distributed and can be implemented using only local measurements in the absence of communication. Finally, simulation examples are provided to show the effectiveness of the proposed control algorithms.
Directory of Open Access Journals (Sweden)
Luiz Augusto da Cruz Meleiro
2005-06-01
Full Text Available In this work a MIMO non-linear predictive controller was developed for an extractive alcoholic fermentation process. The internal model of the controller was represented by two MISO Functional Link Networks (FLNs, identified using simulated data generated from a deterministic mathematical model whose kinetic parameters were determined experimentally. The FLN structure presents as advantages fast training and guaranteed convergence, since the estimation of the weights is a linear optimization problem. Besides, the elimination of non-significant weights generates parsimonious models, which allows for fast execution in an MPC-based algorithm. The proposed algorithm showed good potential in identification and control of non-linear processes.Neste trabalho um controlador preditivo não linear multivariável foi desenvolvido para um processo de fermentação alcoólica extrativa. O modelo interno do controlador foi representado por duas redes do tipo Functional Link (FLN, identificadas usando dados de simulação gerados a partir de um modelo validado experimentalmente. A estrutura FLN apresenta como vantagem o treinamento rápido e convergência garantida, já que a estimação dos seus pesos é um problema de otimização linear. Além disso, a eliminação de pesos não significativos gera modelos parsimoniosos, o que permite a rápida execução em algoritmos de controle preditivo baseado em modelo. Os resultados mostram que o algoritmo proposto tem grande potencial para identificação e controle de processos não lineares.
Intelligent adaptive nonlinear flight control for a high performance aircraft with neural networks.
Savran, Aydogan; Tasaltin, Ramazan; Becerikli, Yasar
2006-04-01
This paper describes the development of a neural network (NN) based adaptive flight control system for a high performance aircraft. The main contribution of this work is that the proposed control system is able to compensate the system uncertainties, adapt to the changes in flight conditions, and accommodate the system failures. The underlying study can be considered in two phases. The objective of the first phase is to model the dynamic behavior of a nonlinear F-16 model using NNs. Therefore a NN-based adaptive identification model is developed for three angular rates of the aircraft. An on-line training procedure is developed to adapt the changes in the system dynamics and improve the identification accuracy. In this procedure, a first-in first-out stack is used to store a certain history of the input-output data. The training is performed over the whole data in the stack at every stage. To speed up the convergence rate and enhance the accuracy for achieving the on-line learning, the Levenberg-Marquardt optimization method with a trust region approach is adapted to train the NNs. The objective of the second phase is to develop intelligent flight controllers. A NN-based adaptive PID control scheme that is composed of an emulator NN, an estimator NN, and a discrete time PID controller is developed. The emulator NN is used to calculate the system Jacobian required to train the estimator NN. The estimator NN, which is trained on-line by propagating the output error through the emulator, is used to adjust the PID gains. The NN-based adaptive PID control system is applied to control three angular rates of the nonlinear F-16 model. The body-axis pitch, roll, and yaw rates are fed back via the PID controllers to the elevator, aileron, and rudder actuators, respectively. The resulting control system has learning, adaptation, and fault-tolerant abilities. It avoids the storage and interpolation requirements for the too many controller parameters of a typical flight control
Gerousis, Costa P.
It is currently predicted that semiconductor device scaling will end at the 22-nm device feature size (7 nm physical channel length) according to the International Technology Roadmap for Semiconductors. The main challenge is then to develop innovative technologies that will extend the scaling beyond roadmap projection. Any new technology must be well matched with complementary metal oxide semiconductor (CMOS) technology and scaleable beyond CMOS scaling projections and must provide low-power high-speed signal processing. Nanotechnology will become an appealing option for developing devices for integrated circuits with dimensions and performances well beyond roadmap predictions. Such devices, based on the controllable transfer of charge between dots or 'islands', can take advantage of the quantum mechanical effects, such as tunneling and energy quantization, which would normally occur at the nanometer scale. An outstanding challenge is in arranging such nanodevices in new architectures that can be integrated on a single chip. In particular, locally interconnected architectures are believed to be necessary to alleviate the problems associated with increasing interconnect length and complexity in ultra-dense circuits. The goal of this work is to investigate the use of nanoelectronic structures in cellular non-linear network (CNN) architectures for potential application in future high-density and low-power CMOS-nanodevice hybrid circuits. The operation of the single-electron tunneling (SET) transistor is first reviewed, followed by a discussion of simple CNN linear architectures using a SET inverter topology as the basis for the non-linear transfer characteristics for individual cells to be used in analog processing arrays for image-processing applications. The basic SET CNN cell acts as a summing node that is capacitively coupled to the inputs and outputs of nearest neighbor cells. Monte Carlo simulation results are used to show CNN-like behavior in attempting to
2015-12-15
convolution, activation functions, and pooling. For a model trained on classes, the output from the classification layer comprises + 1...Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network...Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their
NONLINEAR STABLE ADAPTIVE CONTROL BASED UPON ELMAN NETWORKS%基于Elman网络的非线性稳定自适应控制
Institute of Scientific and Technical Information of China (English)
李翔; 陈增强; 袁著祉
2000-01-01
Elman networks' dynamical modeling capability is discussed in this paper firstly. According to Elman networks' unique structure ,a weight training algorithm is designed and a nonlinear adaptive controller is constructed. Without the PE presumption, neural networkscontroller's closed-loop properties are studied and the whole Elman networks' passivity is demonstrated.
Directory of Open Access Journals (Sweden)
David E. Allen
2016-03-01
Full Text Available This paper features an analysis of major currency exchange rate movements in relation to the US dollar, as constituted in US dollar terms. Euro, British pound, Chinese yuan, and Japanese yen are modelled using a variety of non-linear models, including smooth transition regression models, logistic smooth transition regressions models, threshold autoregressive models, nonlinear autoregressive models, and additive nonlinear autoregressive models, plus Neural Network models. The models are evaluated on the basis of error metrics for twenty day out-of-sample forecasts using the mean average percentage errors (MAPE. The results suggest that there is no dominating class of time series models, and the different currency pairs relationships with the US dollar are captured best by neural net regression models, over the ten year sample of daily exchange rate returns data, from August 2005 to August 2015.
Institute of Scientific and Technical Information of China (English)
Hasan ABBASI NOZARI; Hamed DEHGHAN BANADAKI; Mohammad MOKHTARE; Somaveh HEKMATI VAHED
2012-01-01
This study deals with the neuro-fuzzy (NF) modelling of a real industrial winding process in which the acquired NF model can be exploited to improve control performance and achieve a robust fault-tolerant system.A new simulator model is proposed for a winding process using non-linear identification based on a recurrent local linear neuro-fuzzy (RLLNF) network trained by local linear model tree (LOLIMOT),which is an incremental tree-based learning algorithm.The proposed NF models are compared with other known intelligent identifiers,namely multilayer perceptron (MLP) and radial basis function (RBF).Comparison of our proposed non-linear models and associated models obtained through the least square error (LSE) technique (the optimal modelling method for linear systems) confirms that the winding process is a non-linear system.Experimental results show the effectiveness of our proposed NF modelling approach.
Generalizing a nonlinear geophysical flood theory to medium-sized river networks
Gupta, Vijay K.; Mantilla, Ricardo; Troutman, Brent M.; Dawdy, David; Krajewski, Witold F.
2010-01-01
The central hypothesis of a nonlinear geophysical flood theory postulates that, given space-time rainfall intensity for a rainfall-runoff event, solutions of coupled mass and momentum conservation differential equations governing runoff generation and transport in a self-similar river network produce spatial scaling, or a power law, relation between peak discharge and drainage area in the limit of large area. The excellent fit of a power law for the destructive flood event of June 2008 in the 32,400-km2 Iowa River basin over four orders of magnitude variation in drainage areas supports the central hypothesis. The challenge of predicting observed scaling exponent and intercept from physical processes is explained. We show scaling in mean annual peak discharges, and briefly discuss that it is physically connected with scaling in multiple rainfall-runoff events. Scaling in peak discharges would hold in a non-stationary climate due to global warming but its slope and intercept would change.
Ouyang, Huei-Tau
2017-08-01
Accurate inundation level forecasting during typhoon invasion is crucial for organizing response actions such as the evacuation of people from areas that could potentially flood. This paper explores the ability of nonlinear autoregressive neural networks with exogenous inputs (NARX) to predict inundation levels induced by typhoons. Two types of NARX architecture were employed: series-parallel (NARX-S) and parallel (NARX-P). Based on cross-correlation analysis of rainfall and water-level data from historical typhoon records, 10 NARX models (five of each architecture type) were constructed. The forecasting ability of each model was assessed by considering coefficient of efficiency (CE), relative time shift error (RTS), and peak water-level error (PE). The results revealed that high CE performance could be achieved by employing more model input variables. Comparisons of the two types of model demonstrated that the NARX-S models outperformed the NARX-P models in terms of CE and RTS, whereas both performed exceptionally in terms of PE and without significant difference. The NARX-S and NARX-P models with the highest overall performance were identified and their predictions were compared with those of traditional ARX-based models. The NARX-S model outperformed the ARX-based models in all three indexes, whereas the NARX-P model exhibited comparable CE performance and superior RTS and PE performance.
Robust Integral of Neural Network and Error Sign Control of MIMO Nonlinear Systems.
Yang, Qinmin; Jagannathan, Sarangapani; Sun, Youxian
2015-12-01
This paper presents a novel state-feedback control scheme for the tracking control of a class of multi-input multioutput continuous-time nonlinear systems with unknown dynamics and bounded disturbances. First, the control law consisting of the robust integral of a neural network (NN) output plus sign of the tracking error feedback multiplied with an adaptive gain is introduced. The NN in the control law learns the system dynamics in an online manner, while the NN residual reconstruction errors and the bounded disturbances are overcome by the error sign signal. Since both of the NN output and the error sign signal are included in the integral, the continuity of the control input is ensured. The controller structure and the NN weight update law are novel in contrast with the previous effort, and the semiglobal asymptotic tracking performance is still guaranteed by using the Lyapunov analysis. In addition, the NN weights and all other signals are proved to be bounded simultaneously. The proposed approach also relaxes the need for the upper bounds of certain terms, which are usually required in the previous designs. Finally, the theoretical results are substantiated with simulations.
Directory of Open Access Journals (Sweden)
GEMAN, O.
2014-02-01
Full Text Available Neurological diseases like Alzheimer, epilepsy, Parkinson's disease, multiple sclerosis and other dementias influence the lives of patients, their families and society. Parkinson's disease (PD is a neurodegenerative disease that occurs due to loss of dopamine, a neurotransmitter and slow destruction of neurons. Brain area affected by progressive destruction of neurons is responsible for controlling movements, and patients with PD reveal rigid and uncontrollable gestures, postural instability, small handwriting and tremor. Commercial activity-promoting gaming systems such as the Nintendo Wii and Xbox Kinect can be used as tools for tremor, gait or other biomedical signals acquisitions. They also can aid for rehabilitation in clinical settings. This paper emphasizes the use of intelligent optical sensors or accelerometers in biomedical signal acquisition, and of the specific nonlinear dynamics parameters or fuzzy logic in Parkinson's disease tremor analysis. Nowadays, there is no screening test for early detection of PD. So, we investigated a method to predict PD, based on the image processing of the handwriting belonging to a candidate of PD. For classification and discrimination between healthy people and PD people we used Artificial Neural Networks (Radial Basis Function - RBF and Multilayer Perceptron - MLP and an Adaptive Neuro-Fuzzy Classifier (ANFC. In general, the results may be expressed as a prognostic (risk degree to contact PD.
Mobile robot nonlinear feedback control based on Elman neural network observer
Directory of Open Access Journals (Sweden)
Khaled Al-Mutib
2015-12-01
Full Text Available This article presents a new approach to control a wheeled mobile robot without velocity measurement. The controller developed is based on kinematic model as well as dynamics model to take into account parameters of dynamics. These parameters related to dynamic equations are identified using a proposed methodology. Input–output feedback linearization is considered with a slight modification in the mathematical expressions to implement the dynamic controller and analyze the nonlinear internal behavior. The developed controllers require sensors to obtain the states needed for the closed-loop system. However, some states may not be available due to the absence of the sensors because of the cost, the weight limitation, reliability, induction of errors, failure, and so on. Particularly, for the velocity measurements, the required accuracy may not be achieved in practical applications due to the existence of significant errors induced by stochastic or cyclical noise. In this article, Elman neural network is proposed to work as an observer to estimate the velocity needed to complete the full state required for the closed-loop control and account for all the disturbances and model parameter uncertainties. Different simulations are carried out to demonstrate the feasibility of the approach in tracking different reference trajectories in comparison with other paradigms.
The characteristics of nonlinear chaotic dynamics in quantum cellular neural networks
Institute of Scientific and Technical Information of China (English)
Wang Sen; Cai Li; Kang Qiang; Wu Gang; Li Qin
2008-01-01
With the polarization of quantum-dot cell and quantum phase serving as state variables, this paper does both theoretical analysis and simulation for the complex nonlinear dynamical behaviour of a three-cell-coupled Quantum Cel- lular Neural Network (QCNN), including equilibrium points, bifurcation and chaotic behaviour. Different phenomena, such as quasi-periodic, chaotic and hyper-chaotic states as well as bifurcations are revealed. The system's bifurcation and chaotic behaviour under the influence of the different coupling parameters are analysed. And it finds that the unbalanced ceils coupled QCNN is easy to cause chaotic oscillation and the system response enters into chaotic state from quasi-periodic state by quasi-period bifurcation; however, the balanced cells coupled QCNN also can be chaotic when coupling parameters is in some region. Additionally, both the unbalanced and balanced cells coupled QCNNs can possess hyper-chaotic behaviour. It provides valuable information about QCNNs for future application in high-parallel signal processing and novel ultra-small chaotic generators.
A convolutional neural network neutrino event classifier
Aurisano, A.; Radovic, A.; Rocco, D.; Himmel, A.; Messier, M. D.; Niner, E.; Pawloski, G.; Psihas, F.; Sousa, A.; Vahle, P.
2016-09-01
Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.
A Convolutional Neural Network Neutrino Event Classifier
Aurisano, A; Rocco, D; Himmel, A; Messier, M D; Niner, E; Pawloski, G; Psihas, F; Sousa, A; Vahle, P
2016-01-01
Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.
Sharqawy, Mostafa H.
2016-12-01
Pore network models (PNM) of Berea and Fontainebleau sandstones were constructed using nonlinear programming (NLP) and optimization methods. The constructed PNMs are considered as a digital representation of the rock samples which were based on matching the macroscopic properties of the porous media and used to conduct fluid transport simulations including single and two-phase flow. The PNMs consisted of cubic networks of randomly distributed pores and throats sizes and with various connectivity levels. The networks were optimized such that the upper and lower bounds of the pore sizes are determined using the capillary tube bundle model and the Nelder-Mead method instead of guessing them, which reduces the optimization computational time significantly. An open-source PNM framework was employed to conduct transport and percolation simulations such as invasion percolation and Darcian flow. The PNM model was subsequently used to compute the macroscopic properties; porosity, absolute permeability, specific surface area, breakthrough capillary pressure, and primary drainage curve. The pore networks were optimized to allow for the simulation results of the macroscopic properties to be in excellent agreement with the experimental measurements. This study demonstrates that non-linear programming and optimization methods provide a promising method for pore network modeling when computed tomography imaging may not be readily available.
Nonlinear noninteger order circuits and systems an introduction
Arena, P; Fortuna, L; Porto, D
2001-01-01
In this book, the reader will find a theoretical introduction to noninteger order systems, as well as several applications showing their features and peculiarities. The main definitions and results of research on noninteger order systems and modelling of physical noninteger phenomena are reported together with problems of their approximation. Control applications, noninteger order CNNs and circuit realizations of noninteger order systems are also presented.The book is intended for students and researchers involved in the simulation and control of nonlinear noninteger order systems, with partic
Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification
Ergun, Hilal; Sert, Mustafa
2016-01-01
Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of convolutional neural networks (CNNs) from the big data perspective. We analyze recent studies and different network architectures both in terms of running time and accuracy. We present extensive empirical information along with best practices for big data practitioners...
Sha, Daohang
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given. Although this approach is proposed for three-layer, feed-forward neural networks, it could be extended to multiple layer feed-forward neural networks. The effectiveness of the proposed algorithms applied to the identification of behavior of a two-input and two-output non-linear dynamic system is demonstrated by simulation experiments.
Mohammadzadeh, Ardashir; Ghaemi, Sehraneh
2015-09-01
This paper proposes a novel approach for training of proposed recurrent hierarchical interval type-2 fuzzy neural networks (RHT2FNN) based on the square-root cubature Kalman filters (SCKF). The SCKF algorithm is used to adjust the premise part of the type-2 FNN and the weights of defuzzification and the feedback weights. The recurrence property in the proposed network is the output feeding of each membership function to itself. The proposed RHT2FNN is employed in the sliding mode control scheme for the synchronization of chaotic systems. Unknown functions in the sliding mode control approach are estimated by RHT2FNN. Another application of the proposed RHT2FNN is the identification of dynamic nonlinear systems. The effectiveness of the proposed network and its learning algorithm is verified by several simulation examples. Furthermore, the universal approximation of RHT2FNNs is also shown.
Morrissey, Edward R; Juárez, Miguel A; Denby, Katherine J; Burroughs, Nigel J
2011-10-01
We propose a semiparametric Bayesian model, based on penalized splines, for the recovery of the time-invariant topology of a causal interaction network from longitudinal data. Our motivation is inference of gene regulatory networks from low-resolution microarray time series, where existence of nonlinear interactions is well known. Parenthood relations are mapped by augmenting the model with kinship indicators and providing these with either an overall or gene-wise hierarchical structure. Appropriate specification of the prior is crucial to control the flexibility of the splines, especially under circumstances of scarce data; thus, we provide an informative, proper prior. Substantive improvement in network inference over a linear model is demonstrated using synthetic data drawn from ordinary differential equation models and gene expression from an experimental data set of the Arabidopsis thaliana circadian rhythm.
Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks
Zuo, Zhen; Shuai, Bing; Wang, Gang; Liu, Xiao; Wang, Xingxing; Wang, Bing; Chen, Yushi
2016-07-01
Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the dependencies among different image regions. However, such dependencies are very important for generating explicit image representation. In contrast, recurrent neural networks (RNNs) are well known for their ability of encoding contextual information among sequential data, and they only require a limited number of network parameters. General RNNs can hardly be directly applied on non-sequential data. Thus, we proposed the hierarchical RNNs (HRNNs). In HRNNs, each RNN layer focuses on modeling spatial dependencies among image regions from the same scale but different locations. While the cross RNN scale connections target on modeling scale dependencies among regions from the same location but different scales. Specifically, we propose two recurrent neural network models: 1) hierarchical simple recurrent network (HSRN), which is fast and has low computational cost; and 2) hierarchical long-short term memory recurrent network (HLSTM), which performs better than HSRN with the price of more computational cost. In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs). C-HRNNs not only make use of the representation power of CNNs, but also efficiently encodes spatial and scale dependencies among different image regions. On four of the most challenging object/scene image classification benchmarks, our C-HRNNs achieve state-of-the-art results on Places 205, SUN 397, MIT indoor, and competitive results on ILSVRC 2012.
