NASA Technical Reports Server (NTRS)
Hegemann, S.; Shelhamer, M.; Kramer, P. D.; Zee, D. S.
2000-01-01
The phase of the translational linear VOR (LVOR) can be adaptively modified by exposure to a visual-vestibular mismatch. We extend here our earlier work on LVOR phase adaptation, and discuss the role of the oculomotor neural integrator. Ten subjects were oscillated laterally at 0.5 Hz, 0.3 g peak acceleration, while sitting upright on a linear sled. LVOR was assessed before and after adaptation with subjects tracking the remembered location of a target at 1 m in the dark. Phase and gain were measured by fitting sine waves to the desaccaded eye movements, and comparing sled and eye position. To adapt LVOR phase, the subject viewed a computer-generated stereoscopic visual display, at a virtual distance of 1 m, that moved so as to require either a phase lead or a phase lag of 53 deg. Adaptation lasted 20 min, during which subjects were oscillated at 0.5 Hz/0.3 g. Four of five subjects produced an adaptive change in the lag condition (range 4-45 deg), and each of five produced a change in the lead condition (range 19-56 deg), as requested. Changes in drift on eccentric gaze suggest that the oculomotor velocity-to-position integrator may be involved in the phase changes.
Adaptive-clustering optical neural net.
Casasent, D P; Barnard, E
1990-06-10
Pattern recognition techniques (for clustering and linear discriminant function selection) are combined with neural net methods (that provide an automated method to combine linear discriminant functions into piecewise linear discriminant surfaces). The resulting adaptive-clustering neural net is suitable for optical implementation and has certain desirable properties in comparison with other neural nets. Simulation results are provided.
Neural nets for adaptive filtering and adaptive pattern recognition
Widrow, B.; Winter, R.
1988-03-01
The fields of adaptive signal processing and adaptive neural networks have been developing independently but have that adaptive linear combiner (ALC) in common. With its inputs connected to a tapped delay line, the ALC becomes a key component of an adaptive filter. With its output connected to a quantizer, the ALC becomes an adaptive threshold element of adaptive neuron. Adaptive threshold elements, on the other hand, are the building blocks of neural networks. Today neural nets are the focus of widespread research interest. Areas of investigation include pattern recognition and trainable logic. Neural network systems have not yet had the commercial impact of adaptive filtering. The commonality of the ALC to adaptive signal processing and adaptive neural networks suggests the two fields have much to share with each other. This article describes practical applications of the ALC in signal processing and pattern recognition.
Generalized Adaptive Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1993-01-01
Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.
Synaptic dynamics: linear model and adaptation algorithm.
Yousefi, Ali; Dibazar, Alireza A; Berger, Theodore W
2014-08-01
In this research, temporal processing in brain neural circuitries is addressed by a dynamic model of synaptic connections in which the synapse model accounts for both pre- and post-synaptic processes determining its temporal dynamics and strength. Neurons, which are excited by the post-synaptic potentials of hundred of the synapses, build the computational engine capable of processing dynamic neural stimuli. Temporal dynamics in neural models with dynamic synapses will be analyzed, and learning algorithms for synaptic adaptation of neural networks with hundreds of synaptic connections are proposed. The paper starts by introducing a linear approximate model for the temporal dynamics of synaptic transmission. The proposed linear model substantially simplifies the analysis and training of spiking neural networks. Furthermore, it is capable of replicating the synaptic response of the non-linear facilitation-depression model with an accuracy better than 92.5%. In the second part of the paper, a supervised spike-in-spike-out learning rule for synaptic adaptation in dynamic synapse neural networks (DSNN) is proposed. The proposed learning rule is a biologically plausible process, and it is capable of simultaneously adjusting both pre- and post-synaptic components of individual synapses. The last section of the paper starts with presenting the rigorous analysis of the learning algorithm in a system identification task with hundreds of synaptic connections which confirms the learning algorithm's accuracy, repeatability and scalability. The DSNN is utilized to predict the spiking activity of cortical neurons and pattern recognition tasks. The DSNN model is demonstrated to be a generative model capable of producing different cortical neuron spiking patterns and CA1 Pyramidal neurons recordings. A single-layer DSNN classifier on a benchmark pattern recognition task outperforms a 2-Layer Neural Network and GMM classifiers while having fewer numbers of free parameters and
Adaptive Filtering Using Recurrent Neural Networks
NASA Technical Reports Server (NTRS)
Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.
2005-01-01
A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.
Emotional facial expressions reduce neural adaptation to face identity.
Gerlicher, Anna M V; van Loon, Anouk M; Scholte, H Steven; Lamme, Victor A F; van der Leij, Andries R
2014-05-01
In human social interactions, facial emotional expressions are a crucial source of information. Repeatedly presented information typically leads to an adaptation of neural responses. However, processing seems sustained with emotional facial expressions. Therefore, we tested whether sustained processing of emotional expressions, especially threat-related expressions, would attenuate neural adaptation. Neutral and emotional expressions (happy, mixed and fearful) of same and different identity were presented at 3 Hz. We used electroencephalography to record the evoked steady-state visual potentials (ssVEP) and tested to what extent the ssVEP amplitude adapts to the same when compared with different face identities. We found adaptation to the identity of a neutral face. However, for emotional faces, adaptation was reduced, decreasing linearly with negative valence, with the least adaptation to fearful expressions. This short and straightforward method may prove to be a valuable new tool in the study of emotional processing.
Emotional facial expressions reduce neural adaptation to face identity.
Gerlicher, Anna M V; van Loon, Anouk M; Scholte, H Steven; Lamme, Victor A F; van der Leij, Andries R
2014-05-01
In human social interactions, facial emotional expressions are a crucial source of information. Repeatedly presented information typically leads to an adaptation of neural responses. However, processing seems sustained with emotional facial expressions. Therefore, we tested whether sustained processing of emotional expressions, especially threat-related expressions, would attenuate neural adaptation. Neutral and emotional expressions (happy, mixed and fearful) of same and different identity were presented at 3 Hz. We used electroencephalography to record the evoked steady-state visual potentials (ssVEP) and tested to what extent the ssVEP amplitude adapts to the same when compared with different face identities. We found adaptation to the identity of a neutral face. However, for emotional faces, adaptation was reduced, decreasing linearly with negative valence, with the least adaptation to fearful expressions. This short and straightforward method may prove to be a valuable new tool in the study of emotional processing. PMID:23512931
Adaptive optimization and control using neural networks
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
Equating Scores from Adaptive to Linear Tests
ERIC Educational Resources Information Center
van der Linden, Wim J.
2006-01-01
Two local methods for observed-score equating are applied to the problem of equating an adaptive test to a linear test. In an empirical study, the methods were evaluated against a method based on the test characteristic function (TCF) of the linear test and traditional equipercentile equating applied to the ability estimates on the adaptive test…
Learning and adaptation in fuzzy neural systems
NASA Astrophysics Data System (ADS)
Gupta, Madan M.
1992-03-01
In recent years, an increasing number of researchers have become involved in the subject of fuzzy neural networks in the hope of combining the reasoning strength of fuzzy logic and the learning and adaptation power of neural networks. This provides a more powerful tool for fuzzy information processing and for exploring the functioning of human brains. In this paper, an attempt has been made to establish some basic models for fuzzy neurons. First, several possible fuzzy neuron models are proposed. Second, synaptic and somatic learning and adaptation mechanisms are proposed. Finally, the possibility of applying nonfuzzy neural networks approaches to fuzzy systems is also described.
Neural network with dynamically adaptable neurons
NASA Technical Reports Server (NTRS)
Tawel, Raoul (Inventor)
1994-01-01
This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.
Adaptive Neurotechnology for Making Neural Circuits Functional .
NASA Astrophysics Data System (ADS)
Jung, Ranu
2008-03-01
Two of the most important trends in recent technological developments are that technology is increasingly integrated with biological systems and that it is increasingly adaptive in its capabilities. Neuroprosthetic systems that provide lost sensorimotor function after a neural disability offer a platform to investigate this interplay between biological and engineered systems. Adaptive neurotechnology (hardware and software) could be designed to be biomimetic, guided by the physical and programmatic constraints observed in biological systems, and allow for real-time learning, stability, and error correction. An example will present biomimetic neural-network hardware that can be interfaced with the isolated spinal cord of a lower vertebrate to allow phase-locked real-time neural control. Another will present adaptive neural network control algorithms for functional electrical stimulation of the peripheral nervous system to provide desired movements of paralyzed limbs in rodents or people. Ultimately, the frontier lies in being able to utilize the adaptive neurotechnology to promote neuroplasticity in the living system on a long-time scale under co-adaptive conditions.
Adaptive neural control of aeroelastic response
NASA Astrophysics Data System (ADS)
Lichtenwalner, Peter F.; Little, Gerald R.; Scott, Robert C.
1996-05-01
The Adaptive Neural Control of Aeroelastic Response (ANCAR) program is a joint research and development effort conducted by McDonnell Douglas Aerospace (MDA) and the National Aeronautics and Space Administration, Langley Research Center (NASA LaRC) under a Memorandum of Agreement (MOA). The purpose of the MOA is to cooperatively develop the smart structure technologies necessary for alleviating undesirable vibration and aeroelastic response associated with highly flexible structures. Adaptive control can reduce aeroelastic response associated with buffet and atmospheric turbulence, it can increase flutter margins, and it may be able to reduce response associated with nonlinear phenomenon like limit cycle oscillations. By reducing vibration levels and loads, aircraft structures can have lower acquisition cost, reduced maintenance, and extended lifetimes. Phase I of the ANCAR program involved development and demonstration of a neural network-based semi-adaptive flutter suppression system which used a neural network for scheduling control laws as a function of Mach number and dynamic pressure. This controller was tested along with a robust fixed-gain control law in NASA's Transonic Dynamics Tunnel (TDT) utilizing the Benchmark Active Controls Testing (BACT) wing. During Phase II, a fully adaptive on-line learning neural network control system has been developed for flutter suppression which will be tested in 1996. This paper presents the results of Phase I testing as well as the development progress of Phase II.
Intrinsic adaptation in autonomous recurrent neural networks.
Marković, Dimitrije; Gros, Claudius
2012-02-01
A massively recurrent neural network responds on one side to input stimuli and is autonomously active, on the other side, in the absence of sensory inputs. Stimuli and information processing depend crucially on the quality of the autonomous-state dynamics of the ongoing neural activity. This default neural activity may be dynamically structured in time and space, showing regular, synchronized, bursting, or chaotic activity patterns. We study the influence of nonsynaptic plasticity on the default dynamical state of recurrent neural networks. The nonsynaptic adaption considered acts on intrinsic neural parameters, such as the threshold and the gain, and is driven by the optimization of the information entropy. We observe, in the presence of the intrinsic adaptation processes, three distinct and globally attracting dynamical regimes: a regular synchronized, an overall chaotic, and an intermittent bursting regime. The intermittent bursting regime is characterized by intervals of regular flows, which are quite insensitive to external stimuli, interceded by chaotic bursts that respond sensitively to input signals. We discuss these findings in the context of self-organized information processing and critical brain dynamics. PMID:22091667
Adaptive holographic implementation of a neural network
NASA Astrophysics Data System (ADS)
Downie, John D.; Hine, Butler P., III; Reid, Max B.
1990-07-01
A holographic implementation for neural networks is proposed and demonstrated as an alternative to the optical matrix-vector multiplier architecture. In comparison, the holographic architecture makes more efficient use of the system space-bandwidth product for certain types of neural networks. The principal network component is a thermoplastic hologram, used to provide both interconnection weights and beam redirection. Given the updatable nature of this type of hologram, adaptivity or network learning is possible in the optical system. Two networks with fixed weights are experimentally implemented and verified, and for one of these examples we demonstrate the advantage of the holographic implementation with respect to the matrix-vector processor.
Adaptive Neural Networks for Automatic Negotiation
Sakas, D. P.; Vlachos, D. S.; Simos, T. E.
2007-12-26
The use of fuzzy logic and fuzzy neural networks has been found effective for the modelling of the uncertain relations between the parameters of a negotiation procedure. The problem with these configurations is that they are static, that is, any new knowledge from theory or experiment lead to the construction of entirely new models. To overcome this difficulty, we apply in this work, an adaptive neural topology to model the negotiation process. Finally a simple simulation is carried in order to test the new method.
Adaptive NUC algorithm for uncooled IRFPA based on neural networks
NASA Astrophysics Data System (ADS)
Liu, Ziji; Jiang, Yadong; Lv, Jian; Zhu, Hongbin
2010-10-01
With developments in uncooled infrared plane array (UFPA) technology, many new advanced uncooled infrared sensors are used in defensive weapons, scientific research, industry and commercial applications. A major difference in imaging techniques between infrared IRFPA imaging system and a visible CCD camera is that, IRFPA need nonuniformity correction and dead pixel compensation, we usually called it infrared image pre-processing. Two-point or multi-point correction algorithms based on calibration commonly used may correct the non-uniformity of IRFPAs, but they are limited by pixel linearity and instability. Therefore, adaptive non-uniformity correction techniques are developed. Two of these adaptive non-uniformity correction algorithms are mostly discussed, one is based on temporal high-pass filter, and another is based on neural network. In this paper, a new NUC algorithm based on improved neural networks is introduced, and involves the compare result between improved neural networks and other adaptive correction techniques. A lot of different will discussed in different angle, like correction effects, calculation efficiency, hardware implementation and so on. According to the result and discussion, it could be concluding that the adaptive algorithm offers improved performance compared to traditional calibration mode techniques. This new algorithm not only provides better sensitivity, but also increases the system dynamic range. As the sensor application expended, it will be very useful in future infrared imaging systems.
Linear ubiquitination signals in adaptive immune responses
Ikeda, Fumiyo
2015-01-01
Summary Ubiquitin can form eight different linkage types of chains using the intrinsic Met 1 residue or one of the seven intrinsic Lys residues. Each linkage-type of ubiquitin chain has a distinct three-dimensional topology, functioning as a tag to attract specific signaling molecules, which are so-called ubiquitin readers, and regulates various biological functions. Ubiquitin chains linked via Met 1 in a head-to-tail manner are called linear ubiquitin chains. Linear ubiquitination plays an important role in the regulation of cellular signaling, including the best-characterized Tumor Necrosis Factor (TNF) -induced canonical nuclear factor-kappa B (NF-κB) pathway. Linear ubiquitin chains are specifically generated by an E3 ligase complex called the linear ubiquitin chain assembly complex (LUBAC) and hydrolyzed by a deubiquitinase (DUB) called ovarian tumor (OTU) DUB with linear linkage specificity (OTULIN). LUBAC linearly ubiquitinates critical molecules in the TNF pathway, such as NEMO and RIPK1. The linear ubiquitin chains are then recognized by the ubiquitin readers, including NEMO, which control the TNF pathway. Accumulating evidence indicates an importance of the LUBAC complex in the regulation of apoptosis, development, and inflammation in mice. In this article, I focus on the role of linear ubiquitin chains in adaptive immune responses with an emphasis on the TNF-induced signaling pathways. PMID:26085218
Adaptive nonlinear control of missiles using neural networks
NASA Astrophysics Data System (ADS)
McFarland, Michael Bryan
Research has shown that neural networks can be used to improve upon approximate dynamic inversion for control of uncertain nonlinear systems. In one architecture, the neural network adaptively cancels inversion errors through on-line learning. Such learning is accomplished by a simple weight update rule derived from Lyapunov theory, thus assuring stability of the closed-loop system. In this research, previous results using linear-in-parameters neural networks were reformulated in the context of a more general class of composite nonlinear systems, and the control scheme was shown to possess important similarities and major differences with established methods of adaptive control. The neural-adaptive nonlinear control methodology in question has been used to design an autopilot for an anti-air missile with enhanced agile maneuvering capability, and simulation results indicate that this approach is a feasible one. There are, however, certain difficulties associated with choosing the proper network architecture which make it difficult to achieve the rapid learning required in this application. Accordingly, this technique has been further extended to incorporate the important class of feedforward neural networks with a single hidden layer. These neural networks feature well-known approximation capabilities and provide an effective, although nonlinear, parameterization of the adaptive control problem. Numerical results from a six-degree-of-freedom nonlinear agile anti-air missile simulation demonstrate the effectiveness of the autopilot design based on multilayer networks. Previous work in this area has implicitly assumed precise knowledge of the plant order, and made no allowances for unmodeled dynamics. This thesis describes an approach to the problem of controlling a class of nonlinear systems in the face of both unknown nonlinearities and unmodeled dynamics. The proposed methodology is similar to robust adaptive control techniques derived for control of linear
Neural Adaptation Effects in Conceptual Processing
Marino, Barbara F. M.; Borghi, Anna M.; Gemmi, Luca; Cacciari, Cristina; Riggio, Lucia
2015-01-01
We investigated the conceptual processing of nouns referring to objects characterized by a highly typical color and orientation. We used a go/no-go task in which we asked participants to categorize each noun as referring or not to natural entities (e.g., animals) after a selective adaptation of color-edge neurons in the posterior LV4 region of the visual cortex was induced by means of a McCollough effect procedure. This manipulation affected categorization: the green-vertical adaptation led to slower responses than the green-horizontal adaptation, regardless of the specific color and orientation of the to-be-categorized noun. This result suggests that the conceptual processing of natural entities may entail the activation of modality-specific neural channels with weights proportional to the reliability of the signals produced by these channels during actual perception. This finding is discussed with reference to the debate about the grounded cognition view. PMID:26264031
Adaptive computation algorithm for RBF neural network.
Han, Hong-Gui; Qiao, Jun-Fei
2012-02-01
A novel learning algorithm is proposed for nonlinear modelling and identification using radial basis function neural networks. The proposed method simplifies neural network training through the use of an adaptive computation algorithm (ACA). In addition, the convergence of the ACA is analyzed by the Lyapunov criterion. The proposed algorithm offers two important advantages. First, the model performance can be significantly improved through ACA, and the modelling error is uniformly ultimately bounded. Secondly, the proposed ACA can reduce computational cost and accelerate the training speed. The proposed method is then employed to model classical nonlinear system with limit cycle and to identify nonlinear dynamic system, exhibiting the effectiveness of the proposed algorithm. Computational complexity analysis and simulation results demonstrate its effectiveness.
Real-time Adaptive Control Using Neural Generalized Predictive Control
NASA Technical Reports Server (NTRS)
Haley, Pam; Soloway, Don; Gold, Brian
1999-01-01
The objective of this paper is to demonstrate the feasibility of a Nonlinear Generalized Predictive Control algorithm by showing real-time adaptive control on a plant with relatively fast time-constants. Generalized Predictive Control has classically been used in process control where linear control laws were formulated for plants with relatively slow time-constants. The plant of interest for this paper is a magnetic levitation device that is nonlinear and open-loop unstable. In this application, the reference model of the plant is a neural network that has an embedded nominal linear model in the network weights. The control based on the linear model provides initial stability at the beginning of network training. In using a neural network the control laws are nonlinear and online adaptation of the model is possible to capture unmodeled or time-varying dynamics. Newton-Raphson is the minimization algorithm. Newton-Raphson requires the calculation of the Hessian, but even with this computational expense the low iteration rate make this a viable algorithm for real-time control.
Bounded Linear Stability Margin Analysis of Nonlinear Hybrid Adaptive Control
NASA Technical Reports Server (NTRS)
Nguyen, Nhan T.; Boskovic, Jovan D.
2008-01-01
This paper presents a bounded linear stability analysis for a hybrid adaptive control that blends both direct and indirect adaptive control. Stability and convergence of nonlinear adaptive control are analyzed using an approximate linear equivalent system. A stability margin analysis shows that a large adaptive gain can lead to a reduced phase margin. This method can enable metrics-driven adaptive control whereby the adaptive gain is adjusted to meet stability margin requirements.
Adaptive pattern recognition and neural networks
Pao, Yohhan.
1989-01-01
The application of neural-network computers to pattern-recognition tasks is discussed in an introduction for advanced students. Chapters are devoted to the nature of the pattern-recognition task, the Bayesian approach to the estimation of class membership, the fuzzy-set approach, patterns with nonnumeric feature values, learning discriminants and the generalized perceptron, recognition and recall on the basis of partial cues, associative memories, self-organizing nets, the functional-link net, fuzzy logic in the linking of symbolic and subsymbolic processing, and adaptive pattern recognition and its applications. Also included are C-language programs for (1) a generalized delta-rule net for supervised learning and (2) unsupervised learning based on the discovery of clustered structure. 183 refs.
Adaptive neural network motion control of manipulators with experimental evaluations.
Puga-Guzmán, S; Moreno-Valenzuela, J; Santibáñez, V
2014-01-01
A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller. PMID:24574910
Adaptive Neural Network Motion Control of Manipulators with Experimental Evaluations
Puga-Guzmán, S.; Moreno-Valenzuela, J.; Santibáñez, V.
2014-01-01
A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller. PMID:24574910
Adaptive neural network motion control of manipulators with experimental evaluations.
Puga-Guzmán, S; Moreno-Valenzuela, J; Santibáñez, V
2014-01-01
A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller.
A study of interceptor attitude control based on adaptive wavelet neural networks
NASA Astrophysics Data System (ADS)
Li, Da; Wang, Qing-chao
2005-12-01
This paper engages to study the 3-DOF attitude control problem of the kinetic interceptor. When the kinetic interceptor enters into terminal guidance it has to maneuver with large angles. The characteristic of interceptor attitude system is nonlinearity, strong-coupling and MIMO. A kind of inverse control approach based on adaptive wavelet neural networks was proposed in this paper. Instead of using one complex neural network as the controller, the nonlinear dynamics of the interceptor can be approximated by three independent subsystems applying exact feedback-linearization firstly, and then controllers for each subsystem are designed using adaptive wavelet neural networks respectively. This method avoids computing a large amount of the weights and bias in one massive neural network and the control parameters can be adaptive changed online. Simulation results betray that the proposed controller performs remarkably well.
A biomimetic adaptive algorithm and low-power architecture for implantable neural decoders.
Rapoport, Benjamin I; Wattanapanitch, Woradorn; Penagos, Hector L; Musallam, Sam; Andersen, Richard A; Sarpeshkar, Rahul
2009-01-01
Algorithmically and energetically efficient computational architectures that operate in real time are essential for clinically useful neural prosthetic devices. Such devices decode raw neural data to obtain direct control signals for external devices. They can also perform data compression and vastly reduce the bandwidth and consequently power expended in wireless transmission of raw data from implantable brain-machine interfaces. We describe a biomimetic algorithm and micropower analog circuit architecture for decoding neural cell ensemble signals. The decoding algorithm implements a continuous-time artificial neural network, using a bank of adaptive linear filters with kernels that emulate synaptic dynamics. The filters transform neural signal inputs into control-parameter outputs, and can be tuned automatically in an on-line learning process. We provide experimental validation of our system using neural data from thalamic head-direction cells in an awake behaving rat.
A Biomimetic Adaptive Algorithm and Low-Power Architecture for Implantable Neural Decoders
Rapoport, Benjamin I.; Wattanapanitch, Woradorn; Penagos, Hector L.; Musallam, Sam; Andersen, Richard A.; Sarpeshkar, Rahul
2010-01-01
Algorithmically and energetically efficient computational architectures that operate in real time are essential for clinically useful neural prosthetic devices. Such devices decode raw neural data to obtain direct control signals for external devices. They can also perform data compression and vastly reduce the bandwidth and consequently power expended in wireless transmission of raw data from implantable brain-machine interfaces. We describe a biomimetic algorithm and micropower analog circuit architecture for decoding neural cell ensemble signals. The decoding algorithm implements a continuous-time artificial neural network, using a bank of adaptive linear filters with kernels that emulate synaptic dynamics. The filters transform neural signal inputs into control-parameter outputs, and can be tuned automatically in an on-line learning process. We provide experimental validation of our system using neural data from thalamic head-direction cells in an awake behaving rat. PMID:19964345
Linearly-Constrained Adaptive Signal Processing Methods
NASA Astrophysics Data System (ADS)
Griffiths, Lloyd J.
1988-01-01
In adaptive least-squares estimation problems, a desired signal d(n) is estimated using a linear combination of L observation values samples xi (n), x2(n), . . . , xL-1(n) and denoted by the vector X(n). The estimate is formed as the inner product of this vector with a corresponding L-dimensional weight vector W. One particular weight vector of interest is Wopt which minimizes the mean-square between d(n) and the estimate. In this context, the term `mean-square difference' is a quadratic measure such as statistical expectation or time average. The specific value of W which achieves the minimum is given by the prod-uct of the inverse data covariance matrix and the cross-correlation between the data vector and the desired signal. The latter is often referred to as the P-vector. For those cases in which time samples of both the desired and data vector signals are available, a variety of adaptive methods have been proposed which will guarantee that an iterative weight vector Wa(n) converges (in some sense) to the op-timal solution. Two which have been extensively studied are the recursive least-squares (RLS) method and the LMS gradient approximation approach. There are several problems of interest in the communication and radar environment in which the optimal least-squares weight set is of interest and in which time samples of the desired signal are not available. Examples can be found in array processing in which only the direction of arrival of the desired signal is known and in single channel filtering where the spectrum of the desired response is known a priori. One approach to these problems which has been suggested is the P-vector algorithm which is an LMS-like approximate gradient method. Although it is easy to derive the mean and variance of the weights which result with this algorithm, there has never been an identification of the corresponding underlying error surface which the procedure searches. The purpose of this paper is to suggest an alternative
A recurrent neural network for adaptive beamforming and array correction.
Che, Hangjun; Li, Chuandong; He, Xing; Huang, Tingwen
2016-08-01
In this paper, a recurrent neural network (RNN) is proposed for solving adaptive beamforming problem. In order to minimize sidelobe interference, the problem is described as a convex optimization problem based on linear array model. RNN is designed to optimize system's weight values in the feasible region which is derived from arrays' state and plane wave's information. The new algorithm is proven to be stable and converge to optimal solution in the sense of Lyapunov. So as to verify new algorithm's performance, we apply it to beamforming under array mismatch situation. Comparing with other optimization algorithms, simulations suggest that RNN has strong ability to search for exact solutions under the condition of large scale constraints.
Neural and Fuzzy Adaptive Control of Induction Motor Drives
NASA Astrophysics Data System (ADS)
Bensalem, Y.; Sbita, L.; Abdelkrim, M. N.
2008-06-01
This paper proposes an adaptive neural network speed control scheme for an induction motor (IM) drive. The proposed scheme consists of an adaptive neural network identifier (ANNI) and an adaptive neural network controller (ANNC). For learning the quoted neural networks, a back propagation algorithm was used to automatically adjust the weights of the ANNI and ANNC in order to minimize the performance functions. Here, the ANNI can quickly estimate the plant parameters and the ANNC is used to provide on-line identification of the command and to produce a control force, such that the motor speed can accurately track the reference command. By combining artificial neural network techniques with fuzzy logic concept, a neural and fuzzy adaptive control scheme is developed. Fuzzy logic was used for the adaptation of the neural controller to improve the robustness of the generated command. The developed method is robust to load torque disturbance and the speed target variations when it ensures precise trajectory tracking with the prescribed dynamics. The algorithm was verified by simulation and the results obtained demonstrate the effectiveness of the IM designed controller.
Neural and Fuzzy Adaptive Control of Induction Motor Drives
Bensalem, Y.; Sbita, L.; Abdelkrim, M. N.
2008-06-12
This paper proposes an adaptive neural network speed control scheme for an induction motor (IM) drive. The proposed scheme consists of an adaptive neural network identifier (ANNI) and an adaptive neural network controller (ANNC). For learning the quoted neural networks, a back propagation algorithm was used to automatically adjust the weights of the ANNI and ANNC in order to minimize the performance functions. Here, the ANNI can quickly estimate the plant parameters and the ANNC is used to provide on-line identification of the command and to produce a control force, such that the motor speed can accurately track the reference command. By combining artificial neural network techniques with fuzzy logic concept, a neural and fuzzy adaptive control scheme is developed. Fuzzy logic was used for the adaptation of the neural controller to improve the robustness of the generated command. The developed method is robust to load torque disturbance and the speed target variations when it ensures precise trajectory tracking with the prescribed dynamics. The algorithm was verified by simulation and the results obtained demonstrate the effectiveness of the IM designed controller.
Adaptive Neurons For Artificial Neural Networks
NASA Technical Reports Server (NTRS)
Tawel, Raoul
1990-01-01
Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.
Intelligent control of non-linear dynamical system based on the adaptive neurocontroller
NASA Astrophysics Data System (ADS)
Engel, E.; Kovalev, I. V.; Kobezhicov, V.
2015-10-01
This paper presents an adaptive neuro-controller for intelligent control of non-linear dynamical system. The formed as the fuzzy selective neural net the adaptive neuro-controller on the base of system's state, creates the effective control signal under random perturbations. The validity and advantages of the proposed adaptive neuro-controller are demonstrated by numerical simulations. The simulation results show that the proposed controller scheme achieves real-time control speed and the competitive performance, as compared to PID, fuzzy logic controllers.
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.
Adaptive Optimization of Aircraft Engine Performance Using Neural Networks
NASA Technical Reports Server (NTRS)
Simon, Donald L.; Long, Theresa W.
1995-01-01
Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.
APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION
Musson, John C.; Seaton, Chad; Spata, Mike F.; Yan, Jianxun
2012-11-01
Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.
NASA Astrophysics Data System (ADS)
Kim, Nakwan
Utilizing the universal approximation property of neural networks, we develop several novel approaches to neural network-based adaptive output feedback control of nonlinear systems, and illustrate these approaches for several flight control applications. In particular, we address the problem of non-affine systems and eliminate the fixed point assumption present in earlier work. All of the stability proofs are carried out in a form that eliminates an algebraic loop in the neural network implementation. An approximate input/output feedback linearizing controller is augmented with a neural network using input/output sequences of the uncertain system. These approaches permit adaptation to both parametric uncertainty and unmodeled dynamics. All physical systems also have control position and rate limits, which may either deteriorate performance or cause instability for a sufficiently high control bandwidth. Here we apply a method for protecting an adaptive process from the effects of input saturation and time delays, known as "pseudo control hedging". This method was originally developed for the state feedback case, and we provide a stability analysis that extends its domain of applicability to the case of output feedback. The approach is illustrated by the design of a pitch-attitude flight control system for a linearized model of an R-50 experimental helicopter, and by the design of a pitch-rate control system for a 58-state model of a flexible aircraft consisting of rigid body dynamics coupled with actuator and flexible modes. A new approach to augmentation of an existing linear controller is introduced. It is especially useful when there is limited information concerning the plant model, and the existing controller. The approach is applied to the design of an adaptive autopilot for a guided munition. Design of a neural network adaptive control that ensures asymptotically stable tracking performance is also addressed.