Zhou, Chao; Hong, Ming; Su, Zhongqing; Wang, Qiang; Cheng, Li
2013-01-01
There has been increasing interest in using the nonlinear features of acousto-ultrasonic (AU) waves to detect damage onset (e.g., micro-fatigue cracks) due to their high sensitivity to damage with small dimensions. However, most existing approaches are able to infer the existence of fatigue damage qualitatively, but fail to further ascertain its location and severity. A damage characterization approach, in conjunction with the use of an active piezoelectric sensor network, was established, capable of evaluating fatigue cracks in a quantitative manner (including the co-presence of multiple fatigue cracks, and their individual locations and severities). Fundamental investigations, using both experiment and enhanced finite element analysis dedicated to the simulation of nonlinear AU waves, were carried out to link the accumulation of nonlinearities extracted from high-order AU waves to the characteristic parameters of a fatigue crack. A probability-based diagnostic imaging algorithm was developed, facilitating an intuitive presentation of identification results in images. The approach was verified experimentally by evaluating multi-fatigue cracks near rivet holes of a fatigued aluminum plate, showing satisfactory precision in characterizing real, barely visible fatigue cracks. Compared with existing methods, this approach innovatively (i) uses permanently integrated active sensor networks, conducive to automatic and online health monitoring; (ii) characterizes fatigue cracks at a quantitative level; (iii) allows detection of multiple fatigue cracks; and (iv) visualizes identification results in intuitive images.
Cerebral vessels segmentation for light-sheet microscopy image using convolutional neural networks
Hu, Chaoen; Hui, Hui; Wang, Shuo; Dong, Di; Liu, Xia; Yang, Xin; Tian, Jie
2017-03-01
Cerebral vessel segmentation is an important step in image analysis for brain function and brain disease studies. To extract all the cerebrovascular patterns, including arteries and capillaries, some filter-based methods are used to segment vessels. However, the design of accurate and robust vessel segmentation algorithms is still challenging, due to the variety and complexity of images, especially in cerebral blood vessel segmentation. In this work, we addressed a problem of automatic and robust segmentation of cerebral micro-vessels structures in cerebrovascular images acquired by light-sheet microscope for mouse. To segment micro-vessels in large-scale image data, we proposed a convolutional neural networks (CNNs) architecture trained by 1.58 million pixels with manual label. Three convolutional layers and one fully connected layer were used in the CNNs model. We extracted a patch of size 32x32 pixels in each acquired brain vessel image as training data set to feed into CNNs for classification. This network was trained to output the probability that the center pixel of input patch belongs to vessel structures. To build the CNNs architecture, a series of mouse brain vascular images acquired from a commercial light sheet fluorescence microscopy (LSFM) system were used for training the model. The experimental results demonstrated that our approach is a promising method for effectively segmenting micro-vessels structures in cerebrovascular images with vessel-dense, nonuniform gray-level and long-scale contrast regions.
Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere
2015-04-01
This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.
Neural network-based robust actuator fault diagnosis for a non-linear multi-tank system.
Mrugalski, Marcin; Luzar, Marcel; Pazera, Marcin; Witczak, Marcin; Aubrun, Christophe
2016-03-01
The paper is devoted to the problem of the robust actuator fault diagnosis of the dynamic non-linear systems. In the proposed method, it is assumed that the diagnosed system can be modelled by the recurrent neural network, which can be transformed into the linear parameter varying form. Such a system description allows developing the designing scheme of the robust unknown input observer within H∞ framework for a class of non-linear systems. The proposed approach is designed in such a way that a prescribed disturbance attenuation level is achieved with respect to the actuator fault estimation error, while guaranteeing the convergence of the observer. The application of the robust unknown input observer enables actuator fault estimation, which allows applying the developed approach to the fault tolerant control tasks.
Morgan, Sarah E; Chin, Alex W
2016-01-01
Collective protein modes are expected to be important for facilitating energy transfer in the Fenna-Matthews-Olson (FMO) complex, however to date little work has focussed on the microscopic details of these vibrations. The nonlinear network model (NNM) provides a computationally inexpensive approach to studying vibrational modes at the microscopic level, whilst incorporating anharmonicity in the inter-residue interactions which can influence protein dynamics. We apply the NNM to the FMO complex and find evidence for the existence of nonlinear discrete breather modes. These modes tend to transfer energy to the highly connected core pigments, potentially opening up alternative excitation energy transfer routes. Incorporating localised modes based on these discrete breathers in the optical spectra calculations for FMO using ab initio site energies and excitonic couplings can substantially improve their agreement with experimental results.
Morgan, Sarah E.; Cole, Daniel J.; Chin, Alex W.
2016-11-01
Collective protein modes are expected to be important for facilitating energy transfer in the Fenna-Matthews-Olson (FMO) complex of photosynthetic green sulphur bacteria, however to date little work has focussed on the microscopic details of these vibrations. The nonlinear network model (NNM) provides a computationally inexpensive approach to studying vibrational modes at the microscopic level in large protein structures, whilst incorporating anharmonicity in the inter-residue interactions which can influence protein dynamics. We apply the NNM to the entire trimeric FMO complex and find evidence for the existence of nonlinear discrete breather modes. These modes tend to transfer energy to the highly connected core pigments, potentially opening up alternative excitation energy transfer routes through their influence on pigment properties. Incorporating localised modes based on these discrete breathers in the optical spectra calculations for FMO using ab initio site energies and excitonic couplings can substantially improve their agreement with experimental results.
Do Convolutional Neural Networks Learn Class Hierarchy?
Alsallakh, Bilal; Jourabloo, Amin; Ye, Mao; Liu, Xiaoming; Ren, Liu
2017-08-29
Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.
Lopes, M A; Lee, K-E; Goltsev, A V; Mendes, J F F
2014-11-01
We show that sensory noise can enhance the nonlinear response of neuronal networks, and when delivered together with a weak signal, it improves the signal detection by the network. We reveal this phenomenon in neuronal networks that are in a dynamical state preceding a saddle-node bifurcation corresponding to the appearance of sustained network oscillations. In this state, even a weak subthreshold pulse can evoke a large-amplitude oscillation of neuronal activity. The signal-to-noise ratio reaches a maximum at an optimum level of sensory noise, manifesting stochastic resonance (SR) at the population level. We demonstrate SR by use of simulations and numerical integration of rate equations in a cortical model. Using this model, we mimic the experiments of Gluckman et al. [Phys. Rev. Lett. 77, 4098 (1996)PRLTAO0031-900710.1103/PhysRevLett.77.4098] that have given evidence of SR in mammalian brain. We also study neuronal networks in which neurons are grouped in modules and every module works in the regime of SR. We find that even a few modules can strongly enhance the reliability of signal detection in comparison with the case when a modular organization is absent.
Directory of Open Access Journals (Sweden)
Athanasia Papoutsi
2014-07-01
Full Text Available Technological advances have unraveled the existence of small clusters of co-active neurons in the neocortex. The functional implications of these microcircuits are in large part unexplored. Using a heavily constrained biophysical model of a L5 PFC microcircuit, we recently showed that these structures act as tunable modules of persistent activity, the cellular correlate of working memory. Here, we investigate the mechanisms that underlie persistent activity emergence (ON and termination (OFF and search for the minimum network size required for expressing these states within physiological regimes. We show that (a NMDA-mediated dendritic spikes gate the induction of persistent firing in the microcircuit. (b The minimum network size required for persistent activity induction is inversely proportional to the synaptic drive of each excitatory neuron. (c Relaxation of connectivity and synaptic delay constraints eliminates the gating effect of NMDA spikes, albeit at a cost of much larger networks. (d Persistent activity termination by increased inhibition depends on the strength of the synaptic input and is negatively modulated by dADP. (e Slow synaptic mechanisms and network activity contain predictive information regarding the ability of a given stimulus to turn ON and/or OFF persistent firing in the microcircuit model. Overall, this study zooms out from dendrites to cell assemblies and suggests a tight interaction between dendritic non-linearities and network properties (size/connectivity that may facilitate the short-memory function of the PFC.
Strain-controlled criticality governs the nonlinear mechanics of fibre networks
Sharma, A.; Licup, A. J.; Rens, R.; Sheinman, M.; Jansen, K.A.; Koenderink, G.H.; Mackintosh, F.C.
2015-01-01
Disordered fibrous networks are ubiquitous in nature as major structural components of living cells and tissues. The mechanical stability of networks generally depends on the degree of connectivity: only when the average number of connections between nodes exceeds the isostatic threshold are networks stable (Maxwell, J. C., Philosophical Magazine 27, 294 (1864)). Upon increasing the connectivity through this point, such networks undergo a mechanical phase transition from a floppy to a rigid p...
Pressure Regulation in Nonlinear Hydraulic Networks by Positive and Quantized Controls
Persis, Claudio De; Kallesøe, Carsten Skovmose
2011-01-01
We investigate an industrial case study of a system distributed over a network, namely, a large-scale hydraulic network which underlies a district heating system. The network comprises an arbitrarily large number of components (valves, pipes, and pumps). After introducing the model for this class of
Institute of Scientific and Technical Information of China (English)
ZHOU Rong-yi; LIU Ai-qun; LI Shu-qing
2007-01-01
Directing at the non-linear dynamic characteristics of water inrush from coal seam floor and by the analysis of the shortages of current forecast methods for water inrush from coal seam floor,a new forecast method was raised based on wavelet neural network(WNN)that was a model combining wavelet function with artificiaI neural network.Firstly basic principle of WNN was described.then a forecast model for water inrush from coal seam floor based on WNN was established and analyzed,finally an example of forecasting the quantity of water inrush from coal floor was illustrated to verify the feasibility and superiority of this method.Conclusions show that the forecast result based on WNN is more precise and that using WNN model to forecast the quantity of water inrush from coal seam floor is feasible and practical.
Implementations of artificial neural networks using current-mode pulse width modulation technique.
El-Masry, E I; Yang, H K; Yakout, M A
1997-01-01
The use of a current-mode pulse width modulation (CM-PWM) technique to implement analog artificial neural networks (ANNs) is presented. This technique can be used to efficiently implement the weighted summation operation (WSO) that are required in the realization of a general ANN. The sigmoidal transformation is inherently performed by the nonlinear transconductance amplifier, which is a key component in the current integrator used in the realization of WSO. The CM-PWM implementation results in a minimum silicon area, and therefore is suitable for very large scale neural systems. Other pronounced features of the CM-PWM implementation are its easy programmability, electronically adjustable gains of neurons, and modular structures. In this paper, all the current-mode CMOS circuits (building blocks) required for the realization of CM-PWM ANNs are presented and simulated. Four modules for modular design of ANNs are introduced. Also, it is shown that the CM-PWM technique is an efficient method for implementing discrete-time cellular neural networks (DT-CNNs). Two application examples are given: a winner-take-all circuit and a connected component detector.
Zou, An-Min; Dev Kumar, Krishna; Hou, Zeng-Guang
2010-09-01
This paper investigates the problem of output feedback attitude control of an uncertain spacecraft. Two robust adaptive output feedback controllers based on Chebyshev neural networks (CNN) termed adaptive neural networks (NN) controller-I and adaptive NN controller-II are proposed for the attitude tracking control of spacecraft. The four-parameter representations (quaternion) are employed to describe the spacecraft attitude for global representation without singularities. The nonlinear reduced-order observer is used to estimate the derivative of the spacecraft output, and the CNN is introduced to further improve the control performance through approximating the spacecraft attitude motion. The implementation of the basis functions of the CNN used in the proposed controllers depends only on the desired signals, and the smooth robust compensator using the hyperbolic tangent function is employed to counteract the CNN approximation errors and external disturbances. The adaptive NN controller-II can efficiently avoid the over-estimation problem (i.e., the bound of the CNNs output is much larger than that of the approximated unknown function, and hence, the control input may be very large) existing in the adaptive NN controller-I. Both adaptive output feedback controllers using CNN can guarantee that all signals in the resulting closed-loop system are uniformly ultimately bounded. For performance comparisons, the standard adaptive controller using the linear parameterization of spacecraft attitude motion is also developed. Simulation studies are presented to show the advantages of the proposed CNN-based output feedback approach over the standard adaptive output feedback approach.
Strain-controlled criticality governs the nonlinear mechanics of fibre networks
Sharma, A; Rens, R; Sheinman, M; Jansen, K A; Koenderink, G H; MacKintosh, F C
2015-01-01
Disordered fibrous networks are ubiquitous in nature as major structural components of living cells and tissues. The mechanical stability of networks generally depends on the degree of connectivity: only when the average number of connections between nodes exceeds the isostatic threshold are networks stable (Maxwell, J. C., Philosophical Magazine 27, 294 (1864)). Upon increasing the connectivity through this point, such networks undergo a mechanical phase transition from a floppy to a rigid phase. However, even sub-isostatic networks become rigid when subjected to sufficiently large deformations. To study this strain-controlled transition, we perform a combination of computational modeling of fibre networks and experiments on networks of type I collagen fibers, which are crucial for the integrity of biological tissues. We show theoretically that the development of rigidity is characterized by a strain-controlled continuous phase transition with signatures of criticality. Our experiments demonstrate mechanical...
Bao, Bin; Guyomar, Daniel; Lallart, Mickaël
2017-01-01
Smart periodic structures covered by periodically distributed piezoelectric patches have drawn more and more attention in recent years for wave propagation attenuation and corresponding structural vibration suppression. Since piezoelectric materials are special type of energy conversion materials that link mechanical characteristics with electrical characteristics, shunt circuits coupled with such materials play a key role in the wave propagation and/or vibration control performance in smart periodic structures. Conventional shunt circuit designs utilize resistive shunt (R-shunt) and resonant shunt (RL-shunt). More recently, semi-passive nonlinear approaches have also been developed for efficiently controlling the vibrations of such structures. In this paper, an innovative smart periodic beam structure with nonlinear interleaved-switched electric networks based on synchronized switching damping on inductor (SSDI) is proposed and investigated for vibration reduction and wave propagation attenuation. Different from locally resonant band gap mechanism forming narrow band gaps around the desired resonant frequencies, the proposed interleaved electrical networks can induce new broadly low-frequency stop bands and broaden primitive Bragg stop bands by virtue of unique interleaved electrical configurations and the SSDI technique which has the unique feature of realizing automatic impedance adaptation with a small inductance. Finite element modeling of a Timoshenko electromechanical beam structure is also presented for validating dispersion properties of the structure. Both theoretical and experimental results demonstrate that the proposed beam structure not only shows better vibration and wave propagation attenuation than the smart beam structure with independent switched networks, but also has technical simplicity of requiring only half of the number of switches than the independent switched network needs.
Sharma, P. R. Srikanth
Copolymers of methyl methacrylate (MMA) and 2-propenoic acid, 2-methyl-, 2-[[[[4-methyl-3-[[[2-methyl-4-nitrophenyl)amino]carbonyl]aminophenyl]carbonyl]oxy]ethyl ester (PAMEE) exhibiting nonlinear optical (NLO) properties have been synthesized. Two kinds of urethane containing interpenetrating polymer networks (IPNs), consisting of nonlinear optical (NLO) chromophore, 2-methyl-4-nitroaniline (MNA) or Disperse Red1 (DR1) have been synthesized. The IPN systems consist of either aliphatic polycarbonate urethane (PCU) or 2,6-dimethyl-1,4-phenylene oxide (PPO) as one network and crosslinked poly (MMA-co-PAMEE) or poly (MMA-co-PMNEE) as the second network. Copolymers and interpenetrating polymer networks (IPNs) were characterized by IR spectroscopy, UV-VIS spectroscopy, differential scanning calorimetry (DSC), scanning electron microscopy (SEM), and second harmonic generation (SHG) measurements. The thin films of copolymers and IPNs were optically transparent and the corona poled polymers produced relatively large and stable SHG signals at room temperature. To understand the polarization decay of our NLO polymer we studied a simple theoretical model which can account for the main features which we observe. The addition of an apparent "chemical" reaction with a reaction activation energy EAB to the neighbor-facilitated Fredrickson-Anderson model shows the existence of a beta relaxation occurring simultaneously with the main alpha process. The combination of an Ising-model with antiferromagnetic interaction and the neighbor-facilitated Fredrickson-Anderson model allows a description of the polarization decay of polarized materials, such as our polymers, below the glass transition temperature Tg. The relaxation time for the polarization scales with the relaxation time of the alpha-process of the glass transition, and shows a typical curvature in the ln tau versus T-1 plot. Real polymers, such as poly(MMA-co-PAMEE) which we study possess both of these features and its
Directory of Open Access Journals (Sweden)
Suliang Ma
2016-11-01
Full Text Available Photovoltaic (PV systems have non-linear characteristics that generate maximum power at one particular operating point. Environmental factors such as irradiance and temperature variations greatly affect the maximum power point (MPP. Diverse offline and online techniques have been introduced for tracking the MPP. Here, to track the MPP, an augmented-state feedback linearized (AFL non-linear controller combined with an artificial neural network (ANN is proposed. This approach linearizes the non-linear characteristics in PV systems and DC/DC converters, for tracking and optimizing the PV system operation. It also reduces the dependency of the designed controller on linearized models, to provide global stability. A complete model of the PV system is simulated. The existing maximum power-point tracking (MPPT and DC/DC boost-converter controller techniques are compared with the proposed ANN method. Two case studies, which simulate realistic circumstances, are presented to demonstrate the effectiveness and superiority of the proposed method. The AFL with ANN controller can provide good dynamic operation, faster convergence speed, and fewer operating-point oscillations around the MPP. It also tracks the global maxima under different conditions, especially irradiance-mutating situations, more effectively than the conventional methods. Detailed mathematical models and a control approach for a three-phase grid-connected intelligent hybrid system are proposed using MATLAB/Simulink.
Rios, Anthony; Kavuluru, Ramakanth
2015-09-01
Building high accuracy text classifiers is an important task in biomedicine given the wealth of information hidden in unstructured narratives such as research articles and clinical documents. Due to large feature spaces, traditionally, discriminative approaches such as logistic regression and support vector machines with n-gram and semantic features (e.g., named entities) have been used for text classification where additional performance gains are typically made through feature selection and ensemble approaches. In this paper, we demonstrate that a more direct approach using convolutional neural networks (CNNs) outperforms several traditional approaches in biomedical text classification with the specific use-case of assigning medical subject headings (or MeSH terms) to biomedical articles. Trained annotators at the national library of medicine (NLM) assign on an average 13 codes to each biomedical article, thus semantically indexing scientific literature to support NLM's PubMed search system. Recent evidence suggests that effective automated efforts for MeSH term assignment start with binary classifiers for each term. In this paper, we use CNNs to build binary text classifiers and achieve an absolute improvement of over 3% in macro F-score over a set of selected hard-to-classify MeSH terms when compared with the best prior results on a public dataset. Additional experiments on 50 high frequency terms in the dataset also show improvements with CNNs. Our results indicate the strong potential of CNNs in biomedical text classification tasks.
Kypraios, Ioannis; Young, Rupert C. D.; Birch, Philip M.; Chatwin, Christopher R.
2003-08-01
The various types of synthetic discriminant function (sdf) filter result in a weighted linear superposition of the training set images. Neural network training procedures result in a non-linear superposition of the training set images or, effectively, a feature extraction process, which leads to better interpolation properties than achievable with the sdf filter. However, generally, shift invariance is lost since a data dependant non-linear weighting function is incorporated in the input data window. As a compromise, we train a non-linear superposition filter via neural network methods with the constraint of a linear input to allow for shift invariance. The filter can then be used in a frequency domain based optical correlator. Simulation results are presented that demonstrate the improved training set interpolation achieved by the non-linear filter as compared to a linear superposition filter.
Micheloyannis, Sifis; Sakkalis, Vagelis; Vourkas, Michalis; Stam, Cornelis J; Simos, Panagiotis G
2005-01-20
Using linear and non-linear methods, electroencephalographic (EEG) signals were measured at various brain regions to provide information regarding patterns of local and coordinated activity during performance of three arithmetic tasks (number comparison, single-digit multiplication, and two-digit multiplication) and two control tasks that did not require arithmetic operations. It was hypothesized that these measures would reveal the engagement of local and increasingly complex cortical networks as a function of task specificity and complexity. Results indicated regionally increased neuronal signalling as a function of task complexity at frontal, temporal and parietal brain regions, although more robust task-related changes in EEG-indices of activation were derived over the left hemisphere. Both linear and non-linear indices of synchronization among EEG signals recorded from over different brain regions were consistent with the notion of more "local" processing for the number comparison task. Conversely, multiplication tasks were associated with a widespread pattern of distant signal synchronizations, which could potentially indicate increased demands for neural networks cooperation during performance of tasks that involve a greater number of cognitive operations.
Hwang, Chih-Lyang; Jan, Chau
2016-02-01
At the beginning, an approximate nonlinear autoregressive moving average (NARMA) model is employed to represent a class of multivariable nonlinear dynamic systems with time-varying delay. It is known that the disadvantages of robust control for the NARMA model are as follows: 1) suitable control parameters for larger time delay are more sensitive to achieving desirable performance; 2) it only deals with bounded uncertainty; and 3) the nominal NARMA model must be learned in advance. Due to the dynamic feature of the NARMA model, a recurrent neural network (RNN) is online applied to learn it. However, the system performance becomes deteriorated due to the poor learning of the larger variation of system vector functions. In this situation, a simple network is employed to compensate the upper bound of the residue caused by the linear parameterization of the approximation error of RNN. An e -modification learning law with a projection for weight matrix is applied to guarantee its boundedness without persistent excitation. Under suitable conditions, the semiglobally ultimately bounded tracking with the boundedness of estimated weight matrix is obtained by the proposed RNN-based multivariable adaptive control. Finally, simulations are presented to verify the effectiveness and robustness of the proposed control.
Directory of Open Access Journals (Sweden)
Jaime Buitrago
2017-01-01
Full Text Available Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN with exogenous multi-variable input (NARX. The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction.
A Novel Nonlinear Multitarget k-Degree Coverage Preservation Protocol in Wireless Sensor Networks
Directory of Open Access Journals (Sweden)
Zeyu Sun
2016-01-01
Full Text Available Due to the existence of a large number of redundant data in the process of covering multiple targets, the effective coverage of monitored region decreases, causing the network to consume more energy. To solve this problem, this paper proposes a multitarget k-degree coverage preservation protocol. Firstly, the affiliation between the sensor nodes and target nodes is established in the network model; meanwhile the method used to calculate the coverage expectation value of the monitored region is put forward; secondly, in the aspect of the network energy conversion, use scheduling mechanisms on the sensor nodes to balance the network energy and achieve different network coverage quality with energy conversion between different nodes. Finally, simulation results show that NMCP can improve the network lifetime by effectively reducing the number of active nodes to meet certain coverage requirements.
Contour Detection Using Cost-Sensitive Convolutional Neural Networks
Hwang, Jyh-Jing; Liu, Tyng-Luh
2014-01-01
We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient implementation of multiscale convolutional neural networks (CNNs), to extract an informative feature vector for each pixel and uses an SVM classifier to accomplish contour detection. The main challenge lies in adapting a pre-trained per-image CNN model for yielding per-pixel image features. We propose to base on the Den...
Directory of Open Access Journals (Sweden)
Athanasia Papoutsi
2014-03-01
Full Text Available The ways in which neurons are embedded in a network to support various computations determines the functional output of the cortex. Recently, a number of in vivo studies have shown that dendritic integration in pyramidal neurons shapes neuronal function (Smith et al., 2013; Longordo et al., 2013 and that clusters of few reciprocally connected neurons are co-activated during behavioral tasks (Ko et al., 2011, 2013; Morishima et al., 2011. In the prefrontal cortex (PFC, such microcircuits are linked to persistent activity (prolonged spiking activity that exceeds stimulus presentation, which is the cellular correlate of working memory (Papoutsi et al., 2013. However, the effect of dendritic integration on the functional output of such small microcircuits has remained unexplored. In this work, we investigate the contribution of nonlinear dendritic properties to the induction and coding of upcoming state transitions in PFC microcircuits. Towards this goal we used a heavily constrained biophysical model of a layer 5 PFC microcircuit consisting of 7 pyramidal neurons and 2 interneurons implemented in the NEURON simulation environment. All neuron models are biophysically detailed but morphologically simplified and validated regarding their intrinsic, synaptic and connectivity properties (Papoutsi et al., 2013. Our results show that the non-linear integration of synaptic inputs at the basal dendrites of pyramidal neurons, mediated by the induction of NMDA spikes, is imperative for the emergence of the persistent state in the microcircuit: if synaptic drive is sufficient to induce NMDA spikes, the minimum network size required for persistent activity induction can be reduced down to 2 cells. In addition, slow synaptic mechanisms, such as the NMDA and GABAB currents, determine the ability of a given stimulus to induce persistent firing in the microcircuit model. On the other hand, the necessity for NMDA spikes disappears when persistent activity depends on
Nonlinear dynamics analysis of a self-organizing recurrent neural network: chaos waning.
Directory of Open Access Journals (Sweden)
Jürgen Eser
Full Text Available Self-organization is thought to play an important role in structuring nervous systems. It frequently arises as a consequence of plasticity mechanisms in neural networks: connectivity determines network dynamics which in turn feed back on network structure through various forms of plasticity. Recently, self-organizing recurrent neural network models (SORNs have been shown to learn non-trivial structure in their inputs and to reproduce the experimentally observed statistics and fluctuations of synaptic connection strengths in cortex and hippocampus. However, the dynamics in these networks and how they change with network evolution are still poorly understood. Here we investigate the degree of chaos in SORNs by studying how the networks' self-organization changes their response to small perturbations. We study the effect of perturbations to the excitatory-to-excitatory weight matrix on connection strengths and on unit activities. We find that the network dynamics, characterized by an estimate of the maximum Lyapunov exponent, becomes less chaotic during its self-organization, developing into a regime where only few perturbations become amplified. We also find that due to the mixing of discrete and (quasi-continuous variables in SORNs, small perturbations to the synaptic weights may become amplified only after a substantial delay, a phenomenon we propose to call deferred chaos.
DEFF Research Database (Denmark)
Chon, K H; Hoyer, D; Armoundas, A A;
1999-01-01
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...
Nonlinear dynamics analysis of a self-organizing recurrent neural network: chaos waning.
Eser, Jürgen; Zheng, Pengsheng; Triesch, Jochen
2014-01-01
Self-organization is thought to play an important role in structuring nervous systems. It frequently arises as a consequence of plasticity mechanisms in neural networks: connectivity determines network dynamics which in turn feed back on network structure through various forms of plasticity. Recently, self-organizing recurrent neural network models (SORNs) have been shown to learn non-trivial structure in their inputs and to reproduce the experimentally observed statistics and fluctuations of synaptic connection strengths in cortex and hippocampus. However, the dynamics in these networks and how they change with network evolution are still poorly understood. Here we investigate the degree of chaos in SORNs by studying how the networks' self-organization changes their response to small perturbations. We study the effect of perturbations to the excitatory-to-excitatory weight matrix on connection strengths and on unit activities. We find that the network dynamics, characterized by an estimate of the maximum Lyapunov exponent, becomes less chaotic during its self-organization, developing into a regime where only few perturbations become amplified. We also find that due to the mixing of discrete and (quasi-)continuous variables in SORNs, small perturbations to the synaptic weights may become amplified only after a substantial delay, a phenomenon we propose to call deferred chaos.
Non-Linear State Estimation Using Pre-Trained Neural Networks
DEFF Research Database (Denmark)
Bayramoglu, Enis; Andersen, Nils Axel; Ravn, Ole
2010-01-01
effecting the transformation. This function is approximated by a neural network using offline training. The training is based on monte carlo sampling. A way to obtain parametric distributions of flexible shape to be used easily with these networks is also presented. The method can also be used to improve...
Jaspers, Maarten; Vaessen, Sarah L.; van Schayik, Pim; Voerman, Dion; Rowan, Alan E.; Kouwer, Paul H. J.
2017-05-01
The mechanical properties of cells and the extracellular environment they reside in are governed by a complex interplay of biopolymers. These biopolymers, which possess a wide range of stiffnesses, self-assemble into fibrous composite networks such as the cytoskeleton and extracellular matrix. They interact with each other both physically and chemically to create a highly responsive and adaptive mechanical environment that stiffens when stressed or strained. Here we show that hybrid networks of a synthetic mimic of biological networks and either stiff, flexible and semi-flexible components, even very low concentrations of these added components, strongly affect the network stiffness and/or its strain-responsive character. The stiffness (persistence length) of the second network, its concentration and the interaction between the components are all parameters that can be used to tune the mechanics of the hybrids. The equivalence of these hybrids with biological composites is striking.
Nonlinear Maps for Design of Discrete-Time Models of Neuronal Network Dynamics
2016-03-31
responsive tiring patterns . We propose to use modern DSP ideas to develop new efficient approaches to the design of such discrete-time models for...2016 Performance/Technic~ 03-01-2016- 03-31-2016 4. TITLE AND SUBTITLE Sa. CONTRACT NUMBER Nonlinear Maps for Design of Discrete-Time Models of...simulations is to design a neuronal model in the form of difference equations that generates neuronal states in discrete moments of time. In this
Cao, Hui; Li, Yao-Jiang; Zhou, Yan; Wang, Yan-Xia
2014-11-01
To deal with nonlinear characteristics of spectra data for the thermal power plant flue, a nonlinear partial least square (PLS) analysis method with internal model based on neural network is adopted in the paper. The latent variables of the independent variables and the dependent variables are extracted by PLS regression firstly, and then they are used as the inputs and outputs of neural network respectively to build the nonlinear internal model by train process. For spectra data of flue gases of the thermal power plant, PLS, the nonlinear PLS with the internal model of back propagation neural network (BP-NPLS), the non-linear PLS with the internal model of radial basis function neural network (RBF-NPLS) and the nonlinear PLS with the internal model of adaptive fuzzy inference system (ANFIS-NPLS) are compared. The root mean square error of prediction (RMSEP) of sulfur dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 16.96%, 16.60% and 19.55% than that of PLS, respectively. The RMSEP of nitric oxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 8.60%, 8.47% and 10.09% than that of PLS, respectively. The RMSEP of nitrogen dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 2.11%, 3.91% and 3.97% than that of PLS, respectively. Experimental results show that the nonlinear PLS is more suitable for the quantitative analysis of glue gas than PLS. Moreover, by using neural network function which can realize high approximation of nonlinear characteristics, the nonlinear partial least squares method with internal model mentioned in this paper have well predictive capabilities and robustness, and could deal with the limitations of nonlinear partial least squares method with other internal model such as polynomial and spline functions themselves under a certain extent. ANFIS-NPLS has the best performance with the internal model of adaptive fuzzy inference system having ability to learn more and reduce the residuals effectively. Hence, ANFIS-NPLS is an
Directory of Open Access Journals (Sweden)
Gurudeo Anand Tularam
2012-01-01
Full Text Available House price prediction continues to be important for government agencies insurance companies and real estate industry. This study investigates the performance of house sales price models based on linear and non-linear approaches to study the effects of selected variables. Linear stepwise Multivariate Regression (MR and nonlinear models of Neural Network (NN and Adaptive Neuro-Fuzzy (ANFIS are developed and compared. The GIS methods are used to integrate the data for the study area (Bathurst, Australia. While it was expected that the nonlinear methods would be much better the analysis shows NN and ANFIS are only slightly better than MR suggesting questions about high R2 often found in the literature. While structural data and macro-finance variables may contribute to higher R2 performance comparison was the goal of this study and besides the Australian data lacked structural elements. The results show that MR model could be improved. Also, the land value and location explained at best about 45% of the sale price variation. The analysis of price forecasts (within the 10% range of the actual prediction on average revealed that the non-linear models performed slightly better (29% than the linear (26%. The inclusion of social data improves the MR prediction in most of the suburbs. The suburbs analysis shows the importance of socially based locations and also variance due to types of housing dominant. In general terms of R2, the NN model (0.45 performed only slightly better than ANFIS 0.39 and better than MR (0.37; but the linear MRsoc performed better (0.42. In suburb level, the NN model (7/15 performed better than ANFIS (3/15 but the linear MR (5/15 was better than ANFIS. The improved linear MR (6/15 performed nearly as well as the non-linear NN. Linear methods appear to just as precise as the the more time consuming non linear methods in most cases for accounting for the differences and variation. However, when a much more in depth analysis is
Fitness Effects of Network Non-Linearity Induced by Gene Expression Noise
Ray, Christian; Cooper, Tim; Balazsi, Gabor
2012-02-01
In the non-equilibrium dynamics of growing microbial cells, metabolic enzymes can create non-linearities in metabolite concentration because of non-linear degradation (utilization): an enzyme can saturate in the process of metabolite utilization. Increasing metabolite production past the saturation point then results in an ultrasensitive metabolite response. If the production rate of a metabolite depends on a second enzyme or other protein-mediated process, uncorrelated gene expression noise can thus cause transient metabolite concentration bursts. Such bursts are physiologically unnecessary and may represent a source of selection against the ultrasensitive switch, especially if the fluctuating metabolic intermediate is toxic. Selection may therefore favor correlated gene expression fluctuations for enzymes in the same pathway, such as by same-operon membership in bacteria. Using a modified experimental lac operon system, we are undertaking a combined theoretical-experimental approach to demonstrate that (i) the lac operon has an implicit ultrasensitive switch that we predict is avoided by gene expression correlations induced by same-operon membership; (ii) bacterial growth rates are sensitive to crossing the ultrasensitive threshold. Our results suggest that correlations in intrinsic gene expression noise are exploited by evolution to ameliorate the detrimental effects of nonlinearities in metabolite concentrations.
一种组合神经网络非线性判决反馈均衡器%A New Nonlinear Adaptive Equalizer Based on Combined Neural Networks
Institute of Scientific and Technical Information of China (English)
王军锋; 张斌; 宋国乡
2003-01-01
A new nonlinear decision feedback adaptive equalizer based on Adaline neural network and radial-basis-function neural network is presented. Its structure and algorithm are also investigated. For a typical linear and non-linear channel models, computer simulation shows that its convergence speed is faster and its stable mean square erroris less.
Agarwal, Shankar; Feldman, Hume A; Lahav, Ofer; Thomas, Shaun A
2013-01-01
In this paper we introduce PkANN, a freely available software package for interpolating the non-linear matter power spectrum, constructed using Artificial Neural Networks (ANNs). Previously, using Halofit to calculate matter power spectrum, we demonstrated that ANNs can make extremely quick and accurate predictions of the power spectrum. Now, using a suite of 6380 N-body simulations spanning 580 cosmologies, we train ANNs to predict the power spectrum over the cosmological parameter space spanning $3\\sigma$ confidence level (CL) around the concordance cosmology. When presented with a set of cosmological parameters ($\\Omega_{\\rm m} h^2, \\Omega_{\\rm b} h^2, n_s, w, \\sigma_8, \\sum m_\
Directory of Open Access Journals (Sweden)
Jiuping Xu
2012-01-01
Full Text Available The aim of this study is to deal with a minimum cost network flow problem (MCNFP in a large-scale construction project using a nonlinear multiobjective bilevel model with birandom variables. The main target of the upper level is to minimize both direct and transportation time costs. The target of the lower level is to minimize transportation costs. After an analysis of the birandom variables, an expectation multiobjective bilevel programming model with chance constraints is formulated to incorporate decision makers’ preferences. To solve the identified special conditions, an equivalent crisp model is proposed with an additional multiobjective bilevel particle swarm optimization (MOBLPSO developed to solve the model. The Shuibuya Hydropower Project is used as a real-world example to verify the proposed approach. Results and analysis are presented to highlight the performances of the MOBLPSO, which is very effective and efficient compared to a genetic algorithm and a simulated annealing algorithm.
Li, Xiao-Jian; Yang, Guang-Hong
2016-10-26
This paper is concerned with the adaptive decentralized fault-tolerant tracking control problem for a class of uncertain interconnected nonlinear systems with unknown strong interconnections. An algebraic graph theory result is introduced to address the considered interconnections. In addition, to achieve the desirable tracking performance, a neural-network-based robust adaptive decentralized fault-tolerant control (FTC) scheme is given to compensate the actuator faults and system uncertainties. Furthermore, via the Lyapunov analysis method, it is proven that all the signals of the resulting closed-loop system are semiglobally bounded, and the tracking errors of each subsystem exponentially converge to a compact set, whose radius is adjustable by choosing different controller design parameters. Finally, the effectiveness and advantages of the proposed FTC approach are illustrated with two simulated examples.
Wen, Guoxing; Chen, C L Philip; Liu, Yan-Jun; Liu, Zhi
2016-10-11
Compared with the existing neural network (NN) or fuzzy logic system (FLS) based adaptive consensus methods, the proposed approach can greatly alleviate the computation burden because it needs only to update a few adaptive parameters online. In the multiagent agreement control, the system uncertainties derive from the unknown nonlinear dynamics are counteracted by employing the adaptive NNs; the state delays are compensated by designing a Lyapunov-Krasovskii functional. Finally, based on Lyapunov stability theory, it is demonstrated that the proposed consensus scheme can steer a multiagent system synchronizing to the predefined reference signals. Two simulation examples, a numerical multiagent system and a practical multimanipulator system, are carried out to further verify and testify the effectiveness of the proposed agreement approach.
Directory of Open Access Journals (Sweden)
Wei Zhang
2016-06-01
Full Text Available In the aerospace and aviation sectors, the damage tolerance concept has been applied widely so that the modeling analysis of fatigue crack growth has become more and more significant. Since the process of crack propagation is highly nonlinear and determined by many factors, such as applied stress, plastic zone in the crack tip, length of the crack, etc., it is difficult to build up a general and flexible explicit function to accurately quantify this complicated relationship. Fortunately, the artificial neural network (ANN is considered a powerful tool for establishing the nonlinear multivariate projection which shows potential in handling the fatigue crack problem. In this paper, a novel fatigue crack calculation algorithm based on a radial basis function (RBF-ANN is proposed to study this relationship from the experimental data. In addition, a parameter called the equivalent stress intensity factor is also employed as training data to account for loading interaction effects. The testing data is then placed under constant amplitude loading with different stress ratios or overloads used for model validation. Moreover, the Forman and Wheeler equations are also adopted to compare with our proposed algorithm. The current investigation shows that the ANN-based approach can deliver a better agreement with the experimental data than the other two models, which supports that the RBF-ANN has nontrivial advantages in handling the fatigue crack growth problem. Furthermore, it implies that the proposed algorithm is possibly a sophisticated and promising method to compute fatigue crack growth in terms of loading interaction effects.