Adaptive Synaptogenesis Constructs Neural Codes That Benefit Discrimination
Thomas, Blake T.; Blalock, Davis W.; Levy, William B.
2015-01-01
Intelligent organisms face a variety of tasks requiring the acquisition of expertise within a specific domain, including the ability to discriminate between a large number of similar patterns. From an energy-efficiency perspective, effective discrimination requires a prudent allocation of neural resources with more frequent patterns and their variants being represented with greater precision. In this work, we demonstrate a biologically plausible means of constructing a single-layer neural network that adaptively (i.e., without supervision) meets this criterion. Specifically, the adaptive algorithm includes synaptogenesis, synaptic shedding, and bi-directional synaptic weight modification to produce a network with outputs (i.e. neural codes) that represent input patterns proportional to the frequency of related patterns. In addition to pattern frequency, the correlational structure of the input environment also affects allocation of neural resources. The combined synaptic modification mechanisms provide an explanation of neuron allocation in the case of self-taught experts. PMID:26176744
Application of neural adaptive power system stabilizer in a multi-machine power system
Shamsollahi, P.; Malik, O.P.
1999-09-01
Application of a neural adaptive power system stabilizer (NAPSS) to a five-machine power system is described in this paper. The proposed NAPSS comprises two subnetworks. The adaptive neuro-identifier (ANI) to dynamically identify the non-linear plant, and the adaptive neuro-controller (ANC) to damp output oscillations. The back-propagation training method is used on-line to train these subnetworks. The effectiveness of the proposed NAPSS in damping both local and inter-area modes of oscillations and its self-coordination ability are demonstrated.
Indirect techniques for adaptive input-output linearization of non-linear systems
NASA Technical Reports Server (NTRS)
Teel, Andrew; Kadiyala, Raja; Kokotovic, Peter; Sastry, Shankar
1991-01-01
A technique of indirect adaptive control based on certainty equivalence for input output linearization of nonlinear systems is proven convergent. It does not suffer from the overparameterization drawbacks of the direct adaptive control techniques on the same plant. This paper also contains a semiindirect adaptive controller which has several attractive features of both the direct and indirect schemes.
A recurrent neural network for solving bilevel linear programming problem.
He, Xing; Li, Chuandong; Huang, Tingwen; Li, Chaojie; Huang, Junjian
2014-04-01
In this brief, based on the method of penalty functions, a recurrent neural network (NN) modeled by means of a differential inclusion is proposed for solving the bilevel linear programming problem (BLPP). Compared with the existing NNs for BLPP, the model has the least number of state variables and simple structure. Using nonsmooth analysis, the theory of differential inclusions, and Lyapunov-like method, the equilibrium point sequence of the proposed NNs can approximately converge to an optimal solution of BLPP under certain conditions. Finally, the numerical simulations of a supply chain distribution model have shown excellent performance of the proposed recurrent NNs.
Development of a digital adaptive optimal linear regulator flight controller
NASA Technical Reports Server (NTRS)
Berry, P.; Kaufman, H.
1975-01-01
Digital adaptive controllers have been proposed as a means for retaining uniform handling qualities over the flight envelope of a high-performance aircraft. Towards such an implementation, an explicit adaptive controller, which makes direct use of online parameter identification, has been developed and applied to the linearized lateral equations of motion for a typical fighter aircraft. The system is composed of an online weighted least-squares parameter identifier, a Kalman state filter, and a model following control law designed using optimal linear regulator theory. Simulation experiments with realistic measurement noise indicate that the proposed adaptive system has the potential for onboard implementation.
Peng, Jinzhu; Dubay, Rickey
2011-10-01
In this paper, an adaptive control approach based on the neural networks is presented to control a DC motor system with dead-zone characteristics (DZC), where two neural networks are proposed to formulate the traditional identification and control approaches. First, a Wiener-type neural network (WNN) is proposed to identify the motor DZC, which formulates the Wiener model with a linear dynamic block in cascade with a nonlinear static gain. Second, a feedforward neural network is proposed to formulate the traditional PID controller, termed as PID-type neural network (PIDNN), which is then used to control and compensate for the DZC. In this way, the DC motor system with DZC is identified by the WNN identifier, which provides model information to the PIDNN controller in order to make it adaptive. Back-propagation algorithms are used to train both neural networks. Also, stability and convergence analysis are conducted using the Lyapunov theorem. Finally, experiments on the DC motor system demonstrated accurate identification and good compensation for dead-zone with improved control performance over the conventional PID control.
Increasing autonomy of precision spacecraft using neural network adaptive control
NASA Astrophysics Data System (ADS)
Denoyer, Keith K.; Ninneman, R. Rory
1999-01-01
In recent years, there has been a significant interest in the use of adaptive methods for controlling structures in high precision aerospace applications. This is because adaptive methods offer the potential to autonomously adjust to system characteristics different from those modeled or seen in qualification testing. This is especially true of spacecraft, which are generally tested in a 1-g environment. Despite extensive research, it remains extremely difficult to predict on-orbit 0-g behavior. In addition, system dynamics often tend to be time varying. This can take the form of slow changes due to degradation of materials and aging of the spacecraft or sudden failures such as the loss of a sensor or actuator. These events become increasingly likely as spacecraft become more and more complex. By decreasing modeling and testing requirements, lowering operations and maintenance activities that require human intervention, and increasing reliability, adaptive methods have the potential to significantly reduce cost and increase performance of these systems. One class of adaptive control methods are those which utilize artificial neural networks. The use of neural networks has become increasingly mature in a number of areas such as image processing and speech recognition. However, despite a number of publications on the subject, very few instances exist where neural networks have actually been used in control and in particular, structural control applications. The United States Air Force Research Laboratory (AFRL) is currently engaged in advancing adaptive neural control technologies for application to precision space systems. This paper gives an overview of several past and current ground and space based adaptive neural control experiments.
Adapting the range of validity for the Carleman linearization
NASA Astrophysics Data System (ADS)
Weber, Harry; Mathis, Wolfgang
2016-09-01
In this contribution, the limitations of the Carleman linearization approach are presented and discussed. The Carleman linearization transforms an ordinary nonlinear differential equation into an infinite system of linear differential equations. In order to transform the nonlinear differential equation, orthogonal polynomials which represent solutions of a Sturm-Liouville problem are used as basis. The determination of the time derivate of this basis yields an infinite dimensional linear system that depends on the considered nonlinear differential equation. The infinite linear system has the same properties as the nonlinear differential equation such as limit cycles or chaotic behavior. In general, the infinite dimensional linear system cannot be solved. Therefore, the infinite dimensional linear system has to be approximated by a finite dimensional linear system. Due to limitation of dimension the solution of the finite dimensional linear system does not represent the global behavior of the nonlinear differential equation. In fact, the accuracy of the approximation depends on the considered nonlinear system and the initial value. The idea of this contribution is to adapt the range of validity for the Carleman linearization in order to increase the accuracy of the approximation for different ranges of initial values. Instead of truncating the infinite dimensional system after a certain order a Taylor series approach is used to approximate the behavior of the nonlinear differential equation about different equilibrium points. Thus, the adapted finite linear system describes the local behavior of the solution of the nonlinear differential equation.
Adaptive neural network for image enhancement
NASA Astrophysics Data System (ADS)
Perl, Dan; Marsland, T. A.
1992-09-01
ANNIE is a neural network that removes noise and sharpens edges in digital images. For noise removal, ANNIE makes a weighted average of the values of the pixels over a certain neighborhood. For edge sharpening, ANNIE detects edges and applies a correction around them. Although averaging is a simple operation and needs only a two-layer neural network, detecting edges is more complex and demands several hidden layers. Based on Marr's theory of natural vision, the edge detection method uses zero-crossings in the image filtered by the ∇2G operator (where ∇2 is the Laplacian operator and G stands for a two- dimensional Gaussian distribution), and uses two channels with different spatial frequencies. Edge detectors are tuned for vertical and horizontal orientations. Lateral inhibition implemented through one-step recursion achieves both edge relaxation and correlation of the two channels. Training by means of the quickprop algorithm determines the shapes of the weighted averaging filter and the edge correction filters, and the rules for edge relaxation and channel interaction. ANNIE uses pairs of pictures as training patterns: one picture is a reference for the output of the network and the same picture deteriorated by noise and/or blur is the input of the network.
Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture
Disney, Adam; Reynolds, John
2015-01-01
Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.
Adaptation algorithms for 2-D feedforward neural networks.
Kaczorek, T
1995-01-01
The generalized weight adaptation algorithms presented by J.G. Kuschewski et al. (1993) and by S.H. Zak and H.J. Sira-Ramirez (1990) are extended for 2-D madaline and 2-D two-layer feedforward neural nets (FNNs).
Diminished neural adaptation during implicit learning in autism.
Schipul, Sarah E; Just, Marcel Adam
2016-01-15
Neuroimaging studies have shown evidence of disrupted neural adaptation during learning in individuals with autism spectrum disorder (ASD) in several types of tasks, potentially stemming from frontal-posterior cortical underconnectivity (Schipul et al., 2012). The aim of the current study was to examine neural adaptations in an implicit learning task that entails participation of frontal and posterior regions. Sixteen high-functioning adults with ASD and sixteen neurotypical control participants were trained on and performed an implicit dot pattern prototype learning task in a functional magnetic resonance imaging (fMRI) session. During the preliminary exposure to the type of implicit prototype learning task later to be used in the scanner, the ASD participants took longer than the neurotypical group to learn the task, demonstrating altered implicit learning in ASD. After equating task structure learning, the two groups' brain activation differed during their learning of a new prototype in the subsequent scanning session. The main findings indicated that neural adaptations in a distributed task network were reduced in the ASD group, relative to the neurotypical group, and were related to ASD symptom severity. Functional connectivity was reduced and did not change as much during learning for the ASD group, and was related to ASD symptom severity. These findings suggest that individuals with ASD show altered neural adaptations during learning, as seen in both activation and functional connectivity measures. This finding suggests why many real-world implicit learning situations may pose special challenges for ASD.
Real-Time Adaptive Color Segmentation by Neural Networks
NASA Technical Reports Server (NTRS)
Duong, Tuan A.
2004-01-01
Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural
Neural Control Adaptation to Motor Noise Manipulation.
Hasson, Christopher J; Gelina, Olga; Woo, Garrett
2016-01-01
Antagonistic muscular co-activation can compensate for movement variability induced by motor noise at the expense of increased energetic costs. Greater antagonistic co-activation is commonly observed in older adults, which could be an adaptation to increased motor noise. The present study tested this hypothesis by manipulating motor noise in 12 young subjects while they practiced a goal-directed task using a myoelectric virtual arm, which was controlled by their biceps and triceps muscle activity. Motor noise was increased by increasing the coefficient of variation (CV) of the myoelectric signals. As hypothesized, subjects adapted by increasing antagonistic co-activation, and this was associated with reduced noise-induced performance decrements. A second hypothesis was that a virtual decrease in motor noise, achieved by smoothing the myoelectric signals, would have the opposite effect: co-activation would decrease and motor performance would improve. However, the results showed that a decrease in noise made performance worse instead of better, with no change in co-activation. Overall, these findings suggest that the nervous system adapts to virtual increases in motor noise by increasing antagonistic co-activation, and this preserves motor performance. Reducing noise may have failed to benefit performance due to characteristics of the filtering process itself, e.g., delays are introduced and muscle activity bursts are attenuated. The observed adaptations to increased noise may explain in part why older adults and many patient populations have greater antagonistic co-activation, which could represent an adaptation to increased motor noise, along with a desire for increased joint stability. PMID:26973487
Neural Control Adaptation to Motor Noise Manipulation
Hasson, Christopher J.; Gelina, Olga; Woo, Garrett
2016-01-01
Antagonistic muscular co-activation can compensate for movement variability induced by motor noise at the expense of increased energetic costs. Greater antagonistic co-activation is commonly observed in older adults, which could be an adaptation to increased motor noise. The present study tested this hypothesis by manipulating motor noise in 12 young subjects while they practiced a goal-directed task using a myoelectric virtual arm, which was controlled by their biceps and triceps muscle activity. Motor noise was increased by increasing the coefficient of variation (CV) of the myoelectric signals. As hypothesized, subjects adapted by increasing antagonistic co-activation, and this was associated with reduced noise-induced performance decrements. A second hypothesis was that a virtual decrease in motor noise, achieved by smoothing the myoelectric signals, would have the opposite effect: co-activation would decrease and motor performance would improve. However, the results showed that a decrease in noise made performance worse instead of better, with no change in co-activation. Overall, these findings suggest that the nervous system adapts to virtual increases in motor noise by increasing antagonistic co-activation, and this preserves motor performance. Reducing noise may have failed to benefit performance due to characteristics of the filtering process itself, e.g., delays are introduced and muscle activity bursts are attenuated. The observed adaptations to increased noise may explain in part why older adults and many patient populations have greater antagonistic co-activation, which could represent an adaptation to increased motor noise, along with a desire for increased joint stability. PMID:26973487
A novel recurrent neural network with finite-time convergence for linear programming.
Liu, Qingshan; Cao, Jinde; Chen, Guanrong
2010-11-01
In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.
Wang, Jin-Liang; Wu, Huai-Ning; Huang, Tingwen; Ren, Shun-Yan
2016-04-01
Two types of coupled neural networks with reaction-diffusion terms are considered in this paper. In the first one, the nodes are coupled through their states. In the second one, the nodes are coupled through the spatial diffusion terms. For the former, utilizing Lyapunov functional method and pinning control technique, we obtain some sufficient conditions to guarantee that network can realize synchronization. In addition, considering that the theoretical coupling strength required for synchronization may be much larger than the needed value, we propose an adaptive strategy to adjust the coupling strength for achieving a suitable value. For the latter, we establish a criterion for synchronization using the designed pinning controllers. It is found that the coupled reaction-diffusion neural networks with state coupling under the given linear feedback pinning controllers can realize synchronization when the coupling strength is very large, which is contrary to the coupled reaction-diffusion neural networks with spatial diffusion coupling. Moreover, a general criterion for ensuring network synchronization is derived by pinning a small fraction of nodes with adaptive feedback controllers. Finally, two examples with numerical simulations are provided to demonstrate the effectiveness of the theoretical results.
Memory in linear recurrent neural networks in continuous time.
Hermans, Michiel; Schrauwen, Benjamin
2010-04-01
Reservoir Computing is a novel technique which employs recurrent neural networks while circumventing difficult training algorithms. A very recent trend in Reservoir Computing is the use of real physical dynamical systems as implementation platforms, rather than the customary digital emulations. Physical systems operate in continuous time, creating a fundamental difference with the classic discrete time definitions of Reservoir Computing. The specific goal of this paper is to study the memory properties of such systems, where we will limit ourselves to linear dynamics. We develop an analytical model which allows the calculation of the memory function for continuous time linear dynamical systems, which can be considered as networks of linear leaky integrator neurons. We then use this model to research memory properties for different types of reservoir. We start with random connection matrices with a shifted eigenvalue spectrum, which perform very poorly. Next, we transform two specific reservoir types, which are known to give good performance in discrete time, to the continuous time domain. Reservoirs based on uniform spreading of connection matrix eigenvalues on the unit disk in discrete time give much better memory properties than reservoirs with random connection matrices, where reservoirs based on orthogonal connection matrices in discrete time are very robust against noise and their memory properties can be tuned. The overall results found in this work yield important insights into how to design networks for continuous time.
Neural networks: What non-linearity to choose
NASA Technical Reports Server (NTRS)
Kreinovich, Vladik YA.; Quintana, Chris
1991-01-01
Neural networks are now one of the most successful learning formalisms. Neurons transform inputs (x(sub 1),...,x(sub n)) into an output f(w(sub 1)x(sub 1) + ... + w(sub n)x(sub n)), where f is a non-linear function and w, are adjustable weights. What f to choose? Usually the logistic function is chosen, but sometimes the use of different functions improves the practical efficiency of the network. The problem of choosing f as a mathematical optimization problem is formulated and solved under different optimality criteria. As a result, a list of functions f that are optimal under these criteria are determined. This list includes both the functions that were empirically proved to be the best for some problems, and some new functions that may be worth trying.
Percolation transition in active neural networks with adaptive geometry
NASA Astrophysics Data System (ADS)
Iudin, F. D.; Iudin, D. I.; Kazantsev, V. B.
2015-02-01
A mathematical model has been proposed for a neural network whose morphological structure varies dynamically depending on activity. This is the property of the so-called structural plasticity typical of developed neural systems of a brain. It has been shown that the spontaneous generation and propagation of a signal in such networks correspond to a percolation transition and the appearance of the connectivity component covering the entire system. Furthermore, adaptive change in the geometric structure of a network results in the clustering of cells and in the reduction of the effective percolation threshold, which corresponds to experimental neurobiological observations.
Adaptive neural network nonlinear control for BTT missile based on the differential geometry method
NASA Astrophysics Data System (ADS)
Wu, Hao; Wang, Yongji; Xu, Jiangsheng
2007-11-01
A new nonlinear control strategy incorporated the differential geometry method with adaptive neural networks is presented for the nonlinear coupling system of Bank-to-Turn missile in reentry phase. The basic control law is designed using the differential geometry feedback linearization method, and the online learning neural networks are used to compensate the system errors due to aerodynamic parameter errors and external disturbance in view of the arbitrary nonlinear mapping and rapid online learning ability for multi-layer neural networks. The online weights and thresholds tuning rules are deduced according to the tracking error performance functions by Levenberg-Marquardt algorithm, which will make the learning process faster and more stable. The six degree of freedom simulation results show that the attitude angles can track the desired trajectory precisely. It means that the proposed strategy effectively enhance the stability, the tracking performance and the robustness of the control system.
Neural controller for adaptive movements with unforeseen payloads
NASA Technical Reports Server (NTRS)
Kuperstein, Michael; Wang, Jyhpyng
1990-01-01
A theory and computer simulation of a neural controller that learns to move and position a link carrying an unforeseen payload accurately are presented. The neural controller learns adaptive dynamic control from its own experience. It does not use information about link mass, link length, or direction of gravity, and it uses only indirect uncalibrated information about payload and actuator limits. Its average positioning accuracy across a large range of payloads after learning is 3 percent of the positioning range. This neural controller can be used as a basis for coordinating any number of sensory inputs with limbs of any number of joints. The feedforward nature of control allows parallel implementation in real time across multiple joints.
Stability of bumps in piecewise smooth neural fields with nonlinear adaptation
NASA Astrophysics Data System (ADS)
Kilpatrick, Zachary P.; Bressloff, Paul C.
2010-06-01
We study the linear stability of stationary bumps in piecewise smooth neural fields with local negative feedback in the form of synaptic depression or spike frequency adaptation. The continuum dynamics is described in terms of a nonlocal integrodifferential equation, in which the integral kernel represents the spatial distribution of synaptic weights between populations of neurons whose mean firing rate is taken to be a Heaviside function of local activity. Discontinuities in the adaptation variable associated with a bump solution means that bump stability cannot be analyzed by constructing the Evans function for a network with a sigmoidal gain function and then taking the high-gain limit. In the case of synaptic depression, we show that linear stability can be formulated in terms of solutions to a system of pseudo-linear equations. We thus establish that sufficiently strong synaptic depression can destabilize a bump that is stable in the absence of depression. These instabilities are dominated by shift perturbations that evolve into traveling pulses. In the case of spike frequency adaptation, we show that for a wide class of perturbations the activity and adaptation variables decouple in the linear regime, thus allowing us to explicitly determine stability in terms of the spectrum of a smooth linear operator. We find that bumps are always unstable with respect to this class of perturbations, and destabilization of a bump can result in either a traveling pulse or a spatially localized breather.
Neural control of chronic stress adaptation
Herman, James P.
2013-01-01
Stress initiates adaptive processes that allow the organism to physiologically cope with prolonged or intermittent exposure to real or perceived threats. A major component of this response is repeated activation of glucocorticoid secretion by the hypothalamo-pituitary-adrenocortical (HPA) axis, which promotes redistribution of energy in a wide range of organ systems, including the brain. Prolonged or cumulative increases in glucocorticoid secretion can reduce benefits afforded by enhanced stress reactivity and eventually become maladaptive. The long-term impact of stress is kept in check by the process of habituation, which reduces HPA axis responses upon repeated exposure to homotypic stressors and likely limits deleterious actions of prolonged glucocorticoid secretion. Habituation is regulated by limbic stress-regulatory sites, and is at least in part glucocorticoid feedback-dependent. Chronic stress also sensitizes reactivity to new stimuli. While sensitization may be important in maintaining response flexibility in response to new threats, it may also add to the cumulative impact of glucocorticoids on the brain and body. Finally, unpredictable or severe stress exposure may cause long-term and lasting dysregulation of the HPA axis, likely due to altered limbic control of stress effector pathways. Stress-related disorders, such as depression and PTSD, are accompanied by glucocorticoid imbalances and structural/ functional alterations in limbic circuits that resemble those seen following chronic stress, suggesting that inappropriate processing of stressful information may be part of the pathological process. PMID:23964212
Self-characterization of linear and nonlinear adaptive optics systems.
Hampton, Peter J; Conan, Rodolphe; Keskin, Onur; Bradley, Colin; Agathoklis, Pan
2008-01-10
We present methods used to determine the linear or nonlinear static response and the linear dynamic response of an adaptive optics (AO) system. This AO system consists of a nonlinear microelectromechanical systems deformable mirror (DM), a linear tip-tilt mirror (TTM), a control computer, and a Shack-Hartmann wavefront sensor. The system is modeled using a single-input-single-output structure to determine the one-dimensional transfer function of the dynamic response of the chain of system hardware. An AO system has been shown to be able to characterize its own response without additional instrumentation. Experimentally determined models are given for a TTM and a DM. PMID:18188192
Neural Basis of Adaptive Response Time Adjustment during Saccade Countermanding
Pouget, Pierre; Logan, Gordon D.; Palmeri, Thomas J.; Boucher, Leanne; Paré, Martin; Schall, Jeffrey D.
2011-01-01
Humans and macaque monkeys adjust their response time adaptively in stop signal (countermanding) tasks, responding slower after stop-signal trials than after control trials with no stop signal. We investigated the neural mechanism underlying this adaptive response time adjustment in macaque monkeys performing a saccade countermanding task. Earlier research showed that movements are initiated when the random accumulation of presaccadic movement-related activity reaches a fixed threshold. We found that a systematic delay in response time after stop signal trials was accomplished not through a change of threshold, baseline, or accumulation rate, but instead through a change in the time when activity first began to accumulate. The neurons underlying movement initiation have been identified with mathematical accumulator models of response time performance. Therefore, this new result provides surprising new insights into the neural instantiation of stochastic accumulator models and the mechanisms through which executive control can be exerted. PMID:21880921
Variable Neural Adaptive Robust Control: A Switched System Approach
Lian, Jianming; Hu, Jianghai; Zak, Stanislaw H.
2015-05-01
Variable neural adaptive robust control strategies are proposed for the output tracking control of a class of multi-input multi-output uncertain systems. The controllers incorporate a variable-structure radial basis function (RBF) network as the self-organizing approximator for unknown system dynamics. The variable-structure RBF network solves the problem of structure determination associated with fixed-structure RBF networks. It can determine the network structure on-line dynamically by adding or removing radial basis functions according to the tracking performance. The structure variation is taken into account in the stability analysis of the closed-loop system using a switched system approach with the aid of the piecewise quadratic Lyapunov function. The performance of the proposed variable neural adaptive robust controllers is illustrated with simulations.
Manoonpong, Poramate; Parlitz, Ulrich; Wörgötter, Florentin
2013-01-01
Living creatures, like walking animals, have found fascinating solutions for the problem of locomotion control. Their movements show the impression of elegance including versatile, energy-efficient, and adaptable locomotion. During the last few decades, roboticists have tried to imitate such natural properties with artificial legged locomotion systems by using different approaches including machine learning algorithms, classical engineering control techniques, and biologically-inspired control mechanisms. However, their levels of performance are still far from the natural ones. By contrast, animal locomotion mechanisms seem to largely depend not only on central mechanisms (central pattern generators, CPGs) and sensory feedback (afferent-based control) but also on internal forward models (efference copies). They are used to a different degree in different animals. Generally, CPGs organize basic rhythmic motions which are shaped by sensory feedback while internal models are used for sensory prediction and state estimations. According to this concept, we present here adaptive neural locomotion control consisting of a CPG mechanism with neuromodulation and local leg control mechanisms based on sensory feedback and adaptive neural forward models with efference copies. This neural closed-loop controller enables a walking machine to perform a multitude of different walking patterns including insect-like leg movements and gaits as well as energy-efficient locomotion. In addition, the forward models allow the machine to autonomously adapt its locomotion to deal with a change of terrain, losing of ground contact during stance phase, stepping on or hitting an obstacle during swing phase, leg damage, and even to promote cockroach-like climbing behavior. Thus, the results presented here show that the employed embodied neural closed-loop system can be a powerful way for developing robust and adaptable machines. PMID:23408775
Manoonpong, Poramate; Parlitz, Ulrich; Wörgötter, Florentin
2013-01-01
Living creatures, like walking animals, have found fascinating solutions for the problem of locomotion control. Their movements show the impression of elegance including versatile, energy-efficient, and adaptable locomotion. During the last few decades, roboticists have tried to imitate such natural properties with artificial legged locomotion systems by using different approaches including machine learning algorithms, classical engineering control techniques, and biologically-inspired control mechanisms. However, their levels of performance are still far from the natural ones. By contrast, animal locomotion mechanisms seem to largely depend not only on central mechanisms (central pattern generators, CPGs) and sensory feedback (afferent-based control) but also on internal forward models (efference copies). They are used to a different degree in different animals. Generally, CPGs organize basic rhythmic motions which are shaped by sensory feedback while internal models are used for sensory prediction and state estimations. According to this concept, we present here adaptive neural locomotion control consisting of a CPG mechanism with neuromodulation and local leg control mechanisms based on sensory feedback and adaptive neural forward models with efference copies. This neural closed-loop controller enables a walking machine to perform a multitude of different walking patterns including insect-like leg movements and gaits as well as energy-efficient locomotion. In addition, the forward models allow the machine to autonomously adapt its locomotion to deal with a change of terrain, losing of ground contact during stance phase, stepping on or hitting an obstacle during swing phase, leg damage, and even to promote cockroach-like climbing behavior. Thus, the results presented here show that the employed embodied neural closed-loop system can be a powerful way for developing robust and adaptable machines. PMID:23408775
Non—Linear Flood Assessment with Neural Network
NASA Astrophysics Data System (ADS)
Murariu, Gabriel; Puscasu, Gheorghe; Gogoncea, Vlad
2010-01-01
In our days, theoretical investigations are used in obtaining the mathematical model for the studied systems or processes. In general, the dynamics of the system are deeply nonlinear, complex or unknown. Generally speaking, such complex structure is a set of interconnected components. The common approach is therefore to start from measurements of the behavior of the system and the external influences (inputs) and try to determine a mathematical relation between them without going into the details of what is actually happening inside the system. Such strategy had known a great success during the time and it was applied for a large class of multifaceted processes. Accepting this approach, there could be investigated the climatic phenomena. In this paper is presented, in a comparative way, a non-linear water flood assessment made in a very sensitive area of the Lower Danube zone where, in the past years, a series of climatic problems have been happening. In these conditions, climatic risk factor management is a necessity. In a regular way, there could be considered and designed nonlinear models for the climatic factors' analysis by using a huge historical evidence data archive. In a previous paper we reached a notable intermediary result basing on a mathematical model constructed on internal recurrent neural network structure. Such approach had been presented considering the internal state estimation when no measurements coming from the sensors are available for system states. A modified backpropagation algorithm had been introduced in order to train the internal recurrent neural networks for nonlinear system identification. In this paper is exposed a comparative study between a numerical advances based on fluid dynamics' equations and our previous approach, based on internal recurrent neural networks (IRNN). The numerical approaching was made in order to succeed in building a physics model of a water flow evaluation and further, to achieve including the rainfall
Adaptive conventional power system stabilizer based on artificial neural network
Kothari, M.L.; Segal, R.; Ghodki, B.K.
1995-12-31
This paper deals with an artificial neural network (ANN) based adaptive conventional power system stabilizer (PSS). The ANN comprises an input layer, a hidden layer and an output layer. The input vector to the ANN comprises real power (P) and reactive power (Q), while the output vector comprises optimum PSS parameters. A systematic approach for generating training set covering wide range of operating conditions, is presented. The ANN has been trained using back-propagation training algorithm. Investigations reveal that the dynamic performance of ANN based adaptive conventional PSS is quite insensitive to wide variations in loading conditions.
Patterns of interval correlations in neural oscillators with adaptation
Schwalger, Tilo; Lindner, Benjamin
2013-01-01
Neural firing is often subject to negative feedback by adaptation currents. These currents can induce strong correlations among the time intervals between spikes. Here we study analytically the interval correlations of a broad class of noisy neural oscillators with spike-triggered adaptation of arbitrary strength and time scale. Our weak-noise theory provides a general relation between the correlations and the phase-response curve (PRC) of the oscillator, proves anti-correlations between neighboring intervals for adapting neurons with type I PRC and identifies a single order parameter that determines the qualitative pattern of correlations. Monotonically decaying or oscillating correlation structures can be related to qualitatively different voltage traces after spiking, which can be explained by the phase plane geometry. At high firing rates, the long-term variability of the spike train associated with the cumulative interval correlations becomes small, independent of model details. Our results are verified by comparison with stochastic simulations of the exponential, leaky, and generalized integrate-and-fire models with adaptation. PMID:24348372
Complex Environmental Data Modelling Using Adaptive General Regression Neural Networks
NASA Astrophysics Data System (ADS)
Kanevski, Mikhail
2015-04-01
The research deals with an adaptation and application of Adaptive General Regression Neural Networks (GRNN) to high dimensional environmental data. GRNN [1,2,3] are efficient modelling tools both for spatial and temporal data and are based on nonparametric kernel methods closely related to classical Nadaraya-Watson estimator. Adaptive GRNN, using anisotropic kernels, can be also applied for features selection tasks when working with high dimensional data [1,3]. In the present research Adaptive GRNN are used to study geospatial data predictability and relevant feature selection using both simulated and real data case studies. The original raw data were either three dimensional monthly precipitation data or monthly wind speeds embedded into 13 dimensional space constructed by geographical coordinates and geo-features calculated from digital elevation model. GRNN were applied in two different ways: 1) adaptive GRNN with the resulting list of features ordered according to their relevancy; and 2) adaptive GRNN applied to evaluate all possible models N [in case of wind fields N=(2^13 -1)=8191] and rank them according to the cross-validation error. In both cases training were carried out applying leave-one-out procedure. An important result of the study is that the set of the most relevant features depends on the month (strong seasonal effect) and year. The predictabilities of precipitation and wind field patterns, estimated using the cross-validation and testing errors of raw and shuffled data, were studied in detail. The results of both approaches were qualitatively and quantitatively compared. In conclusion, Adaptive GRNN with their ability to select features and efficient modelling of complex high dimensional data can be widely used in automatic/on-line mapping and as an integrated part of environmental decision support systems. 1. Kanevski M., Pozdnoukhov A., Timonin V. Machine Learning for Spatial Environmental Data. Theory, applications and software. EPFL Press
Design of an adaptive neural network based power system stabilizer.
Liu, Wenxin; Venayagamoorthy, Ganesh K; Wunsch, Donald C
2003-01-01
Power system stabilizers (PSS) are used to generate supplementary control signals for the excitation system in order to damp the low frequency power system oscillations. To overcome the drawbacks of conventional PSS (CPSS), numerous techniques have been proposed in the literature. Based on the analysis of existing techniques, this paper presents an indirect adaptive neural network based power system stabilizer (IDNC) design. The proposed IDNC consists of a neuro-controller, which is used to generate a supplementary control signal to the excitation system, and a neuro-identifier, which is used to model the dynamics of the power system and to adapt the neuro-controller parameters. The proposed method has the features of a simple structure, adaptivity and fast response. The proposed IDNC is evaluated on a single machine infinite bus power system under different operating conditions and disturbances to demonstrate its effectiveness and robustness. PMID:12850048
Mead, W.C.; Fisher, H.N.; Jones, R.D.; Bisset, K.R.; Lee, L.A.
1993-09-01
We are developing a Traffic Volume and Classification Monitoring (TVCM) system based on adaptive and neural network computational techniques. The value of neutral networks in this application lies in their ability to learn from data and to form a mapping of arbitrary topology. The piezoelectric strip and magnetic loop sensors typically used for TVCM provide signals that are complicated and variable, and that correspond in indirect ways with the desired FWHA 13-class classification system. Further, the wide variety of vehicle configurations adds to the complexity of the classification task. Our goal is to provide a TVCM system featuring high accuracy, adaptability to wide sensor and envirorunental variations, and continuous fault detection. We have instrumented an experimental TVCM site, developed PC-based on-line data acquisition software, collected a large database of vehicles` signals together with accurate ground truth determination, and analyzed the data off-line with a neural net classification system that can distinguish between class 2 (automobiles) and class 3 (utility vehicles) with better than 90% accuracy. The neural network used, called the Connectionist Hyperprism Classification (CHC) network, features simple basis functions; rapid, linear training algorithms for basis function amplitudes and widths; and basis function elimination that enhances network speed and accuracy. Work is in progress to extend the system to other classes, to quantify the system`s adaptability, and to develop automatic fault detection techniques.
Structure-unknown non-linear dynamic systems: identification through neural networks
NASA Astrophysics Data System (ADS)
Masri, S. F.; Chassiakos, A. G.; Caughey, T. K.
1992-03-01
Explores the potential of using parallel distributed processing (neural network) approaches to identify the internal forces of structure-unknown non-linear dynamic systems typically encountered in the field of applied mechanics. The relevant characteristics of neural networks, such as the processing elements, network topology, and learning algorithms, are discussed in the context of system identification. The analogy of the neural network procedure to a qualitatively similar non-parametric identification approach, which was previously developed by the authors for handling arbitrary non-linear systems, is discussed. The utility of the neural network approach is demonstrated by application to several illustrative problems.
Adaptive model predictive process control using neural networks
Buescher, Kevin L.; Baum, Christopher C.; Jones, Roger D.
1997-01-01
A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.
Adaptive model predictive process control using neural networks
Buescher, K.L.; Baum, C.C.; Jones, R.D.
1997-08-19
A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data. 46 figs.
FPGA-based Elman neural network control system for linear ultrasonic motor.
Lin, Faa-Jeng; Hung, Ying-Chih
2009-01-01
A field-programmable gate array (FPGA)-based Elman neural network (ENN) control system is proposed to control the mover position of a linear ultrasonic motor (LUSM) in this study. First, the structure and operating principle of the LUSM are introduced. Because the dynamic characteristics and motor parameters of the LUSM are nonlinear and time-varying, an ENN control system is designed to achieve precision position control. The network structure and online learning algorithm using delta adaptation law of the ENN are described in detail. Then, a piecewise continuous function is adopted to replace the sigmoid function in the hidden layer of the ENN to facilitate hardware implementation. In addition, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. The effectiveness of the proposed control scheme is verified by some experimental results.
NASA Astrophysics Data System (ADS)
Qin, Sitian; Fan, Dejun; Su, Peng; Liu, Qinghe
2014-04-01
In this paper, the optimization techniques for solving pseudoconvex optimization problems are investigated. A simplified recurrent neural network is proposed according to the optimization problem. We prove that the optimal solution of the optimization problem is just the equilibrium point of the neural network, and vice versa if the equilibrium point satisfies the linear constraints. The proposed neural network is proven to be globally stable in the sense of Lyapunov and convergent to an exact optimal solution of the optimization problem. A numerical simulation is given to illustrate the global convergence of the neural network. Applications in business and chemistry are given to demonstrate the effectiveness of the neural network.
A new one-layer neural network for linear and quadratic programming.
Gao, Xingbao; Liao, Li-Zhi
2010-06-01
In this paper, we present a new neural network for solving linear and quadratic programming problems in real time by introducing some new vectors. The proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem when the objective function is convex on the set defined by equality constraints. Compared with existing one-layer neural networks for quadratic programming problems, the proposed neural network has the least neurons and requires weak stability conditions. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.
Modeling neural adaptation in the frog auditory system
NASA Astrophysics Data System (ADS)
Wotton, Janine; McArthur, Kimberly; Bohara, Amit; Ferragamo, Michael; Megela Simmons, Andrea
2005-09-01
Extracellular recordings from the auditory midbrain, Torus semicircularis, of the leopard frog reveal a wide diversity of tuning patterns. Some cells seem to be well suited for time-based coding of signal envelope, and others for rate-based coding of signal frequency. Adaptation for ongoing stimuli plays a significant role in shaping the frequency-dependent response rate at different levels of the frog auditory system. Anuran auditory-nerve fibers are unusual in that they reveal frequency-dependent adaptation [A. L. Megela, J. Acoust. Soc. Am. 75, 1155-1162 (1984)], and therefore provide rate-based input. In order to examine the influence of these peripheral inputs on central responses, three layers of auditory neurons were modeled to examine short-term neural adaptation to pure tones and complex signals. The response of each neuron was simulated with a leaky integrate and fire model, and adaptation was implemented by means of an increasing threshold. Auditory-nerve fibers, dorsal medullary nucleus neurons, and toral cells were simulated and connected in three ascending layers. Modifying the adaptation properties of the peripheral fibers dramatically alters the response at the midbrain. [Work supported by NOHR to M.J.F.; Gustavus Presidential Scholarship to K.McA.; NIH DC05257 to A.M.S.
NASA Technical Reports Server (NTRS)
Gupta, Pramod; Loparo, Kenneth; Mackall, Dale; Schumann, Johann; Soares, Fola
2004-01-01
Recent research has shown that adaptive neural based control systems are very effective in restoring stability and control of an aircraft in the presence of damage or failures. The application of an adaptive neural network with a flight critical control system requires a thorough and proven process to ensure safe and proper flight operation. Unique testing tools have been developed as part of a process to perform verification and validation (V&V) of real time adaptive neural networks used in recent adaptive flight control system, to evaluate the performance of the on line trained neural networks. The tools will help in certification from FAA and will help in the successful deployment of neural network based adaptive controllers in safety-critical applications. The process to perform verification and validation is evaluated against a typical neural adaptive controller and the results are discussed.
Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks
NASA Technical Reports Server (NTRS)
Jorgensen, Charles C.
1997-01-01
A Dynamic Cell Structure (DCS) Neural Network was developed which learns topology representing networks (TRNS) of F-15 aircraft aerodynamic stability and control derivatives. The network is integrated into a direct adaptive tracking controller. The combination produces a robust adaptive architecture capable of handling multiple accident and off- nominal flight scenarios. This paper describes the DCS network and modifications to the parameter estimation procedure. The work represents one step towards an integrated real-time reconfiguration control architecture for rapid prototyping of new aircraft designs. Performance was evaluated using three off-line benchmarks and on-line nonlinear Virtual Reality simulation. Flight control was evaluated under scenarios including differential stabilator lock, soft sensor failure, control and stability derivative variations, and air turbulence.
Permitted and forbidden sets in discrete-time linear threshold recurrent neural networks.
Yi, Zhang; Zhang, Lei; Yu, Jiali; Tan, Kok Kiong
2009-06-01
The concepts of permitted and forbidden sets enable a new perspective of the memory in neural networks. Such concepts exhibit interesting dynamics in recurrent neural networks. This paper studies the basic theories of permitted and forbidden sets of the linear threshold discrete-time recurrent neural networks. The linear threshold transfer function has been regarded as an adequate transfer function for recurrent neural networks. Networks with this transfer function form a class of hybrid analog and digital networks which are especially useful for perceptual computations. Networks in discrete time can directly provide algorithms for efficient implementation in digital hardware. The main contribution of this paper is to establish foundations of permitted and forbidden sets. Necessary and sufficient conditions for the linear threshold discrete-time recurrent neural networks are obtained for complete convergence, existence of permitted and forbidden sets, as well as conditionally multiattractivity, respectively. Simulation studies explore some possible interesting practical applications.
Adaptive neural-network-based control of robotic manipulators
NASA Astrophysics Data System (ADS)
Mitchell, Kyle; Dagli, Cihan H.
2001-03-01
Robotic manipulators are beginning to be seen doing more tasks in our environment. Classical controls engineers have long known how to control these automated hands. They have failed to address the continued control of these devices after parts of the control infrastructure have failed. A failed motor or actuator in a manipulator decreases its range of motion and changes its control structure. Most failures however do not render the manipulator useless. This paper will discuss the use of a neural network to actively update the controller design as portions of a manipulator fail. Actuators can become stuck and later free themselves. Motors can lose range of motion or stop completely. Connecting arms can become bent or entangled. Results will be presented on the ability to maintain functionality through a variety of failure modes. The neural network is constructed and tested in a Matlab environment. This allows testing of several neural network techniques such as back propagation and temporal processing without the need to continually reconfigure target hardware. In this paper we will demonstrate that a modified ensemble of back propagation experts can be trained to control a robotic manipulator without the need to calculate the inverse kinematics equations. Further individual experts can be retrained online to allow for adaptive control through changing dynamics. This allows for manipulators to remain in service through failures in the manipulator infrastructure without the need for human intervention into control equations.
Development vs. behavior: a role for neural adaptation in evolution?
Ghysen, Alain; Dambly-Chaudière, Christine
2016-01-01
We examine the evolution of sensory organ patterning in the lateral line system of fish. Based on recent studies of how this system develops in zebrafish, and on comparative analyses between zebrafish and tuna, we argue that the evolution of lateral line patterns is mostly determined by variations in the underlying developmental processes, independent of any selective pressure. Yet the development of major developmental innovations is so directly linked to their exploitation that it is hard not to think of them as selected for, i.e., adaptive. We propose that adaptation resides mostly in how the nervous system adjusts to new morphologies to make them functional, i.e., that species are neurally adapted to whatever morphology is provided to them by their own developmental program. We show that recent data on behavioral differences between cave forms (blind) and surface forms (eyed) of the mexican fish Astyanax fasciatus support this view, and we propose that this species might provide a unique opportunity to assess the nature of adaptation and of selection in animal evolution. PMID:27389980
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.
An integrated architecture of adaptive neural network control for dynamic systems
Ke, Liu; Tokar, R.; Mcvey, B.
1994-07-01
In this study, an integrated neural network control architecture for nonlinear dynamic systems is presented. Most of the recent emphasis in the neural network control field has no error feedback as the control input which rises the adaptation problem. The integrated architecture in this paper combines feed forward control and error feedback adaptive control using neural networks. The paper reveals the different internal functionality of these two kinds of neural network controllers for certain input styles, e.g., state feedback and error feedback. Feed forward neural network controllers with state feedback establish fixed control mappings which can not adapt when model uncertainties present. With error feedbacks, neural network controllers learn the slopes or the gains respecting to the error feedbacks, which are error driven adaptive control systems. The results demonstrate that the two kinds of control scheme can be combined to realize their individual advantages. Testing with disturbances added to the plant shows good tracking and adaptation.
Peaking-Free Output-Feedback Adaptive Neural Control Under a Nonseparation Principle.
Pan, Yongping; Sun, Tairen; Yu, Haoyong
2015-12-01
High-gain observers have been extensively applied to construct output-feedback adaptive neural control (ANC) for a class of feedback linearizable uncertain nonlinear systems under a nonlinear separation principle. Yet due to static-gain and linear properties, high-gain observers are usually subject to peaking responses and noise sensitivity. Existing adaptive neural network (NN) observers cannot effectively relax the limitations of high-gain observers. This paper presents an output-feedback indirect ANC strategy under a nonseparation principle, where a hybrid estimation scheme that integrates an adaptive NN observer with state variable filters is proposed to estimate plant states. By applying a single Lyapunov function candidate to the entire system, it is proved that the closed-loop system achieves practical asymptotic stability under a relatively low observer gain dominated by controller parameters. Our approach can completely avoid peaking responses without control saturation while keeping favourable noise rejection ability. Simulation results have shown effectiveness and superiority of this approach.
Task-specific neural adaptations to isoinertial resistance training.
Buckthorpe, M; Erskine, R M; Fletcher, G; Folland, J P
2015-10-01
This study aimed to delineate the contribution of adaptations in agonist, antagonist, and stabilizer muscle activation to changes in isometric and isoinertial lifting strength after short-term isoinertial resistance training (RT). Following familiarization, 45 men (23.2 ± 2.8 years) performed maximal isometric and isoinertial strength tests of the elbow flexors of their dominant arms before and after 3 weeks of isoinertial RT. During these tasks, surface electromyography (EMG) amplitude was recorded from the agonist (biceps brachii short and long heads), antagonist (triceps brachii lateral head), and stabilizer (anterior deltoid, pectoralis major) muscles and normalized to either Mmax (agonists) or to maximum EMG during relevant reference tasks (antagonist, stabilizers). After training, there was more than a twofold greater increase in training task-specific isoinertial than isometric strength (17% vs 7%). There were also task-specific adaptations in agonist EMG, with greater increases during the isoinertial than isometric strength task [analysis of variance (ANOVA), training × task, P = 0.005]. A novel finding of this study was that training increased stabilizer muscle activation during all the elbow flexion strength tasks (P < 0.001), although these were not task-specific training effects. RT elicited specific neural adaptations to the training task that appeared to explain the greater increase in isoinertial than isometric strength.
Optimal Control Problem of Feeding Adaptations of Daphnia and Neural Network Simulation
NASA Astrophysics Data System (ADS)
Kmet', Tibor; Kmet'ov, Mria
2010-09-01
A neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints and open final time. The optimal control problem is transcribed into nonlinear programming problem, which is implemented with adaptive critic neural network [9] and recurrent neural network for solving nonlinear proprojection equations [10]. The proposed simulation methods is illustrated by the optimal control problem of feeding adaptation of filter feeders of Daphnia. Results show that adaptive critic based systematic approach and neural network solving of nonlinear equations hold promise for obtaining the optimal control with control and state constraints and open final time.
Nonlinear adaptive trajectory tracking using dynamic neural networks.
Poznyak, A S; Yu, W; Sanchez, E N; Perez, J P
1999-01-01
In this paper the adaptive nonlinear identification and trajectory tracking are discussed via dynamic neural networks. By means of a Lyapunov-like analysis we determine stability conditions for the identification error. Then we analyze the trajectory tracking error by a local optimal controller. An algebraic Riccati equation and a differential one are used for the identification and the tracking error analysis. As our main original contributions, we establish two theorems: the first one gives a bound for the identification error and the second one establishes a bound for the tracking error. We illustrate the effectiveness of these results by two examples: the second-order relay system with multiple isolated equilibrium points and the chaotic system given by Duffing equation. PMID:18252641
Adaptive neural coding: from biological to behavioral decision-making
Louie, Kenway; Glimcher, Paul W.; Webb, Ryan
2015-01-01
Empirical decision-making in diverse species deviates from the predictions of normative choice theory, but why such suboptimal behavior occurs is unknown. Here, we propose that deviations from optimality arise from biological decision mechanisms that have evolved to maximize choice performance within intrinsic biophysical constraints. Sensory processing utilizes specific computations such as divisive normalization to maximize information coding in constrained neural circuits, and recent evidence suggests that analogous computations operate in decision-related brain areas. These adaptive computations implement a relative value code that may explain the characteristic context-dependent nature of behavioral violations of classical normative theory. Examining decision-making at the computational level thus provides a crucial link between the architecture of biological decision circuits and the form of empirical choice behavior. PMID:26722666
Adaptive evolutionary artificial neural networks for pattern classification.
Oong, Tatt Hee; Isa, Nor Ashidi Mat
2011-11-01
This paper presents a new evolutionary approach called the hybrid evolutionary artificial neural network (HEANN) for simultaneously evolving an artificial neural networks (ANNs) topology and weights. Evolutionary algorithms (EAs) with strong global search capabilities are likely to provide the most promising region. However, they are less efficient in fine-tuning the search space locally. HEANN emphasizes the balancing of the global search and local search for the evolutionary process by adapting the mutation probability and the step size of the weight perturbation. This is distinguishable from most previous studies that incorporate EA to search for network topology and gradient learning for weight updating. Four benchmark functions were used to test the evolutionary framework of HEANN. In addition, HEANN was tested on seven classification benchmark problems from the UCI machine learning repository. Experimental results show the superior performance of HEANN in fine-tuning the network complexity within a small number of generations while preserving the generalization capability compared with other algorithms. PMID:21968733
Adaptive nonlinear polynomial neural networks for control of boundary layer/structural interaction
NASA Technical Reports Server (NTRS)
Parker, B. Eugene, Jr.; Cellucci, Richard L.; Abbott, Dean W.; Barron, Roger L.; Jordan, Paul R., III; Poor, H. Vincent
1993-01-01
The acoustic pressures developed in a boundary layer can interact with an aircraft panel to induce significant vibration in the panel. Such vibration is undesirable due to the aerodynamic drag and structure-borne cabin noises that result. The overall objective of this work is to develop effective and practical feedback control strategies for actively reducing this flow-induced structural vibration. This report describes the results of initial evaluations using polynomial, neural network-based, feedback control to reduce flow induced vibration in aircraft panels due to turbulent boundary layer/structural interaction. Computer simulations are used to develop and analyze feedback control strategies to reduce vibration in a beam as a first step. The key differences between this work and that going on elsewhere are as follows: that turbulent and transitional boundary layers represent broadband excitation and thus present a more complex stochastic control scenario than that of narrow band (e.g., laminar boundary layer) excitation; and secondly, that the proposed controller structures are adaptive nonlinear infinite impulse response (IIR) polynomial neural network, as opposed to the traditional adaptive linear finite impulse response (FIR) filters used in most studies to date. The controllers implemented in this study achieved vibration attenuation of 27 to 60 dB depending on the type of boundary layer established by laminar, turbulent, and intermittent laminar-to-turbulent transitional flows. Application of multi-input, multi-output, adaptive, nonlinear feedback control of vibration in aircraft panels based on polynomial neural networks appears to be feasible today. Plans are outlined for Phase 2 of this study, which will include extending the theoretical investigation conducted in Phase 2 and verifying the results in a series of laboratory experiments involving both bum and plate models.
Adaptive nonlinear polynomial neural networks for control of boundary layer/structural interaction
NASA Astrophysics Data System (ADS)
Parker, B. Eugene, Jr.; Cellucci, Richard L.; Abbott, Dean W.; Barron, Roger L.; Jordan, Paul R., III; Poor, H. Vincent
1993-12-01
The acoustic pressures developed in a boundary layer can interact with an aircraft panel to induce significant vibration in the panel. Such vibration is undesirable due to the aerodynamic drag and structure-borne cabin noises that result. The overall objective of this work is to develop effective and practical feedback control strategies for actively reducing this flow-induced structural vibration. This report describes the results of initial evaluations using polynomial, neural network-based, feedback control to reduce flow induced vibration in aircraft panels due to turbulent boundary layer/structural interaction. Computer simulations are used to develop and analyze feedback control strategies to reduce vibration in a beam as a first step. The key differences between this work and that going on elsewhere are as follows: that turbulent and transitional boundary layers represent broadband excitation and thus present a more complex stochastic control scenario than that of narrow band (e.g., laminar boundary layer) excitation; and secondly, that the proposed controller structures are adaptive nonlinear infinite impulse response (IIR) polynomial neural network, as opposed to the traditional adaptive linear finite impulse response (FIR) filters used in most studies to date. The controllers implemented in this study achieved vibration attenuation of 27 to 60 dB depending on the type of boundary layer established by laminar, turbulent, and intermittent laminar-to-turbulent transitional flows. Application of multi-input, multi-output, adaptive, nonlinear feedback control of vibration in aircraft panels based on polynomial neural networks appears to be feasible today. Plans are outlined for Phase 2 of this study, which will include extending the theoretical investigation conducted in Phase 2 and verifying the results in a series of laboratory experiments involving both bum and plate models.
Zhang, Fawen; Benson, Chelsea; Murphy, Dora; Boian, Melissa; Scott, Michael; Keith, Robert; Xiang, Jing; Abbas, Paul
2013-01-01
The objective was to determine if one of the neural temporal features, neural adaptation, can account for the across-subject variability in behavioral measures of temporal processing and speech perception performance in cochlear implant (CI) recipients. Neural adaptation is the phenomenon in which neural responses are the strongest at the beginning of the stimulus and decline following stimulus repetition (e.g., stimulus trains). It is unclear how this temporal property of neural responses relates to psychophysical measures of temporal processing (e.g., gap detection) or speech perception. The adaptation of the electrical compound action potential (ECAP) was obtained using 1000 pulses per second (pps) biphasic pulse trains presented directly to the electrode. The adaptation of the late auditory evoked potential (LAEP) was obtained using a sequence of 1-kHz tone bursts presented acoustically, through the cochlear implant. Behavioral temporal processing was measured using the Random Gap Detection Test at the most comfortable listening level. Consonant nucleus consonant (CNC) word and AzBio sentences were also tested. The results showed that both ECAP and LAEP display adaptive patterns, with a substantial across-subject variability in the amount of adaptation. No correlations between the amount of neural adaptation and gap detection thresholds (GDTs) or speech perception scores were found. The correlations between the degree of neural adaptation and demographic factors showed that CI users having more LAEP adaptation were likely to be those implanted at a younger age than CI users with less LAEP adaptation. The results suggested that neural adaptation, at least this feature alone, cannot account for the across-subject variability in temporal processing ability in the CI users. However, the finding that the LAEP adaptive pattern was less prominent in the CI group compared to the normal hearing group may suggest the important role of normal adaptation pattern at the
Zhang, Fawen; Benson, Chelsea; Murphy, Dora; Boian, Melissa; Scott, Michael; Keith, Robert; Xiang, Jing; Abbas, Paul
2013-01-01
The objective was to determine if one of the neural temporal features, neural adaptation, can account for the across-subject variability in behavioral measures of temporal processing and speech perception performance in cochlear implant (CI) recipients. Neural adaptation is the phenomenon in which neural responses are the strongest at the beginning of the stimulus and decline following stimulus repetition (e.g., stimulus trains). It is unclear how this temporal property of neural responses relates to psychophysical measures of temporal processing (e.g., gap detection) or speech perception. The adaptation of the electrical compound action potential (ECAP) was obtained using 1000 pulses per second (pps) biphasic pulse trains presented directly to the electrode. The adaptation of the late auditory evoked potential (LAEP) was obtained using a sequence of 1-kHz tone bursts presented acoustically, through the cochlear implant. Behavioral temporal processing was measured using the Random Gap Detection Test at the most comfortable listening level. Consonant nucleus consonant (CNC) word and AzBio sentences were also tested. The results showed that both ECAP and LAEP display adaptive patterns, with a substantial across-subject variability in the amount of adaptation. No correlations between the amount of neural adaptation and gap detection thresholds (GDTs) or speech perception scores were found. The correlations between the degree of neural adaptation and demographic factors showed that CI users having more LAEP adaptation were likely to be those implanted at a younger age than CI users with less LAEP adaptation. The results suggested that neural adaptation, at least this feature alone, cannot account for the across-subject variability in temporal processing ability in the CI users. However, the finding that the LAEP adaptive pattern was less prominent in the CI group compared to the normal hearing group may suggest the important role of normal adaptation pattern at the
Super-linear Precision in Simple Neural Population Codes
NASA Astrophysics Data System (ADS)
Schwab, David; Fiete, Ila
2015-03-01
A widely used tool for quantifying the precision with which a population of noisy sensory neurons encodes the value of an external stimulus is the Fisher Information (FI). Maximizing the FI is also a commonly used objective for constructing optimal neural codes. The primary utility and importance of the FI arises because it gives, through the Cramer-Rao bound, the smallest mean-squared error achievable by any unbiased stimulus estimator. However, it is well-known that when neural firing is sparse, optimizing the FI can result in codes that perform very poorly when considering the resulting mean-squared error, a measure with direct biological relevance. Here we construct optimal population codes by minimizing mean-squared error directly and study the scaling properties of the resulting network, focusing on the optimal tuning curve width. We then extend our results to continuous attractor networks that maintain short-term memory of external stimuli in their dynamics. Here we find similar scaling properties in the structure of the interactions that minimize diffusive information loss.
Linear and nonlinear ARMA model parameter estimation using an artificial neural network
NASA Technical Reports Server (NTRS)
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.
Wai, Rong-Jong; Lin, Chih-Min; Peng, Ya-Fu
2004-11-01
This paper presents an adaptive hybrid control system using a diagonal recurrent cerebellar-model-articulation-computer (DRCMAC) network to control a linear piezoelectric ceramic motor (LPCM) driven by a two-inductance two-capacitance (LLCC) resonant inverter. Since the dynamic characteristics and motor parameters of the LPCM are highly nonlinear and time varying, an adaptive hybrid control system is therefore designed based on a hypothetical dynamic model to achieve high-precision position control. The architecture of DRCMAC network is a modified model of a cerebellar-model-articulation-computer (CMAC) network to attain a small number of receptive-fields. The novel idea of this study is that it employs the concept of diagonal recurrent neural network (DRNN) in order to capture the system dynamics and convert the static CMAC into a dynamic one. This adaptive hybrid control system is composed of two parts. One is a DRCMAC network controller that is used to mimic a conventional computed torque control law due to unknown system dynamics, and the other is a compensated controller with bound estimation algorithm that is utilized to recover the residual approximation error for guaranteeing the stable characteristic. The effectiveness of the proposed driving circuit and control system is verified with hardware experiments under the occurrence of uncertainties. In addition, the advantages of the proposed control scheme are indicated in comparison with a traditional integral-proportional (IP) position control system.
Cao, Xiaohua; Jiang, Bei; Gaspar, Carl; Li, Chao
2014-09-01
Faces and words both evoke an N170, a strong electrophysiological response that is often used as a marker for the early stages of expert pattern perception. We examine the relationship of neural selectivity between faces and words by using a novel application of cross-category adaptation to the N170. We report a strong asymmetry between N170 adaptation induced by faces and by words. This is the first electrophysiological result showing that neural selectivity to faces encompasses neural selectivity to words and suggests that the N170 response to faces constitutes a neural marker for versatile representations of familiar visual patterns.
Effects of adaptation on neural coding by primary sensory interneurons in the cricket cercal system.
Clague, H; Theunissen, F; Miller, J P
1997-01-01
Methods of stochastic systems analysis were applied to examine the effect of adaptation on frequency encoding by two functionally identical primary interneurons of the cricket cercal system. Stimulus reconstructions were obtained from a linear filtering transformation of spike trains elicited in response to bursts of broadband white noise air current stimuli (5-400 Hz). Each linear reconstruction was compared with the actual stimulus in the frequency domain to obtain a measure of waveform coding accuracy as a function of frequency. The term adaptation in this paper refers to the decrease in firing rate of a cell after the onset or increase in power of a white noise stimulus. The increase in firing rate after stimulus offset or decrease in stimulus power is assumed to be a complementary aspect of the same phenomenon. As the spike rate decreased during the course of adaptation, the total amount of information carried about the velocity waveform of the stimulus also decreased. The quality of coding of frequencies between 70 and 400 Hz decreased dramatically. The quality of coding of frequencies between 5 and 70 Hz decreased only slightly or even increased in some cases. The disproportionate loss of information about the higher frequencies could be attributed in part to the more rapid loss of spikes correlated with high-frequency stimulus components than of spikes correlated with low-frequency components. An increase in the responsiveness of a cell to frequencies > 70 Hz was correlated with a decrease in the ability of that cell to encode frequencies in the 5-70 Hz range. This nonlinear property could explain the improvement seen in some cases in the coding accuracy of frequencies between 5 and 70 Hz during the course of adaptation. Waveform coding properties also were characterized for fully adapted neurons at several stimulus intensities. The changes in coding observed through the course of adaptation were similar in nature to those found across stimulus powers
Predicting musically induced emotions from physiological inputs: linear and neural network models
Russo, Frank A.; Vempala, Naresh N.; Sandstrom, Gillian M.