Nonlinear Maps for Design of Discrete Time Models of Neuronal Network Dynamics
2016-02-29
and K+ pumps responsible for generation of action potential (spike). This map is of the form Xn+l = fa(Xn, y), where Xn is a dynamical variable and...function fa(. . ) is a piecewise nonlinear function containing three segments . In the original form the function is { a 1 + y, Xn ~ 0, fa(Xn,y...a~~~ 0 < Xn <a+ y and Xn-1 ~ 0, -1, Xn 2:: a+ y or Xn- 1 > 0, where variable Xn_ 1 is used to define a condition that prevents system to remain at
Neural Network Nonlinear Predictive Control Based on Tent-map Chaos Optimization%基于Tent混沌优化的神经网络预测控制
Institute of Scientific and Technical Information of China (English)
宋莹; 陈增强; 袁著祉
2007-01-01
With the unique ergodicity, irregularity, and special ability to avoid being trapped in local optima, chaos optimization has been a novel global optimization technique and has attracted considerable attention for application in various fields, such as nonlinear programming problems. In this article, a novel neural network nonlinear predictive control (NNPC) strategy based on the new Tent-map chaos optimization algorithm (TCOA) is presented. The feedforward neural network is used as the multi-step predictive model. In addition, the TCOA is applied to perform the nonlinear rolling optimization to enhance the convergence and accuracy in the NNPC. Simulation on a laboratory-scale liquid-level system is given to illustrate the effectiveness of the proposed method.
Gradient radial basis function networks for nonlinear and nonstationary time series prediction.
Chng, E S; Chen, S; Mulgrew, B
1996-01-01
We present a method of modifying the structure of radial basis function (RBF) network to work with nonstationary series that exhibit homogeneous nonstationary behavior. In the original RBF network, the hidden node's function is to sense the trajectory of the time series and to respond when there is a strong correlation between the input pattern and the hidden node's center. This type of response, however, is highly sensitive to changes in the level and trend of the time series. To counter these effects, the hidden node's function is modified to one which detects and reacts to the gradient of the series. We call this new network the gradient RBF (GRBF) model. Single and multistep predictive performance for the Mackey-Glass chaotic time series were evaluated using the classical RBF and GRBF models. The simulation results for the series without and with a tine-varying mean confirm the superior performance of the GRBF predictor over the RBF predictor.
Convergence and periodicity in a delayed network of neurons with threshold nonlinearity
Directory of Open Access Journals (Sweden)
Shangjiang Guo
2003-05-01
Full Text Available We consider an artificial neural network where the signal transmission is of a digital (McCulloch-Pitts nature and is delayed due to the finite switching speed of neurons (amplifiers. The discontinuity of the signal transmission functions, however, makes it difficult to apply the existing dynamical systems theory which usually requires continuity and smoothness. Moreover, observe that the dynamics of the network completely depends on the connection weights, we distinguish several cases to discuss the behaviors of their solutions. We show that the dynamics of the model can be understood in terms of the iterations of a one-dimensional map. As, a result, we present a detailed analysis of the dynamics of the network starting from non-oscillatory states and show how the connection topology and synaptic weights determine the rich dynamics.
Contribution of hidden modes to nonlinear epidemic dynamics in urban human proximity networks
Fujiwara, Naoya; Iwayama, Koji; Aihara, Kazuyuki
2015-01-01
Recently developed techniques to acquire high-quality human mobility data allow large-scale simulations of the spread of infectious diseases with high spatial and temporal resolution.Analysis of such data has revealed the oversimplification of existing theoretical frameworks to infer the final epidemic size or influential nodes from the network topology. Here we propose a spectral decomposition-based framework for the quantitative analysis of epidemic processes on realistic networks of human proximity derived from urban mobility data. Common wisdom suggests that modes with larger eigenvalues contribute more to the epidemic dynamics. However, we show that hidden dominant structures, namely modes with smaller eigenvalues but a greater contribution to the epidemic dynamics, exist in the proximity network. This framework provides a basic understanding of the relationship between urban human motion and epidemic dynamics, and will contribute to strategic mitigation policy decisions.
Chacón, R.; García-Hoz, A. Martínez; Martínez, J. A.
2017-05-01
We study the effectiveness of locally controlling the impulse transmitted by parametric periodic excitations at inducing and suppressing chaos in starlike networks of driven damped pendula, leading to asynchronous chaotic states and equilibria, respectively. We found that the inducing (suppressor) effect of increasing (decreasing) the impulse transmitted by the parametric excitations acting on particular nodes depends strongly on their number and degree of connectivity as well as the coupling strength. Additionally, we provide a theoretical analysis explaining the basic physical mechanisms of the emergence and suppression of chaos as well as the main features of the chaos-control scenario. Our findings constitute proof of the impulse-induced control of chaos in a simple model of complex networks, thus opening the way to its application to real-world networks.
DEFF Research Database (Denmark)
Asif, Rameez
2016-01-01
We have evaluated that in-line non-linear compensation schemes decrease the complexity of digital backward propagation and enhance the transmission performance of 40/112/224 Gbit/s mixed line rate network. Multiple bit rates, i.e. 40/112/224 Gbit/s and modulation formats (i.e. DP-QPSK and DP-16QA...
Application of nonlinear neural network to analyze the stope structure parameters
Energy Technology Data Exchange (ETDEWEB)
Lai, X.; Cai, M.; Zhang, B. [University of Science and Technoogy of Beijing (China). Civil and Environmental School
2001-06-01
In this paper, the state-of-the-art of neural computing in geotechnical structural analysis and design has been surveyed. Its computing strategies and research trends are given. The principle of the BP neural networks and computing for constitutive modelling have been discussed, then achieved in applying to analyse the underground stope structure parameters in the Xincheng gold mine with the applications of BP network, it is proven that the neurocomputing is a practical tool for solving large-scale rock underground structural engineering problems. 4 refs., 2 figs., 2 tabs.
Third-Order Leader-Following Consensus in a Nonlinear Multiagent Network via Impulsive Control
Directory of Open Access Journals (Sweden)
Xiaomei Li
2013-01-01
Full Text Available Many facts indicate that the impulsive control method is a finer method, which is simple, efficient, and low in cost, for achieving consensus. In this paper, based on graph theory, Lyapunov stability theory, and matrix theory, a novel impulsive control protocol is given to realize the consensus of the multiagent network. Numerical simulations are performed to verify the theoretical results.
Experimental mapping of nonlinear dynamics in synchronized coupled semiconductor laser networks
Argyris, Apostolos; Bourmpos, Michail; Syvridis, Dimitris
2015-05-01
The potential of conventional semiconductor lasers to generate complex and chaotic dynamics at a bandwidth that extends up to tens of GHz turns them into useful components in applications oriented to sensing and security. Specifically, latest theoretical and experimental works have demonstrated the capability of mutually coupled semiconductor lasers to exhibit a joint behaviour under various conditions. In an uncoupled network consisting of N similar SLs - representing autonomous nodes in the network - each node emits an optical signal of various dynamics depending on its biasing conditions and internal properties. These nodes remain unsynchronized unless appropriate coupling and biasing conditions apply. A synchronized behaviour can be in principle observed in sub-groups of lasers or in the overall laser network. In the present work, experimental topologies that employ eight SLs, under diverse biasing and coupling conditions, are built and investigated. The deployed systems incorporate off-the-shelf fiber-optic communications components operating at the 1550nm spectral window. The role of emission wavelength detuning of each participating node in the network - at GHz level - is evaluated.
Kaabi, Mohamed Ghaith; Tonnelier, Arnaud; Martinez, Dominique
2011-05-01
In traditional event-driven strategies, spike timings are analytically given or calculated with arbitrary precision (up to machine precision). Exact computation is possible only for simplified neuron models, mainly the leaky integrate-and-fire model. In a recent paper, Zheng, Tonnelier, and Martinez (2009) introduced an approximate event-driven strategy, named voltage stepping, that allows the generic simulation of nonlinear spiking neurons. Promising results were achieved in the simulation of single quadratic integrate-and-fire neurons. Here, we assess the performance of voltage stepping in network simulations by considering more complex neurons (quadratic integrate-and-fire neurons with adaptation) coupled with multiple synapses. To handle the discrete nature of synaptic interactions, we recast voltage stepping in a general framework, the discrete event system specification. The efficiency of the method is assessed through simulations and comparisons with a modified time-stepping scheme of the Runge-Kutta type. We demonstrated numerically that the original order of voltage stepping is preserved when simulating connected spiking neurons, independent of the network activity and connectivity.
Liu, Derong; Wang, Ding; Wang, Fei-Yue; Li, Hongliang; Yang, Xiong
2014-12-01
In this paper, the infinite horizon optimal robust guaranteed cost control of continuous-time uncertain nonlinear systems is investigated using neural-network-based online solution of Hamilton-Jacobi-Bellman (HJB) equation. By establishing an appropriate bounded function and defining a modified cost function, the optimal robust guaranteed cost control problem is transformed into an optimal control problem. It can be observed that the optimal cost function of the nominal system is nothing but the optimal guaranteed cost of the original uncertain system. A critic neural network is constructed to facilitate the solution of the modified HJB equation corresponding to the nominal system. More importantly, an additional stabilizing term is introduced for helping to verify the stability, which reinforces the updating process of the weight vector and reduces the requirement of an initial stabilizing control. The uniform ultimate boundedness of the closed-loop system is analyzed by using the Lyapunov approach as well. Two simulation examples are provided to verify the effectiveness of the present control approach.
Yu, Haitao; Liu, Jing; Cai, Lihui; Wang, Jiang; Cao, Yibin; Hao, Chongqing
2017-02-01
Electroencephalogram (EEG) signal evoked by acupuncture stimulation at "Zusanli" acupoint is analyzed to investigate the modulatory effect of manual acupuncture on the functional brain activity. Power spectral density of EEG signal is first calculated based on the autoregressive Burg method. It is shown that the EEG power is significantly increased during and after acupuncture in delta and theta bands, but decreased in alpha band. Furthermore, synchronization likelihood is used to estimate the nonlinear correlation between each pairwise EEG signals. By applying a threshold to resulting synchronization matrices, functional networks for each band are reconstructed and further quantitatively analyzed to study the impact of acupuncture on network structure. Graph theoretical analysis demonstrates that the functional connectivity of the brain undergoes obvious change under different conditions: pre-acupuncture, acupuncture, and post-acupuncture. The minimum path length is largely decreased and the clustering coefficient keeps increasing during and after acupuncture in delta and theta bands. It is indicated that acupuncture can significantly modulate the functional activity of the brain, and facilitate the information transmission within different brain areas. The obtained results may facilitate our understanding of the long-lasting effect of acupuncture on the brain function.
Directory of Open Access Journals (Sweden)
Neela Deshpande
2014-12-01
Full Text Available In the recent past Artificial Neural Networks (ANN have emerged out as a promising technique for predicting compressive strength of concrete. In the present study back propagation was used to predict the 28 day compressive strength of recycled aggregate concrete (RAC along with two other data driven techniques namely Model Tree (MT and Non-linear Regression (NLR. Recycled aggregate is the current need of the hour owing to its environmental friendly aspect of re-use of the construction waste. The study observed that, prediction of 28 day compressive strength of RAC was done better by ANN than NLR and MT. The input parameters were cubic meter proportions of Cement, Natural fine aggregate, Natural coarse Aggregates, recycled aggregates, Admixture and Water (also called as raw data. The study also concluded that ANN performs better when non-dimensional parameters like Sand–Aggregate ratio, Water–total materials ratio, Aggregate–Cement ratio, Water–Cement ratio and Replacement ratio of natural aggregates by recycled aggregates, were used as additional input parameters. Study of each network developed using raw data and each non dimensional parameter facilitated in studying the impact of each parameter on the performance of the models developed using ANN, MT and NLR as well as performance of the ANN models developed with limited number of inputs. The results indicate that ANN learn from the examples and grasp the fundamental domain rules governing strength of concrete.
Toward Model-Based Control of Non-linear Hydraulic Networks
DEFF Research Database (Denmark)
Tahavori, Maryamsadat; Jensen, Tom Nørgaard; Kallesøe, Carsten;
2013-01-01
consumption. To have a better understanding of leakage in WSSs, to control pressure and leakage effectively, and for optimal design of WSSs, suitable modeling is an important prerequisite. In this paper a model with the main objective of pressure control and consequently leakage reduction is presented......Water leakage is an important component of water loss. Many methods have emerged from urban water supply systems (WSSs) for leakage control, but it still remains a challenge in many countries. Pressure management is an effective way to reduce the leakage in a system. It can also reduce the power....... Following an analogy to electric circuits, first the mathematical expression for pressure drop over each component of the pipe network (WSS) such as pipes, pumps, valves and water towers is presented. Then the network model is derived based on the circuit theory and subsequently used for pressure management...
Directory of Open Access Journals (Sweden)
O. О. Sudakov
2015-12-01
Full Text Available In present work the Ukrainian National Grid (UNG infrastructure was applied for investigation of synchronization in large networks of interacting neurons. This application is important for solving of modern neuroscience problems related to mechanisms of nervous system activities (memory, cognition etc. and nervous pathologies (epilepsy, Parkinsonism, etc.. Modern non-linear dynamics theories and applications provides powerful basis for computer simulations of biological neuronal networks and investigation of phenomena which mechanisms hardly could be clarified by other approaches. Cubic millimeter of brain tissue contains about 105 neurons, so realistic (Hodgkin-Huxley model and phenomenological (Kuramoto-Sakaguchi, FitzHugh-Nagumo, etc. models simulations require consideration of large neurons numbers.
Observer-Based Control Design for Nonlinear Networked Control Systems with Limited Information
Directory of Open Access Journals (Sweden)
Yilin Wang
2013-01-01
Full Text Available This paper is concerned with the problem of designing a robust observer-based controller for discrete-time networked systems with limited information. An improved networked control system model is proposed and the effects of random packet dropout, time-varying delay, and quantization are considered simultaneously. Based on the obtained model, a stability criterion is developed by constructing an appropriate Lyapunov-Krasovskii functional and sufficient conditions for the existence of a dynamic quantized output feedback controller which are given in terms of linear matrix inequalities (LMIs such that the augmented error system is stochastically stable with an performance level. An example is presented to illustrate the effectiveness of the proposed method.
Nonlinear momentum transfer control of a gyrostat with a discrete damper using neural networks
Seo, In-Ho; Leeghim, Henzeh; Bang, Hyochoong
2008-03-01
An adaptive feedback linearization technique combined with neural networks is addressed for the momentum transfer control of a torque-free gyrostat with an attached spring-mass-dashpot damper. The neural network is used to adaptively compensate for the model error uncertainties of internal dynamics. The total spacecraft angular momentum component of the wheel spin axis is selected as an output function for the feedback linearization. Thus, a desired output function is predefined for which the total angular momentum of the spacecraft is absorbed into the wheel spin direction at the steady state with nutation angle converging to zero. The ultimate boundedness of the tracking error is proved by the Lyapunov stability theory. We also investigate the effect of rotor misalignment on the steady spin of the spacecraft and the initial stability condition to overcome the inverted turn due to unstable mass moment of inertia configuration. The effectiveness of the proposed control law is verified through a simulation study.
Directory of Open Access Journals (Sweden)
Janmenjoy Nayak
2015-09-01
Full Text Available In this paper, a Chemical Reaction Optimization (CRO based higher order neural network with a single hidden layer called Pi–Sigma Neural Network (PSNN has been proposed for data classification which maintains fast learning capability and avoids the exponential increase of number of weights and processing units. CRO is a recent metaheuristic optimization algorithm inspired by chemical reactions, free from intricate operator and parameter settings such as other algorithms and loosely couples chemical reactions with optimization. The performance of the proposed CRO-PSNN has been tested with various benchmark datasets from UCI machine learning repository and compared with the resulting performance of PSNN, GA-PSNN, PSO-PSNN. The methods have been implemented in MATLAB and the accuracy measures have been tested by using the ANOVA statistical tool. Experimental results show that the proposed method is fast, steady and reliable and provides better classification accuracy than others.
1992-09-01
input. The architecture of artificial neural-network has three main levels: topological, data flow, and neurodynamics . The architectural and...and neurodynamics . The presentation here will follow the guidelines of Neural Computing by NeuralWare, Inc. [NC91], who developed the basic software... neurodynamics , describes in detail the operations that act upon the data within a processing element. This level defines the functions and the
Institute of Scientific and Technical Information of China (English)
Chen Di-Lan; Zhang Wei-Dong
2008-01-01
This paper is concerned with the problem of robust H∞ control for structured uncertain stochastic neural networks with both discrete and distributed time varying delays. A sufficient condition is presented for the existence of H∞ control based on the Lyapunov stability theory. The stability criterion is described in terms of linear matrix inequalities (LMIs),which can be easily checked in practice. An example is provided to demonstrate the effectiveness of the proposed result.
Energy Technology Data Exchange (ETDEWEB)
Jammes, B. [Centre National de la Recherche Scientifique (CNRS), 31 - Toulouse (France). Laboratoire d`Analyse et d`Architecture des Systemes; Dragos, A. [Bucharest Univ. Politechnica (Romania)
1998-11-01
In this paper, artificial neural networks are used to elaborate non-linear control of the average output voltage of Buck and Boost converters. The training of the regulator is based on the adjustment technique used by indirect adaptative command structures. These techniques require a system model and performances of inputs/outputs and state models are compared. It is shown that this approach allows to generate non-linear regulators for the converters under study, but it is preferable to introduce some modifications in order to facilitate the training of the regulator. (J.S.) 4 refs.
Modeling Topology and Nonlinear Dynamical Behavior of the Weighted Scale-Free Networks
Institute of Scientific and Technical Information of China (English)
YANG Qiu-Ying; ZHANG Gui-Qing; ZHANG Ying-Yue; CHEN Tian-Lun
2008-01-01
An improved weighted scale-free network,which has two evolution mechanisms:topological growth and strength dynamics,has been introduced.The topology structure of the model will be explored in details in this work.The evolution driven mechanism of Olami-Feder-Christensen (OFC) model is added to our model to study the self-organized criticality and the dynamical behavior.We also.consider attack mechanism and the study of the model with attack is also investigated in this paper.We find there axe differences between the model with attack and without attack.
On the Capability of Artificial Neural Networks to Compensate Nonlinearities in Wavelength Sensing
Directory of Open Access Journals (Sweden)
Otto Manck
2009-04-01
Full Text Available An intelligent sensor for light wavelength readout, suitable for visible range optical applications, has been developed. Using buried triple photo-junction as basic pixel sensing element in combination with artificial neural network (ANN, the wavelength readout with a full-scale error of less than 1.5% over the range of 400 to 780 nm can be achieved. Through this work, the applicability of the ANN approach in optical sensing is investigated and compared with conventional methods, and a good compromise between accuracy and the possibility for on-chip implementation was thus found. Indeed, this technique can serve different purposes and may replace conventional methods.
Directory of Open Access Journals (Sweden)
Abd El-Naser A. Mohammed
2010-09-01
Full Text Available In the present paper, the problem amplification techniques of ultra dense wavelength division multiplexing (UDWDM in nonlinear optical networks are investigated through five transmission techniques. The impact of tailoring of chirped pulses of different temporal waveforms is investigated in a normal dispersion fiber. The set of multiplexed signals are tailored in a different a subset to assure approximately the same output level of power to hold the signal-to-noise ratio at the same level. Moreover, three different transmission techniques, namely, soliton propagation, maximum time division multiplexing (MTDM and ìShannonî capacity, are employed where successive section of alternating dispersion are used as a technique to manage the dispersion. Distributed ìRamanî amplifiers as well as Erbium doped fiber amplifier are engaged to maximize the repeater spacing. We have succeeded to multiplex 2400 (UDWDM channels in the optical range 1.45 1.65 µm with channel spacing ranging from 0.3 up to 0.6 nm where each channel has its own characteristic parameters of loss, dispersion, and amplification. The channels are divided into sub-groups ( each of 4, 5, 6, 7,Ö.,24 where the technique of space division multiplexing (SDM is applied. The multispan effects of ìKerrî nonlinearity and amplifier noise on ìShannonî channel capacity of dispersion-free nonlinear fiber is considered as a ceiling value for the sake of comparison. The case of soliton with modified Raman amplification via parametric gain also is investigated. Each link has special chemical structure, optical signals power, and optical Raman pumping. The cable contains {4, 5, 6, 7,Ö. , 24} links in SDM. It has been shown that the modified Raman gain yields higher effects on the variable under consideration if compared with the conventional Raman gain. The number of links is in positive correlations with the set of effects {Repeater spacing, Soliton product, MTDM product}. In general
Edelen, A. L.; Biedron, S. G.; Milton, S. V.; Edelen, J. P.