2013-01-01
Listening to music often leads to physiological responses. Do these physiological responses contain sufficient information to infer emotion induced in the listener? The current study explores this question by attempting to predict judgments of “felt” emotion from physiological responses alone using linear and neural network models. We measured five channels of peripheral physiology from 20 participants—heart rate (HR), respiration, galvanic skin response, and activity in corrugator supercilii and zygomaticus major facial muscles. Using valence and arousal (VA) dimensions, participants rated their felt emotion after listening to each of 12 classical music excerpts. After extracting features from the five channels, we examined their correlation with VA ratings, and then performed multiple linear regression to see if a linear relationship between the physiological responses could account for the ratings. Although linear models predicted a significant amount of variance in arousal ratings, they were unable to do so with valence ratings. We then used a neural network to provide a non-linear account of the ratings. The network was trained on the mean ratings of eight of the 12 excerpts and tested on the remainder. Performance of the neural network confirms that physiological responses alone can be used to predict musically induced emotion. The non-linear model derived from the neural network was more accurate than linear models derived from multiple linear regression, particularly along the valence dimension. A secondary analysis allowed us to quantify the relative contributions of inputs to the non-linear model. The study represents a novel approach to understanding the complex relationship between physiological responses and musically induced emotion. PMID:23964250
Fuzzy controlled neural network for sensor fusion with adaptability to sensor failure
NASA Astrophysics Data System (ADS)
Chen, Judy; Kostrzewski, Andrew A.; Kim, Dai Hyun; Savant, Gajendra D.; Kim, Jeongdal; Vasiliev, Anatoly A.
1997-10-01
Artificial neural networks have proven to be powerful tools for sensor fusion, but they are not adaptable to sensor failure in a sensor suite. Physical Optics Corporation (POC) presents a new sensor fusion algorithm, applying fuzzy logic to give a neural network real-time adaptability to compensate for faulty sensors. Identifying data that originates from malfunctioning sensors, and excluding it from sensor fusion, allows the fuzzy neural network to achieve better results. A fuzzy logic-based functionality evaluator detects malfunctioning sensors in real time. A separate neural network is trained for each potential sensor failure situation. Since the number of possible sensor failure situations is large, the large number of neural networks is then fuzzified into a small number of fuzzy neural networks. Experimental results show the feasibility of the proposed approach -- the system correctly recognized airplane models in a computer simulation.
Freiwald, W A; Valdes, P; Bosch, J; Biscay, R; Jimenez, J C; Rodriguez, L M; Rodriguez, V; Kreiter, A K; Singer, W
1999-12-15
Information processing in the visual cortex depends on complex and context sensitive patterns of interactions between neuronal groups in many different cortical areas. Methods used to date for disentangling this functional connectivity presuppose either linearity or instantaneous interactions, assumptions that are not necessarily valid. In this paper a general framework that encompasses both linear and non-linear modelling of neurophysiological time series data by means of Local Linear Non-linear Autoregressive models (LLNAR) is described. Within this framework a new test for non-linearity of time series and for non-linearity of directedness of neural interactions based on LLNAR is presented. These tests assess the relative goodness of fit of linear versus non-linear models via the bootstrap technique. Additionally, a generalised definition of Granger causality is presented based on LLNAR that is valid for both linear and non-linear systems. Finally, the use of LLNAR for measuring non-linearity and directional influences is illustrated using artificial data, reference data as well as local field potentials (LFPs) from macaque area TE. LFP data is well described by the linear variant of LLNAR. Models of this sort, including lagged values of the preceding 25 to 60 ms, revealed the existence of both uni- and bi-directional influences between recording sites.
A comparison between criterion functions for linear classifiers, with an application to neural nets
Barnard, E.; Casasent, D. )
1989-09-01
A variety of criterion functions (or scalar performance measures) have been suggested for the design of nonparametric linear classifiers. The classification performance of the most important of these on a typical two-class problem are investigated. The results of the investigation are then applied to the analysis and synthesis of neural-net classifiers.classifiers.
Using Neural Net Technology To Enhance the Efficiency of a Computer Adaptive Testing Application.
ERIC Educational Resources Information Center
Van Nelson, C.; Henriksen, Larry W.
The potential for computer adaptive testing (CAT) has been well documented. In order to improve the efficiency of this process, it may be possible to utilize a neural network, or more specifically, a back propagation neural network. The paper asserts that in order to accomplish this end, it must be shown that grouping examinees by ability as…
NASA Technical Reports Server (NTRS)
Burken, John J.
2005-01-01
This viewgraph presentation covers the following topics: 1) Brief explanation of Generation II Flight Program; 2) Motivation for Neural Network Adaptive Systems; 3) Past/ Current/ Future IFCS programs; 4) Dynamic Inverse Controller with Explicit Model; 5) Types of Neural Networks Investigated; and 6) Brief example
Adaptive Error Estimation in Linearized Ocean General Circulation Models
NASA Technical Reports Server (NTRS)
Chechelnitsky, Michael Y.
1999-01-01
Data assimilation methods are routinely used in oceanography. The statistics of the model and measurement errors need to be specified a priori. This study addresses the problem of estimating model and measurement error statistics from observations. We start by testing innovation based methods of adaptive error estimation with low-dimensional models in the North Pacific (5-60 deg N, 132-252 deg E) to TOPEX/POSEIDON (TIP) sea level anomaly data, acoustic tomography data from the ATOC project, and the MIT General Circulation Model (GCM). A reduced state linear model that describes large scale internal (baroclinic) error dynamics is used. The methods are shown to be sensitive to the initial guess for the error statistics and the type of observations. A new off-line approach is developed, the covariance matching approach (CMA), where covariance matrices of model-data residuals are "matched" to their theoretical expectations using familiar least squares methods. This method uses observations directly instead of the innovations sequence and is shown to be related to the MT method and the method of Fu et al. (1993). Twin experiments using the same linearized MIT GCM suggest that altimetric data are ill-suited to the estimation of internal GCM errors, but that such estimates can in theory be obtained using acoustic data. The CMA is then applied to T/P sea level anomaly data and a linearization of a global GFDL GCM which uses two vertical modes. We show that the CMA method can be used with a global model and a global data set, and that the estimates of the error statistics are robust. We show that the fraction of the GCM-T/P residual variance explained by the model error is larger than that derived in Fukumori et al.(1999) with the method of Fu et al.(1993). Most of the model error is explained by the barotropic mode. However, we find that impact of the change in the error statistics on the data assimilation estimates is very small. This is explained by the large
Neural correlates of priming and adaptation in familiar face perception.
Walther, Christian; Schweinberger, Stefan R; Kaiser, Daniel; Kovács, Gyula
2013-01-01
Priming (PR) and adaptation-related aftereffects (AEs) are two phenomena when recent perceptual experiences alter face perception. While AEs are often reflected in contrastive perceptual biases, PR typically leads to behavioural facilitation. Previous research suggests that both phenomena modulate broadly similar components of the event-related potentials (ERPs). To disentangle the underlying neural mechanisms of PR and AE, we induced both effects within the same subjects and paradigm. We presented pairs of stimuli, where the first (S1) was a famous face (identity A, B or C), a morph between two famous faces (50/50% A/B), or a Fourier phase randomized face (as a control stimulus matched for low-level visual information) and the second (S2) was a face drawn from morph continua between identity A and B. Participants' performance in matching S2s to either A or B revealed contrastive aftereffects for ambiguous S2 faces, which were more likely perceived as identity B following the presentation of A and vice versa. Unambiguous S2 faces, however, showed PR, with significantly shorter response times, as well as higher classification performance, for identity-congruent than for incongruent S1-S2 pairs. Analyses of the simultaneously recorded ERPs revealed clear categorical adaptation at around 155-205 msec post-stimulus onset. We also found amplitude modulations for unambiguous S2 faces following identity-congruent S1 faces, related to PR, starting at 90 msec and being the most pronounced at around 205-255 msec. For ambiguous S2 faces, we also observed an ERP effect at around 205-255 msec that was correlated with behavioural AEs. Our results show that face PR and AEs are present simultaneously within a single paradigm, depending on the ambiguity of S2 faces and/or on the similarity of S1 and S2, and suggest that exclusive mechanisms might underlie both PR and AEs and that object-category and identity processing might run in parallel during face processing. PMID:23021070
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.
Self: an adaptive pressure arising from self-organization, chaotic dynamics, and neural Darwinism.
Bruzzo, Angela Alessia; Vimal, Ram Lakhan Pandey
2007-12-01
In this article, we establish a model to delineate the emergence of "self" in the brain making recourse to the theory of chaos. Self is considered as the subjective experience of a subject. As essential ingredients of subjective experiences, our model includes wakefulness, re-entry, attention, memory, and proto-experiences. The stability as stated by chaos theory can potentially describe the non-linear function of "self" as sensitive to initial conditions and can characterize it as underlying order from apparently random signals. Self-similarity is discussed as a latent menace of a pathological confusion between "self" and "others". Our test hypothesis is that (1) consciousness might have emerged and evolved from a primordial potential or proto-experience in matter, such as the physical attractions and repulsions experienced by electrons, and (2) "self" arises from chaotic dynamics, self-organization and selective mechanisms during ontogenesis, while emerging post-ontogenically as an adaptive pressure driven by both volume and synaptic-neural transmission and influencing the functional connectivity of neural nets (structure).
Adaptive neural control for a class of perturbed strict-feedback nonlinear time-delay systems.
Wang, Min; Chen, Bing; Shi, Peng
2008-06-01
This paper proposes a novel adaptive neural control scheme for a class of perturbed strict-feedback nonlinear time-delay systems with unknown virtual control coefficients. Based on the radial basis function neural network online approximation capability, an adaptive neural controller is presented by combining the backstepping approach and Lyapunov-Krasovskii functionals. The proposed controller guarantees the semiglobal boundedness of all the signals in the closed-loop system and contains minimal learning parameters. Finally, three simulation examples are given to demonstrate the effectiveness and applicability of the proposed scheme.
Xue, Y.; Liu, S.; Hu, Y.; Yang, J.; Chen, Q.
2007-01-01
To improve the accuracy in prediction, Genetic Algorithm based Adaptive Neural Network Ensemble (GA-ANNE) is presented. Intersections are allowed between different training sets based on the fuzzy clustering analysis, which ensures the diversity as well as the accuracy of individual Neural Networks (NNs). Moreover, to improve the accuracy of the adaptive weights of individual NNs, GA is used to optimize the cluster centers. Empirical results in predicting carbon flux of Duke Forest reveal that GA-ANNE can predict the carbon flux more accurately than Radial Basis Function Neural Network (RBFNN), Bagging NN ensemble, and ANNE. ?? 2007 IEEE.
Dynamic recurrent neural networks for stable adaptive control of wing rock motion
NASA Astrophysics Data System (ADS)
Kooi, Steven Boon-Lam
Wing rock is a self-sustaining limit cycle oscillation (LCO) which occurs as the result of nonlinear coupling between the dynamic response of the aircraft and the unsteady aerodynamic forces. In this thesis, dynamic recurrent RBF (Radial Basis Function) network control methodology is proposed to control the wing rock motion. The concept based on the properties of the Presiach hysteresis model is used in the design of dynamic neural networks. The structure and memory mechanism in the Preisach model is analogous to the parallel connectivity and memory formation in the RBF neural networks. The proposed dynamic recurrent neural network has a feature for adding or pruning the neurons in the hidden layer according to the growth criteria based on the properties of ensemble average memory formation of the Preisach model. The recurrent feature of the RBF network deals with the dynamic nonlinearities and endowed temporal memories of the hysteresis model. The control of wing rock is a tracking problem, the trajectory starts from non-zero initial conditions and it tends to zero as time goes to infinity. In the proposed neural control structure, the recurrent dynamic RBF network performs identification process in order to approximate the unknown non-linearities of the physical system based on the input-output data obtained from the wing rock phenomenon. The design of the RBF networks together with the network controllers are carried out in discrete time domain. The recurrent RBF networks employ two separate adaptation schemes where the RBF's centre and width are adjusted by the Extended Kalman Filter in order to give a minimum networks size, while the outer networks layer weights are updated using the algorithm derived from Lyapunov stability analysis for the stable closed loop control. The issue of the robustness of the recurrent RBF networks is also addressed. The effectiveness of the proposed dynamic recurrent neural control methodology is demonstrated through simulations to
Adaptive artificial neural network for autonomous robot control
NASA Technical Reports Server (NTRS)
Arras, Michael K.; Protzel, Peter W.; Palumbo, Daniel L.
1992-01-01
The topics are presented in viewgraph form and include: neural network controller for robot arm positioning with visual feedback; initial training of the arm; automatic recovery from cumulative fault scenarios; and error reduction by iterative fine movements.
Nie, Xiaobing; Zheng, Wei Xing
2015-11-01
In this paper, we discuss the coexistence and dynamical behaviors of multiple equilibrium points for recurrent neural networks with a class of discontinuous nonmonotonic piecewise linear activation functions. It is proved that under some conditions, such n -neuron neural networks can have at least 5(n) equilibrium points, 3(n) of which are locally stable and the others are unstable, based on the contraction mapping theorem and the theory of strict diagonal dominance matrix. The investigation shows that the neural networks with the discontinuous activation functions introduced in this paper can have both more total equilibrium points and more locally stable equilibrium points than the ones with continuous Mexican-hat-type activation function or discontinuous two-level activation functions. An illustrative example with computer simulations is presented to verify the theoretical analysis.
Zhang, Tianping; Ge, Shuzhi Sam
2009-03-01
In this paper, adaptive neural network (NN) tracking control is investigated for a class of uncertain multiple-input-multiple-output (MIMO) nonlinear systems in triangular control structure with unknown nonsymmetric dead zones and control directions. The design is based on the principle of sliding mode control and the use of Nussbaum-type functions in solving the problem of the completely unknown control directions. It is shown that the dead-zone output can be represented as a simple linear system with a static time-varying gain and bounded disturbance by introducing characteristic function. By utilizing the integral-type Lyapunov function and introducing an adaptive compensation term for the upper bound of the optimal approximation error and the dead-zone disturbance, the closed-loop control system is proved to be semiglobally uniformly ultimately bounded, with tracking errors converging to zero under the condition that the slopes of unknown dead zones are equal. Simulation results demonstrate the effectiveness of the approach.
Adaptive neural control for a class of nonlinearly parametric time-delay systems.
Ho, Daniel W C; Li, Junmin; Niu, Yugang
2005-05-01
In this paper, an adaptive neural controller for a class of time-delay nonlinear systems with unknown nonlinearities is proposed. Based on a wavelet neural network (WNN) online approximation model, a state feedback adaptive controller is obtained by constructing a novel integral-type Lyapunov-Krasovskii functional, which also efficiently overcomes the controller singularity problem. It is shown that the proposed method guarantees the semiglobal boundedness of all signals in the adaptive closed-loop systems. An example is provided to illustrate the application of the approach.
Asymptotic Linearity of Optimal Control Modification Adaptive Law with Analytical Stability Margins
NASA Technical Reports Server (NTRS)
Nguyen, Nhan T.
2010-01-01
Optimal control modification has been developed to improve robustness to model-reference adaptive control. For systems with linear matched uncertainty, optimal control modification adaptive law can be shown by a singular perturbation argument to possess an outer solution that exhibits a linear asymptotic property. Analytical expressions of phase and time delay margins for the outer solution can be obtained. Using the gradient projection operator, a free design parameter of the adaptive law can be selected to satisfy stability margins.
Robust MPC for a non-linear system - a neural network approach
NASA Astrophysics Data System (ADS)
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.
NASA Astrophysics Data System (ADS)
Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min
2015-12-01
In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.
Shifted encoding strategy in retinal luminance adaptation: from firing rate to neural correlation.
Xiao, Lei; Zhang, Mingsha; Xing, Dajun; Liang, Pei-Ji; Wu, Si
2013-10-01
Neuronal responses to prolonged stimulation attenuate over time. Here, we ask a fundamental question: is adaptation a simple process for the neural system during which sustained input is ignored, or is it actually part of a strategy for the neural system to adjust its encoding properties dynamically? After simultaneously recording the activities of a group of bullfrog's retinal ganglion cells (dimming detectors) in response to sustained dimming stimulation, we applied a combination of information analysis approaches to explore the time-dependent nature of information encoding during the adaptation. We found that at the early stage of the adaptation, the stimulus information was mainly encoded in firing rates, whereas at the late stage of the adaptation, it was more encoded in neural correlations. Such a transition in encoding properties is not a simple consequence of the attenuation of neuronal firing rates, but rather involves an active change in the neural correlation strengths, suggesting that it is a strategy adopted by the neural system for functional purposes. Our results reveal that in encoding a prolonged stimulation, the neural system may utilize concerted, but less active, firings of neurons to encode information.
Nie, Xiaobing; Zheng, Wei Xing
2016-03-01
This paper addresses the problem of coexistence and dynamical behaviors of multiple equilibria for competitive neural networks. First, a general class of discontinuous nonmonotonic piecewise linear activation functions is introduced for competitive neural networks. Then based on the fixed point theorem and theory of strict diagonal dominance matrix, it is shown that under some conditions, such n -neuron competitive neural networks can have 5(n) equilibria, among which 3(n) equilibria are locally stable and the others are unstable. More importantly, it is revealed that the neural networks with the discontinuous activation functions introduced in this paper can have both more total equilibria and locally stable equilibria than the ones with other activation functions, such as the continuous Mexican-hat-type activation function and discontinuous two-level activation function. Furthermore, the 3(n) locally stable equilibria given in this paper are located in not only saturated regions, but also unsaturated regions, which is different from the existing results on multistability of neural networks with multiple level activation functions. A simulation example is provided to illustrate and validate the theoretical findings.
NASA Astrophysics Data System (ADS)
Akdemir, Bayram; Doǧan, Sercan; Aksoy, Muharrem H.; Canli, Eyüp; Özgören, Muammer
2015-03-01
Liquid behaviors are very important for many areas especially for Mechanical Engineering. Fast camera is a way to observe and search the liquid behaviors. Camera traces the dust or colored markers travelling in the liquid and takes many pictures in a second as possible as. Every image has large data structure due to resolution. For fast liquid velocity, there is not easy to evaluate or make a fluent frame after the taken images. Artificial intelligence has much popularity in science to solve the nonlinear problems. Adaptive neural fuzzy inference system is a common artificial intelligence in literature. Any particle velocity in a liquid has two dimension speed and its derivatives. Adaptive Neural Fuzzy Inference System has been used to create an artificial frame between previous and post frames as offline. Adaptive neural fuzzy inference system uses velocities and vorticities to create a crossing point vector between previous and post points. In this study, Adaptive Neural Fuzzy Inference System has been used to fill virtual frames among the real frames in order to improve image continuity. So this evaluation makes the images much understandable at chaotic or vorticity points. After executed adaptive neural fuzzy inference system, the image dataset increase two times and has a sequence as virtual and real, respectively. The obtained success is evaluated using R2 testing and mean squared error. R2 testing has a statistical importance about similarity and 0.82, 0.81, 0.85 and 0.8 were obtained for velocities and derivatives, respectively.
Bounded Linear Stability Analysis - A Time Delay Margin Estimation Approach for Adaptive Control
NASA Technical Reports Server (NTRS)
Nguyen, Nhan T.; Ishihara, Abraham K.; Krishnakumar, Kalmanje Srinlvas; Bakhtiari-Nejad, Maryam
2009-01-01
This paper presents a method for estimating time delay margin for model-reference adaptive control of systems with almost linear structured uncertainty. The bounded linear stability analysis method seeks to represent the conventional model-reference adaptive law by a locally bounded linear approximation within a small time window using the comparison lemma. The locally bounded linear approximation of the combined adaptive system is cast in a form of an input-time-delay differential equation over a small time window. The time delay margin of this system represents a local stability measure and is computed analytically by a matrix measure method, which provides a simple analytical technique for estimating an upper bound of time delay margin. Based on simulation results for a scalar model-reference adaptive control system, both the bounded linear stability method and the matrix measure method are seen to provide a reasonably accurate and yet not too conservative time delay margin estimation.
Xia, Kewei; Huo, Wei
2016-05-01
This paper presents a robust adaptive neural networks control strategy for spacecraft rendezvous and docking with the coupled position and attitude dynamics under input saturation. Backstepping technique is applied to design a relative attitude controller and a relative position controller, respectively. The dynamics uncertainties are approximated by radial basis function neural networks (RBFNNs). A novel switching controller consists of an adaptive neural networks controller dominating in its active region combined with an extra robust controller to avoid invalidation of the RBFNNs destroying stability of the system outside the neural active region. An auxiliary signal is introduced to compensate the input saturation with anti-windup technique, and a command filter is employed to approximate derivative of the virtual control in the backstepping procedure. Globally uniformly ultimately bounded of the relative states is proved via Lyapunov theory. Simulation example demonstrates effectiveness of the proposed control scheme.
Xia, Kewei; Huo, Wei
2016-05-01
This paper presents a robust adaptive neural networks control strategy for spacecraft rendezvous and docking with the coupled position and attitude dynamics under input saturation. Backstepping technique is applied to design a relative attitude controller and a relative position controller, respectively. The dynamics uncertainties are approximated by radial basis function neural networks (RBFNNs). A novel switching controller consists of an adaptive neural networks controller dominating in its active region combined with an extra robust controller to avoid invalidation of the RBFNNs destroying stability of the system outside the neural active region. An auxiliary signal is introduced to compensate the input saturation with anti-windup technique, and a command filter is employed to approximate derivative of the virtual control in the backstepping procedure. Globally uniformly ultimately bounded of the relative states is proved via Lyapunov theory. Simulation example demonstrates effectiveness of the proposed control scheme. PMID:26892402
Learning from adaptive neural dynamic surface control of strict-feedback systems.
Wang, Min; Wang, Cong
2015-06-01
Learning plays an essential role in autonomous control systems. However, how to achieve learning in the nonstationary environment for nonlinear systems is a challenging problem. In this paper, we present learning method for a class of n th-order strict-feedback systems by adaptive dynamic surface control (DSC) technology, which achieves the human-like ability of learning by doing and doing with learned knowledge. To achieve the learning, this paper first proposes stable adaptive DSC with auxiliary first-order filters, which ensures the boundedness of all the signals in the closed-loop system and the convergence of tracking errors in a finite time. With the help of DSC, the derivative of the filter output variable is used as the neural network (NN) input instead of traditional intermediate variables. As a result, the proposed adaptive DSC method reduces greatly the dimension of NN inputs, especially for high-order systems. After the stable DSC design, we decompose the stable closed-loop system into a series of linear time-varying perturbed subsystems. Using a recursive design, the recurrent property of NN input variables is easily verified since the complexity is overcome using DSC. Subsequently, the partial persistent excitation condition of the radial basis function NN is satisfied. By combining a state transformation, accurate approximations of the closed-loop system dynamics are recursively achieved in a local region along recurrent orbits. Then, the learning control method using the learned knowledge is proposed to achieve the closed-loop stability and the improved control performance. Simulation studies are performed to demonstrate the proposed scheme can not only reuse the learned knowledge to achieve the better control performance with the faster tracking convergence rate and the smaller tracking error but also greatly alleviate the computational burden because of reducing the number and complexity of NN input variables.
Cumulative history quantifies the role of neural adaptation in multistable perception.
Pastukhov, Alexander; Braun, Jochen
2011-09-19
Neural adaptation plays an important role in multistable perception, but its effects are difficult to discern in sequences of perceptual reversals. Investigating the multistable appearance of kinetic depth and binocular rivalry displays, we introduce cumulative history as a novel statistical measure of adaptive state. We show that cumulative history-an integral of past perceptual states, weighted toward the most recent states-significantly and consistently correlates with future dominance durations: the larger the cumulative history measure, the shorter are future dominance times, revealing a robust effect of neural adaptation. The characteristic time scale of cumulative history, which may be computed by Monte Carlo methods, correlates with average dominance durations, as expected for a measure of neural adaptation. When the cumulative histories of two competing percepts are balanced, perceptual reversals take longer and their outcome becomes random, demonstrating that perceptual reversals are fluctuation-driven in the absence of adaptational bias. Our findings quantify the role of neural adaptation in multistable perception, which accounts for approximately 10% of the variability of reversal timing.
Grinke, Eduard; Tetzlaff, Christian; Wörgötter, Florentin; Manoonpong, Poramate
2015-01-01
Walking animals, like insects, with little neural computing can effectively perform complex behaviors. For example, they can walk around their environment, escape from corners/deadlocks, and avoid or climb over obstacles. While performing all these behaviors, they can also adapt their movements to deal with an unknown situation. As a consequence, they successfully navigate through their complex environment. The versatile and adaptive abilities are the result of an integration of several ingredients embedded in their sensorimotor loop. Biological studies reveal that the ingredients include neural dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a many degrees-of-freedom (DOFs) walking robot is a challenging task. Thus, in this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural mechanisms with plasticity, exteroceptive sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent neural network consisting of two fully connected neurons. Online correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors) in the network to generate different turning angles with short-term memory for a walking robot. The turning information is transmitted as descending steering signals to the neural locomotion control which translates the signals into motor actions. As a result, the robot can walk around and adapt its turning angle for avoiding obstacles in different situations. The adaptation also enables the robot to effectively escape from sharp corners or deadlocks. Using backbone joint control embedded in the the locomotion control allows the robot to climb over small obstacles
Grinke, Eduard; Tetzlaff, Christian; Wörgötter, Florentin; Manoonpong, Poramate
2015-01-01
Walking animals, like insects, with little neural computing can effectively perform complex behaviors. For example, they can walk around their environment, escape from corners/deadlocks, and avoid or climb over obstacles. While performing all these behaviors, they can also adapt their movements to deal with an unknown situation. As a consequence, they successfully navigate through their complex environment. The versatile and adaptive abilities are the result of an integration of several ingredients embedded in their sensorimotor loop. Biological studies reveal that the ingredients include neural dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a many degrees-of-freedom (DOFs) walking robot is a challenging task. Thus, in this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural mechanisms with plasticity, exteroceptive sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent neural network consisting of two fully connected neurons. Online correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors) in the network to generate different turning angles with short-term memory for a walking robot. The turning information is transmitted as descending steering signals to the neural locomotion control which translates the signals into motor actions. As a result, the robot can walk around and adapt its turning angle for avoiding obstacles in different situations. The adaptation also enables the robot to effectively escape from sharp corners or deadlocks. Using backbone joint control embedded in the the locomotion control allows the robot to climb over small obstacles
Grinke, Eduard; Tetzlaff, Christian; Wörgötter, Florentin; Manoonpong, Poramate
2015-01-01
Walking animals, like insects, with little neural computing can effectively perform complex behaviors. For example, they can walk around their environment, escape from corners/deadlocks, and avoid or climb over obstacles. While performing all these behaviors, they can also adapt their movements to deal with an unknown situation. As a consequence, they successfully navigate through their complex environment. The versatile and adaptive abilities are the result of an integration of several ingredients embedded in their sensorimotor loop. Biological studies reveal that the ingredients include neural dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a many degrees-of-freedom (DOFs) walking robot is a challenging task. Thus, in this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural mechanisms with plasticity, exteroceptive sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent neural network consisting of two fully connected neurons. Online correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors) in the network to generate different turning angles with short-term memory for a walking robot. The turning information is transmitted as descending steering signals to the neural locomotion control which translates the signals into motor actions. As a result, the robot can walk around and adapt its turning angle for avoiding obstacles in different situations. The adaptation also enables the robot to effectively escape from sharp corners or deadlocks. Using backbone joint control embedded in the the locomotion control allows the robot to climb over small obstacles
A new gradient-based neural network for solving linear and quadratic programming problems.
Leung, Y; Chen, K Z; Jiao, Y C; Gao, X B; Leung, K S
2001-01-01
A new gradient-based neural network is constructed on the basis of the duality theory, optimization theory, convex analysis theory, Lyapunov stability theory, and LaSalle invariance principle to solve linear and quadratic programming problems. In particular, a new function F(x, y) is introduced into the energy function E(x, y) such that the function E(x, y) is convex and differentiable, and the resulting network is more efficient. This network involves all the relevant necessary and sufficient optimality conditions for convex quadratic programming problems. For linear programming and quadratic programming (QP) problems with unique and infinite number of solutions, we have proven strictly that for any initial point, every trajectory of the neural network converges to an optimal solution of the QP and its dual problem. The proposed network is different from the existing networks which use the penalty method or Lagrange method, and the inequality constraints are properly handled. The simulation results show that the proposed neural network is feasible and efficient.
Vocal learning in elephants: neural bases and adaptive context.
Stoeger, Angela S; Manger, Paul
2014-10-01
In the last decade clear evidence has accumulated that elephants are capable of vocal production learning. Examples of vocal imitation are documented in African (Loxodonta africana) and Asian (Elephas maximus) elephants, but little is known about the function of vocal learning within the natural communication systems of either species. We are also just starting to identify the neural basis of elephant vocalizations. The African elephant diencephalon and brainstem possess specializations related to aspects of neural information processing in the motor system (affecting the timing and learning of trunk movements) and the auditory and vocalization system. Comparative interdisciplinary (from behavioral to neuroanatomical) studies are strongly warranted to increase our understanding of both vocal learning and vocal behavior in elephants.