2016-01-01
At present, a variety of image-based diagnostics are used in particle accelerator systems. Often times, these are viewed by a human operator who then makes appropriate adjustments to the machine. Given recent advances in using convolutional neural networks (CNNs) for image processing, it should be possible to use image diagnostics directly in control routines (NN-based or otherwise). This is especially appealing for non-intercepting diagnostics that could run continuously during beam operatio...
A Deep 3D Convolutional Neural Network Based Design for Manufacturability Framework
Balu, Aditya; Lore, Kin Gwn; Young, Gavin; Krishnamurthy, Adarsh; Sarkar, Soumik
2016-01-01
Deep 3D Convolutional Neural Networks (3D-CNN) are traditionally used for object recognition, video data analytics and human gesture recognition. In this paper, we present a novel application of 3D-CNNs in understanding difficult-to-manufacture features from computer-aided design (CAD) models to develop a decision support tool for cyber-enabled manufacturing. Traditionally, design for manufacturability (DFM) rules are hand-crafted and used to accelerate the engineering product design cycle by...
Directory of Open Access Journals (Sweden)
El-Sayed A. El-Badawy
2008-02-01
Full Text Available Although research into the use of optics in computers has increased in the last and current decades, the fact remains that electronics is still superior to optics in almost every way. Research into the use of optics at this stage mirrors the research into electronics after the 2nd World War. The advantages of using fiber optics over wiring are the same as the argument for using optics over electronics in computers. Even through totally optical computers are now a reality, computers that combine both electronics and optics, electro-optic hybrids, have been in use for some time. In the present paper, architecture of optical interconnect is built up on the bases of four Vertical-Cavity Surface- Emitting Laser Diodes (VCSELD and two optical links where thermal effects of both the diodes and the links are included. Nonlinear relations are correlated to investigate the power-current and the voltage-current dependences of the four devices. The good performance (high speed of the interconnect is deeply and parametrically investigated under wide ranges of the affecting parameters. The high speed performance is processed through three different effects, namely the device 3-dB bandwidth, the link dispersion characteristics, and the transmitted bit rate (soliton. Eight combinations are investigated; each possesses its own characteristics. The best architecture is the one composed of VCSELD that operates at 850 nm and the silica fiber whatever the operating set of causes. This combination possesses the largest device 3-dB bandwidth, the largest link bandwidth and the largest soliton transmitted bit rate. The increase of the ambient temperature reduces the high-speed performance of the interconnect
Directory of Open Access Journals (Sweden)
El-Sayed A. El-Badawy
2008-02-01
Full Text Available Although research into the use of optics in computers has increased in the last and current decades, the fact remains that electronics is still superior to optics in almost every way. Research into the use of optics at this stage mirrors the research into electronics after the 2nd World War. The advantages of using fiber optics over wiring are the same as the argument for using optics over electronics in computers. Even through totally optical computers are now a reality, computers that combine both electronics and optics, electro-optic hybrids, have been in use for some time. In the present paper, architecture of optical interconnect is built up on the bases of four Vertical-Cavity Surface- Emitting Laser Diodes (VCSELD and two optical links where thermal effects of both the diodes and the links are included. Nonlinear relations are correlated to investigate the power-current and the voltage-current dependences of the four devices. The good performance (high speed of the interconnect is deeply and parametrically investigated under wide ranges of the affecting parameters. The high speed performance is processed through three different effects, namely the device 3-dB bandwidth, the link dispersion characteristics, and the transmitted bit rate (soliton. Eight combinations are investigated; each possesses its own characteristics. The best architecture is the one composed of VCSELD that operates at 850 nm and the silica fiber whatever the operating set of causes. This combination possesses the largest device 3-dB bandwidth, the largest link bandwidth and the largest soliton transmitted bit rate. The increase of the ambient temperature reduces the high-speed performance of the interconnect
Model reduction and parameter estimation of non-linear dynamical biochemical reaction networks.
Sun, Xiaodian; Medvedovic, Mario
2016-02-01
Parameter estimation for high dimension complex dynamic system is a hot topic. However, the current statistical model and inference approach is known as a large p small n problem. How to reduce the dimension of the dynamic model and improve the accuracy of estimation is more important. To address this question, the authors take some known parameters and structure of system as priori knowledge and incorporate it into dynamic model. At the same time, they decompose the whole dynamic model into subset network modules, based on different modules, and then they apply different estimation approaches. This technique is called Rao-Blackwellised particle filters decomposition methods. To evaluate the performance of this method, the authors apply it to synthetic data generated from repressilator model and experimental data of the JAK-STAT pathway, but this method can be easily extended to large-scale cases.
Hua, Changchun; Zhang, Liuliu; Guan, Xinping
2017-01-01
This paper studies the problem of distributed output tracking consensus control for a class of high-order stochastic nonlinear multiagent systems with unknown nonlinear dead-zone under a directed graph topology. The adaptive neural networks are used to approximate the unknown nonlinear functions and a new inequality is used to deal with the completely unknown dead-zone input. Then, we design the controllers based on backstepping method and the dynamic surface control technique. It is strictly proved that the resulting closed-loop system is stable in probability in the sense of semiglobally uniform ultimate boundedness and the tracking errors between the leader and the followers approach to a small residual set based on Lyapunov stability theory. Finally, two simulation examples are presented to show the effectiveness and the advantages of the proposed techniques.
Indian Academy of Sciences (India)
Pietro-Luciano Buono; Bernard Chan; Antonio Palacios; Visarath In
2015-11-01
Over the past twelve years, ideas and methods from nonlinear dynamics system theory, in particular, group theoretical methods in bifurcation theory, have been used to study, design, and fabricate novel engineering technologies. For instance, the existence and stability of heteroclinic cycles in coupled bistable systems has been exploited to develop and deploy highly sensitive, lowpower, magnetic and electric field sensors. Also, patterns of behaviour in networks of oscillators with certain symmetry groups have been extensively studied and the results have been applied to conceptualize a multifrequency up/down converter, a channelizer to lock into incoming signals, and a microwave signal generator at the nanoscale. In this manuscript, a review of the most recent work on modelling and analysis of two seemingly different systems, an array of gyroscopes and an array of energy harvesters, is presented. Empirical values of operational parameters suggest that damping and external forcing occur at a lower scale compared to other parameters, so that the individual units can be treated as Hamiltonian systems. Casting the governing equations in Hamiltonian form leads to a common approach to study both arrays. More importantly, the approach yields analytical expressions for the onset of bifurcations to synchronized oscillations. The expressions are valid for arrays of any size and the ensuing synchronized oscillations are critical to enhance performance.
Directory of Open Access Journals (Sweden)
Mohammad Ali Afshari
2012-10-01
Full Text Available The aim of this paper is to present mathematical models optimizing all materials flows in supply chain. In this research a fuzzy multi-objective nonlinear mixed- integer programming model with piecewise linear membership function is applied to design a multi echelon supply chain network (SCN by considering total transportation costs and capacities of all echelons with fuzzy objectives. The model that is proposed in this study has 4 fuzzy functions. The first function is minimizing the total transportation costs between all echelons (suppliers, factories, distribution centers (DCs and customers. The second one is minimizing holding and ordering cost on DCs. The third objective is minimizing the unnecessary and unused capacity of factories and DCs via decreasing variance of transported amounts between echelons. The forth is minimizing the number of total vehicles that ship the materials and products along with SCN. For solving such a problem, as nodes increases in SCN, the traditional method does not have ability to solve large scale problem. So, we applied a Meta heuristic method called Genetic Algorithm. The numerical example is real world applied and compared the results with each other demonstrate the feasibility of applying the proposed model to given problem, and also its advantages are discussed.
Ma, Lifeng; Wang, Zidong; Lam, Hak-Keung; Kyriakoulis, Nikos
2016-07-07
In this paper, the distributed set-membership filtering problem is investigated for a class of discrete time-varying system with an event-based communication mechanism over sensor networks. The system under consideration is subject to sector-bounded nonlinearity, unknown but bounded noises and sensor saturations. Each intelligent sensing node transmits the data to its neighbors only when certain triggering condition is violated. By means of a set of recursive matrix inequalities, sufficient conditions are derived for the existence of the desired distributed event-based filter which is capable of confining the system state in certain ellipsoidal regions centered at the estimates. Within the established theoretical framework, two additional optimization problems are formulated: one is to seek the minimal ellipsoids (in the sense of matrix trace) for the best filtering performance, and the other is to maximize the triggering threshold so as to reduce the triggering frequency with satisfactory filtering performance. A numerically attractive chaos algorithm is employed to solve the optimization problems. Finally, an illustrative example is presented to demonstrate the effectiveness and applicability of the proposed algorithm.
Directory of Open Access Journals (Sweden)
Chaoyang Dong
2015-01-01
Full Text Available This paper is concerned with the robust fault-tolerant tracking control problem for networked control system (NCS. Firstly, considering the locally overlapped switching law widely existed in engineering applications, the NCS is modeled as a locally overlapped switched polytopic system to reduce designing conservatism and solving complexity. Then, switched parameter dependent fault-tolerant tracking controllers are constructed to deal with the asynchronous switching phenomenon caused by the updating delays of the switching signals and weighted coefficients. Additionally, the global uniform asymptotic stability in the mean (GUAS-M and desired weighted l2 performance are guaranteed by combining the switched parameter dependent Lyapunov functional method with the average dwell time (ADT method, and the feasible conditions for the fault-tolerant tracking controllers are obtained in the form of linear matrix inequalities (LMIs. Finally, the performance of the proposed approach is verified on a highly maneuverable technology (HiMAT vehicle’s tracking control problem. Simulation results show the effectiveness of the proposed method.
Directory of Open Access Journals (Sweden)
Tienfuan Kerh
2014-01-01
Full Text Available The effects of extreme weather and overdevelopment may cause some coastal areas to exhibit erosion problems, which in turn may contribute to creating disasters of varying scale, particularly in regions comprising islands. This study used aerial survey information from three periods (1990, 2001, and 2010 and used graphical software to establish the spatial data of six beaches surrounding the island of Taiwan. An overlaying technique was then implemented to compare the sandy area of each beach in the aforementioned study periods. In addition, an artificial neural network model was developed based on available digitised coordinates for predicting coastline variation for 2015 and 2020. An onsite investigation was performed using a global positioning system for comparing the beaches. The results revealed that two beaches from this study may have experienced significant changes in total sandy areas under a statistical 95% confidence interval. The proposed method and the result of this study may provide a valuable reference in follow-up research and applications.
Nonlinear prediction of gold prices based on BP neural network%基于 BP神经网络的黄金价格非线性预测
Institute of Scientific and Technical Information of China (English)
张延利
2013-01-01
针对黄金价格的非线性特征和神经网络的自身特点，利用BP神经网络建立了黄金价格的非线性预测模型。实证研究结果表明，BP神经网络模型具有较好的预测精度，可以为黄金投资和宏观经济决策提供一定的参考依据。%According to the neural network nonlinear characteristics of gold price and its own characteristics ,using BP neural network nonlinear prediction model was set up for the price of gold .The results show that the BP prediction has good accuracy and is available to provide references for the gold investment and macroeconomic decisions .
Zhang, Huaguang; Cui, Lili; Luo, Yanhong
2013-02-01
In this paper, a near-optimal control scheme is proposed to solve the nonzero-sum differential games of continuous-time nonlinear systems. The single-network adaptive dynamic programming (ADP) is utilized to obtain the optimal control policies which make the cost functions reach the Nash equilibrium of nonzero-sum differential games, where only one critic network is used for each player instead of the action-critic dual network used in a typical ADP architecture. Furthermore, the novel weight tuning laws for critic neural networks are proposed, which not only ensure the Nash equilibrium to be reached but also guarantee the system to be stable. No initial stabilizing control policy is required for each player. Moreover, Lyapunov theory is utilized to demonstrate the uniform ultimate boundedness of the closed-loop system. Finally, a simulation example is given to verify the effectiveness of the proposed near-optimal control scheme.
De, Suvranu; Deo, Dhannanjay; Sankaranarayanan, Ganesh; Arikatla, Venkata S
2011-08-01
BACKGROUND: While an update rate of 30 Hz is considered adequate for real time graphics, a much higher update rate of about 1 kHz is necessary for haptics. Physics-based modeling of deformable objects, especially when large nonlinear deformations and complex nonlinear material properties are involved, at these very high rates is one of the most challenging tasks in the development of real time simulation systems. While some specialized solutions exist, there is no general solution for arbitrary nonlinearities. METHODS: In this work we present PhyNNeSS - a Physics-driven Neural Networks-based Simulation System - to address this long-standing technical challenge. The first step is an off-line pre-computation step in which a database is generated by applying carefully prescribed displacements to each node of the finite element models of the deformable objects. In the next step, the data is condensed into a set of coefficients describing neurons of a Radial Basis Function network (RBFN). During real-time computation, these neural networks are used to reconstruct the deformation fields as well as the interaction forces. RESULTS: We present realistic simulation examples from interactive surgical simulation with real time force feedback. As an example, we have developed a deformable human stomach model and a Penrose-drain model used in the Fundamentals of Laparoscopic Surgery (FLS) training tool box. CONCLUSIONS: A unique computational modeling system has been developed that is capable of simulating the response of nonlinear deformable objects in real time. The method distinguishes itself from previous efforts in that a systematic physics-based pre-computational step allows training of neural networks which may be used in real time simulations. We show, through careful error analysis, that the scheme is scalable, with the accuracy being controlled by the number of neurons used in the simulation. PhyNNeSS has been integrated into SoFMIS (Software Framework for Multimodal
Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho
2017-03-01
Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.
Zhang, Xiuyu; Su, Chun-Yi; Lin, Yan; Ma, Lianwei; Wang, Jianguo
2015-11-01
In this paper, an adaptive neural network (NN) dynamic surface control is proposed for a class of time-delay nonlinear systems with dynamic uncertainties and unknown hysteresis. The main advantages of the developed scheme are: 1) NNs are utilized to approximately describe nonlinearities and unknown dynamics of the nonlinear time-delay systems, making it possible to deal with unknown nonlinear uncertain systems and pursue the L∞ performance of the tracking error; 2) using the finite covering lemma together with the NNs approximators, the Krasovskii function is abandoned, which paves the way for obtaining the L∞ performance of the tracking error; 3) by introducing an initializing technique, the L∞ performance of the tracking error can be achieved; 4) using a generalized Prandtl-Ishlinskii (PI) model, the limitation of the traditional PI hysteresis model is overcome; and 5) by applying the Young's inequalities to deal with the weight vector of the NNs, the updated laws are needed only at the last controller design step with only two parameters being estimated, which reduces the computational burden. It is proved that the proposed scheme can guarantee semiglobal stability of the closed-loop system and achieves the L∞ performance of the tracking error. Simulation results for general second-order time-delay nonlinear systems and the tuning metal cutting system are presented to demonstrate the efficiency of the proposed method.
Institute of Scientific and Technical Information of China (English)
张燕; 陈增强; 杨鹏; 袁著祉
2004-01-01
A nonlinear proportional-integral-derivative (PID) controller is constructed based on recurrent neural networks. In the control process of nonlinear multivariable systems, several nonlinear PID controllers have been adopted in parallel. Under the decoupling cost function, a decoupling control strategy is proposed. Then the stability condition of the controller is presented based on the Lyapunov theory. Simulation examples are given to show effectiveness of the proposed decoupling control.
Directory of Open Access Journals (Sweden)
vahid Rezaverdinejad
2017-01-01
important models to estimate ETc in greenhouse. The inputs of these models are net radiation, temperature, day after planting and air vapour pressure deficit (or relative humidity. Materials and Methods: In this study, daily ETc of reference crop, greenhouse tomato and cucumber crops were measured using lysimeter method in Urmia region. Several linear, nonlinear regressions and artificial neural networks were considered for ETc modelling in greenhouse. For this purpose, the effective meteorological parameters on ETc process includes: air temperature (T, air humidity (RH, air pressure (P, air vapour pressure deficit (VPD, day after planting (N and greenhouse net radiation (SR were considered and measured. According to the goodness of fit, different models of artificial neural networks and regression were compared and evaluated. Furthermore, based on partial derivatives of regression models, sensitivity analysis was conducted. The accuracy and performance of the employed models was judged by ten statistical indices namely root mean square error (RMSE, normalized root mean square error (NRMSE and coefficient of determination (R2. Results and Discussion: Based on the results, the most accurate regression model to reference ETc prediction was obtained three variables exponential function of VPD, RH and SR with RMSE=0.378 mm day-1. The RMSE of optimal artificial neural network to reference ET prediction for train and test data sets were obtained 0.089 and 0.365 mm day-1, respectively. The performance of logarithmic and exponential functions to prediction of cucumber ETc were proper, with high dependent variables especially, and the most accurate regression model to cucumber ET prediction was obtained for exponential function of five variables: VPD, N, T, RH and SR with RMSE=0.353 mm day-1. In addition, for tomato ET prediction, the most accurate regression model was obtained for exponential function of four variables: VPD, N, RH and SR with RMSE= 0.329 mm day-1. The best
Drogue detection for autonomous aerial refueling based on convolutional neural networks
Directory of Open Access Journals (Sweden)
Xufeng Wang
2017-02-01
Full Text Available Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling (AAR. To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks (CNNs is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of “Probe and Drogue” aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units (GPUs, a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method’s accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.
Heidari, Mohammad; Heidari, Ali; Homaei, Hadi
2014-01-01
The static pull-in instability of beam-type microelectromechanical systems (MEMS) is theoretically investigated. Two engineering cases including cantilever and double cantilever microbeam are considered. Considering the midplane stretching as the source of the nonlinearity in the beam behavior, a nonlinear size-dependent Euler-Bernoulli beam model is used based on a modified couple stress theory, capable of capturing the size effect. By selecting a range of geometric parameters such as beam lengths, width, thickness, gaps, and size effect, we identify the static pull-in instability voltage. A MAPLE package is employed to solve the nonlinear differential governing equations to obtain the static pull-in instability voltage of microbeams. Radial basis function artificial neural network with two functions has been used for modeling the static pull-in instability of microcantilever beam. The network has four inputs of length, width, gap, and the ratio of height to scale parameter of beam as the independent process variables, and the output is static pull-in voltage of microbeam. Numerical data, employed for training the network, and capabilities of the model have been verified in predicting the pull-in instability behavior. The output obtained from neural network model is compared with numerical results, and the amount of relative error has been calculated. Based on this verification error, it is shown that the radial basis function of neural network has the average error of 4.55% in predicting pull-in voltage of cantilever microbeam. Further analysis of pull-in instability of beam under different input conditions has been investigated and comparison results of modeling with numerical considerations shows a good agreement, which also proves the feasibility and effectiveness of the adopted approach. The results reveal significant influences of size effect and geometric parameters on the static pull-in instability voltage of MEMS.
Destexhe, Alain
2009-12-01
Randomly-connected networks of integrate-and-fire (IF) neurons are known to display asynchronous irregular (AI) activity states, which resemble the discharge activity recorded in the cerebral cortex of awake animals. However, it is not clear whether such activity states are specific to simple IF models, or if they also exist in networks where neurons are endowed with complex intrinsic properties similar to electrophysiological measurements. Here, we investigate the occurrence of AI states in networks of nonlinear IF neurons, such as the adaptive exponential IF (Brette-Gerstner-Izhikevich) model. This model can display intrinsic properties such as low-threshold spike (LTS), regular spiking (RS) or fast-spiking (FS). We successively investigate the oscillatory and AI dynamics of thalamic, cortical and thalamocortical networks using such models. AI states can be found in each case, sometimes with surprisingly small network size of the order of a few tens of neurons. We show that the presence of LTS neurons in cortex or in thalamus, explains the robust emergence of AI states for relatively small network sizes. Finally, we investigate the role of spike-frequency adaptation (SFA). In cortical networks with strong SFA in RS cells, the AI state is transient, but when SFA is reduced, AI states can be self-sustained for long times. In thalamocortical networks, AI states are found when the cortex is itself in an AI state, but with strong SFA, the thalamocortical network displays Up and Down state transitions, similar to intracellular recordings during slow-wave sleep or anesthesia. Self-sustained Up and Down states could also be generated by two-layer cortical networks with LTS cells. These models suggest that intrinsic properties such as adaptation and low-threshold bursting activity are crucial for the genesis and control of AI states in thalamocortical networks.
Deep Convolutional Networks for Event Reconstruction and Particle Tagging on NOvA and DUNE
CERN. Geneva
2017-01-01
Deep Convolutional Neural Networks (CNNs) have been widely applied in computer vision to solve complex problems in image recognition and analysis. In recent years many efforts have emerged to extend the use of this technology to HEP applications, including the Convolutional Visual Network (CVN), our implementation for identification of neutrino events. In this presentation I will describe the core concepts of CNNs, the details of our particular implementation in the Caffe framework and our application to identify NOvA events. NOvA is a long baseline neutrino experiment whose main goal is the measurement of neutrino oscillations. This relies on the accurate identification and reconstruction of the neutrino flavor in the interactions we observe. In 2016 the NOvA experiment released results for the observation of oscillations in the ν μ → ν e channel, the first HEP result employing CNNs. I will also discuss our approach at event identification on NOvA as well as recent developments in the application of CNN...
Nonlinear dynamics and complexity
Luo, Albert; Fu, Xilin
2014-01-01
This important collection presents recent advances in nonlinear dynamics including analytical solutions, chaos in Hamiltonian systems, time-delay, uncertainty, and bio-network dynamics. Nonlinear Dynamics and Complexity equips readers to appreciate this increasingly main-stream approach to understanding complex phenomena in nonlinear systems as they are examined in a broad array of disciplines. The book facilitates a better understanding of the mechanisms and phenomena in nonlinear dynamics and develops the corresponding mathematical theory to apply nonlinear design to practical engineering.
Directory of Open Access Journals (Sweden)
Mohammad Heidari
2013-01-01
Full Text Available In this study, the static pull-in instability of beam-type micro-electromechanical system (MEMS is theoretically investigated. Considering the mid-plane stretching as the source of the nonlinearity in the beam behavior, a nonlinear size dependent Euler-Bernoulli beam model is used based on a modified couple stress theory, capable of capturing the size effect. Two supervised neural networks, namely, back propagation (BP and radial basis function (RBF, have been used for modeling the static pull-in instability of microcantilever beam. These networks have four inputs of length, width, gap, and the ratio of height to scale parameter of beam as the independent process variables, and the output is static pull-in voltage of microbeam. Numerical data employed for training the networks and capabilities of the models in predicting the pull-in instability behavior has been verified. Based on verification errors, it is shown that the radial basis function of neural network is superior in this particular case and has the average errors of 4.55% in predicting pull-in voltage of cantilever microbeam. Further analysis of pull-in instability of beam under different input conditions has been investigated and comparison results of modeling with numerical considerations show a good agreement, which also proves the feasibility and effectiveness of the adopted approach.
Transforming Musical Signals through a Genre Classifying Convolutional Neural Network
Geng, S.; Ren, G.; Ogihara, M.
2017-05-01
Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the abstracting process. One can hope to manipulate existing music based on this 'informed' network and create music with new features corresponding to the knowledge obtained by the network. In this paper, we propose a method to utilize the stored information from a CNN trained on musical genre classification task. The network was composed of three convolutional layers, and was trained to classify five-second song clips into five different genres. After training, randomly selected clips were modified by maximizing the sum of outputs from the network layers. In addition to the potential of such CNNs to produce interesting audio transformation, more information about the network and the original music could be obtained from the analysis of the generated features since these features indicate how the network 'understands' the music.
Continuous speech recognition by convolutional neural networks%基于卷积神经网络的连续语音识别
Institute of Scientific and Technical Information of China (English)
张晴晴; 刘勇; 潘接林; 颜永红
2015-01-01
在语音识别中,卷积神经网络( convolutional neural networks,CNNs)相比于目前广泛使用的深层神经网络( deep neural network,DNNs),能在保证性能的同时,大大压缩模型的尺寸。本文深入分析了卷积神经网络中卷积层和聚合层的不同结构对识别性能的影响情况,并与目前广泛使用的深层神经网络模型进行了对比。在标准语音识别库TIMIT以及大词表非特定人电话自然口语对话数据库上的实验结果证明,相比传统深层神经网络模型,卷积神经网络明显降低模型规模的同时,识别性能更好,且泛化能力更强。%Convolutional neural networks ( CNNs ) , which show success in achieving translation invariance for many image processing tasks, were investigated for continuous speech recognition. Compared to deep neural networks ( DNNs) , which are proven to be successful in many speech recognition tasks nowadays, CNNs can reduce the neural network model sizes significantly, and at the same time achieve even a better recognition accuracy. Experiments on standard speech corpus TIMIT and conversational speech corpus show that CNNs outperform DNNs in terms of the accuracy and the generalization ability.
Sambo, Francesco; de Oca, Marco A Montes; Di Camillo, Barbara; Toffolo, Gianna; Stützle, Thomas
2012-01-01
Reverse engineering is the problem of inferring the structure of a network of interactions between biological variables from a set of observations. In this paper, we propose an optimization algorithm, called MORE, for the reverse engineering of biological networks from time series data. The model inferred by MORE is a sparse system of nonlinear differential equations, complex enough to realistically describe the dynamics of a biological system. MORE tackles separately the discrete component of the problem, the determination of the biological network topology, and the continuous component of the problem, the strength of the interactions. This approach allows us both to enforce system sparsity, by globally constraining the number of edges, and to integrate a priori information about the structure of the underlying interaction network. Experimental results on simulated and real-world networks show that the mixed discrete/continuous optimization approach of MORE significantly outperforms standard continuous optimization and that MORE is competitive with the state of the art in terms of accuracy of the inferred networks.
Institute of Scientific and Technical Information of China (English)
张燕; 梁秀霞; 杨鹏; 陈增强; 袁著祉
2009-01-01
An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.
Directory of Open Access Journals (Sweden)
Sergi Bermúdez i Badia
2010-03-01
Full Text Available In principle it appears advantageous for single neurons to perform non-linear operations. Indeed it has been reported that some neurons show signatures of such operations in their electrophysiological response. A particular case in point is the Lobula Giant Movement Detector (LGMD neuron of the locust, which is reported to locally perform a functional multiplication. Given the wide ramifications of this suggestion with respect to our understanding of neuronal computations, it is essential that this interpretation of the LGMD as a local multiplication unit is thoroughly tested. Here we evaluate an alternative model that tests the hypothesis that the non-linear responses of the LGMD neuron emerge from the interactions of many neurons in the opto-motor processing structure of the locust. We show, by exposing our model to standard LGMD stimulation protocols, that the properties of the LGMD that were seen as a hallmark of local non-linear operations can be explained as emerging from the dynamics of the pre-synaptic network. Moreover, we demonstrate that these properties strongly depend on the details of the synaptic projections from the medulla to the LGMD. From these observations we deduce a number of testable predictions. To assess the real-time properties of our model we applied it to a high-speed robot. These robot results show that our model of the locust opto-motor system is able to reliably stabilize the movement trajectory of the robot and can robustly support collision avoidance. In addition, these behavioural experiments suggest that the emergent non-linear responses of the LGMD neuron enhance the system's collision detection acuity. We show how all reported properties of this neuron are consistently reproduced by this alternative model, and how they emerge from the overall opto-motor processing structure of the locust. Hence, our results propose an alternative view on neuronal computation that emphasizes the network properties as opposed
Global sea surface temperature (SST) anomalies can affect terrestrial precipitation via ocean-atmosphere interaction known as climate teleconnection. Non-stationary and non-linear characteristics of the ocean-atmosphere system make the identification of the teleconnection signals...
Ramaswamy, Rajesh; Sbalzarini, Ivo F; González-Segredo, Nélido
2011-01-28
Stochastic effects from correlated noise non-trivially modulate the kinetics of non-linear chemical reaction networks. This is especially important in systems where reactions are confined to small volumes and reactants are delivered in bursts. We characterise how the two noise sources confinement and burst modulate the relaxation kinetics of a non-linear reaction network around a non-equilibrium steady state. We find that the lifetimes of species change with burst input and confinement. Confinement increases the lifetimes of all species that are involved in any non-linear reaction as a reactant. Burst monotonically increases or decreases lifetimes. Competition between burst-induced and confinement-induced modulation may hence lead to a non-monotonic modulation. We quantify lifetime as the integral of the time autocorrelation function (ACF) of concentration fluctuations around a non-equilibrium steady state of the reaction network. Furthermore, we look at the first and second derivatives of the ACF, each of which is affected in opposite ways by burst and confinement. This allows discriminating between these two noise sources. We analytically derive the ACF from the linear Fokker-Planck approximation of the chemical master equation in order to establish a baseline for the burst-induced modulation at low confinement. Effects of higher confinement are then studied using a partial-propensity stochastic simulation algorithm. The results presented here may help understand the mechanisms that deviate stochastic kinetics from its deterministic counterpart. In addition, they may be instrumental when using fluorescence-lifetime imaging microscopy (FLIM) or fluorescence-correlation spectroscopy (FCS) to measure confinement and burst in systems with known reaction rates, or, alternatively, to correct for the effects of confinement and burst when experimentally measuring reaction rates.
2D image classification for 3D anatomy localization: employing deep convolutional neural networks
de Vos, Bob D.; Wolterink, Jelmer M.; de Jong, Pim A.; Viergever, Max A.; Išgum, Ivana
2016-03-01
Localization of anatomical regions of interest (ROIs) is a preprocessing step in many medical image analysis tasks. While trivial for humans, it is complex for automatic methods. Classic machine learning approaches require the challenge of hand crafting features to describe differences between ROIs and background. Deep convolutional neural networks (CNNs) alleviate this by automatically finding hierarchical feature representations from raw images. We employ this trait to detect anatomical ROIs in 2D image slices in order to localize them in 3D. In 100 low-dose non-contrast enhanced non-ECG synchronized screening chest CT scans, a reference standard was defined by manually delineating rectangular bounding boxes around three anatomical ROIs -- heart, aortic arch, and descending aorta. Every anatomical ROI was automatically identified using a combination of three CNNs, each analyzing one orthogonal image plane. While single CNNs predicted presence or absence of a specific ROI in the given plane, the combination of their results provided a 3D bounding box around it. Classification performance of each CNN, expressed in area under the receiver operating characteristic curve, was >=0.988. Additionally, the performance of ROI localization was evaluated. Median Dice scores for automatically determined bounding boxes around the heart, aortic arch, and descending aorta were 0.89, 0.70, and 0.85 respectively. The results demonstrate that accurate automatic 3D localization of anatomical structures by CNN-based 2D image classification is feasible.
Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L
2016-07-01
Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text
Institute of Scientific and Technical Information of China (English)
宋浩; 蔡遵生; 赵学庄; 李勇军; 习保民; 李燕妮
1999-01-01
A new method of controlling chemical chaos to attain the stabilized unstable periodic orbit (UPO) is proposed. It is an extension of the occasional proportional feedback (OPF) control strategy which spans the limitations of OPF, i.e. the linear region of the control rule, and extends to the whole chaotic region. It also expresses the nonlinear control rule with the back propogation-artificial neural network (BP-ANN) in order to increase the robustness of the control. Its effectiveness is examined through controlling an autocatalytic chaotic reaction model numerically.
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
In this paper, we introduce a modified small-world network added with new links with preferential connection instead of adding randomly, then we apply Bak-Sneppen (BS) evolution model on this network. Several dynamical character of the model such as the evolution graph, fo avalanche, the critical exponent D and τ, and the distribution of mutation times of all the nodes, show particular behaviors different from those of the model based on the regular network and the small-world network.
Robustness Design for CNN Templates with Performance of Extracting Closed Domain
Institute of Scientific and Technical Information of China (English)
LI Wei-Dong; MIN Le-Quan
2006-01-01
The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing,robotic and biological visions. This paper introduces a kind of CNNs with performance of extracting closed domains in binary images, and gives a general method for designing templates of such a kind of CNNs. One theorem provides parameter inequalities for determining parameter intervals for implementing prescribed image processing functions,respectively. Examples for extracting closed domains in binary scale images are given.
Non-fragile H∞Control for Networked Nonlinear System%网络化非线性系统的非脆弱H∞控制
Institute of Scientific and Technical Information of China (English)
马卫国; 杨忠
2013-01-01
The additive non-fragile state feedback H∞ controller is designed for networked Lipschitz nonlinear system with logarithmic data quantization, networked induced delay shorter than one sampling period and packet dropout governed by Markov chain subject to controller parameter perturbation. The effect of data quantization and network induced delay is converted the parameter uncertainties of the controlled system. The networked nonlinear system is formulated as a Markovian jump system. The sufficient condition of the additive non-fragile state feedback H∞ controller for the networked nonlinear system is derived in terms of linear matrix inequality based on Lyapunov stability theory. The H∞controller can be obtained by the solution of linear matrix inequalities. Simulation results show that when there exit parameter perturbations in controller, the non-fragile controller can stabilize the controlled system and meet setting H∞performance index compared with the traditional one.%具有对数量化、网络诱导时延和数据包丢失的网络化Lipschitz非陑性系统控制器，存在参数摄动问题。为此，设计一种加性非脆弱状态反馈H∞控制器。将数据量化和网络诱导时延对被控系统的影陞，转化为系统的不确定参数，网络化控制系统建模为马尔可夫跳变系统。采用Lyapunov稳定性理论和陑性矩阵不等式方法，给出网络化Lipschitz非陑性系统的加性非脆弱状态反馈H∞控制器存在的充分条件，该非脆弱 H∞控制器可通过解陑性矩阵不等式求出。仿真结果表明，当控制器存在参数摄动时，与传统控制器陒比，非脆弱控制器不仅能使被控系统稳定，而且满足设定的H∞性能指标。
Konovalov, I B
2002-01-01
The nonlinear features of the relationships between particulate matter (PM) and volatile organic compounds (VOC) and oxides of nitrogen (NOx) are derived directly from data of long-term routine measurements of NOx, VOC, and total suspended PM. The main idea of the method used for the analysis is creation of special empirical models based on artificial neural networks of the perceptron type. These models which are in essence the nonlinear extension of commonly used linear regression models are believed to provide the best fit for the real nonlinear PM-NOx-VOC relationships under different observed levels of air pollution and various meteorological conditions. It is believed that such models may be useful in context of various scientific and practical problems concerning PM. The method is demonstrated by the example of two empirical models created with independent data-sets collected at two air quality monitoring stations at South Coast Air Basin, California. It is shown that in spite of considerable distance b...
Yousif, Nada A B; Denham, Michael
2005-12-01
The thalamocortical network is modelled using the Wilson-Cowan equations for neuronal population activity. We show that this population model with biologically derived parameters possesses intrinsic nonlinear oscillatory dynamics, and that the frequency of oscillation lies within the spindle range. Spindle oscillations are an early sleep oscillation characterized by high-frequency bursts of action potentials followed by a period of quiescence, at a frequency of 7-14 Hz. Spindles are generally regarded as being generated by intrathalamic circuitry, as decorticated thalamic slices and the isolated thalamic reticular nucleus exhibit spindles. However, the role of cortical feedback has been shown to regulate and synchronize the oscillation. Previous modelling studies have mainly used conductance-based models and hence the mechanism relied upon the inclusion of ionic currents, particularly the T-type calcium current. Here we demonstrate that spindle-frequency oscillatory activity can also arise from the nonlinear dynamics of the thalamocortical circuit, and we use bifurcation analysis to examine the robustness of this oscillation in terms of the functional range of the parameters used in the model. The results suggest that the thalamocortical circuit has intrinsic nonlinear population dynamics which are capable of providing robust support for oscillatory activity within the frequency range of spindle oscillations.
Minati, Ludovico; Chiesa, Pietro; Tabarelli, Davide; D'Incerti, Ludovico; Jovicich, Jorge
2015-03-01
In this paper, the topographical relationship between functional connectivity (intended as inter-regional synchronization), spectral and non-linear dynamical properties across cortical areas of the healthy human brain is considered. Based upon functional MRI acquisitions of spontaneous activity during wakeful idleness, node degree maps are determined by thresholding the temporal correlation coefficient among all voxel pairs. In addition, for individual voxel time-series, the relative amplitude of low-frequency fluctuations and the correlation dimension (D2), determined with respect to Fourier amplitude and value distribution matched surrogate data, are measured. Across cortical areas, high node degree is associated with a shift towards lower frequency activity and, compared to surrogate data, clearer saturation to a lower correlation dimension, suggesting presence of non-linear structure. An attempt to recapitulate this relationship in a network of single-transistor oscillators is made, based on a diffusive ring (n = 90) with added long-distance links defining four extended hub regions. Similarly to the brain data, it is found that oscillators in the hub regions generate signals with larger low-frequency cycle amplitude fluctuations and clearer saturation to a lower correlation dimension compared to surrogates. The effect emerges more markedly close to criticality. The homology observed between the two systems despite profound differences in scale, coupling mechanism and dynamics appears noteworthy. These experimental results motivate further investigation into the heterogeneity of cortical non-linear dynamics in relation to connectivity and underline the ability for small networks of single-transistor oscillators to recreate collective phenomena arising in much more complex biological systems, potentially representing a future platform for modelling disease-related changes.
Nonlinear effects in optical fibers
Ferreira, Mario F
2011-01-01
Cutting-edge coverage of nonlinear phenomena occurring inside optical fibers Nonlinear fiber optics is a specialized part of fiber optics dealing with optical nonlinearities and their applications. As fiber-optic communication systems have become more advanced and complex, the nonlinear effects in optical fibers have increased in importance, as they adversely affect system performance. Paradoxically, the same nonlinear phenomena also offer the promise of addressing the bandwidth bottleneck for signal processing for future ultra-high speed optical networks. Nonlinear Effects in Optical Fiber
Energy Technology Data Exchange (ETDEWEB)
Trezza, M.; Cirillo, C.; Sabatino, P.; Carapella, G.; Attanasio, C. [CNR-SPIN Salerno and Dipartimento di Fisica “E. R. Caianiello”, Università degli Studi di Salerno, Fisciano I-84084 (Italy); Prischepa, S. L. [Belarusian State University of Informatics and Radioelectronics, P. Browka 6, Minsk 220013 (Belarus)
2013-12-16
We report on the transport properties of an array of N∼30 interconnected Nb nanowires, grown by sputtering on robust porous Si substrates. The analyzed system exhibits a broad resistive transition in zero magnetic field, H, and highly nonlinear V(I) characteristics as a function of H, which can be both consistently described by quantum tunneling of phase slips.