Vocal learning in elephants: neural bases and adaptive context
Stoeger, Angela S; Manger, Paul
2014-01-01
In the last decade clear evidence has accumulated that elephants are capable of vocal production learning. Examples of vocal imitation are documented in African (Loxodonta africana) and Asian (Elephas maximus) elephants, but little is known about the function of vocal learning within the natural communication systems of either species. We are also just starting to identify the neural basis of elephant vocalizations. The African elephant diencephalon and brainstem possess specializations related to aspects of neural information processing in the motor system (affecting the timing and learning of trunk movements) and the auditory and vocalization system. Comparative interdisciplinary (from behavioral to neuroanatomical) studies are strongly warranted to increase our understanding of both vocal learning and vocal behavior in elephants. PMID:25062469
Vocal learning in elephants: neural bases and adaptive context.
Stoeger, Angela S; Manger, Paul
2014-10-01
In the last decade clear evidence has accumulated that elephants are capable of vocal production learning. Examples of vocal imitation are documented in African (Loxodonta africana) and Asian (Elephas maximus) elephants, but little is known about the function of vocal learning within the natural communication systems of either species. We are also just starting to identify the neural basis of elephant vocalizations. The African elephant diencephalon and brainstem possess specializations related to aspects of neural information processing in the motor system (affecting the timing and learning of trunk movements) and the auditory and vocalization system. Comparative interdisciplinary (from behavioral to neuroanatomical) studies are strongly warranted to increase our understanding of both vocal learning and vocal behavior in elephants. PMID:25062469
NASA Technical Reports Server (NTRS)
Clendaniel, Richard A.; Lasker, David M.; Minor, Lloyd B.; Shelhamer, M. J. (Principal Investigator)
2002-01-01
Previous work in squirrel monkeys has demonstrated the presence of linear and nonlinear components to the horizontal vestibuloocular reflex (VOR) evoked by high-acceleration rotations. The nonlinear component is seen as a rise in gain with increasing velocity of rotation at frequencies more than 2 Hz (a velocity-dependent gain enhancement). We have shown that there are greater changes in the nonlinear than linear component of the response after spectacle-induced adaptation. The present study was conducted to determine if the two components of the response share a common adaptive process. The gain of the VOR, in the dark, to sinusoidal stimuli at 4 Hz (peak velocities: 20-150 degrees /s) and 10 Hz (peak velocities: 20 and 100 degrees /s) was measured pre- and postadaptation. Adaptation was induced over 4 h with x0.45 minimizing spectacles. Sum-of-sines stimuli were used to induce adaptation, and the parameters of the stimuli were adjusted to invoke only the linear or both linear and nonlinear components of the response. Preadaptation, there was a velocity-dependent gain enhancement at 4 and 10 Hz. In postadaptation with the paradigms that only recruited the linear component, there was a decrease in gain and a persistent velocity-dependent gain enhancement (indicating adaptation of only the linear component). After adaptation with the paradigm designed to recruit both the linear and nonlinear components, there was a decrease in gain and no velocity-dependent gain enhancement (indicating adaptation of both components). There were comparable changes in the response to steps of acceleration. We interpret these results to indicate that separate processes drive the adaptation of the linear and nonlinear components of the response.
Chang, H.-C.; Kopaska-Merkel, D. C.; Chen, H.-C.; Rocky, Durrans S.
2000-01-01
Lithofacies identification supplies qualitative information about rocks. Lithofacies represent rock textures and are important components of hydrocarbon reservoir description. Traditional techniques of lithofacies identification from core data are costly and different geologists may provide different interpretations. In this paper, we present a low-cost intelligent system consisting of three adaptive resonance theory neural networks and a rule-based expert system to consistently and objectively identify lithofacies from well-log data. The input data are altered into different forms representing different perspectives of observation of lithofacies. Each form of input is processed by a different adaptive resonance theory neural network. Among these three adaptive resonance theory neural networks, one neural network processes the raw continuous data, another processes categorial data, and the third processes fuzzy-set data. Outputs from these three networks are then combined by the expert system using fuzzy inference to determine to which facies the input data should be assigned. Rules are prioritized to emphasize the importance of firing order. This new approach combines the learning ability of neural networks, the adaptability of fuzzy logic, and the expertise of geologists to infer facies of the rocks. This approach is applied to the Appleton Field, an oil field located in Escambia County, Alabama. The hybrid intelligence system predicts lithofacies identity from log data with 87.6% accuracy. This prediction is more accurate than those of single adaptive resonance theory networks, 79.3%, 68.0% and 66.0%, using raw, fuzzy-set, and categorical data, respectively, and by an error-backpropagation neural network, 57.3%. (C) 2000 Published by Elsevier Science Ltd. All rights reserved.
Neural adaptation in the generation of rhythmic behavior.
Pearson, K G
2000-01-01
Motor systems can adapt rapidly to changes in external conditions and to switching of internal goals. They can also adapt slowly in response to training, alterations in the mechanics of the system, and any changes in the system resulting from injury. This article reviews the mechanisms underlying short- and long-term adaptation in rhythmic motor systems. The neuronal networks underlying the generation of rhythmic motor patterns (central pattern generators; CPGs) are extremely flexible. Neuromodulators, central commands, and afferent signals all influence the pattern produced by a CPG by altering the cellular and synaptic properties of individual neurons and the coupling between different populations of neurons. This flexibility allows the generation of a variety of motor patterns appropriate for the mechanical requirements of different forms of a behavior. The matching of motor output to mechanical requirements depends on the capacity of pattern-generating networks to adapt to slow changes in body mechanics and persistent errors in performance. Afferent feedback from body and limb proprioceptors likely plays an important role in driving these long-term adaptive processes.
Non-linear, adaptive array processing for acoustic interference suppression.
Hoppe, Elizabeth; Roan, Michael
2009-06-01
A method is introduced where blind source separation of acoustical sources is combined with spatial processing to remove non-Gaussian, broadband interferers from space-time displays such as bearing track recorder displays. This differs from most standard techniques such as generalized sidelobe cancellers in that the separation of signals is not done spatially. The algorithm performance is compared to adaptive beamforming techniques such as minimum variance distortionless response beamforming. Simulations and experiments using two acoustic sources were used to verify the performance of the algorithm. Simulations were also used to determine the effectiveness of the algorithm under various signal to interference, signal to noise, and array geometry conditions. A voice activity detection algorithm was used to benchmark the performance of the source isolation.
Study on adaptive BTT reentry speed depletion guidance law based on BP neural network
NASA Astrophysics Data System (ADS)
Zheng, Zongzhun; Wang, Yongji; Wu, Hao
2007-11-01
Reentry guidance is one of the key technologies in hypersonic vehicle research field. In addition to the constraints on its final position coordinates, the vehicle must also impact the target from a specified direction with high precision. And therefore the adaptability of guidance law is critical to control the velocity of hypersonic vehicle and firing accuracy properly in different surroundings of large airspace. In this paper, a new adaptive guidance strategy based on Back Propagation (BP) neural network for the reentry mission of a generic hypersonic vehicle is presented. Depending on the nicer self-learn ability of BP neural network, the guidance law considers the influence of biggish mis-modeling of aerodynamics, structure error and other initial disturbances on the flight capability of vehicle. Consequently, terminal position accuracy and velocity are guaranteed, while many constraints are satisfied. Numerical simulation results clearly bring out the fact that the proposed reentry guidance law based on BP neural network is rational and effective.
Paillard, Thierry
2012-01-01
P. Bezerra, S. Zhou, Z. Crowley, A. Davie, and R. Baglin (2011) suggested that the neural mechanisms responsible for steadiness improvement relate in particular to the discharge behavior of motor units and the practice and learning of skills rather than the strength gain after electromyostimulation superimposed over voluntary training. However, the afferent inputs are determining in control of the force level produced and thus contribute to ensure muscle steadiness. Hence, it is possible that electromyostimulation interferes in neurophysiological afference integration and prevents neural adaptations that enable improvement of the control of force (and then muscle steadiness) to occur. Therefore, the neural adaptations induced by electromyostimulation superimposed onto voluntary training should also be researched in relation to the sensory pathways.
Altered temporal dynamics of neural adaptation in the aging human auditory cortex.
Herrmann, Björn; Henry, Molly J; Johnsrude, Ingrid S; Obleser, Jonas
2016-09-01
Neural response adaptation plays an important role in perception and cognition. Here, we used electroencephalography to investigate how aging affects the temporal dynamics of neural adaptation in human auditory cortex. Younger (18-31 years) and older (51-70 years) normal hearing adults listened to tone sequences with varying onset-to-onset intervals. Our results show long-lasting neural adaptation such that the response to a particular tone is a nonlinear function of the extended temporal history of sound events. Most important, aging is associated with multiple changes in auditory cortex; older adults exhibit larger and less variable response magnitudes, a larger dynamic response range, and a reduced sensitivity to temporal context. Computational modeling suggests that reduced adaptation recovery times underlie these changes in the aging auditory cortex and that the extended temporal stimulation has less influence on the neural response to the current sound in older compared with younger individuals. Our human electroencephalography results critically narrow the gap to animal electrophysiology work suggesting a compensatory release from cortical inhibition accompanying hearing loss and aging. PMID:27459921
Adaptive Neural Star Tracker Calibration for Precision Spacecraft Pointing and Tracking
NASA Technical Reports Server (NTRS)
Bayard, David S.
1996-01-01
The Star Tracker is an essential sensor for precision pointing and tracking in most 3-axis stabilized spacecraft. In the interest (of) improving pointing performance by taking advantage of dramatic increases in flight computer power and memory anticipated over the next decade, this paper investigates the use of a neural net for adaptive in-flight calibration of the Star Tracker.
The neural oscillations of conflict adaptation in the human frontal region.
Tang, Dandan; Hu, Li; Chen, Antao
2013-07-01
Incongruency between print color and the semantic meaning of a word in a classical Stroop task activates the human conflict monitoring system and triggers a behavioral conflict. Conflict adaptation has been suggested to mediate the cortical processing of neural oscillations in such a conflict situation. However, the basic mechanisms that underlie the influence of conflict adaptation on the changes of neural oscillations are not clear. In the present study, electroencephalography (EEG) data were recorded from sixteen healthy human participants while they were performing a color-word Stroop task within a novel look-to-do transition design that included two response modalities. In the 'look' condition, participants were informed to look at the color of presented words but no responses were required; in the 'do' condition, they were informed to make arranged responses to the color of presented words. Behaviorally, a reliable conflict adaptation was observed. Time-frequency analysis revealed that (1) in the 'look' condition, theta-band activity in the left- and right-frontal regions reflected a conflict-related process at a response inhibition level; and (2) in the 'do' condition, both theta-band activity in the left-frontal region and alpha-band activity in the left-, right-, and centro-frontal regions reflected a process of conflict control, which triggered neural and behavioral adaptation. Taken together, these results suggest that there are frontal mechanisms involving neural oscillations that can mediate response inhibition processes and control behavioral conflict.
An Application Specific Instruction Set Processor (ASIP) for Adaptive Filters in Neural Prosthetics.
Xin, Yao; Li, Will X Y; Zhang, Zhaorui; Cheung, Ray C C; Song, Dong; Berger, Theodore W
2015-01-01
Neural coding is an essential process for neuroprosthetic design, in which adaptive filters have been widely utilized. In a practical application, it is needed to switch between different filters, which could be based on continuous observations or point process, when the neuron models, conditions, or system requirements have changed. As candidates of coding chip for neural prostheses, low-power general purpose processors are not computationally efficient especially for large scale neural population coding. Application specific integrated circuits (ASICs) do not have flexibility to switch between different adaptive filters while the cost for design and fabrication is formidable. In this research work, we explore an application specific instruction set processor (ASIP) for adaptive filters in neural decoding activity. The proposed architecture focuses on efficient computation for the most time-consuming matrix/vector operations among commonly used adaptive filters, being able to provide both flexibility and throughput. Evaluation and implementation results are provided to demonstrate that the proposed ASIP design is area-efficient while being competitive to commercial CPUs in computational performance.
An Application Specific Instruction Set Processor (ASIP) for Adaptive Filters in Neural Prosthetics.
Xin, Yao; Li, Will X Y; Zhang, Zhaorui; Cheung, Ray C C; Song, Dong; Berger, Theodore W
2015-01-01
Neural coding is an essential process for neuroprosthetic design, in which adaptive filters have been widely utilized. In a practical application, it is needed to switch between different filters, which could be based on continuous observations or point process, when the neuron models, conditions, or system requirements have changed. As candidates of coding chip for neural prostheses, low-power general purpose processors are not computationally efficient especially for large scale neural population coding. Application specific integrated circuits (ASICs) do not have flexibility to switch between different adaptive filters while the cost for design and fabrication is formidable. In this research work, we explore an application specific instruction set processor (ASIP) for adaptive filters in neural decoding activity. The proposed architecture focuses on efficient computation for the most time-consuming matrix/vector operations among commonly used adaptive filters, being able to provide both flexibility and throughput. Evaluation and implementation results are provided to demonstrate that the proposed ASIP design is area-efficient while being competitive to commercial CPUs in computational performance. PMID:26451817
Distinguishing Conjoint and Independent Neural Tuning for Stimulus Features With fMRI Adaptation
Drucker, Daniel M.; Kerr, Wesley Thomas; Aguirre, Geoffrey Karl
2009-01-01
A central focus of cognitive neuroscience is identification of the neural codes that represent stimulus dimensions. One common theme is the study of whether dimensions, such as color and shape, are encoded independently by separate pools of neurons or are represented by neurons conjointly tuned for both properties. We describe an application of functional magnetic resonance imaging (fMRI) adaptation to distinguish between independent and conjoint neural representations of dimensions by examining the neural signal evoked by changes in one versus two stimulus dimensions and considering the metric of two-dimension additivity. We describe how a continuous carry-over paradigm may be used to efficiently estimate this metric. The assumptions of the method are examined as are optimizations. Finally, we demonstrate that the method produces the expected result for fMRI data collected from ventral occipitotemporal cortex while subjects viewed sets of shapes predicted to be represented by conjoint or independent neural tuning. PMID:19357342
Manipulator adaptive control by neural networks in an orange picking robot.
Cavalieri, S; Plebe, A
1996-12-01
The paper focuses on the use of neural networks for process identification in an orange-picking robot adaptive control system. The results that will be shown in the paper refer to a study carried out under the European Community ESPRIT project "CONNY", dealing with the application of neural networks to robotics. The aim of the research is to verify the possibility of integrating a neural identification module in a traditional system to control the movement of the manipulators of the robot. The paper illustrates integration of neural identification in the existing orange-picking robot control system, highlighting the improvement of performance obtainable. Although the proposal refers to a specific robot, it can be applied to any system with the same dynamic features. PMID:9113534
NASA Astrophysics Data System (ADS)
Vasant, P.; Ganesan, T.; Elamvazuthi, I.
2012-11-01
A fairly reasonable result was obtained for non-linear engineering problems using the optimization techniques such as neural network, genetic algorithms, and fuzzy logic independently in the past. Increasingly, hybrid techniques are being used to solve the non-linear problems to obtain better output. This paper discusses the use of neuro-genetic hybrid technique to optimize the geological structure mapping which is known as seismic survey. It involves the minimization of objective function subject to the requirement of geophysical and operational constraints. In this work, the optimization was initially performed using genetic programming, and followed by hybrid neuro-genetic programming approaches. Comparative studies and analysis were then carried out on the optimized results. The results indicate that the hybrid neuro-genetic hybrid technique produced better results compared to the stand-alone genetic programming method.
Adaptive neural models of queuing and timing in fluent action.
Bullock, Daniel
2004-09-01
In biological cognition, specialized representations and associated control processes solve the temporal problems inherent in skilled action. Recent data and neural circuit models highlight three distinct levels of temporal structure: sequence preparation, velocity scaling, and state-sensitive timing. Short sequences of actions are prepared collectively in prefrontal cortex, then queued for performance by a cyclic competitive process that operates on a parallel analog representation. Successful acts like ball-catching depend on coordinated scaling of effector velocities, and velocity scaling, mediated by the basal ganglia, may be coupled to perceived time-to-contact. Making acts accurate at high speeds requires state-sensitive and precisely timed activations of muscle forces in patterns that accelerate and decelerate the effectors. The cerebellum may provide a maximally efficient representational basis for learning to generate such timed activation patterns.
Hedayatpour, Nosratollah; Falla, Deborah
2015-01-01
Eccentric exercise is characterized by initial unfavorable effects such as subcellular muscle damage, pain, reduced fiber excitability, and initial muscle weakness. However, stretch combined with overload, as in eccentric contractions, is an effective stimulus for inducing physiological and neural adaptations to training. Eccentric exercise-induced adaptations include muscle hypertrophy, increased cortical activity, and changes in motor unit behavior, all of which contribute to improved muscle function. In this brief review, neuromuscular adaptations to different forms of exercise are reviewed, the positive training effects of eccentric exercise are presented, and the implications for training are considered. PMID:26543850
Hedayatpour, Nosratollah; Falla, Deborah
2015-01-01
Eccentric exercise is characterized by initial unfavorable effects such as subcellular muscle damage, pain, reduced fiber excitability, and initial muscle weakness. However, stretch combined with overload, as in eccentric contractions, is an effective stimulus for inducing physiological and neural adaptations to training. Eccentric exercise-induced adaptations include muscle hypertrophy, increased cortical activity, and changes in motor unit behavior, all of which contribute to improved muscle function. In this brief review, neuromuscular adaptations to different forms of exercise are reviewed, the positive training effects of eccentric exercise are presented, and the implications for training are considered.
Practical experiences with an adaptive neural network short-term load forecasting system
Mohammed, O.; Park, D.; Merchant, R.; Dinh, T.; Tong, C.; Azeem, A.; Farah, J.; Drake, C.
1995-02-01
An adaptive neural network based short-term electric load forecasting system is presented. The system is developed and implemented for Florida Power and Light Company (FPL). Practical experiences with the system are discussed. The system accounts for seasonal and daily characteristics, as well as abnormal conditions such as cold fronts, heat waves, holidays and other conditions. It is capable of forecasting load with a lead time of one hour to seven days. The adaptive mechanism is used to train the neural networks when on-line. The results indicate that the load forecasting system presented gives robust and more accurate forecasts and allows greater adaptability to sudden climatic changes compared with statistical methods. The system is portable and can be modified to suit the requirements of other utility companies.
Unipolar terminal-attractor based neural associative memory with adaptive threshold
NASA Technical Reports Server (NTRS)
Liu, Hua-Kuang (Inventor); Barhen, Jacob (Inventor); Farhat, Nabil H. (Inventor); Wu, Chwan-Hwa (Inventor)
1993-01-01
A unipolar terminal-attractor based neural associative memory (TABAM) system with adaptive threshold for perfect convergence is presented. By adaptively setting the threshold values for the dynamic iteration for the unipolar binary neuron states with terminal-attractors for the purpose of reducing the spurious states in a Hopfield neural network for associative memory and using the inner product approach, perfect convergence and correct retrieval is achieved. Simulation is completed with a small number of stored states (M) and a small number of neurons (N) but a large M/N ratio. An experiment with optical exclusive-OR logic operation using LCTV SLMs shows the feasibility of optoelectronic implementation of the models. A complete inner-product TABAM is implemented using a PC for calculation of adaptive threshold values to achieve a unipolar TABAM (UIT) in the case where there is no crosstalk, and a crosstalk model (CRIT) in the case where crosstalk corrupts the desired state.
Unipolar Terminal-Attractor Based Neural Associative Memory with Adaptive Threshold
NASA Technical Reports Server (NTRS)
Liu, Hua-Kuang (Inventor); Barhen, Jacob (Inventor); Farhat, Nabil H. (Inventor); Wu, Chwan-Hwa (Inventor)
1996-01-01
A unipolar terminal-attractor based neural associative memory (TABAM) system with adaptive threshold for perfect convergence is presented. By adaptively setting the threshold values for the dynamic iteration for the unipolar binary neuron states with terminal-attractors for the purpose of reducing the spurious states in a Hopfield neural network for associative memory and using the inner-product approach, perfect convergence and correct retrieval is achieved. Simulation is completed with a small number of stored states (M) and a small number of neurons (N) but a large M/N ratio. An experiment with optical exclusive-OR logic operation using LCTV SLMs shows the feasibility of optoelectronic implementation of the models. A complete inner-product TABAM is implemented using a PC for calculation of adaptive threshold values to achieve a unipolar TABAM (UIT) in the case where there is no crosstalk, and a crosstalk model (CRIT) in the case where crosstalk corrupts the desired state.
A neural learning classifier system with self-adaptive constructivism for mobile robot control.
Hurst, Jacob; Bull, Larry
2006-01-01
For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform.
Adaptive superposition of finite element meshes in linear and nonlinear dynamic analysis
NASA Astrophysics Data System (ADS)
Yue, Zhihua
2005-11-01
The numerical analysis of transient phenomena in solids, for instance, wave propagation and structural dynamics, is a very important and active area of study in engineering. Despite the current evolutionary state of modern computer hardware, practical analysis of large scale, nonlinear transient problems requires the use of adaptive methods where computational resources are locally allocated according to the interpolation requirements of the solution form. Adaptive analysis of transient problems involves obtaining solutions at many different time steps, each of which requires a sequence of adaptive meshes. Therefore, the execution speed of the adaptive algorithm is of paramount importance. In addition, transient problems require that the solution must be passed from one adaptive mesh to the next adaptive mesh with a bare minimum of solution-transfer error since this form of error compromises the initial conditions used for the next time step. A new adaptive finite element procedure (s-adaptive) is developed in this study for modeling transient phenomena in both linear elastic solids and nonlinear elastic solids caused by progressive damage. The adaptive procedure automatically updates the time step size and the spatial mesh discretization in transient analysis, achieving the accuracy and the efficiency requirements simultaneously. The novel feature of the s-adaptive procedure is the original use of finite element mesh superposition to produce spatial refinement in transient problems. The use of mesh superposition enables the s-adaptive procedure to completely avoid the need for cumbersome multipoint constraint algorithms and mesh generators, which makes the s-adaptive procedure extremely fast. Moreover, the use of mesh superposition enables the s-adaptive procedure to minimize the solution-transfer error. In a series of different solid mechanics problem types including 2-D and 3-D linear elastic quasi-static problems, 2-D material nonlinear quasi-static problems
Adaptive Control Using Neural Network Augmentation for a Modified F-15 Aircraft
NASA Technical Reports Server (NTRS)
Burken, John J.; Williams-Hayes, Peggy; Karneshige, J. T.; Stachowiak, Susan J.
2006-01-01
Description of the performance of a simplified dynamic inversion controller with neural network augmentation follows. Simulation studies focus on the results with and without neural network adaptation through the use of an F-15 aircraft simulator that has been modified to include canards. Simulated control law performance with a surface failure, in addition to an aerodynamic failure, is presented. The aircraft, with adaptation, attempts to minimize the inertial cross-coupling effect of the failure (a control derivative anomaly associated with a jammed control surface). The dynamic inversion controller calculates necessary surface commands to achieve desired rates. The dynamic inversion controller uses approximate short period and roll axis dynamics. The yaw axis controller is a sideslip rate command system. Methods are described to reduce the cross-coupling effect and maintain adequate tracking errors for control surface failures. The aerodynamic failure destabilizes the pitching moment due to angle of attack. The results show that control of the aircraft with the neural networks is easier (more damped) than without the neural networks. Simulation results show neural network augmentation of the controller improves performance with aerodynamic and control surface failures in terms of tracking error and cross-coupling reduction.
Mapping the dimensionality, density and topology of data: the growing adaptive neural gas.
Cselényi, Zsolt
2005-05-01
Self-organized maps are commonly applied for tasks of cluster analysis, vector quantization or interpolation. The artificial neural network model introduced in this paper is a hybrid model of the growing neural gas model introduced by Fritzke (Fritzke, in Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995) and the adaptive resolution clustering modification for self-organized maps proposed by Firenze (Firenze et al., in International Conference on Artificial Neural Networks, Springer-Verlag, London, 1994). The hybrid model is capable of mapping the distribution, dimensionality and topology of the input data. It has a local performance measure that enables the network to terminate growing in areas of the input space that is mapped by units reaching a performance goal. Therefore the network can accurately map clusters of data appearing on different scales of density. The capabilities of the algorithm are tested using simulated datasets with similar spatial spread but different local density distributions, and a simulated multivariate MR dataset of an anatomical human brain phantom with mild multiple sclerosis lesions. These tests demonstrate the advantages of the model compared to the growing neural gas algorithm when adaptive mapping of areas with low sample density is desirable. PMID:15848269
Sharma, Richa; Kumar, Vikas; Gaur, Prerna; Mittal, A P
2016-05-01
Being complex, non-linear and coupled system, the robotic manipulator cannot be effectively controlled using classical proportional-integral-derivative (PID) controller. To enhance the effectiveness of the conventional PID controller for the nonlinear and uncertain systems, gains of the PID controller should be conservatively tuned and should adapt to the process parameter variations. In this work, a mix locally recurrent neural network (MLRNN) architecture is investigated to mimic a conventional PID controller which consists of at most three hidden nodes which act as proportional, integral and derivative node. The gains of the mix locally recurrent neural network based PID (MLRNNPID) controller scheme are initialized with a newly developed cuckoo search algorithm (CSA) based optimization method rather than assuming randomly. A sequential learning based least square algorithm is then investigated for the on-line adaptation of the gains of MLRNNPID controller. The performance of the proposed controller scheme is tested against the plant parameters uncertainties and external disturbances for both links of the two link robotic manipulator with variable payload (TL-RMWVP). The stability of the proposed controller is analyzed using Lyapunov stability criteria. A performance comparison is carried out among MLRNNPID controller, CSA optimized NNPID (OPTNNPID) controller and CSA optimized conventional PID (OPTPID) controller in order to establish the effectiveness of the MLRNNPID controller. PMID:26920088
Sharma, Richa; Kumar, Vikas; Gaur, Prerna; Mittal, A P
2016-05-01
Being complex, non-linear and coupled system, the robotic manipulator cannot be effectively controlled using classical proportional-integral-derivative (PID) controller. To enhance the effectiveness of the conventional PID controller for the nonlinear and uncertain systems, gains of the PID controller should be conservatively tuned and should adapt to the process parameter variations. In this work, a mix locally recurrent neural network (MLRNN) architecture is investigated to mimic a conventional PID controller which consists of at most three hidden nodes which act as proportional, integral and derivative node. The gains of the mix locally recurrent neural network based PID (MLRNNPID) controller scheme are initialized with a newly developed cuckoo search algorithm (CSA) based optimization method rather than assuming randomly. A sequential learning based least square algorithm is then investigated for the on-line adaptation of the gains of MLRNNPID controller. The performance of the proposed controller scheme is tested against the plant parameters uncertainties and external disturbances for both links of the two link robotic manipulator with variable payload (TL-RMWVP). The stability of the proposed controller is analyzed using Lyapunov stability criteria. A performance comparison is carried out among MLRNNPID controller, CSA optimized NNPID (OPTNNPID) controller and CSA optimized conventional PID (OPTPID) controller in order to establish the effectiveness of the MLRNNPID controller.
Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control
NASA Technical Reports Server (NTRS)
Hageman, Jacob J.; Smith, Mark S.; Stachowiak, Susan
2003-01-01
An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.
NASA Astrophysics Data System (ADS)
Lohani, A. K.; Kumar, Rakesh; Singh, R. D.
2012-06-01
SummaryTime series modeling is necessary for the planning and management of reservoirs. More recently, the soft computing techniques have been used in hydrological modeling and forecasting. In this study, the potential of artificial neural networks and neuro-fuzzy system in monthly reservoir inflow forecasting are examined by developing and comparing monthly reservoir inflow prediction models, based on autoregressive (AR), artificial neural networks (ANNs) and adaptive neural-based fuzzy inference system (ANFIS). To take care the effect of monthly periodicity in the flow data, cyclic terms are also included in the ANN and ANFIS models. Working with time series flow data of the Sutlej River at Bhakra Dam, India, several ANN and adaptive neuro-fuzzy models are trained with different input vectors. To evaluate the performance of the selected ANN and adaptive neural fuzzy inference system (ANFIS) models, comparison is made with the autoregressive (AR) models. The ANFIS model trained with the input data vector including previous inflows and cyclic terms of monthly periodicity has shown a significant improvement in the forecast accuracy in comparison with the ANFIS models trained with the input vectors considering only previous inflows. In all cases ANFIS gives more accurate forecast than the AR and ANN models. The proposed ANFIS model coupled with the cyclic terms is shown to provide better representation of the monthly inflow forecasting for planning and operation of reservoir.
NASA Technical Reports Server (NTRS)
Grantham, Katie
2003-01-01
Reusable Launch Vehicles (RLVs) have different mission requirements than the Space Shuttle, which is used for benchmark guidance design. Therefore, alternative Terminal Area Energy Management (TAEM) and Approach and Landing (A/L) Guidance schemes can be examined in the interest of cost reduction. A neural network based solution for a finite horizon trajectory optimization problem is presented in this paper. In this approach the optimal trajectory of the vehicle is produced by adaptive critic based neural networks, which were trained off-line to maintain a gradual glideslope.
Learning about stress: neural, endocrine and behavioral adaptations.
McCarty, Richard
2016-09-01
In this review, nonassociative learning is advanced as an organizing principle to draw together findings from both sympathetic-adrenal medullary and hypothalamic-pituitary-adrenocortical (HPA) axis responses to chronic intermittent exposure to a variety of stressors. Studies of habituation, facilitation and sensitization of stress effector systems are reviewed and linked to an animal's prior experience with a given stressor, the intensity of the stressor and the appraisal by the animal of its ability to mobilize physiological systems to adapt to the stressor. Brain pathways that regulate physiological and behavioral responses to stress are discussed, especially in light of their regulation of nonassociative processes in chronic intermittent stress. These findings may have special relevance to various psychiatric diseases, including depression and post-traumatic stress disorder (PTSD). PMID:27294884
Learning about stress: neural, endocrine and behavioral adaptations.
McCarty, Richard
2016-09-01
In this review, nonassociative learning is advanced as an organizing principle to draw together findings from both sympathetic-adrenal medullary and hypothalamic-pituitary-adrenocortical (HPA) axis responses to chronic intermittent exposure to a variety of stressors. Studies of habituation, facilitation and sensitization of stress effector systems are reviewed and linked to an animal's prior experience with a given stressor, the intensity of the stressor and the appraisal by the animal of its ability to mobilize physiological systems to adapt to the stressor. Brain pathways that regulate physiological and behavioral responses to stress are discussed, especially in light of their regulation of nonassociative processes in chronic intermittent stress. These findings may have special relevance to various psychiatric diseases, including depression and post-traumatic stress disorder (PTSD).