Fedota, John R; Matous, Allison L; Salmeron, Betty Jo; Gu, Hong; Ross, Thomas J; Stein, Elliot A
2016-09-01
Deficits in cognitive control processes are a primary characteristic of nicotine addiction. However, while network-based connectivity measures of dysfunction have frequently been observed, empirical evidence of task-based dysfunction in these processes has been inconsistent. Here, in a sample of smokers (n=35) and non-smokers (n=21), a previously validated parametric flanker task is employed to characterize addiction-related alterations in responses to varying (ie, high, intermediate, and low) demands for cognitive control. This approach yields a demand-response curve that aims to characterize potential non-linear responses to increased demand for control, including insensitivities or lags in fully activating the cognitive control network. We further used task-based differences in activation between groups as seeds for resting-state analysis of network dysfunction in an effort to more closely link prior inconsistencies in task-related activation with evidence of impaired network connectivity in smokers. For both smokers and non-smokers, neuroimaging results showed similar increases in activation in brain areas associated with cognitive control. However, reduced activation in right insula was seen only in smokers and only when processing intermediate demand for cognitive control. Further, in smokers, this task-modulated right insula showed weaker functional connectivity with the superior frontal gyrus, a component of the task-positive executive control network. These results demonstrate that the neural instantiation of salience attribution in smokers is both more effortful to fully activate and has more difficulty communicating with the exogenous, task-positive, executive control network. Together, these findings further articulate the cognitive control dysfunction associated with smoking and illustrate a specific brain circuit potentially responsible.
Convolutional neural network architectures for predicting DNA–protein binding
Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.
2016-01-01
Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608
Event Discrimination using Convolutional Neural Networks
Menon, Hareesh; Hughes, Richard; Daling, Alec; Winer, Brian
2017-01-01
Convolutional Neural Networks (CNNs) are computational models that have been shown to be effective at classifying different types of images. We present a method to use CNNs to distinguish events involving the production of a top quark pair and a Higgs boson from events involving the production of a top quark pair and several quark and gluon jets. To do this, we generate and simulate data using MADGRAPH and DELPHES for a general purpose LHC detector at 13 TeV. We produce images using a particle flow algorithm by binning the particles geometrically based on their position in the detector and weighting the bins by the energy of each particle within each bin, and by defining channels based on particle types (charged track, neutral hadronic, neutral EM, lepton, heavy flavor). Our classification results are competitive with standard machine learning techniques. We have also looked into the classification of the substructure of the events, in a process known as scene labeling. In this context, we look for the presence of boosted objects (such as top quarks) with substructure encompassed within single jets. Preliminary results on substructure classification will be presented.
Falzone, Tobias; Blair, Savanna; Robertson-Anderson, Rae
2015-03-01
The semiflexible biopolymer actin, a ubiquitous component of nearly all biological organisms, plays an important role in many mechanically-driven processes such as muscle contraction, cancer invasion and cell motility. As such, entangled actin networks, which possess unique and complex viscoelastic properties, have been the subject of much theoretical and experimental work. However, due to this viscoelastic complexity, much is still unknown regarding the correlation of the applied stress on actin networks to the induced filament strain at the molecular and micro scale. Here, we use simultaneous optical trapping and fluorescence microscopy to characterize the link between applied microscopic forces and strain propagation as a function of strain rate and concentration. Specifically, we track fiduciary markers on entangled actin filaments before, during and after actively driving embedded microspheres through the network. These measurements provide much needed insight into the molecular-level dynamics connecting stress and strain in semiflexible polymer networks.
1988-12-01
Researchers have suggested other solution strategies, using ideas from nonlinear progamming for solving this general separable convex cost flow problems. Some...plane methods and branch and bound procedures of integer programming, primal-dual methods of linear and nonlinear programming, and polyhedral methods...Combinatorial Optimization: Networks and Matroids), Bazaraa and Jarvis [1978] (Linear Programming and Network Flows), Minieka [1978] (Optimization Algorithms for
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.
Niu, Ben; Qin, Tian; Fan, Xiaodong
2016-10-01
In this paper, an adaptive neural network tracking control approach is proposed for a class of switched stochastic pure-feedback nonlinear systems with backlash-like hysteresis. In the design procedure, an affine variable is constructed, which avoids the use of the mean value theorem, and the additional first-order low-pass filter is employed to deal with the problem of explosion of complexity. Then, a common Lyapunov function and a state feedback controller are explicitly obtained for all subsystems. It is proved that the proposed controller that guarantees all signals in the closed-loop system are semi-globally uniformly ultimately bounded and the tracking error remains an adjustable neighbourhood of the origin. Finally, simulation results show the effectiveness of the presented control design approach.
Teslic, Luka; Hartmann, Benjamin; Nelles, Oliver; Skrjanc, Igor
2011-12-01
This paper deals with the problem of fuzzy nonlinear model identification in the framework of a local model network (LMN). A new iterative identification approach is proposed, where supervised and unsupervised learning are combined to optimize the structure of the LMN. For the purpose of fitting the cluster-centers to the process nonlinearity, the Gustafsson-Kessel (GK) fuzzy clustering, i.e., unsupervised learning, is applied. In combination with the LMN learning procedure, a new incremental method to define the number and the initial locations of the cluster centers for the GK clustering algorithm is proposed. Each data cluster corresponds to a local region of the process and is modeled with a local linear model. Since the validity functions are calculated from the fuzzy covariance matrices of the clusters, they are highly adaptable and thus the process can be described with a very sparse amount of local models, i.e., with a parsimonious LMN model. The proposed method for constructing the LMN is finally tested on a drug absorption spectral process and compared to two other methods, namely, Lolimot and Hilomot. The comparison between the experimental results when using each method shows the usefulness of the proposed identification algorithm.
Biyanto, Totok R.
2016-06-01
Fouling in a heat exchanger in Crude Preheat Train (CPT) refinery is an unsolved problem that reduces the plant efficiency, increases fuel consumption and CO2 emission. The fouling resistance behavior is very complex. It is difficult to develop a model using first principle equation to predict the fouling resistance due to different operating conditions and different crude blends. In this paper, Artificial Neural Networks (ANN) MultiLayer Perceptron (MLP) with input structure using Nonlinear Auto-Regressive with eXogenous (NARX) is utilized to build the fouling resistance model in shell and tube heat exchanger (STHX). The input data of the model are flow rates and temperatures of the streams of the heat exchanger, physical properties of product and crude blend data. This model serves as a predicting tool to optimize operating conditions and preventive maintenance of STHX. The results show that the model can capture the complexity of fouling characteristics in heat exchanger due to thermodynamic conditions and variations in crude oil properties (blends). It was found that the Root Mean Square Error (RMSE) are suitable to capture the nonlinearity and complexity of the STHX fouling resistance during phases of training and validation.
Energy Technology Data Exchange (ETDEWEB)
Biyanto, Totok R. [Department of Engineering Physics, Institute Technology of Sepuluh Nopember Surabaya, Surabaya, Indonesia 60111 (Indonesia)
2016-06-03
Fouling in a heat exchanger in Crude Preheat Train (CPT) refinery is an unsolved problem that reduces the plant efficiency, increases fuel consumption and CO{sub 2} emission. The fouling resistance behavior is very complex. It is difficult to develop a model using first principle equation to predict the fouling resistance due to different operating conditions and different crude blends. In this paper, Artificial Neural Networks (ANN) MultiLayer Perceptron (MLP) with input structure using Nonlinear Auto-Regressive with eXogenous (NARX) is utilized to build the fouling resistance model in shell and tube heat exchanger (STHX). The input data of the model are flow rates and temperatures of the streams of the heat exchanger, physical properties of product and crude blend data. This model serves as a predicting tool to optimize operating conditions and preventive maintenance of STHX. The results show that the model can capture the complexity of fouling characteristics in heat exchanger due to thermodynamic conditions and variations in crude oil properties (blends). It was found that the Root Mean Square Error (RMSE) are suitable to capture the nonlinearity and complexity of the STHX fouling resistance during phases of training and validation.
Directory of Open Access Journals (Sweden)
Ruofeng Rao
2013-01-01
Full Text Available The robust exponential stability of delayed fuzzy Markovian-jumping Cohen-Grossberg neural networks (CGNNs with nonlinear p-Laplace diffusion is studied. Fuzzy mathematical model brings a great difficulty in setting up LMI criteria for the stability, and stochastic functional differential equations model with nonlinear diffusion makes it harder. To study the stability of fuzzy CGNNs with diffusion, we have to construct a Lyapunov-Krasovskii functional in non-matrix form. But stochastic mathematical formulae are always described in matrix forms. By way of some variational methods in W1,p(Ω, Itô formula, Dynkin formula, the semi-martingale convergence theorem, Schur Complement Theorem, and LMI technique, the LMI-based criteria on the robust exponential stability and almost sure exponential robust stability are finally obtained, the feasibility of which can efficiently be computed and confirmed by computer MatLab LMI toolbox. It is worth mentioning that even corollaries of the main results of this paper improve some recent related existing results. Moreover, some numerical examples are presented to illustrate the effectiveness and less conservatism of the proposed method due to the significant improvement in the allowable upper bounds of time delays.
Ebert, F.; Berger, M.
The application of band mechanisms offers a wide range of possibilities in designing concepts of modern guide mechanisms. The applied belt pulleys are designed as continuous convex cam disks and allow the application of different transmission functions. A large number of transmission functions can be generated with convex curve shapes. It takes a great deal of effort to determine the correct pulley curve and is difficult for engineers without special knowledge to calculate. The syntheses process of a nonlinear band mechanism is based on the relationships between the evolute and evolvente [1]. The evolute corresponds to the pulley curve and the evolvente corresponds, for example, to the curve of the fix point of a rocker arm. By applying this method in relation with the reverse kinematics and the maintenance of total band length, allowing to generate band mechanism with required curve of transmission ratio. Beside the comments of band mechanism construction and the mathematical method of resolution—the first part of the article explains a simple four bar mechanism of couch chest the total gravity force balance with band mechanism. Therefore, the essential computing steps and limits of the solving process will be explained. With this it is possible to calculate the nonlinear transmission ratio of band mechanism with consideration of elastic band properties and inertia of bodies.
Grip, H°avard Fjær; Saberi, Ali; Stoorvogel, Anton A.
2015-01-01
We consider the synchronization problem for a class of directed networks where the agents receive relative output information from their neighbors, but lack independent information about their own state or output (they are non-introspective) and are unable to exchange internal controller states with
Chiang, Tung-Sheng; Chiu, Chian-Song
This paper proposes the sliding mode control using LMI techniques and adaptive recurrent fuzzy neural network (RFNN) for a class of uncertain nonlinear time-delay systems. First, a novel TS recurrent fuzzy neural network (TS-RFNN) is developed to provide more flexible and powerful compensation of system uncertainty. Then, the TS-RFNN based sliding model control is proposed for uncertain time-delay systems. In detail, sliding surface design is derived to cope with the non-Isidori-Bynes canonical form of dynamics, unknown delay time, and mismatched uncertainties. Based on the Lyapunov-Krasoviskii method, the asymptotic stability condition of the sliding motion is formulated into solving a Linear Matrix Inequality (LMI) problem which is independent on the time-varying delay. Furthermore, the input coupling uncertainty is also taken into our consideration. The overall controlled system achieves asymptotic stability even if considering poor modeling. The contributions include: i) asymptotic sliding surface is designed from solving a simple and legible delay-independent LMI; and ii) the TS-RFNN is more realizable (due to fewer fuzzy rules being used). Finally, simulation results demonstrate the validity of the proposed control scheme.
Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.
Durant, Thomas J S; Olson, Eben M; Schulz, Wade L; Torres, Richard
2017-09-06
Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. © 2017 American Association for Clinical Chemistry.
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given...
A synthesis procedure for associative memories based on space-varying cellular neural networks.
Park, J; Kim, H Y; Park, Y; Lee, S W
2001-01-01
In this paper, we consider the problem of realizing associative memories via space-varying CNNs (cellular neural networks). Based on some known results and a newly derived theorem for the CNN model, we propose a synthesis procedure for obtaining a space-varying CNN that can store given bipolar vectors with certain desirable properties. The major part of our synthesis procedure consists of solving generalized eigenvalue problems and/or linear matrix inequality problems, which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by a design example.
Jordan, Tyler S.
2016-05-01
This paper presents the findings of using convolutional neural networks (CNNs) to classify human activity from micro-Doppler features. An emphasis on activities involving potential security threats such as holding a gun are explored. An automotive 24 GHz radar on chip was used to collect the data and a CNN (normally applied to image classification) was trained on the resulting spectrograms. The CNN achieves an error rate of 1.65 % on classifying running vs. walking, 17.3 % error on armed walking vs. unarmed walking, and 22 % on classifying six different actions.
Yildiz, Nihat; Karabacak, Mehmet; Kurt, Mustafa; Akkoyun, Serkan
2012-05-01
Being directly related to the electric charge distributions in a molecule, the vibrational spectra intensities are both experimentally and theoretically important physical quantities. However, these intensities are inherently highly nonlinear and of complex pattern. Therefore, in particular for unknown detailed spatial molecular structures, it is difficult to make ab initio intensity calculations to compare with new experimental data. In this respect, we very recently initiated entirely novel layered feedforward neural network (LFNN) approach to construct empirical physical formulas (EPFs) for density functional theory (DFT) vibrational spectra of some molecules. In this paper, as a new and far improved contribution to our novel molecular vibrational spectra LFNN-EPF approach, we constructed LFFN-EPFs for absorbances and intensities of 6-choloronicotinic acid (6-CNA) molecule. The 6-CNA data, borrowed from our previous study, was entirely different and much larger than the vibrational intensity data of our formerly used LFNN-EPF molecules. In line with our another previous work which theoretically proved the LFNN relevance to EPFs, although the 6-CNA DFT absorbance and intensity were inherently highly nonlinear and sharply fluctuating in character, still the optimally constructed train set LFFN-EPFs very successfully fitted the absorbances and intensities. Moreover, test set (i.e. yet-to-be measured experimental data) LFNN-EPFs consistently and successfully predicted the absorbance and intensity data. This simply means that the physical law embedded in the 6-CNA vibrational data was successfully extracted by the LFNN-EPFs. In conclusion, these vibrational LFNN-EPFs are of explicit form. Therefore, by various suitable operations of mathematical analysis, they can be used to estimate the electronic charge distributions of the unknown molecule of the significant complexity. Additionally, these estimations can be combined with those of theoretical DFT atomic polar
Nonlinear correction of sensors based on neural network model%基于神经网络模型的传感器非线性校正
Institute of Scientific and Technical Information of China (English)
田社平; 赵阳; 韦红雨; 王志武
2006-01-01
Back propagation (BP) neural network models are applied to correct nonlinear characteristics of sensors in this paper. Two sensors of the same type are used to measure two interrelated measurands and their outputs are put into the trained neural network model to obtain linear input-output characteristics. A Recursive Prediction Error(RPE) algorithm, which converges fast, is applied to train the neural network model. As an example, a correction method based on BP is applied to reduce the nonlinear output errors of range sensors. Experimental results show that linear input-output characteristics can be obtained by connecting the trained neural network model with the range sensors. The correction precision increases with the increasing number of nodes in the hidden layer. When the number of nodes in the hidden layer is 40 and the neural network model converges in about 100 iterations,the Error Index(EI) is 9.6×10-6.%讨论了BP神经网络模型在传感器非线性补偿中的应用.给出了相应的补偿方法,即采用两个相同的传感器对同一被测量进行不同的测量,其测量结果作为神经网络模型的输入,经过补偿后的传感器具有线性的输入输出关系.采用递推预报误差算法(PRE)训练神经网络,具有收敛速度快、收敛精度高的特点.以距离传感器为例,将基于BP神经网络的校正方法应用于减少距离传感器的非线性输出误差.实验结果表明,将训练后的神经网络接入距离传感器可以得到线性的输入-输出关系,增加神经网络隐层节点的数目可以提高校正精度.当隐层节点数取为40时,用于距离传感器非线性校正的神经网络模型在训练100步后的误差指数(EI)为9.6×10-6.结果表明:本文提出的基于神经网络模型的传感器非线性校正方法是行之有效的.
Saurabh, K.; Dimri, A. P.
2016-05-01
Fog affects human life in a number of ways by reducing the visibility, hence affecting critical infrastructure, transportation, tourism or by the formation of frost, thus harming the standing crops. Smog is becoming a regular phenomenon in urban areas which is highly toxic to humans. Delhi was chosen as the area of study as it encounters all these hazards of fog stated apart from other political and economic reasons. The complex relationship behind the parameters and processes behind the formation of fog makes it extremely difficult to model and forecast it accurately. It is attempted to forecast the fog and understand its dynamics through a statistical downscaling technique of artificial neural network which is deemed accurate for short-term forecasting and usually outperform time-series models. The backpropagation neural network, which is a gradient descent algorithm where the network weights are moved along the negative of the gradient of the performance function, has been used for our analysis. Indian Meteorological Department (IMD) supported National Oceanic and Atmospheric Administration (NOAA) data had been used for carrying out the simulations. The model was found to have high accuracy but lacking in skill. An attempt has been made to present the data in a binary form by determining a threshold by the contingency table approach followed by its critical analysis. It is found that the calculation of an optimum threshold was also difficult to fix as the parameters of fog formation on which the model has been has been trained had shown some changes in their trend over a period of time.
Energy Technology Data Exchange (ETDEWEB)
Cogo, Joao Roberto [Escola Federal de Engenharia de Itajuba, MG (Brazil)
1994-12-31
The non linear electrical loads can give rise to a number of disturbances in electrical power networks. Among them, the high consumption of relative power is to be noted and so is the several harmonic components which may be injected in the industry system and very often in the utility system. So, by using appropriate technical considerations, as well as measurements in typical special electrical loads, such negative effects are analyzed and ways of minimizing them are suggested. (author) 3 refs., 11 figs., 6 tabs.
Arneson, Heather M.; Dousse, Nicholas; Langbort, Cedric
2014-01-01
We consider control design for positive compartmental systems in which each compartment's outflow rate is described by a concave function of the amount of material in the compartment.We address the problem of determining the routing of material between compartments to satisfy time-varying state constraints while ensuring that material reaches its intended destination over a finite time horizon. We give sufficient conditions for the existence of a time-varying state-dependent routing strategy which ensures that the closed-loop system satisfies basic network properties of positivity, conservation and interconnection while ensuring that capacity constraints are satisfied, when possible, or adjusted if a solution cannot be found. These conditions are formulated as a linear programming problem. Instances of this linear programming problem can be solved iteratively to generate a solution to the finite horizon routing problem. Results are given for the application of this control design method to an example problem. Key words: linear programming; control of networks; positive systems; controller constraints and structure.