NASA Technical Reports Server (NTRS)
Balas, M. J.
1985-01-01
Distributed Parameter Systems (DPS), such as systems described by partial differential equations, require infinite-dimensional state space descriptions to correctly model their dynamical behavior. However, any adaptive control algorithm must be finite-dimensional in order to be implemented via on-line digital computers. Finite-dimensional adaptive control of linear DPS requires stability analysis of nonlinear, time-varying, infinite-dimensional systems. The structure of nonadaptive finite-dimensional control of linear DPS is summarized as it relates to the existence of limiting systems for adaptive control. Two candidate schemes for finite-dimensional adaptive control of DPS are described and critical issues in infinite-dimensional stability analysis are discussed, in particular, the invariance principle, center manifold theory, and relationships between input-output and internal stability.
Li, Zhijun; Su, Chun-Yi
2013-09-01
In this paper, adaptive neural network control is investigated for single-master-multiple-slaves teleoperation in consideration of time delays and input dead-zone uncertainties for multiple mobile manipulators carrying a common object in a cooperative manner. Firstly, concise dynamics of teleoperation systems consisting of a single master robot, multiple coordinated slave robots, and the object are developed in the task space. To handle asymmetric time-varying delays in communication channels and unknown asymmetric input dead zones, the nonlinear dynamics of the teleoperation system are transformed into two subsystems through feedback linearization: local master or slave dynamics including the unknown input dead zones and delayed dynamics for the purpose of synchronization. Then, a model reference neural network control strategy based on linear matrix inequalities (LMI) and adaptive techniques is proposed. The developed control approach ensures that the defined tracking errors converge to zero whereas the coordination internal force errors remain bounded and can be made arbitrarily small. Throughout this paper, stability analysis is performed via explicit Lyapunov techniques under specific LMI conditions. The proposed adaptive neural network control scheme is robust against motion disturbances, parametric uncertainties, time-varying delays, and input dead zones, which is validated by simulation studies.
Li, Zhijun; Su, Chun-Yi
2013-09-01
In this paper, adaptive neural network control is investigated for single-master-multiple-slaves teleoperation in consideration of time delays and input dead-zone uncertainties for multiple mobile manipulators carrying a common object in a cooperative manner. Firstly, concise dynamics of teleoperation systems consisting of a single master robot, multiple coordinated slave robots, and the object are developed in the task space. To handle asymmetric time-varying delays in communication channels and unknown asymmetric input dead zones, the nonlinear dynamics of the teleoperation system are transformed into two subsystems through feedback linearization: local master or slave dynamics including the unknown input dead zones and delayed dynamics for the purpose of synchronization. Then, a model reference neural network control strategy based on linear matrix inequalities (LMI) and adaptive techniques is proposed. The developed control approach ensures that the defined tracking errors converge to zero whereas the coordination internal force errors remain bounded and can be made arbitrarily small. Throughout this paper, stability analysis is performed via explicit Lyapunov techniques under specific LMI conditions. The proposed adaptive neural network control scheme is robust against motion disturbances, parametric uncertainties, time-varying delays, and input dead zones, which is validated by simulation studies. PMID:24808577
Adaptive stabilization of discrete-time systems using linear periodically time varying controllers
NASA Technical Reports Server (NTRS)
Ortega, Romeo; Albertos, Pedro; Lozano, Rogelio
1988-01-01
A direct adaptive scheme based on the use of linear time-varying periodic controllers is proposed which estimates online the periodic coefficients of the controller. It is shown that adaptive stabilization is attained for all possibly nonstably invertible plants of known order but unknown delay. Although no appeal is made to persistency of excitation arguments, a provision is needed to avoid the singularity of an estimated matrix, this property being required only for the analysis and not the control calculations.
An adaptive training method for optimal interpolative neural nets.
Liu, T Z; Yen, C W
1997-04-01
In contrast to conventional multilayered feedforward networks which are typically trained by iterative gradient search methods, an optimal interpolative (OI) net can be trained by a noniterative least squares algorithm called RLS-OI. The basic idea of RLS-OI is to use a subset of the training set, whose inputs are called subprototypes, to constrain the OI net solution. A subset of these subprototypes, called prototypes, is then chosen as the parameter vectors of the activation functions of the OI net to satisfy the subprototype constraints in the least squares (LS) sense. By dynamically increasing the numbers of subprototypes and prototypes, RLS-OI evolves the OI net from scratch to the extent sufficient to solve a given classification problem. To improve the performance of RLS-OI, this paper addresses two important problems in OI net training: the selection of the subprototypes and the selection of the prototypes. By choosing subprototypes from poorly classified regions, this paper proposes a new subprototype selection method which is adaptive to the changing classification performance of the growing OI net. This paper also proposes a new prototype selection criterion to reduce the complexity of the OI net. For the same training accuracy, simulation results demonstrate that the proposed approach produces smaller OI net than the RLS-OI algorithm. Experimental results also show that the proposed approach is less sensitive to the variation of the training set than RLS-OI.
Adaptations of motor neural structures' activity to lapses in attention.
Derosière, Gérard; Billot, Maxime; Ward, E Tomas; Perrey, Stéphane
2015-01-01
Sustained attention is fundamental for cognition and when impaired, impacts negatively on important contemporary living skills. Degradation in sustained attention is characterized by the time-on-task (TOT) effect, which manifests as a gradual increase in reaction time (RT). The TOT effect is accompanied by changes in relative brain activity patterns in attention-related areas, most noticeably in the prefrontal cortex (PFC) and the right parietal areas. However, activity changes in task-relevant motor structures have not been confirmed to date. This article describes an investigation of such motor-related activity changes as measured with 1) the time course of corticospinal excitability (CSE) through single-pulse transcranial magnetic stimulation; and 2) the changes in activity of premotor (PMC), primary motor (M1), PFC, and right parietal areas by means of near-infrared spectroscopy, during a sustained attention RT task exhibiting the TOT effect. Our results corroborate established findings such as a significant increase (P < 0.05) in lateral prefrontal and right parietal areas activity after the emergence of the TOT effect but also reveal adaptations in the form of motor activity changes--in particular, a significant increase in CSE (P < 0.01) and in primary motor area (M1) activity (P < 0.05).
Balshaw, Thomas G; Massey, Garry J; Maden-Wilkinson, Thomas M; Tillin, Neale A; Folland, Jonathan P
2016-06-01
Training specificity is considered important for strength training, although the functional and underpinning physiological adaptations to different types of training, including brief explosive contractions, are poorly understood. This study compared the effects of 12 wk of explosive-contraction (ECT, n = 13) vs. sustained-contraction (SCT, n = 16) strength training vs. control (n = 14) on the functional, neural, hypertrophic, and intrinsic contractile characteristics of healthy young men. Training involved 40 isometric knee extension repetitions (3 times/wk): contracting as fast and hard as possible for ∼1 s (ECT) or gradually increasing to 75% of maximum voluntary torque (MVT) before holding for 3 s (SCT). Torque and electromyography during maximum and explosive contractions, torque during evoked octet contractions, and total quadriceps muscle volume (QUADSVOL) were quantified pre and post training. MVT increased more after SCT than ECT [23 vs. 17%; effect size (ES) = 0.69], with similar increases in neural drive, but greater QUADSVOL changes after SCT (8.1 vs. 2.6%; ES = 0.74). ECT improved explosive torque at all time points (17-34%; 0.54 ≤ ES ≤ 0.76) because of increased neural drive (17-28%), whereas only late-phase explosive torque (150 ms, 12%; ES = 1.48) and corresponding neural drive (18%) increased after SCT. Changes in evoked torque indicated slowing of the contractile properties of the muscle-tendon unit after both training interventions. These results showed training-specific functional changes that appeared to be due to distinct neural and hypertrophic adaptations. ECT produced a wider range of functional adaptations than SCT, and given the lesser demands of ECT, this type of training provides a highly efficient means of increasing function.
Video-image-based neural network guidance system with adaptive view-angles for autonomous vehicles
NASA Astrophysics Data System (ADS)
Luebbers, Paul G.; Pandya, Abhijit S.
1991-08-01
This paper describes the guidance function of an autonomous vehicle based on a neural network controller using video images with adaptive view angles for sensory input. The guidance function for an autonomous vehicle provides the low-level control required for maintaining the autonomous vehicle on a prescribed trajectory. Neural networks possess unique properties such as the ability to perform sensor fusion, the ability to learn, and fault tolerant architectures, qualities which are desirable for autonomous vehicle applications. To demonstrate the feasibility of using neural networks in this type of an application, an Intelledex 405 robot fitted with a video camera and vision system was used to model an autonomous vehicle with a limited range of motion. In addition to fixed-angle video images, a set of images using adaptively varied view angles based on speed are used as the input to the neural network controller. It was shown that the neural network was able to control the autonomous vehicle model along a path composed of path segments unlike the exemplars with which it was trained. This system was designed to assess only the guidance system, and it was assumed that other functions employed in autonomous vehicle control systems (mission planning, navigation, and obstacle avoidance) are to be implemented separately and are providing a desired path to the guidance system. The desired path trajectory is presented to the robot in the form of a two-dimensional path, with centerline, that is to be followed. A video camera and associated vision system provides video image data as control feedback to the guidance system. The neural network controller uses Gaussian curves for the output vector to facilitate interpolation and generalization of the output space.
Linear-phase delay filters for ultra-low-power signal processing in neural recording implants.
Gosselin, Benoit; Sawan, Mohamad; Kerherve, Eric
2010-06-01
We present the design and implementation of linear-phase delay filters for ultra-low-power signal processing in neural recording implants. We use these filters as low-distortion delay elements along with an automatic biopotential detector to perform integral waveform extraction and efficient power management. The presented delay elements are realized employing continuous-time OTA-C filters featuring 9th-order equiripple transfer functions with constant group delay. Such analog delay enables processing neural waveforms with reduced overhead compared to a digital delay since it does not requires sampling and digitization. It uses an allpass transfer function for achieving wider constant-delay bandwidth than all-pole does. Two filters realizations are compared for implementing the delay element: the Cascaded structure and the Inverse follow-the-leader feedback filter. Their respective strengths and drawbacks are assessed by modeling parasitics and non-idealities of OTAs, and by transistor-level simulations. A budget of 200 nA is used in both filters. Experimental measurements with the chosen filter topology are presented and discussed.
Tunik, Eugene; Schmitt, Paul J.; Grafton, Scott T.
2007-01-01
In the natural world, we experience and adapt to multiple extrinsic perturbations. This poses a challenge to neural circuits in discriminating between different context-appropriate responses. Using event-related fMRI, we characterized the neural dynamics involved in this process by randomly delivering a position- or velocity-dependent torque perturbation to subjects’ arms during a target capture task. Each perturbation was color-cued during movement preparation to provide contextual information. Though trajectories differed between perturbations, subjects significantly reduced error under both conditions. This was paralleled by reduced BOLD signal in the right dentate nucleus, the left sensorimotor cortex, and the left intraparietal sulcus. Trials included ‘NoGo’ conditions to dissociate activity related to preparation from execution and adaptation. Subsequent analysis identified perturbation-specific neural processes underlying preparation (‘NoGo’) and adaptation (‘Go’) early and late into learning. Between-perturbation comparisons of BOLD magnitude revealed negligible differences for both preparation and adaptation trials. However, a network-level analysis of BOLD coherence revealed that by late learning, response preparation (‘NoGo’) was attributed to a relative focusing of coherence within cortical and basal ganglia networks in both perturbation conditions, demonstrating a common network interaction for establishing arbitrary visuomotor associations. Conversely, late-learning adaptation (‘Go’) was attributed to a focusing of BOLD coherence between a cortical-basal ganglia network in the viscous condition and between a cortical-cerebellar network in the positional condition. Our findings demonstrate that trial-to-trial acquisition of two distinct adaptive responses is attributed not to anatomically segregated regions, but to differential functional interactions within common sensorimotor circuits. PMID:17202232
Self-organized adaptation of a simple neural circuit enables complex robot behaviour
NASA Astrophysics Data System (ADS)
Steingrube, Silke; Timme, Marc; Wörgötter, Florentin; Manoonpong, Poramate
2010-03-01
Controlling sensori-motor systems in higher animals or complex robots is a challenging combinatorial problem, because many sensory signals need to be simultaneously coordinated into a broad behavioural spectrum. To rapidly interact with the environment, this control needs to be fast and adaptive. Present robotic solutions operate with limited autonomy and are mostly restricted to few behavioural patterns. Here we introduce chaos control as a new strategy to generate complex behaviour of an autonomous robot. In the presented system, 18 sensors drive 18 motors by means of a simple neural control circuit, thereby generating 11 basic behavioural patterns (for example, orienting, taxis, self-protection and various gaits) and their combinations. The control signal quickly and reversibly adapts to new situations and also enables learning and synaptic long-term storage of behaviourally useful motor responses. Thus, such neural control provides a powerful yet simple way to self-organize versatile behaviours in autonomous agents with many degrees of freedom.
Adaptive neural control for an uncertain robotic manipulator with joint space constraints
NASA Astrophysics Data System (ADS)
Tang, Zhong-Liang; Ge, Shuzhi Sam; Tee, Keng Peng; He, Wei
2016-07-01
In this paper, adaptive neural tracking control is proposed for a robotic manipulator with uncertainties in both manipulator dynamics and joint actuator dynamics. The manipulator joints are subject to inequality constraints, i.e., the joint angles are required to remain in some compact sets. Integral barrier Lyapunov functionals (iBLFs) are employed to address the joint space constraints directly without performing an additional mapping to the error space. Neural networks (NNs) are utilised to compensate for the unknown robot dynamics and external force. Adapting parameters are developed to estimate the unknown bounds on NN approximations. By the Lyapunov synthesis, the proposed control can guarantee the semi-global uniform ultimate boundedness of the closed-loop system, and the practical tracking of joint reference trajectory is achieved without the violation of predefined joint space constraints. Simulation results are given to validate the effectiveness of the proposed control scheme.
STAR adaptation of QR algorithm. [program for solving over-determined systems of linear equations
NASA Technical Reports Server (NTRS)
Shah, S. N.
1981-01-01
The QR algorithm used on a serial computer and executed on the Control Data Corporation 6000 Computer was adapted to execute efficiently on the Control Data STAR-100 computer. How the scalar program was adapted for the STAR-100 and why these adaptations yielded an efficient STAR program is described. Program listings of the old scalar version and the vectorized SL/1 version are presented in the appendices. Execution times for the two versions applied to the same system of linear equations, are compared.
Specific neural correlates of successful learning and adaptation during social exchanges
Fiorentini, Chiara; Kessler, Esther; Boyd, Harriet; Roberts, Fiona; Skuse, David H.
2013-01-01
Cooperation and betrayal are universal features of social interactions, and knowing who to trust is vital in human society. Previous studies have identified brain regions engaged by decision making during social encounters, but the mechanisms supporting modification of future behaviour by utilizing social experience are not well characterized. Using functional magnetic resonance imaging (fMRI), we show that cooperation and betrayal during social exchanges elicit specific patterns of neural activity associated with future behaviour. Unanticipated cooperation leads to greater behavioural adaptation than unexpected betrayal, and is signalled by specific neural responses in the striatum and midbrain. Neural responses to betrayal and willingness to trust novel partners both decrease as the number of individuals encountered during repeated social encounters increases. We propose that, as social groups increase in size, uncooperative or untrustworthy behaviour becomes progressively less surprising, with cooperation becoming increasingly important as a stimulus for social learning. Effects on reputation of non-trusting decisions may also act to drive pro-social behaviour. Our findings characterize the dynamic neural processes underlying social adaptation, and suggest that the brain is optimized to cooperate with trustworthy partners, rather than avoiding those who might betray us. PMID:22956669
NASA Astrophysics Data System (ADS)
López-Lineros, M.; Estévez, J.; Giráldez, J. V.; Madueño, A.
2014-03-01
The main purpose of this work is the develop of a new quality control method based on non-linear autoregressive neural networks (NARNN) for validating hydrological information, more specifically of 10-min river stage data, for automatic detection of incorrect records. To assess the effectiveness of this new approach, a comparison with adapted conventional validation tests extensively used for hydro-meteorological data was carried out. Different parameters of NARNN and their stability were also analyzed in order to select the most appropriate configuration for obtaining the optimal performance. A set of errors of different magnitudes was artificially introduced into the dataset to evaluate detection efficiency. The NARNN method detected more than 90% of altered records, when the magnitude of error introduced was very high, while conventional tests detected only around 13%. In addition, the NARNN method maintained a similar efficiency at the intermediate and lower error ratios, while the conventional tests were not able to detect more than 6% of erroneous data.
Linear response theory for two neural populations applied to gamma oscillation generation
NASA Astrophysics Data System (ADS)
Payeur, Alexandre; Lefebvre, Jérémie; Maler, Leonard; Longtin, André
2013-03-01
Linear response theory (LRT) can be used to compute spectral properties of single and populations of stochastic leaky integrate-and-fire neurons. The effects of inputs, both external and from delayed feedback, can be modeled within that theory when the neural function is sufficiently linearized by noise. It has been used to explain experiments where gamma oscillations are induced by spatially correlated stochastic inputs to a network with delayed inhibitory feedback. Here we expand this theory to include two distinct population types. We first show how to deal with homogeneous networks where both types of neurons have identical intrinsic properties. We further tackle the asymmetric case, where noise or bias differ. We also analyze the case where the membrane time constants differ, based on experimental evidence, which requires delicate alterations of the theory. We directly apply the theory to networks of ON and OFF cells in the electrosensory system, which together provide global delayed negative feedback to all cells; however, ON and OFF cells receive external inputs of opposite polarities. Theoretical results are in excellent agreement with numerical simulations of the two population network. In contrast to the case of a single ON cell population with feedback, the more realistic presence of both cell types can significantly reduce the propensity of the delayed feedback network to oscillate for spatially correlated inputs. Our results are further linked to recent predictions from deterministic neural field theory. Among other findings, our work suggests that the observed gamma oscillations could be explained only if the ON and OFF cell feedback pathways are anatomically segregated. Thus our two population LRT can make specific predictions about network topography in specific systems.
NASA Astrophysics Data System (ADS)
Miao, Zuohua; Xu, Hong; Chen, Yong; Zeng, Xiangyang
2009-10-01
Back-propagation neural network model (BPNN) is an intelligent computational model based on stylebook learning. This model is different from traditional adaptability symbolic logic reasoning method based on knowledge and rules. At the same time, BPNN model has shortcoming such as: slowly convergence speed and partial minimum. During the process of adaptability evaluation, the factors were diverse, complicated and uncertain, so an effectual model should adopt the technique of data mining method and fuzzy logical technology. In this paper, the author ameliorated the backpropagation of BPNN and applied fuzzy logical theory for dynamic inference of fuzzy rules. Authors also give detail description on training and experiment process of the novel model.
Adaptive recurrent neural network control of uncertain constrained nonholonomic mobile manipulators
NASA Astrophysics Data System (ADS)
Wang, Z. P.; Zhou, T.; Mao, Y.; Chen, Q. J.
2014-02-01
In this article, motion/force control problem of a class of constrained mobile manipulators with unknown dynamics is considered. The system is subject to both holonomic and nonholonomic constraints. An adaptive recurrent neural network controller is proposed to deal with the unmodelled system dynamics. The proposed control strategy guarantees that the system motion asymptotically converges to the desired manifold while the constraint force remains bounded. In addition, an adaptive method is proposed to identify the contact surface. Simulation studies are carried out to verify the validation of the proposed approach.
Adaptive Synchronization of Memristor-Based Neural Networks with Time-Varying Delays.
Wang, Leimin; Shen, Yi; Yin, Quan; Zhang, Guodong
2015-09-01
In this paper, adaptive synchronization of memristor-based neural networks (MNNs) with time-varying delays is investigated. The dynamical analysis here employs results from the theory of differential equations with discontinuous right-hand sides as introduced by Filippov. Sufficient conditions for the global synchronization of MNNs are established with a general adaptive controller. The update gain of the controller can be adjusted to control the synchronization speed. The obtained results complement and improve the previously known results. Finally, numerical simulations are carried out to demonstrate the effectiveness of the obtained results.
Adaptive Synchronization of Memristor-Based Neural Networks with Time-Varying Delays.
Wang, Leimin; Shen, Yi; Yin, Quan; Zhang, Guodong
2015-09-01
In this paper, adaptive synchronization of memristor-based neural networks (MNNs) with time-varying delays is investigated. The dynamical analysis here employs results from the theory of differential equations with discontinuous right-hand sides as introduced by Filippov. Sufficient conditions for the global synchronization of MNNs are established with a general adaptive controller. The update gain of the controller can be adjusted to control the synchronization speed. The obtained results complement and improve the previously known results. Finally, numerical simulations are carried out to demonstrate the effectiveness of the obtained results. PMID:25389244
Neuroplasticity beyond Sounds: Neural Adaptations Following Long-Term Musical Aesthetic Experiences
Reybrouck, Mark; Brattico, Elvira
2015-01-01
Capitalizing from neuroscience knowledge on how individuals are affected by the sound environment, we propose to adopt a cybernetic and ecological point of view on the musical aesthetic experience, which includes subprocesses, such as feature extraction and integration, early affective reactions and motor actions, style mastering and conceptualization, emotion and proprioception, evaluation and preference. In this perspective, the role of the listener/composer/performer is seen as that of an active “agent” coping in highly individual ways with the sounds. The findings concerning the neural adaptations in musicians, following long-term exposure to music, are then reviewed by keeping in mind the distinct subprocesses of a musical aesthetic experience. We conclude that these neural adaptations can be conceived of as the immediate and lifelong interactions with multisensorial stimuli (having a predominant auditory component), which result in lasting changes of the internal state of the “agent”. In a continuous loop, these changes affect, in turn, the subprocesses involved in a musical aesthetic experience, towards the final goal of achieving better perceptual, motor and proprioceptive responses to the immediate demands of the sounding environment. The resulting neural adaptations in musicians closely depend on the duration of the interactions, the starting age, the involvement of attention, the amount of motor practice and the musical genre played. PMID:25807006
Neuroplasticity beyond Sounds: Neural Adaptations Following Long-Term Musical Aesthetic Experiences.
Reybrouck, Mark; Brattico, Elvira
2015-01-01
Capitalizing from neuroscience knowledge on how individuals are affected by the sound environment, we propose to adopt a cybernetic and ecological point of view on the musical aesthetic experience, which includes subprocesses, such as feature extraction and integration, early affective reactions and motor actions, style mastering and conceptualization, emotion and proprioception, evaluation and preference. In this perspective, the role of the listener/composer/performer is seen as that of an active "agent" coping in highly individual ways with the sounds. The findings concerning the neural adaptations in musicians, following long-term exposure to music, are then reviewed by keeping in mind the distinct subprocesses of a musical aesthetic experience. We conclude that these neural adaptations can be conceived of as the immediate and lifelong interactions with multisensorial stimuli (having a predominant auditory component), which result in lasting changes of the internal state of the "agent". In a continuous loop, these changes affect, in turn, the subprocesses involved in a musical aesthetic experience, towards the final goal of achieving better perceptual, motor and proprioceptive responses to the immediate demands of the sounding environment. The resulting neural adaptations in musicians closely depend on the duration of the interactions, the starting age, the involvement of attention, the amount of motor practice and the musical genre played. PMID:25807006
Gürel, Tayfun; Rotter, Stefan; Egert, Ulrich
2010-08-01
The complexity of biological neural networks does not allow to directly relate their biophysical properties to the dynamics of their electrical activity. We present a reservoir computing approach for functionally identifying a biological neural network, i.e. for building an artificial system that is functionally equivalent to the reference biological network. Employing feed-forward and recurrent networks with fading memory, i.e. reservoirs, we propose a point process based learning algorithm to train the internal parameters of the reservoir and the connectivity between the reservoir and the memoryless readout neurons. Specifically, the model is an Echo State Network (ESN) with leaky integrator neurons, whose individual leakage time constants are also adapted. The proposed ESN algorithm learns a predictive model of stimulus-response relations in in vitro and simulated networks, i.e. it models their response dynamics. Receiver Operating Characteristic (ROC) curve analysis indicates that these ESNs can imitate the response signal of a reference biological network. Reservoir adaptation improved the performance of an ESN over readout-only training methods in many cases. This also held for adaptive feed-forward reservoirs, which had no recurrent dynamics. We demonstrate the predictive power of these ESNs on various tasks with cultured and simulated biological neural networks.
NASA Technical Reports Server (NTRS)
Momoh, James A.; Wang, Yanchun; Dolce, James L.
1997-01-01
This paper describes the application of neural network adaptive wavelets for fault diagnosis of space station power system. The method combines wavelet transform with neural network by incorporating daughter wavelets into weights. Therefore, the wavelet transform and neural network training procedure become one stage, which avoids the complex computation of wavelet parameters and makes the procedure more straightforward. The simulation results show that the proposed method is very efficient for the identification of fault locations.
Yee, Eiling; Drucker, Daniel M.; Thompson-Schill, Sharon L.
2010-01-01
Sensorimotor-based theories of semantic memory contend that semantic information about an object is represented in the neural substrate invoked when we perceive or interact with it. We used fMRI adaptation to test this prediction, measuring brain activation as participants read pairs of words. Pairs shared function (flashlight–lantern), shape (marble–grape), both (pencil–pen), were unrelated (saucer–needle), or were identical (drill–drill). We observed adaptation for pairs with both function and shape similarity in left premotor cortex. Further, degree of function similarity was correlated with adaptation in three regions: two in the left temporal lobe (left medial temporal lobe, left middle temporal gyrus), which has been hypothesized to play a role in mutimodal integration, and one in left superior frontal gyrus. We also found that degree of manipulation (i.e., action) and function similarity were both correlated with adaptation in two regions: left premotor cortex and left intraparietal sulcus (involved in guiding actions). Additional considerations suggest that the adaptation in these two regions was driven by manipulation similarity alone; thus, these results imply that manipulation information about objects is encoded in brain regions involved in performing or guiding actions. Unexpectedly, these same two regions showed increased activation (rather than adaptation) for objects similar in shape. Overall, we found evidence (in the form of adaptation) that objects that share semantic features have overlapping representations. Further, the particular regions of overlap provide support for the existence of both sensorimotor and amodal/multimodal representations. PMID:20034582
Design of adaptive fuzzy wavelet neural sliding mode controller for uncertain nonlinear systems.
Shahriari kahkeshi, Maryam; Sheikholeslam, Farid; Zekri, Maryam
2013-05-01
This paper proposes novel adaptive fuzzy wavelet neural sliding mode controller (AFWN-SMC) for a class of uncertain nonlinear systems. The main contribution of this paper is to design smooth sliding mode control (SMC) for a class of high-order nonlinear systems while the structure of the system is unknown and no prior knowledge about uncertainty is available. The proposed scheme composed of an Adaptive Fuzzy Wavelet Neural Controller (AFWNC) to construct equivalent control term and an Adaptive Proportional-Integral (A-PI) controller for implementing switching term to provide smooth control input. Asymptotical stability of the closed loop system is guaranteed, using the Lyapunov direct method. To show the efficiency of the proposed scheme, some numerical examples are provided. To validate the results obtained by proposed approach, some other methods are adopted from the literature and applied for comparison. Simulation results show superiority and capability of the proposed controller to improve the steady state performance and transient response specifications by using less numbers of fuzzy rules and on-line adaptive parameters in comparison to other methods. Furthermore, control effort has considerably decreased and chattering phenomenon has been completely removed.
NASA Astrophysics Data System (ADS)
Baraldi, Andrea; Parmiggiani, Flavio
1997-10-01
In the first part of this paper a new on-line fully self- organizing artificial neural network model (FSONN), pursuing dynamic generation and removal of neurons and synaptic links, is proposed. The model combines properties of the self- organizing map (SOM), fuzzy c-means (FCM), growing neural gas (GNG) and fuzzy simplified adaptive resonance theory (Fuzzy SART) algorithms. In the second part of the paper experimental results are provided and discussed. Our conclusion is that the proposed connectionist model features several interesting properties, such as the following: (1) the system requires no a priori knowledge of the dimension, size and/or adjacency structure of the network; (2) with respect to other connectionist models found in the literature, the system can be employed successfully in: (a) a vector quantization; (b) density function estimation; and (c) structure detection in input data to be mapped topologically correctly onto an output lattice pursuing dimensionality reduction; and (3) the system is computationally efficient, its processing time increasing linearly with the number of neurons and synaptic links.
Learning from adaptive neural network output feedback control of a unicycle-type mobile robot.
Zeng, Wei; Wang, Qinghui; Liu, Fenglin; Wang, Ying
2016-03-01
This paper studies learning from adaptive neural network (NN) output feedback control of nonholonomic unicycle-type mobile robots. The major difficulties are caused by the unknown robot system dynamics and the unmeasurable states. To overcome these difficulties, a new adaptive control scheme is proposed including designing a new adaptive NN output feedback controller and two high-gain observers. It is shown that the stability of the closed-loop robot system and the convergence of tracking errors are guaranteed. The unknown robot system dynamics can be approximated by radial basis function NNs. When repeating same or similar control tasks, the learned knowledge can be recalled and reused to achieve guaranteed stability and better control performance, thereby avoiding the tremendous repeated training process of NNs. PMID:26830003
Learning from adaptive neural network output feedback control of a unicycle-type mobile robot.
Zeng, Wei; Wang, Qinghui; Liu, Fenglin; Wang, Ying
2016-03-01
This paper studies learning from adaptive neural network (NN) output feedback control of nonholonomic unicycle-type mobile robots. The major difficulties are caused by the unknown robot system dynamics and the unmeasurable states. To overcome these difficulties, a new adaptive control scheme is proposed including designing a new adaptive NN output feedback controller and two high-gain observers. It is shown that the stability of the closed-loop robot system and the convergence of tracking errors are guaranteed. The unknown robot system dynamics can be approximated by radial basis function NNs. When repeating same or similar control tasks, the learned knowledge can be recalled and reused to achieve guaranteed stability and better control performance, thereby avoiding the tremendous repeated training process of NNs.
Vrabie, Draguna; Lewis, Frank
2009-04-01
In this paper we present in a continuous-time framework an online approach to direct adaptive optimal control with infinite horizon cost for nonlinear systems. The algorithm converges online to the optimal control solution without knowledge of the internal system dynamics. Closed-loop dynamic stability is guaranteed throughout. The algorithm is based on a reinforcement learning scheme, namely Policy Iterations, and makes use of neural networks, in an Actor/Critic structure, to parametrically represent the control policy and the performance of the control system. The two neural networks are trained to express the optimal controller and optimal cost function which describes the infinite horizon control performance. Convergence of the algorithm is proven under the realistic assumption that the two neural networks do not provide perfect representations for the nonlinear control and cost functions. The result is a hybrid control structure which involves a continuous-time controller and a supervisory adaptation structure which operates based on data sampled from the plant and from the continuous-time performance dynamics. Such control structure is unlike any standard form of controllers previously seen in the literature. Simulation results, obtained considering two second-order nonlinear systems, are provided.
Protein Secondary Structure Prediction Using Local Adaptive Techniques in Training Neural Networks
NASA Astrophysics Data System (ADS)
Aik, Lim Eng; Zainuddin, Zarita; Joseph, Annie
2008-01-01
One of the most significant problems in computer molecular biology today is how to predict a protein's three-dimensional structure from its one-dimensional amino acid sequence or generally call the protein folding problem and difficult to determine the corresponding protein functions. Thus, this paper involves protein secondary structure prediction using neural network in order to solve the protein folding problem. The neural network used for protein secondary structure prediction is multilayer perceptron (MLP) of the feed-forward variety. The training set are taken from the protein data bank which are 120 proteins while 60 testing set is the proteins which were chosen randomly from the protein data bank. Multiple sequence alignment (MSA) is used to get the protein similar sequence and Position Specific Scoring matrix (PSSM) is used for network input. The training process of the neural network involves local adaptive techniques. Local adaptive techniques used in this paper comprises Learning rate by sign changes, SuperSAB, Quickprop and RPROP. From the simulation, the performance for learning rate by Rprop and Quickprop are superior to all other algorithms with respect to the convergence time. However, the best result was obtained using Rprop algorithm.
Adaptive statistic tracking control based on two-step neural networks with time delays.
Yi, Yang; Guo, Lei; Wang, Hong
2009-03-01
This paper presents a new type of control framework for dynamical stochastic systems, called statistic tracking control (STC). The system considered is general and non-Gaussian and the tracking objective is the statistical information of a given target probability density function (pdf), rather than a deterministic signal. The control aims at making the statistical information of the output pdfs to follow those of a target pdf. For such a control framework, a variable structure adaptive tracking control strategy is first established using two-step neural network models. Following the B-spline neural network approximation to the integrated performance function, the concerned problem is transferred into the tracking of given weights. The dynamic neural network (DNN) is employed to identify the unknown nonlinear dynamics between the control input and the weights related to the integrated function. To achieve the required control objective, an adaptive controller based on the proposed DNN is developed so as to track a reference trajectory. Stability analysis for both the identification and tracking errors is developed via the use of Lyapunov stability criterion. Simulations are given to demonstrate the efficiency of the proposed approach. PMID:19179249
Vrabie, Draguna; Lewis, Frank
2009-04-01
In this paper we present in a continuous-time framework an online approach to direct adaptive optimal control with infinite horizon cost for nonlinear systems. The algorithm converges online to the optimal control solution without knowledge of the internal system dynamics. Closed-loop dynamic stability is guaranteed throughout. The algorithm is based on a reinforcement learning scheme, namely Policy Iterations, and makes use of neural networks, in an Actor/Critic structure, to parametrically represent the control policy and the performance of the control system. The two neural networks are trained to express the optimal controller and optimal cost function which describes the infinite horizon control performance. Convergence of the algorithm is proven under the realistic assumption that the two neural networks do not provide perfect representations for the nonlinear control and cost functions. The result is a hybrid control structure which involves a continuous-time controller and a supervisory adaptation structure which operates based on data sampled from the plant and from the continuous-time performance dynamics. Such control structure is unlike any standard form of controllers previously seen in the literature. Simulation results, obtained considering two second-order nonlinear systems, are provided. PMID:19362449
Adaptive Neural Control of Pure-Feedback Nonlinear Time-Delay Systems via Dynamic Surface Technique.
Min Wang; Xiaoping Liu; Peng Shi
2011-12-01
This paper is concerned with robust stabilization problem for a class of nonaffine pure-feedback systems with unknown time-delay functions and perturbed uncertainties. Novel continuous packaged functions are introduced in advance to remove unknown nonlinear terms deduced from perturbed uncertainties and unknown time-delay functions, which avoids the functions with control law to be approximated by radial basis function (RBF) neural networks. This technique combining implicit function and mean value theorems overcomes the difficulty in controlling the nonaffine pure-feedback systems. Dynamic surface control (DSC) is used to avoid "the explosion of complexity" in the backstepping design. Design difficulties from unknown time-delay functions are overcome using the function separation technique, the Lyapunov-Krasovskii functionals, and the desirable property of hyperbolic tangent functions. RBF neural networks are employed to approximate desired virtual controls and desired practical control. Under the proposed adaptive neural DSC, the number of adaptive parameters required is reduced significantly, and semiglobal uniform ultimate boundedness of all of the signals in the closed-loop system is guaranteed. Simulation studies are given to demonstrate the effectiveness of the proposed design scheme.
NASA Astrophysics Data System (ADS)
Gao, Shigen; Dong, Hairong; Lyu, Shihang; Ning, Bin
2016-07-01
This paper studies decentralised neural adaptive control of a class of interconnected nonlinear systems, each subsystem is in the presence of input saturation and external disturbance and has independent system order. Using a novel truncated adaptation design, dynamic surface control technique and minimal-learning-parameters algorithm, the proposed method circumvents the problems of 'explosion of complexity' and 'dimension curse' that exist in the traditional backstepping design. Comparing to the methodology that neural weights are online updated in the controllers, only one scalar needs to be updated in the controllers of each subsystem when dealing with unknown systematic dynamics. Radial basis function neural networks (NNs) are used in the online approximation of unknown systematic dynamics. It is proved using Lyapunov stability theory that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded. The tracking errors of each subsystems, the amplitude of NN approximation residuals and external disturbances can be attenuated to arbitrarily small by tuning proper design parameters. Simulation results are given to demonstrate the effectiveness of the proposed method.
ERIC Educational Resources Information Center
Baker, Bruce D.; Richards, Craig E.
1999-01-01
Applies neural network methods for forecasting 1991-95 per-pupil expenditures in U.S. public elementary and secondary schools. Forecasting models included the National Center for Education Statistics' multivariate regression model and three neural architectures. Regarding prediction accuracy, neural network results were comparable or superior to…
Hummel, Dennis; Rudolf, Anne K; Brandi, Marie-Luise; Untch, Karl-Heinz; Grabhorn, Ralph; Hampel, Harald; Mohr, Harald M
2013-12-01
Visual perception can be strongly biased due to exposure to specific stimuli in the environment, often causing neural adaptation and visual aftereffects. In this study, we investigated whether adaptation to certain body shapes biases the perception of the own body shape. Furthermore, we aimed to evoke neural adaptation to certain body shapes. Participants completed a behavioral experiment (n = 14) to rate manipulated pictures of their own bodies after adaptation to demonstratively thin or fat pictures of their own bodies. The same stimuli were used in a second experiment (n = 16) using functional magnetic resonance imaging (fMRI) adaptation. In the behavioral experiment, after adapting to a thin picture of the own body participants also judged a thinner than actual body picture to be the most realistic and vice versa, resembling a typical aftereffect. The fusiform body area (FBA) and the right middle occipital gyrus (rMOG) show neural adaptation to specific body shapes while the extrastriate body area (EBA) bilaterally does not. The rMOG cluster is highly selective for bodies and perhaps body parts. The findings of the behavioral experiment support the existence of a perceptual body shape aftereffect, resulting from a specific adaptation to thin and fat pictures of one's own body. The fMRI results imply that body shape adaptation occurs in the FBA and the rMOG. The role of the EBA in body shape processing remains unclear. The results are also discussed in the light of clinical body image disturbances.
Accuracy requirements of optical linear algebra processors in adaptive optics imaging systems
NASA Technical Reports Server (NTRS)
Downie, John D.; Goodman, Joseph W.
1989-01-01
The accuracy requirements of optical processors in adaptive optics systems are determined by estimating the required accuracy in a general optical linear algebra processor (OLAP) that results in a smaller average residual aberration than that achieved with a conventional electronic digital processor with some specific computation speed. Special attention is given to an error analysis of a general OLAP with regard to the residual aberration that is created in an adaptive mirror system by the inaccuracies of the processor, and to the effect of computational speed of an electronic processor on the correction. Results are presented on the ability of an OLAP to compete with a digital processor in various situations.
Adaptive Threshold Neural Spike Detector Using Stationary Wavelet Transform in CMOS.
Yang, Yuning; Boling, C Sam; Kamboh, Awais M; Mason, Andrew J
2015-11-01
Spike detection is an essential first step in the analysis of neural recordings. Detection at the frontend eases the bandwidth requirement for wireless data transfer of multichannel recordings to extra-cranial processing units. In this work, a low power digital integrated spike detector based on the lifting stationary wavelet transform is presented and developed. By monitoring the standard deviation of wavelet coefficients, the proposed detector can adaptively set a threshold value online for each channel independently without requiring user intervention. A prototype 16-channel spike detector was designed and tested in an FPGA. The method enables spike detection with nearly 90% accuracy even when the signal-to-noise ratio is as low as 2. The design was mapped to 130 nm CMOS technology and shown to occupy 0.014 mm(2) of area and dissipate 1.7 μW of power per channel, making it suitable for implantable multichannel neural recording systems. PMID:25955990
Multi-layer holographic bifurcative neural network system for real-time adaptive EOS data analysis
NASA Technical Reports Server (NTRS)
Liu, Hua-Kuang; Huang, K. S.; Diep, J.
1993-01-01
Optical data processing techniques have the inherent advantage of high data throughout, low weight and low power requirements. These features are particularly desirable for onboard spacecraft in-situ real-time data analysis and data compression applications. the proposed multi-layer optical holographic neural net pattern recognition technique will utilize the nonlinear photorefractive devices for real-time adaptive learning to classify input data content and recognize unexpected features. Information can be stored either in analog or digital form in a nonlinear photofractive device. The recording can be accomplished in time scales ranging from milliseconds to microseconds. When a system consisting of these devices is organized in a multi-layer structure, a feedforward neural net with bifurcating data classification capability is formed. The interdisciplinary research will involve the collaboration with top digital computer architecture experts at the University of Southern California.
Adaptive Threshold Neural Spike Detector Using Stationary Wavelet Transform in CMOS.
Yang, Yuning; Boling, C Sam; Kamboh, Awais M; Mason, Andrew J
2015-11-01
Spike detection is an essential first step in the analysis of neural recordings. Detection at the frontend eases the bandwidth requirement for wireless data transfer of multichannel recordings to extra-cranial processing units. In this work, a low power digital integrated spike detector based on the lifting stationary wavelet transform is presented and developed. By monitoring the standard deviation of wavelet coefficients, the proposed detector can adaptively set a threshold value online for each channel independently without requiring user intervention. A prototype 16-channel spike detector was designed and tested in an FPGA. The method enables spike detection with nearly 90% accuracy even when the signal-to-noise ratio is as low as 2. The design was mapped to 130 nm CMOS technology and shown to occupy 0.014 mm(2) of area and dissipate 1.7 μW of power per channel, making it suitable for implantable multichannel neural recording systems.
Liu, Rong; Zhou, Jiawei; Zhao, Haoxin; Dai, Yun; Zhang, Yudong; Tang, Yong; Zhou, Yifeng
2014-01-01
This study aimed to explore the neural development status of the visual system of children (around 8 years old) using contrast sensitivity. We achieved this by eliminating the influence of higher order aberrations (HOAs) with adaptive optics correction. We measured HOAs, modulation transfer functions (MTFs) and contrast sensitivity functions (CSFs) of six children and five adults with both corrected and uncorrected HOAs. We found that when HOAs were corrected, children and adults both showed improvements in MTF and CSF. However, the CSF of children was still lower than the adult level, indicating the difference in contrast sensitivity between groups cannot be explained by differences in optical factors. Further study showed that the difference between the groups also could not be explained by differences in non-visual factors. With these results we concluded that the neural systems underlying vision in children of around 8 years old are still immature in contrast sensitivity. PMID:24732728
Robust adaptive neural control for a class of uncertain MIMO nonlinear systems
NASA Astrophysics Data System (ADS)
Wang, Chenliang; Lin, Yan
2015-08-01
In this paper, a novel robust adaptive neural control scheme is proposed for a class of uncertain multi-input multi-output nonlinear systems. The proposed scheme has the following main features: (1) a kind of Hurwitz condition is introduced to handle the state-dependent control gain matrix and some assumptions in existing schemes are relaxed; (2) by introducing a novel matrix normalisation technique, it is shown that all bound restrictions imposed on the control gain matrix in existing schemes can be removed; (3) the singularity problem is avoided without any extra effort, which makes the control law quite simple. Besides, with the aid of the minimal learning parameter technique, only one parameter needs to be updated online regardless of the system input-output dimension and the number of neural network nodes. Simulation results are presented to illustrate the effectiveness of the proposed scheme.
He, Wei; Dong, Yiting; Sun, Changyin
2015-09-01
In this paper, we aim to solve the control problem of nonlinear affine systems, under the condition of the input deadzone and output constraint with the external unknown disturbance. To eliminate the effects of the input deadzone, a Radial Basis Function Neural Network (RBFNN) is introduced to compensate for the negative impact of input deadzone. Meanwhile, we design a barrier Lyapunov function to ensure that the output parameters are restricted. In support of the barrier Lyapunov method, we build an adaptive neural network controller based on state feedback and output feedback methods. The stability of the closed-loop system is proven via the Lyapunov method and the performance of the expected effects is verified in simulation.
Thurman, Steven M; van Boxtel, Jeroen J A; Monti, Martin M; Chiang, Jeffrey N; Lu, Hongjing
2016-08-01
The adaptive nature of biological motion perception has been documented in behavioral studies, with research showing that prolonged viewing of an action can bias judgments of subsequent actions towards the opposite of its attributes. However, the neural mechanisms underlying action adaptation aftereffects remain unknown. We examined adaptation-induced changes in brain responses to an ambiguous action after adapting to walking or running actions within two bilateral regions of interest: 1) human middle temporal area (hMT+), a lower-level motion-sensitive region of cortex, and 2) posterior superior temporal sulcus (pSTS), a higher-level action-selective area. We found a significant correlation between neural adaptation strength in right pSTS and perceptual aftereffects to biological motion measured behaviorally, but not in hMT+. The magnitude of neural adaptation in right pSTS was also strongly correlated with individual differences in the degree of autistic traits. Participants with more autistic traits exhibited less adaptation-induced modulations of brain responses in right pSTS and correspondingly weaker perceptual aftereffects. These results suggest a direct link between perceptual aftereffects and adaptation of neural populations in right pSTS after prolonged viewing of a biological motion stimulus, and highlight the potential importance of this brain region for understanding differences in social-cognitive processing along the autistic spectrum.
Sengupta, Ranit; Nasir, Sazzad M
2015-04-01
Despite recent progress in our understanding of sensorimotor integration in speech learning, a comprehensive framework to investigate its neural basis is lacking at behaviorally relevant timescales. Structural and functional imaging studies in humans have helped us identify brain networks that support speech but fail to capture the precise spatiotemporal coordination within the networks that takes place during speech learning. Here we use neuronal oscillations to investigate interactions within speech motor networks in a paradigm of speech motor adaptation under altered feedback with continuous recording of EEG in which subjects adapted to the real-time auditory perturbation of a target vowel sound. As subjects adapted to the task, concurrent changes were observed in the theta-gamma phase coherence during speech planning at several distinct scalp regions that is consistent with the establishment of a feedforward map. In particular, there was an increase in coherence over the central region and a decrease over the fronto-temporal regions, revealing a redistribution of coherence over an interacting network of brain regions that could be a general feature of error-based motor learning in general. Our findings have implications for understanding the neural basis of speech motor learning and could elucidate how transient breakdown of neuronal communication within speech networks relates to speech disorders.
Non-linear adaptive sliding mode switching control with average dwell-time
NASA Astrophysics Data System (ADS)
Yu, Lei; Zhang, Maoqing; Fei, Shumin
2013-03-01
In this article, an adaptive integral sliding mode control scheme is addressed for switched non-linear systems in the presence of model uncertainties and external disturbances. The control law includes two parts: a slide mode controller for the reduced model of the plant and a compensation controller to deal with the non-linear systems with parameter uncertainties. The adaptive updated laws have been derived from the switched multiple Lyapunov function method, also an admissible switching signal with average dwell-time technique is given. The simplicity of the proposed control scheme facilitates its implementation and the overall control scheme guarantees the global asymptotic stability in the Lyapunov sense such that the sliding surface of the control system is well reached. Simulation results are presented to demonstrate the effectiveness and the feasibility of the proposed approach.
2014-01-01
This paper examined the efficiency of multivariate linear regression (MLR) and artificial neural network (ANN) models in prediction of two major water quality parameters in a wastewater treatment plant. Biochemical oxygen demand (BOD) and chemical oxygen demand (COD) as well as indirect indicators of organic matters are representative parameters for sewer water quality. Performance of the ANN models was evaluated using coefficient of correlation (r), root mean square error (RMSE) and bias values. The computed values of BOD and COD by model, ANN method and regression analysis were in close agreement with their respective measured values. Results showed that the ANN performance model was better than the MLR model. Comparative indices of the optimized ANN with input values of temperature (T), pH, total suspended solid (TSS) and total suspended (TS) for prediction of BOD was RMSE = 25.1 mg/L, r = 0.83 and for prediction of COD was RMSE = 49.4 mg/L, r = 0.81. It was found that the ANN model could be employed successfully in estimating the BOD and COD in the inlet of wastewater biochemical treatment plants. Moreover, sensitive examination results showed that pH parameter have more effect on BOD and COD predicting to another parameters. Also, both implemented models have predicted BOD better than COD. PMID:24456676
Zare Abyaneh, Hamid
2014-01-01
This paper examined the efficiency of multivariate linear regression (MLR) and artificial neural network (ANN) models in prediction of two major water quality parameters in a wastewater treatment plant. Biochemical oxygen demand (BOD) and chemical oxygen demand (COD) as well as indirect indicators of organic matters are representative parameters for sewer water quality. Performance of the ANN models was evaluated using coefficient of correlation (r), root mean square error (RMSE) and bias values. The computed values of BOD and COD by model, ANN method and regression analysis were in close agreement with their respective measured values. Results showed that the ANN performance model was better than the MLR model. Comparative indices of the optimized ANN with input values of temperature (T), pH, total suspended solid (TSS) and total suspended (TS) for prediction of BOD was RMSE = 25.1 mg/L, r = 0.83 and for prediction of COD was RMSE = 49.4 mg/L, r = 0.81. It was found that the ANN model could be employed successfully in estimating the BOD and COD in the inlet of wastewater biochemical treatment plants. Moreover, sensitive examination results showed that pH parameter have more effect on BOD and COD predicting to another parameters. Also, both implemented models have predicted BOD better than COD. PMID:24456676
Christodoulou, Manolis A; Kontogeorgou, Chrysa
2008-10-01
In recent years there has been a great effort to convert the existing Air Traffic Control system into a novel system known as Free Flight. Free Flight is based on the concept that increasing international airspace capacity will grant more freedom to individual pilots during the enroute flight phase, thereby giving them the opportunity to alter flight paths in real time. Under the current system, pilots must request, then receive permission from air traffic controllers to alter flight paths. Understandably the new system allows pilots to gain the upper hand in air traffic. At the same time, however, this freedom increase pilot responsibility. Pilots face a new challenge in avoiding the traffic shares congested air space. In order to ensure safety, an accurate system, able to predict and prevent conflict among aircraft is essential. There are certain flight maneuvers that exist in order to prevent flight disturbances or collision and these are graded in the following categories: vertical, lateral and airspeed. This work focuses on airspeed maneuvers and tries to introduce a new idea for the control of Free Flight, in three dimensions, using neural networks trained with examples prepared through non-linear programming.
Zare Abyaneh, Hamid
2014-01-01
This paper examined the efficiency of multivariate linear regression (MLR) and artificial neural network (ANN) models in prediction of two major water quality parameters in a wastewater treatment plant. Biochemical oxygen demand (BOD) and chemical oxygen demand (COD) as well as indirect indicators of organic matters are representative parameters for sewer water quality. Performance of the ANN models was evaluated using coefficient of correlation (r), root mean square error (RMSE) and bias values. The computed values of BOD and COD by model, ANN method and regression analysis were in close agreement with their respective measured values. Results showed that the ANN performance model was better than the MLR model. Comparative indices of the optimized ANN with input values of temperature (T), pH, total suspended solid (TSS) and total suspended (TS) for prediction of BOD was RMSE = 25.1 mg/L, r = 0.83 and for prediction of COD was RMSE = 49.4 mg/L, r = 0.81. It was found that the ANN model could be employed successfully in estimating the BOD and COD in the inlet of wastewater biochemical treatment plants. Moreover, sensitive examination results showed that pH parameter have more effect on BOD and COD predicting to another parameters. Also, both implemented models have predicted BOD better than COD.
Contrast gain, signal-to-noise ratio, and linearity in light-adapted blowfly photoreceptors
1994-01-01
Response properties of short-type (R1-6) photoreceptors of the blowfly (Calliphora vicina) were investigated with intracellular recordings using repeated sequences of pseudorandomly modulated light contrast stimuli at adapting backgrounds covering 5 log intensity units. The resulting voltage responses were used to determine the effects of adaptational regulation on signal-to-noise ratios (SNR), signal induced noise, contrast gain, linearity and the dead time in phototransduction. In light adaptation the SNR of the photoreceptors improved more than 100-fold due to (a) increased photoreceptor voltage responses to a contrast stimulus and (b) reduction of voltage noise at high intensity backgrounds. In the frequency domain the SNR was attenuated in low frequencies with an increase in the middle and high frequency ranges. A pseudorandom contrast stimulus by itself did not produce any additional noise. The contrast gain of the photoreceptor frequency responses increased with mean illumination and the gain was best fitted with a model consisting of two second order and one double pole of first order. The coherence function (a normalized measure of linearity and SNR) of the frequency responses demonstrated that the photoreceptors responded linearly (from 1 to 150 Hz) to the contrast stimuli even under fairly dim conditions. The theoretically derived and the recorded phase functions were used to calculate phototransduction dead time, which decreased in light adaptation from approximately 5-2.5 ms. This analysis suggests that the ability of fly photoreceptors to maintain linear performance under dynamic stimulation conditions results from the high early gain followed by delayed compressive feed-back mechanisms. PMID:7807062
Adaptive neural control of nonlinear time-delay systems with unknown virtual control coefficients.
Ge, Shuzhi Sam; Hong, Fan; Lee, Tong Heng
2004-02-01
In this paper, adaptive neural control is presented for a class of strict-feedback nonlinear systems with unknown time delays. The proposed design method does not require a priori knowledge of the signs of the unknown virtual control coefficients. The unknown time delays are compensated for using appropriate Lyapunov-Krasovskii functionals in the design. It is proved that the proposed backstepping design method is able to guarantee semiglobal uniformly ultimately boundedness of all the signals in the closed-loop. In addition, the output of the system is proven to converge to a small neighborhood of the origin. Simulation results are provided to show the effectiveness of the proposed approach.
Flight envelope protection of aircraft using adaptive neural network and online linearisation
NASA Astrophysics Data System (ADS)
Shin, Hohyun; Kim, Youdan
2016-03-01
Flight envelope protection algorithm is proposed to improve the safety of an aircraft. Flight envelope protection systems find the control inputs to prevent an aircraft from exceeding structure/aerodynamic limits and maximum control surface deflections. The future values of state variables are predicted using the current states and control inputs based on linearised aircraft model. To apply the envelope protection algorithm for the wide envelope of the aircraft, online linearisation is adopted. Finally, the flight envelope protection system is designed using adaptive neural network and least-squares method. Numerical simulations are conducted to verify the performance of the proposed scheme.
Validity of tests under covariate-adaptive biased coin randomization and generalized linear models.
Shao, Jun; Yu, Xinxin
2013-12-01
Some covariate-adaptive randomization methods have been used in clinical trials for a long time, but little theoretical work has been done about testing hypotheses under covariate-adaptive randomization until Shao et al. (2010) who provided a theory with detailed discussion for responses under linear models. In this article, we establish some asymptotic results for covariate-adaptive biased coin randomization under generalized linear models with possibly unknown link functions. We show that the simple t-test without using any covariate is conservative under covariate-adaptive biased coin randomization in terms of its Type I error rate, and that a valid test using the bootstrap can be constructed. This bootstrap test, utilizing covariates in the randomization scheme, is shown to be asymptotically as efficient as Wald's test correctly using covariates in the analysis. Thus, the efficiency loss due to not using covariates in the analysis can be recovered by utilizing covariates in covariate-adaptive biased coin randomization. Our theory is illustrated with two most popular types of discrete outcomes, binary responses and event counts under the Poisson model, and exponentially distributed continuous responses. We also show that an alternative simple test without using any covariate under the Poisson model has an inflated Type I error rate under simple randomization, but is valid under covariate-adaptive biased coin randomization. Effects on the validity of tests due to model misspecification is also discussed. Simulation studies about the Type I errors and powers of several tests are presented for both discrete and continuous responses. PMID:23848580
A new adaptive multiple modelling approach for non-linear and non-stationary systems
NASA Astrophysics Data System (ADS)
Chen, Hao; Gong, Yu; Hong, Xia
2016-07-01
This paper proposes a novel adaptive multiple modelling algorithm for non-linear and non-stationary systems. This simple modelling paradigm comprises K candidate sub-models which are all linear. With data available in an online fashion, the performance of all candidate sub-models are monitored based on the most recent data window, and M best sub-models are selected from the K candidates. The weight coefficients of the selected sub-model are adapted via the recursive least square (RLS) algorithm, while the coefficients of the remaining sub-models are unchanged. These M model predictions are then optimally combined to produce the multi-model output. We propose to minimise the mean square error based on a recent data window, and apply the sum to one constraint to the combination parameters, leading to a closed-form solution, so that maximal computational efficiency can be achieved. In addition, at each time step, the model prediction is chosen from either the resultant multiple model or the best sub-model, whichever is the best. Simulation results are given in comparison with some typical alternatives, including the linear RLS algorithm and a number of online non-linear approaches, in terms of modelling performance and time consumption.
Crop classification by forward neural network with adaptive chaotic particle swarm optimization.
Zhang, Yudong; Wu, Lenan
2011-01-01
This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10(-7) s.
An alternative approach for adaptive real-time control using a nonparametric neural network
Alves da Silva, A.P.; Nascimento, P.C.; Lambert-Torres, G.; Borges da Silva, L.E.
1995-12-31
This paper presents a nonparametric Artificial Neural Network (ANN) model for adaptive control of nonlinear systems. The proposed ANN, Functional Polynomial Network (FPN), mixes the concept of orthogonal basis functions with the idea of polynomial networks. A combination of orthogonal functions can be used to produce a desired mapping. However, there is no way besides trial and error to choose which orthogonal functions should be selected. Polynomial nets can be used for function approximation, but, it is not easy to set the order of the activation function. The combination of the two concepts produces a very powerful ANN model due to the automatic input selection capability of the polynomial networks. The proposed FPN has been tested for speed control of a DC motor. The results have been compared with the ones provided by an indirect adaptive control scheme based on multilayer perceptrons trained by backpropagation.
Short term load forecasting using a self-supervised adaptive neural network
Yoo, H.; Pimmel, R.L.
1999-05-01
The authors developed a self-supervised adaptive neural network to perform short term load forecasts (STLF) for a large power system covering a wide service area with several heavy load centers. They used the self-supervised network to extract correlational features from temperature and load data. In using data from the calendar year 1993 as a test case, they found a 0.90 percent error for hour-ahead forecasting and 1.92 percent error for day-ahead forecasting. These levels of error compare favorably with those obtained by other techniques. The algorithm ran in a couple of minutes on a PC containing an Intel Pentium -- 120 MHz CPU. Since the algorithm included searching the historical database, training the network, and actually performing the forecasts, this approach provides a real-time, portable, and adaptable STLF.
Modeling the behavioral substrates of associate learning and memory - Adaptive neural models
NASA Technical Reports Server (NTRS)
Lee, Chuen-Chien
1991-01-01
Three adaptive single-neuron models based on neural analogies of behavior modification episodes are proposed, which attempt to bridge the gap between psychology and neurophysiology. The proposed models capture the predictive nature of Pavlovian conditioning, which is essential to the theory of adaptive/learning systems. The models learn to anticipate the occurrence of a conditioned response before the presence of a reinforcing stimulus when training is complete. Furthermore, each model can find the most nonredundant and earliest predictor of reinforcement. The behavior of the models accounts for several aspects of basic animal learning phenomena in Pavlovian conditioning beyond previous related models. Computer simulations show how well the models fit empirical data from various animal learning paradigms.