Nanda, Trushnamayee; Sahoo, Bhabagrahi; Beria, Harsh; Chatterjee, Chandranath
2016-08-01
Although flood forecasting and warning system is a very important non-structural measure in flood-prone river basins, poor raingauge network as well as unavailability of rainfall data in real-time could hinder its accuracy at different lead times. Conversely, since the real-time satellite-based rainfall products are now becoming available for the data-scarce regions, their integration with the data-driven models could be effectively used for real-time flood forecasting. To address these issues in operational streamflow forecasting, a new data-driven model, namely, the wavelet-based non-linear autoregressive with exogenous inputs (WNARX) is proposed and evaluated in comparison with four other data-driven models, viz., the linear autoregressive moving average with exogenous inputs (ARMAX), static artificial neural network (ANN), wavelet-based ANN (WANN), and dynamic nonlinear autoregressive with exogenous inputs (NARX) models. First, the quality of input rainfall products of Tropical Rainfall Measuring Mission Multi-satellite Precipitation Analysis (TMPA), viz., TRMM and TRMM-real-time (RT) rainfall products is assessed through statistical evaluation. The results reveal that the satellite rainfall products moderately correlate with the observed rainfall, with the gauge-adjusted TRMM product outperforming the real-time TRMM-RT product. The TRMM rainfall product better captures the ground observations up to 95 percentile range (30.11 mm/day), although the hit rate decreases for high rainfall intensity. The effect of antecedent rainfall (AR) and climate forecast system reanalysis (CFSR) temperature product on the catchment response is tested in all the developed models. The results reveal that, during real-time flow simulation, the satellite-based rainfall products generally perform worse than the gauge-based rainfall. Moreover, as compared to the existing models, the flow forecasting by the WNARX model is way better than the other four models studied herein with the
Santosa, H.; Hobara, Y.; Balikhin, M. A.
2015-12-01
Very Low Frequency (VLF) waves have been proposed as an approach to study and monitor the lower ionospheric conditions. The ionospheric perturbations are identified in relation with thunderstorm activity, geomagnetic storm and other factors. The temporal dependence of VLF amplitude has a complicated and large daily variabilities in general due to combinations of both effects from above (space weather effect) and below (atmospheric and crustal processes) of the ionosphere. Quantitative contributions from different external sources are not known well yet. Thus the modelling and prediction of VLF wave amplitude are important issues to study the lower ionospheric responses from various external parameters and to also detect the anomalies of the ionosphere. The purpose of the study is to model and predict nighttime average amplitude of VLF wave propagation from the VLF transmitter in Hawaii (NPM) to receiver in Chofu (CHO) Tokyo, Japan path using NARX neural network. The constructed model was trained for the target parameter of nighttime average amplitude of NPM-CHO path. The NARX model, which was built based on daily input variables of various physical parameters such as stratosphere temperature, cosmic rays and total column ozone, possessed good accuracies. As a result, the constructed models are capable of performing accurate multistep ahead predictions, while maintaining acceptable one step ahead prediction accuracy. The results of the predicted daily VLF amplitude are in good agreement with observed (true) value for one step ahead prediction (r = 0.92, RMSE = 1.99), multi-step ahead 5 days prediction (r = 0.91, RMSE = 1.14) and multi-step ahead 10 days prediction (r = 0.75, RMSE = 1.74). The developed model indicates the feasibility and reliability of predicting lower ionospheric properties by the NARX neural network approach, and provides physical insights on the responses of lower ionosphere due to various external forcing.
Shin, Hoo-Chang; Roth, Holger R; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel; Summers, Ronald M
2016-05-01
Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
Directory of Open Access Journals (Sweden)
Fan Hu
2015-11-01
Full Text Available Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs, which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance.
Fault detection for nonlinear networked control system with random packet losses%非线性网络控制系统的故障检测
Institute of Scientific and Technical Information of China (English)
马晔; 崔宝同
2012-01-01
With the presence of random packet losses effects in the network, the problem of fault detection for a class of nonlinear networked control systems is investigated Firstly, based on a T-S fuzzy model, the object is linearized. Random packet losses from the sensor to the controller and from the controller to the actuator are simultaneously considered. And the random packet losses are described by a binary switching sequence satisfying a Bernoulli distribution. Secondly, the fuzzy observer is designed by using the fuzzy dominant subsystem rule. Moreover, sufficient conditions for asymptotical stability of the observer-based closed-loop systems are proposed. Finally, one numerical example is given to illustrate the effectiveness of the proposed results.%针对一类具有随机丢包的非线性网络控制系统,研究了系统的故障检测问题.基于T-S模糊模型将对象线性化,考虑了控制器和执行器之间、控制器和传感器之间的随机丢包现象,采用满足Bernoulli分布的二进制序列来描述数据传输的随机丢包.同时利用模糊主导子系统规则,设计了模糊观测器,给出了基于观测器闭环系统渐近稳定的充分条件,并通过数值仿真实验验证了该方法的有效性.
Institute of Scientific and Technical Information of China (English)
王赟松; 刘钦龙; 高卫中
2004-01-01
标准BP神经网络算法收敛速度慢是限制其广泛应用的主要原因.为此,以标准BP算法为基础,应用最小二乘法理论,提出了一种收敛速度快的BP算法--NLMSBP算法.仿真结果表明,和标准BP算法及其它改进形式比较,NLMSBP算法收敛速度大大提高,稳定性并未降低,这为BP神经网络应用于实时性要求高的场合提供了算法基础.该算法缺点是计算量大,所需计算机内存大,不适于大型网络的计算.%That standard backpropagation(BP) algorithm for training neural networks converges slowly is the main reason why it cannot be used widely in practical applications. Therefore, a new kind of BP algorithm, called the NLMSBP algorithm for short, is put forward in this paper by using solutions for a nonlinear least mean square problem. The experimental results have proved that the algorithm converges very fast and has good stability compared with the standard BP algorithm and the other modifications. It is suitable for training the network with a few thousands of weights and offsets and high training precision demand. If the computer memory is enough, the superiority of the algorithm over the others is very notable. Indeed, it is worth popularizing.
Bloembergen, Nicolaas
1996-01-01
Nicolaas Bloembergen, recipient of the Nobel Prize for Physics (1981), wrote Nonlinear Optics in 1964, when the field of nonlinear optics was only three years old. The available literature has since grown by at least three orders of magnitude.The vitality of Nonlinear Optics is evident from the still-growing number of scientists and engineers engaged in the study of new nonlinear phenomena and in the development of new nonlinear devices in the field of opto-electronics. This monograph should be helpful in providing a historical introduction and a general background of basic ideas both for expe
Sahoo, Avimanyu; Xu, Hao; Jagannathan, Sarangapani
2016-01-01
This paper presents a novel adaptive neural network (NN) control of single-input and single-output uncertain nonlinear discrete-time systems under event sampled NN inputs. In this control scheme, the feedback signals are transmitted, and the NN weights are tuned in an aperiodic manner at the event sampled instants. After reviewing the NN approximation property with event sampled inputs, an adaptive state estimator (SE), consisting of linearly parameterized NNs, is utilized to approximate the unknown system dynamics in an event sampled context. The SE is viewed as a model and its approximated dynamics and the state vector, during any two events, are utilized for the event-triggered controller design. An adaptive event-trigger condition is derived by using both the estimated NN weights and a dead-zone operator to determine the event sampling instants. This condition both facilitates the NN approximation and reduces the transmission of feedback signals. The ultimate boundedness of both the NN weight estimation error and the system state vector is demonstrated through the Lyapunov approach. As expected, during an initial online learning phase, events are observed more frequently. Over time with the convergence of the NN weights, the inter-event times increase, thereby lowering the number of triggered events. These claims are illustrated through the simulation results.
Energy Technology Data Exchange (ETDEWEB)
Geniet, F; Leon, J [Physique Mathematique et Theorique, CNRS-UMR 5825, 34095 Montpellier (France)
2003-05-07
A nonlinear system possessing a natural forbidden band gap can transmit energy of a signal with a frequency in the gap, as recently shown for a nonlinear chain of coupled pendulums (Geniet and Leon 2002 Phys. Rev. Lett. 89 134102). This process of nonlinear supratransmission, occurring at a threshold that is exactly predictable in many cases, is shown to have a simple experimental realization with a mechanical chain of pendulums coupled by a coil spring. It is then analysed in more detail. First we go to different (nonintegrable) systems which do sustain nonlinear supratransmission. Then a Josephson transmission line (a one-dimensional array of short Josephson junctions coupled through superconducting wires) is shown to also sustain nonlinear supratransmission, though being related to a different class of boundary conditions, and despite the presence of damping, finiteness, and discreteness. Finally, the mechanism at the origin of nonlinear supratransmission is found to be a nonlinear instability, and this is briefly discussed here.
Lessmann, Nikolas; Išgum, Ivana; Setio, Arnaud A. A.; de Vos, Bob D.; Ciompi, Francesco; de Jong, Pim A.; Oudkerk, Matthjis; Mali, Willem P. Th. M.; Viergever, Max A.; van Ginneken, Bram
2016-03-01
The amount of calcifications in the coronary arteries is a powerful and independent predictor of cardiovascular events and is used to identify subjects at high risk who might benefit from preventive treatment. Routine quantification of coronary calcium scores can complement screening programs using low-dose chest CT, such as lung cancer screening. We present a system for automatic coronary calcium scoring based on deep convolutional neural networks (CNNs). The system uses three independently trained CNNs to estimate a bounding box around the heart. In this region of interest, connected components above 130 HU are considered candidates for coronary artery calcifications. To separate them from other high intensity lesions, classification of all extracted voxels is performed by feeding two-dimensional 50 mm × 50 mm patches from three orthogonal planes into three concurrent CNNs. The networks consist of three convolutional layers and one fully-connected layer with 256 neurons. In the experiments, 1028 non-contrast-enhanced and non-ECG-triggered low-dose chest CT scans were used. The network was trained on 797 scans. In the remaining 231 test scans, the method detected on average 194.3 mm3 of 199.8 mm3 coronary calcifications per scan (sensitivity 97.2 %) with an average false-positive volume of 10.3 mm3 . Subjects were assigned to one of five standard cardiovascular risk categories based on the Agatston score. Accuracy of risk category assignment was 84.4 % with a linearly weighted κ of 0.89. The proposed system can perform automatic coronary artery calcium scoring to identify subjects undergoing low-dose chest CT screening who are at risk of cardiovascular events with high accuracy.
A deep convolutional neural network for recognizing foods
Jahani Heravi, Elnaz; Habibi Aghdam, Hamed; Puig, Domenec
2015-12-01
Controlling the food intake is an efficient way that each person can undertake to tackle the obesity problem in countries worldwide. This is achievable by developing a smartphone application that is able to recognize foods and compute their calories. State-of-art methods are chiefly based on hand-crafted feature extraction methods such as HOG and Gabor. Recent advances in large-scale object recognition datasets such as ImageNet have revealed that deep Convolutional Neural Networks (CNN) possess more representation power than the hand-crafted features. The main challenge with CNNs is to find the appropriate architecture for each problem. In this paper, we propose a deep CNN which consists of 769; 988 parameters. Our experiments show that the proposed CNN outperforms the state-of-art methods and improves the best result of traditional methods 17%. Moreover, using an ensemble of two CNNs that have been trained two different times, we are able to improve the classification performance 21:5%.
Institute of Scientific and Technical Information of China (English)
P. Balasubramaniam; M. Kalpana; R. Rakkiyappan
2012-01-01
Fuzzy cellular neural networks (FCNNs) are special kinds of cellular neural networks (CNNs).Each cell in an FCNN contains fuzzy operating abilities.The entire network is governed by cellular computing laws.The design of FCNNs is based on fuzzy local rules.In this paper,a linear matrix inequality (LMI) approach for synchronization control of FCNNs with mixed delays is investigated.Mixed delays include discrete time-varying delays and unbounded distributed delays.A dynamic control scheme is proposed to achieve the synchronization between a drive network and a response network.By constructing the Lyapunov-Krasovskii functional which contains a triple-integral term and the free-weighting matrices method an improved delay-dependent stability criterion is derived in terms of LMIs.The controller can be easily obtained by solving the derived LMIs.A numerical example and its simulations are presented to illustrate the effectiveness of the proposed method.
Energy Technology Data Exchange (ETDEWEB)
Duran, Ana Cecilia
1990-03-01
This thesis aims to find a better way to solve large scale nonlinear sparse system problems giving special emphasis to load flow in electric power networks. The suggested algorithms are presented 63 refs., 28 figs., 16 tabs.
Agrawal, Govind
2012-01-01
Since the 4e appeared, a fast evolution of the field has occurred. The 5e of this classic work provides an up-to-date account of the nonlinear phenomena occurring inside optical fibers, the basis of all our telecommunications infastructure as well as being used in the medical field. Reflecting the big developments in research, this new edition includes major new content: slow light effects, which offers a reduction in noise and power consumption and more ordered network traffic-stimulated Brillouin scattering; vectorial treatment of highly nonlinear fibers; and a brand new chapter o
Nonlinear Multiantenna Detection Methods
Directory of Open Access Journals (Sweden)
Chen Sheng
2004-01-01
Full Text Available A nonlinear detection technique designed for multiple-antenna assisted receivers employed in space-division multiple-access systems is investigated. We derive the optimal solution of the nonlinear spatial-processing assisted receiver for binary phase shift keying signalling, which we refer to as the Bayesian detector. It is shown that this optimal Bayesian receiver significantly outperforms the standard linear beamforming assisted receiver in terms of a reduced bit error rate, at the expense of an increased complexity, while the achievable system capacity is substantially enhanced with the advent of employing nonlinear detection. Specifically, when the spatial separation expressed in terms of the angle of arrival between the desired and interfering signals is below a certain threshold, a linear beamformer would fail to separate them, while a nonlinear detection assisted receiver is still capable of performing adequately. The adaptive implementation of the optimal Bayesian detector can be realized using a radial basis function network. Two techniques are presented for constructing block-data-based adaptive nonlinear multiple-antenna assisted receivers. One of them is based on the relevance vector machine invoked for classification, while the other on the orthogonal forward selection procedure combined with the Fisher ratio class-separability measure. A recursive sample-by-sample adaptation procedure is also proposed for training nonlinear detectors based on an amalgam of enhanced -means clustering techniques and the recursive least squares algorithm.
Perrin, Douglas P.; Bueno, Alejandra; Rodriguez, Andrea; Marx, Gerald R.; del Nido, Pedro J.
2017-03-01
In this paper we describe a pilot study, where machine learning methods are used to differentiate between congenital heart diseases. Our approach was to apply convolutional neural networks (CNNs) to echocardiographic images from five different pediatric populations: normal, coarctation of the aorta (CoA), hypoplastic left heart syndrome (HLHS), transposition of the great arteries (TGA), and single ventricle (SV). We used a single network topology that was trained in a pairwise fashion in order to evaluate the potential to differentiate between patient populations. In total we used 59,151 echo frames drawn from 1,666 clinical sequences. Approximately 80% of the data was used for training, and the remainder for validation. Data was split at sequence boundaries to avoid having related images in the training and validation sets. While training was done with echo images/frames, evaluation was performed for both single frame discrimination as well as sequence discrimination (by majority voting). In total 10 networks were generated and evaluated. Unlike other domains where this network topology has been used, in ultrasound there is low visual variation between classes. This work shows the potential for CNNs to be applied to this low-variation domain of medical imaging for disease discrimination.
2016-07-01
Advanced Research Projects Agency (DARPA) Dynamics-Enabled Frequency Sources (DEFYS) program is focused on the convergence of nonlinear dynamics and...Early work in this program has shown that nonlinear dynamics can provide performance advantages. However, the pathway from initial results to...dependent nonlinear stiffness observed in these devices. This work is ongoing, and will continue through the final period of this program . Reference 9
Nayfeh, Ali Hasan
1995-01-01
Nonlinear Oscillations is a self-contained and thorough treatment of the vigorous research that has occurred in nonlinear mechanics since 1970. The book begins with fundamental concepts and techniques of analysis and progresses through recent developments and provides an overview that abstracts and introduces main nonlinear phenomena. It treats systems having a single degree of freedom, introducing basic concepts and analytical methods, and extends concepts and methods to systems having degrees of freedom. Most of this material cannot be found in any other text. Nonlinear Oscillations uses sim
Yoshida, Zensho
2010-01-01
This book gives a general, basic understanding of the mathematical structure "nonlinearity" that lies in the depths of complex systems. Analyzing the heterogeneity that the prefix "non" represents with respect to notions such as the linear space, integrability and scale hierarchy, "nonlinear science" is explained as a challenge of deconstruction of the modern sciences. This book is not a technical guide to teach mathematical tools of nonlinear analysis, nor a zoology of so-called nonlinear phenomena. By critically analyzing the structure of linear theories, and cl
Nanda, Sudarsan
2013-01-01
"Nonlinear analysis" presents recent developments in calculus in Banach space, convex sets, convex functions, best approximation, fixed point theorems, nonlinear operators, variational inequality, complementary problem and semi-inner-product spaces. Nonlinear Analysis has become important and useful in the present days because many real world problems are nonlinear, nonconvex and nonsmooth in nature. Although basic concepts have been presented here but many results presented have not appeared in any book till now. The book could be used as a text for graduate students and also it will be useful for researchers working in this field.
Li, Jing; Fan, Ming; Zhang, Juan; Li, Lihua
2017-03-01
Convolutional neural networks (CNNs) are the state-of-the-art deep learning network architectures that can be used in a range of applications, including computer vision and medical image analysis. It exhibits a powerful representation learning mechanism with an automated design to learn features directly from the data. However, the common 2D CNNs only use the two dimension spatial information without evaluating the correlation between the adjoin slices. In this study, we established a method of 3D CNNs to discriminate between malignant and benign breast tumors. To this end, 143 patients were enrolled which include 66 benign and 77 malignant instances. The MRI images were pre-processed for noise reduction and breast tumor region segmentation. Data augmentation by spatial translating, rotating and vertical and horizontal flipping is applied to the cases to reduce possible over-fitting. A region-of-interest (ROI) and a volume-of-interest (VOI) were segmented in 2D and 3D DCE-MRI, respectively. The enhancement ratio for each MR series was calculated for the 2D and 3D images. The results for the enhancement ratio images in the two series are integrated for classification. The results of the area under the ROC curve(AUC) values are 0.739 and 0.801 for 2D and 3D methods, respectively. The results for 3D CNN which combined 5 slices for each enhancement ratio images achieved a high accuracy(Acc), sensitivity(Sens) and specificity(Spec) of 0.781, 0.744 and 0.823, respectively. This study indicates that 3D CNN deep learning methods can be a promising technology for breast tumor classification without manual feature extraction.
Glaucoma detection based on deep convolutional neural network.
Xiangyu Chen; Yanwu Xu; Damon Wing Kee Wong; Tien Yin Wong; Jiang Liu
2015-08-01
Glaucoma is a chronic and irreversible eye disease, which leads to deterioration in vision and quality of life. In this paper, we develop a deep learning (DL) architecture with convolutional neural network for automated glaucoma diagnosis. Deep learning systems, such as convolutional neural networks (CNNs), can infer a hierarchical representation of images to discriminate between glaucoma and non-glaucoma patterns for diagnostic decisions. The proposed DL architecture contains six learned layers: four convolutional layers and two fully-connected layers. Dropout and data augmentation strategies are adopted to further boost the performance of glaucoma diagnosis. Extensive experiments are performed on the ORIGA and SCES datasets. The results show area under curve (AUC) of the receiver operating characteristic curve in glaucoma detection at 0.831 and 0.887 in the two databases, much better than state-of-the-art algorithms. The method could be used for glaucoma detection.
Electronic Nose Based on an Optimized Competition Neural Network
Directory of Open Access Journals (Sweden)
Haiping Zhang
2011-05-01
Full Text Available In view of the fact that there are disadvantages in that the class number must be determined in advance, the value of learning rates are hard to fix, etc., when using traditional competitive neural networks (CNNs in electronic noses (E-noses, an optimized CNN method was presented. The optimized CNN was established on the basis of the optimum class number of samples according to the changes of the Davies and Bouldin (DB value and it could increase, divide, or delete neurons in order to adjust the number of neurons automatically. Moreover, the learning rate changes according to the variety of training times of each sample. The traditional CNN and the optimized CNN were applied to five kinds of sorted vinegars with an E-nose. The results showed that optimized network structures could adjust the number of clusters dynamically and resulted in good classifications.