A Neural Network Approach to Intention Modeling for User-Adapted Conversational Agents
Griol, David
2016-01-01
Spoken dialogue systems have been proposed to enable a more natural and intuitive interaction with the environment and human-computer interfaces. In this contribution, we present a framework based on neural networks that allows modeling of the user's intention during the dialogue and uses this prediction to dynamically adapt the dialogue model of the system taking into consideration the user's needs and preferences. We have evaluated our proposal to develop a user-adapted spoken dialogue system that facilitates tourist information and services and provide a detailed discussion of the positive influence of our proposal in the success of the interaction, the information and services provided, and the quality perceived by the users. PMID:26819592
Distributed Adaptive Coordinated Control of Multi-Manipulator Systems Using Neural Networks
NASA Astrophysics Data System (ADS)
Hou, Zeng-Guang; Cheng, Long; Tan, Min; Wang, Xu
On many occasions, all the manipulators in the multi-manipulator system need to achieve the same joint configuration to fulfill certain coordination tasks. In this chapter, a distributed adaptive approach is proposed for solving this coordination problem based on the leader-follower strategy. The proposed algorithm is distributed because the controller for each follower manipulator is solely based on the information of connected neighbor manipulators, and the joint value of leader manipulator is only accessible to partial follower manipulators. The uncertain term in the manipulator's dynamics is considered in the controller design, and it is approximated by the adaptive neural network scheme. The neural network weight matrix is adjusted on-line by the projection method, and the pre-training phase is no longer required. Effects of approximation error and external disturbances are counteracted by employing the robustness signal. According to the theoretical analysis, all the joints of follower manipulators can be regulated into an arbitrary small neighborhood of the value of leader's joint. Finally, simulation results are given to demonstrate the satisfactory performance of the proposed method.
Predicting neutron diffusion eigenvalues with a query-based adaptive neural architecture.
Lysenko, M G; Wong, H I; Maldonado, G I
1999-01-01
A query-based approach for adaptively retraining and restructuring a two-hidden-layer artificial neural network (ANN) has been developed for the speedy prediction of the fundamental mode eigenvalue of the neutron diffusion equation, a standard nuclear reactor core design calculation which normally requires the iterative solution of a large-scale system of nonlinear partial differential equations (PDE's). The approach developed focuses primarily upon the adaptive selection of training and cross-validation data and on artificial neural-network (ANN) architecture adjustments, with the objective of improving the accuracy and generalization properties of ANN-based neutron diffusion eigenvalue predictions. For illustration, the performance of a "bare bones" feedforward multilayer perceptron (MLP) is upgraded through a variety of techniques; namely, nonrandom initial training set selection, adjoint function input weighting, teacher-student membership and equivalence queries for generation of appropriate training data, and a dynamic node architecture (DNA) implementation. The global methodology is flexible in that it can "wrap around" any specific training algorithm selected for the static calculations (i.e., training iterations with a fixed training set and architecture). Finally, the improvements obtained are carefully contrasted against past works reported in the literature.
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.
Adaptive dynamic inversion robust control for BTT missile based on wavelet neural network
NASA Astrophysics Data System (ADS)
Li, Chuanfeng; Wang, Yongji; Deng, Zhixiang; Wu, Hao
2009-10-01
A new nonlinear control strategy incorporated the dynamic inversion method with wavelet neural networks is presented for the nonlinear coupling system of Bank-to-Turn(BTT) missile in reentry phase. The basic control law is designed by using the dynamic inversion feedback linearization method, and the online learning wavelet neural network is used to compensate the inversion error due to aerodynamic parameter errors, modeling imprecise and external disturbance in view of the time-frequency localization properties of wavelet transform. Weights adjusting laws are derived according to Lyapunov stability theory, which can guarantee the boundedness of all signals in the whole system. Furthermore, robust stability of the closed-loop system under this tracking law is proved. Finally, the six degree-of-freedom(6DOF) simulation results have shown that the attitude angles can track the anticipant command precisely under the circumstances of existing external disturbance and in the presence of parameter uncertainty. It means that the dependence on model by dynamic inversion method is reduced and the robustness of control system is enhanced by using wavelet neural network(WNN) to reconstruct inversion error on-line.
Sen, Baris Ali; Menon, Suresh
2010-01-15
A large eddy simulation (LES) sub-grid model is developed based on the artificial neural network (ANN) approach to calculate the species instantaneous reaction rates for multi-step, multi-species chemical kinetics mechanisms. The proposed methodology depends on training the ANNs off-line on a thermo-chemical database representative of the actual composition and turbulence (but not the actual geometrical problem) of interest, and later using them to replace the stiff ODE solver (direct integration (DI)) to calculate the reaction rates in the sub-grid. The thermo-chemical database is tabulated with respect to the thermodynamic state vector without any reduction in the number of state variables. The thermo-chemistry is evolved by stand-alone linear eddy mixing (LEM) model simulations under both premixed and non-premixed conditions, where the unsteady interaction of turbulence with chemical kinetics is included as a part of the training database. The proposed methodology is tested in LES and in stand-alone LEM studies of three distinct test cases with different reduced mechanisms and conditions. LES of premixed flame-turbulence-vortex interaction provides direct comparison of the proposed ANN method against DI and ANNs trained on thermo-chemical database created using another type of tabulation method. It is shown that the ANN trained on the LEM database can capture the correct flame physics with accuracy comparable to DI, which cannot be achieved by ANN trained on a laminar premix flame database. A priori evaluation of the ANN generality within and outside its training domain is carried out using stand-alone LEM simulations as well. Results in general are satisfactory, and it is shown that the ANN provides considerable amount of memory saving and speed-up with reasonable and reliable accuracy. The speed-up is strongly affected by the stiffness of the reduced mechanism used for the computations, whereas the memory saving is considerable regardless. (author)
Short-term training for explosive strength causes neural and mechanical adaptations.
Tillin, Neale A; Pain, Matthew T G; Folland, Jonathan P
2012-05-01
This study investigated the neural and peripheral adaptations to short-term training for explosive force production. Ten men trained the knee extensors with unilateral explosive isometric contractions (1 s 'fast and hard') for 4 weeks. Before and after training, force was recorded at 50-ms intervals from force onset (F(50), F(100) and F(150)) during both voluntary and involuntary (supramaximal evoked octet; eight pulses at 300 Hz) explosive isometric contractions. Neural drive during the explosive voluntary contractions was measured with the ratio of voluntary/octet force, and average EMG normalized to the peak-to-peak M-wave of the three superficial quadriceps. Maximal voluntary force (MVF) was also measured, and ultrasonic images of the vastus lateralis were recorded during ramped contractions to assess muscle-tendon unit stiffness between 50 and 90% MVF. There was an increase in voluntary F(50) (+54%), F(100) (+15%) and F(150) (+14%) and in octet F(50) (+7%) and F(100) (+10%). Voluntary F(100) and F(150), and octet F(50) and F(100) increased proportionally with MVF (+11%). However, the increase in voluntary F(50) was +37% even after normalization to MVF, and coincided with a 42% increase in both voluntary/octet force and agonist-normalized EMG over the first 50 ms. Muscle-tendon unit stiffness between 50 and 90% MVF also increased. In conclusion, enhanced agonist neural drive and MVF accounted for improved explosive voluntary force production in the early and late phases of the contraction, respectively. The increases in explosive octet force and muscle-tendon unit stiffness provide novel evidence of peripheral adaptations within merely 4 weeks of training for explosive force production.
[Automated recognition of quasars based on adaptive radial basis function neural networks].
Zhao, Mei-Fang; Luo, A-Li; Wu, Fu-Chao; Hu, Zhan-Yi
2006-02-01
Recognizing and certifying quasars through the research on spectra is an important method in the field of astronomy. This paper presents a novel adaptive method for the automated recognition of quasars based on the radial basis function neural networks (RBFN). The proposed method is composed of the following three parts: (1) The feature space is reduced by the PCA (the principal component analysis) on the normalized input spectra; (2) An adaptive RBFN is constructed and trained in this reduced space. At first, the K-means clustering is used for the initialization, then based on the sum of squares errors and a gradient descent optimization technique, the number of neurons in the hidden layer is adaptively increased to improve the recognition performance; (3) The quasar spectra recognition is effectively carried out by the above trained RBFN. The author's proposed adaptive RBFN is shown to be able to not only overcome the difficulty of selecting the number of neurons in hidden layer of the traditional RBFN algorithm, but also increase the stability and accuracy of recognition of quasars. Besides, the proposed method is particularly useful for automatic voluminous spectra processing produced from a large-scale sky survey project, such as our LAMOST, due to its efficiency.
ERIC Educational Resources Information Center
Everson, Howard T.; And Others
This paper explores the feasibility of neural computing methods such as artificial neural networks (ANNs) and abductory induction mechanisms (AIM) for use in educational measurement. ANNs and AIMS methods are contrasted with more traditional statistical techniques, such as multiple regression and discriminant function analyses, for making…
NASA Astrophysics Data System (ADS)
Zhang, Ruikun; Hou, Zhongsheng; Ji, Honghai; Yin, Chenkun
2016-04-01
In this paper, an adaptive iterative learning control scheme is proposed for a class of non-linearly parameterised systems with unknown time-varying parameters and input saturations. By incorporating a saturation function, a new iterative learning control mechanism is presented which includes a feedback term and a parameter updating term. Through the use of parameter separation technique, the non-linear parameters are separated from the non-linear function and then a saturated difference updating law is designed in iteration domain by combining the unknown parametric term of the local Lipschitz continuous function and the unknown time-varying gain into an unknown time-varying function. The analysis of convergence is based on a time-weighted Lyapunov-Krasovskii-like composite energy function which consists of time-weighted input, state and parameter estimation information. The proposed learning control mechanism warrants a L2[0, T] convergence of the tracking error sequence along the iteration axis. Simulation results are provided to illustrate the effectiveness of the adaptive iterative learning control scheme.
1991-01-01
Impulse and sine wave responses of crayfish photoreceptors were examined to establish the limits and the parameters of linear behavior. These receptors exhibit simple low pass behavior which is well described by the transfer function of a linear resistor-capacitor cascade of three to five stages, each with the same time constant (tau). Additionally, variations in mean light intensity modify tau twofold and the contrast sensitivity by fourfold. The angular sensitivity profile is Gaussian and the acceptance angle (phi) increases 3.2-fold with dark adaptation. The responses to moving stripes of positive and negative contrast were measured over a 100-fold velocity range. The amplitude, phase, and waveform of these responses were predicted from the convolution of the receptor's impulse response and angular sensitivity profile. A theoretical calculation based on the convolution of a linear impulse response and a Gaussian sensitivity profile indicates that the sensitivity to variations in stimulus velocity is determined by the ratio phi/tau. These two parameters are sufficient to predict the velocity of the half-maximal response over a wide range of ambient illumination levels. Because phi and tau vary in parallel during light adaptation, it is inferred that many arthropods can maintain approximately constant velocity sensitivity during large shifts in mean illumination and receptor time constant. The results are discussed relative to other arthropod and vertebrate receptors and the strategies that have evolved for movement detection in varying ambient illumination. PMID:2056307
Wang, Huanqing; Liu, Kefu; Liu, Xiaoping; Chen, Bing; Lin, Chong
2015-09-01
In this paper, we consider the problem of observer-based adaptive neural output-feedback control for a class of stochastic nonlinear systems with nonstrict-feedback structure. To overcome the design difficulty from the nonstrict-feedback structure, a variable separation approach is introduced by using the monotonically increasing property of system bounding functions. On the basis of the state observer, and by combining the adaptive backstepping technique with radial basis function neural networks' universal approximation capability, an adaptive neural output feedback control algorithm is presented. It is shown that the proposed controller can guarantee that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded in the sense of mean quartic value. Simulation results are provided to show the effectiveness of the proposed control scheme.
Remembering forward: Neural correlates of memory and prediction in human motor adaptation
Scheidt, Robert A; Zimbelman, Janice L; Salowitz, Nicole M G; Suminski, Aaron J; Mosier, Kristine M; Houk, James; Simo, Lucia
2011-01-01
We used functional MR imaging (FMRI), a robotic manipulandum and systems identification techniques to examine neural correlates of predictive compensation for spring-like loads during goal-directed wrist movements in neurologically-intact humans. Although load changed unpredictably from one trial to the next, subjects nevertheless used sensorimotor memories from recent movements to predict and compensate upcoming loads. Prediction enabled subjects to adapt performance so that the task was accomplished with minimum effort. Population analyses of functional images revealed a distributed, bilateral network of cortical and subcortical activity supporting predictive load compensation during visual target capture. Cortical regions - including prefrontal, parietal and hippocampal cortices - exhibited trial-by-trial fluctuations in BOLD signal consistent with the storage and recall of sensorimotor memories or “states” important for spatial working memory. Bilateral activations in associative regions of the striatum demonstrated temporal correlation with the magnitude of kinematic performance error (a signal that could drive reward-optimizing reinforcement learning and the prospective scaling of previously learned motor programs). BOLD signal correlations with load prediction were observed in the cerebellar cortex and red nuclei (consistent with the idea that these structures generate adaptive fusimotor signals facilitating cancellation of expected proprioceptive feedback, as required for conditional feedback adjustments to ongoing motor commands and feedback error learning). Analysis of single subject images revealed that predictive activity was at least as likely to be observed in more than one of these neural systems as in just one. We conclude therefore that motor adaptation is mediated by predictive compensations supported by multiple, distributed, cortical and subcortical structures. PMID:21840405
Algorithms for adaptive stochastic control for a class of linear systems
NASA Technical Reports Server (NTRS)
Toda, M.; Patel, R. V.
1977-01-01
Control of linear, discrete time, stochastic systems with unknown control gain parameters is discussed. Two suboptimal adaptive control schemes are derived: one is based on underestimating future control and the other is based on overestimating future control. Both schemes require little on-line computation and incorporate in their control laws some information on estimation errors. The performance of these laws is studied by Monte Carlo simulations on a computer. Two single input, third order systems are considered, one stable and the other unstable, and the performance of the two adaptive control schemes is compared with that of the scheme based on enforced certainty equivalence and the scheme where the control gain parameters are known.
Ayati, Moosa; Alwan, Mohamad; Liu Xinzhi; Khaloozadeh, Hamid
2011-11-30
State observation (estimation) is a very important issue in system analysis and control. This paper develops a new observer called Stochastic Adaptive Impulsive Observer (SAIO) for the state estimation of impulsive systems. The proposed observer is applicable to linear and nonlinear stochastic impulsive systems. In addition, the effect of parametric uncertainty is considered and unknown parameters of the system are estimated by suitable adaptation laws. Impulsive system theory, particularly stochastic Lyapunov-like function, is used to analyze the stability and convergence of the state estimations. The main advantages of the proposed observer are: 1) it gives continuous estimation from discrete time measurements of the system output, and 2) it is useful for state estimation when continuous measurements are impossible or expensive. Simulation results show the effectiveness of the proposed observer and we believe that it has many applications in control and estimation theories.
Dasgupta, Sakyasingha; Goldschmidt, Dennis; Wörgötter, Florentin; Manoonpong, Poramate
2015-01-01
Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, (2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and (3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps, leg damage adaptations, as well as climbing over high obstacles. Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models
Dasgupta, Sakyasingha; Goldschmidt, Dennis; Wörgötter, Florentin; Manoonpong, Poramate
2015-01-01
Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated movements, (2) distributed (at each leg) recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and (3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps, leg damage adaptations, as well as climbing over high obstacles. Furthermore, we demonstrate that the newly developed recurrent network based approach to online forward models outperforms the adaptive neuron forward models
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
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
Doulamis, A; Doulamis, N; Ntalianis, K; Kollias, S
2003-01-01
In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).
Raffone, Antonino; Srinivasan, Narayanan
2009-01-01
While enormous progress has been made to identify neural correlates of consciousness (NCC), crucial NCC aspects are still very controversial. A major hurdle is the lack of an adequate definition and characterization of different aspects of conscious experience and also its relationship to attention and metacognitive processes like monitoring. In this paper, we therefore attempt to develop a unitary theoretical framework for NCC, with an interdependent characterization of endogenous attention, access consciousness, phenomenal awareness, metacognitive consciousness, and a non-referential form of unified consciousness. We advance an adaptive workspace hypothesis about the NCC based on the global workspace model emphasizing transient resonant neurodynamics and prefrontal cortex function, as well as meditation-related characterizations of conscious experiences. In this hypothesis, transient dynamic links within an adaptive coding net in prefrontal cortex, especially in anterior prefrontal cortex, and between it and the rest of the brain, in terms of ongoing intrinsic and long-range signal exchanges, flexibly regulate the interplay between endogenous attention, access consciousness, phenomenal awareness, and metacognitive consciousness processes. Such processes are established in terms of complementary aspects of an ongoing transition between context-sensitive global workspace assemblies, modulated moment-to-moment by body and environment states. Brain regions associated to momentary interoceptive and exteroceptive self-awareness, or first-person experiential perspective as emphasized in open monitoring meditation, play an important modulatory role in adaptive workspace transitions.
An adaptive recurrent-neural-network motion controller for X-Y table in CNC machine.
Lin, Faa-Jeng; Shieh, Hsin-Jang; Shieh, Po-Huang; Shen, Po-Hung
2006-04-01
In this paper, an adaptive recurrent-neural-network (ARNN) motion control system for a biaxial motion mechanism driven by two field-oriented control permanent magnet synchronous motors (PMSMs) in the computer numerical control (CNC) machine is proposed. In the proposed ARNN control system, a RNN with accurate approximation capability is employed to approximate an unknown dynamic function, and the adaptive learning algorithms that can learn the parameters of the RNN on line are derived using Lyapunov stability theorem. Moreover, a robust controller is proposed to confront the uncertainties including approximation error, optimal parameter vectors, higher-order terms in Taylor series, external disturbances, cross-coupled interference and friction torque of the system. To relax the requirement for the value of lumped uncertainty in the robust controller, an adaptive lumped uncertainty estimation law is investigated. Using the proposed control, the position tracking performance is substantially improved and the robustness to uncertainties including cross-coupled interference and friction torque can be obtained as well. Finally, some experimental results of the tracking of various reference contours demonstrate the validity of the proposed design for practical applications. PMID:16602590
Mavroforakis, Michael; Georgiou, Harris; Dimitropoulos, Nikos; Cavouras, Dionisis; Theodoridis, Sergios
2005-04-01
models, namely linear classifiers, neural networks and support vector machines, were employed to investigate the true efficiency of each one of them, as well as the overall complexity of the diagnostic task of mammographic tumor characterization. Both the statistical and the classification results have proven the explicit correlation of all the selected features with the final diagnosis, qualifying them as an adequate input base for any type of similar automated diagnosis system. The underlying complexity of the diagnostic task has justified the high value of sophisticated pattern recognition architectures. PMID:15797296
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.
Liu, Yan-Jun; Gao, Ying; Tong, Shaocheng; Chen, C L Philip
2016-01-01
In this paper, an effective adaptive control approach is constructed to stabilize a class of nonlinear discrete-time systems, which contain unknown functions, unknown dead-zone input, and unknown control direction. Different from linear dead zone, the dead zone, in this paper, is a kind of nonlinear dead zone. To overcome the noncausal problem, which leads to the control scheme infeasible, the systems can be transformed into a m -step-ahead predictor. Due to nonlinear dead-zone appearance, the transformed predictor still contains the nonaffine function. In addition, it is assumed that the gain function of dead-zone input and the control direction are unknown. These conditions bring about the difficulties and the complicacy in the controller design. Thus, the implicit function theorem is applied to deal with nonaffine dead-zone appearance, the problem caused by the unknown control direction can be resolved through applying the discrete Nussbaum gain, and the neural networks are used to approximate the unknown function. Based on the Lyapunov theory, all the signals of the resulting closed-loop system are proved to be semiglobal uniformly ultimately bounded. Moreover, the tracking error is proved to be regulated to a small neighborhood around zero. The feasibility of the proposed approach is demonstrated by a simulation example.
Liu, Yan-Jun; Gao, Ying; Tong, Shaocheng; Chen, C L Philip
2016-01-01
In this paper, an effective adaptive control approach is constructed to stabilize a class of nonlinear discrete-time systems, which contain unknown functions, unknown dead-zone input, and unknown control direction. Different from linear dead zone, the dead zone, in this paper, is a kind of nonlinear dead zone. To overcome the noncausal problem, which leads to the control scheme infeasible, the systems can be transformed into a m -step-ahead predictor. Due to nonlinear dead-zone appearance, the transformed predictor still contains the nonaffine function. In addition, it is assumed that the gain function of dead-zone input and the control direction are unknown. These conditions bring about the difficulties and the complicacy in the controller design. Thus, the implicit function theorem is applied to deal with nonaffine dead-zone appearance, the problem caused by the unknown control direction can be resolved through applying the discrete Nussbaum gain, and the neural networks are used to approximate the unknown function. Based on the Lyapunov theory, all the signals of the resulting closed-loop system are proved to be semiglobal uniformly ultimately bounded. Moreover, the tracking error is proved to be regulated to a small neighborhood around zero. The feasibility of the proposed approach is demonstrated by a simulation example. PMID:26353383
Nie, Xiaobing; Zheng, Wei Xing
2015-05-01
This paper is concerned with the problem of coexistence and dynamical behaviors of multiple equilibrium points for neural networks with discontinuous non-monotonic piecewise linear activation functions and time-varying delays. The fixed point theorem and other analytical tools are used to develop certain sufficient conditions that ensure that the n-dimensional discontinuous neural networks with time-varying delays can have at least 5(n) equilibrium points, 3(n) of which are locally stable and the others are unstable. The importance of the derived results is that it reveals that the discontinuous neural networks can have greater storage capacity than the continuous ones. Moreover, different from the existing results on multistability of neural networks with discontinuous activation functions, the 3(n) locally stable equilibrium points obtained in this paper are located in not only saturated regions, but also unsaturated regions, due to the non-monotonic structure of discontinuous activation functions. A numerical simulation study is conducted to illustrate and support the derived theoretical results.
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.
Theodorakopoulos, Achilles; Rovithakis, George A
2015-03-01
In this paper, the problem of deriving a continuous, state-feedback controller for a class of multiinput multioutput feedback linearizable systems is considered with special emphasis on controller simplification and reduction of the overall design complexity with respect to the current state of the art. The proposed scheme achieves prescribed bounds on the transient and steady-state performance of the output tracking errors despite the uncertainty in system nonlinearities. Contrary to the current state of the art, however, only a single neural network is utilized to approximate a scalar function that partly incorporates the system nonlinearities. Furthermore, the loss of model controllability problem, typically introduced owing to approximation model singularities, is avoided without attaching additional complexity to the control or adaptive law. Simulations are performed to verify and clarify the theoretical findings.
NASA Technical Reports Server (NTRS)
Gupta, Pramod; Schumann, Johann
2004-01-01
High reliability of mission- and safety-critical software systems has been identified by NASA as a high-priority technology challenge. We present an approach for the performance analysis of a neural network (NN) in an advanced adaptive control system. This problem is important in the context of safety-critical applications that require certification, such as flight software in aircraft. We have developed a tool to measure the performance of the NN during operation by calculating a confidence interval (error bar) around the NN's output. Our tool can be used during pre-deployment verification as well as monitoring the network performance during operation. The tool has been implemented in Simulink and simulation results on a F-15 aircraft are presented.
NASA Astrophysics Data System (ADS)
Liu, Derong; Huang, Yuzhu; Wang, Ding; Wei, Qinglai
2013-09-01
In this paper, an observer-based optimal control scheme is developed for unknown nonlinear systems using adaptive dynamic programming (ADP) algorithm. First, a neural-network (NN) observer is designed to estimate system states. Then, based on the observed states, a neuro-controller is constructed via ADP method to obtain the optimal control. In this design, two NN structures are used: a three-layer NN is used to construct the observer which can be applied to systems with higher degrees of nonlinearity and without a priori knowledge of system dynamics, and a critic NN is employed to approximate the value function. The optimal control law is computed using the critic NN and the observer NN. Uniform ultimate boundedness of the closed-loop system is guaranteed. The actor, critic, and observer structures are all implemented in real-time, continuously and simultaneously. Finally, simulation results are presented to demonstrate the effectiveness of the proposed control scheme.
AgRP Neural Circuits Mediate Adaptive Behaviors in the Starved State
Padilla, Stephanie L.; Qiu, Jian; Soden, Marta E.; Sanz, Elisenda; Nestor, Casey C; Barker, Forrest D.; Quintana, Albert; Zweifel, Larry S.; Rønnekleiv, Oline K.; Kelly, Martin J.; Palmiter, Richard D.
2016-01-01
In the face of starvation animals will engage in high-risk behaviors that would normally be considered maladaptive. Starving rodents for example will forage in areas that are more susceptible to predators and will also modulate aggressive behavior within a territory of limited or depleted nutrients. The neural basis of these adaptive behaviors likely involves circuits that link innate feeding, aggression, and fear. Hypothalamic AgRP neurons are critically important for driving feeding and project axons to brain regions implicated in aggression and fear. Using circuit-mapping techniques, we define a disynaptic network originating from a subset of AgRP neurons that project to the medial nucleus of the amygdala and then to the principle bed nucleus of the stria terminalis, which plays a role in suppressing territorial aggression and reducing contextual fear. We propose that AgRP neurons serve as a master switch capable of coordinating behavioral decisions relative to internal state and environmental cues. PMID:27019015
An adaptive neural swarm approach for intrusion defense in ad hoc networks
NASA Astrophysics Data System (ADS)
Cannady, James
2011-06-01
Wireless sensor networks (WSN) and mobile ad hoc networks (MANET) are being increasingly deployed in critical applications due to the flexibility and extensibility of the technology. While these networks possess numerous advantages over traditional wireless systems in dynamic environments they are still vulnerable to many of the same types of host-based and distributed attacks common to those systems. Unfortunately, the limited power and bandwidth available in WSNs and MANETs, combined with the dynamic connectivity that is a defining characteristic of the technology, makes it extremely difficult to utilize traditional intrusion detection techniques. This paper describes an approach to accurately and efficiently detect potentially damaging activity in WSNs and MANETs. It enables the network as a whole to recognize attacks, anomalies, and potential vulnerabilities in a distributive manner that reflects the autonomic processes of biological systems. Each component of the network recognizes activity in its local environment and then contributes to the overall situational awareness of the entire system. The approach utilizes agent-based swarm intelligence to adaptively identify potential data sources on each node and on adjacent nodes throughout the network. The swarm agents then self-organize into modular neural networks that utilize a reinforcement learning algorithm to identify relevant behavior patterns in the data without supervision. Once the modular neural networks have established interconnectivity both locally and with neighboring nodes the analysis of events within the network can be conducted collectively in real-time. The approach has been shown to be extremely effective in identifying distributed network attacks.
Circuit Design and Simulation of AN Augmented Adaptive Resonance Theory (aart) Neural Network.
NASA Astrophysics Data System (ADS)
Ho, Ching-Sung
This dissertation presents circuit implementations for an binary-input adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AART1-NN). The AART1-NN is a modification of the popular ART1-NN, developed by Carpenter and Grossberg, and it exhibits the same behavior as the ART1-NN. The AART1-NN is a real -time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AART1-NN circuit is based on a set of coupled nonlinear differential equations that constitute the AART1 -NN model. Various ways are examined to implement an efficient and practical AART1-NN in electronic hardware. They include designing circuits of AART1-NN by means of discrete electronic components, such as operational amplifiers, capacitors, and resistors, digital VLSI circuit, and mixed analog/digital VLSI circuit. The implemented circuit prototypes are verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from PSpice circuit simulations are also compared with results obtained by solving the coupled differential equations numerically. The prototype systems developed in this work can be used as building blocks for larger AART1-NN architectures, as well as for other types of ART architectures that involve the AART1-NN model.
NASA Astrophysics Data System (ADS)
Ho, Ching S.; Liou, Juin J.; Georgiopoulos, Michael; Heileman, Gregory L.; Christodoulou, Christos G.
1993-09-01
This paper presents an analog circuit implementation for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AART1-NN). The AART1-NN is a modification of the popular ART1-NN, developed by Carpenter and Grossberg, and it exhibits the same behavior as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AART1-NN model. The circuit is implemented by utilizing analog electronic components, such as, operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favorably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AART1-NN architectures, as well as for other types of ART architectures that involve the AART1-NN model.
Adaptive neural control of nonlinear MIMO systems with time-varying output constraints.
Meng, Wenchao; Yang, Qinmin; Sun, Youxian
2015-05-01
In this paper, adaptive neural control is investigated for a class of unknown multiple-input multiple-output nonlinear systems with time-varying asymmetric output constraints. To ensure constraint satisfaction, we employ a system transformation technique to transform the original constrained (in the sense of the output restrictions) system into an equivalent unconstrained one, whose stability is sufficient to solve the output constraint problem. It is shown that output tracking is achieved without violation of the output constraint. More specifically, we can shape the system performance arbitrarily on transient and steady-state stages with the output evolving in predefined time-varying boundaries all the time. A single neural network, whose weights are tuned online, is used in our design to approximate the unknown functions in the system dynamics, while the singularity problem of the control coefficient matrix is avoided without assumption on the prior knowledge of control input's bound. All the signals in the closed-loop system are proved to be semiglobally uniformly ultimately bounded via Lyapunov synthesis. Finally, the merits of the proposed controller are verified in the simulation environment.
NASA Astrophysics Data System (ADS)
Yuan, Wu-Jie; Zhou, Jian-Fang; Zhou, Changsong
2016-04-01
Microsaccades are very small eye movements during fixation. Experimentally, they have been found to play an important role in visual information processing. However, neural responses induced by microsaccades are not yet well understood and are rarely studied theoretically. Here we propose a network model with a cascading adaptation including both retinal adaptation and short-term depression (STD) at thalamocortical synapses. In the neural network model, we compare the microsaccade-induced neural responses in the presence of STD and those without STD. It is found that the cascading with STD can give rise to faster and sharper responses to microsaccades. Moreover, STD can enhance response effectiveness and sensitivity to microsaccadic spatiotemporal changes, suggesting improved detection of small eye movements (or moving visual objects). We also explore the mechanism of the response properties in the model. Our studies strongly indicate that STD plays an important role in neural responses to microsaccades. Our model considers simultaneously retinal adaptation and STD at thalamocortical synapses in the study of microsaccade-induced neural activity, and may be useful for further investigation of the functional roles of microsaccades in visual information processing.
Yuan, Wu-Jie; Zhou, Jian-Fang; Zhou, Changsong
2016-04-01
Microsaccades are very small eye movements during fixation. Experimentally, they have been found to play an important role in visual information processing. However, neural responses induced by microsaccades are not yet well understood and are rarely studied theoretically. Here we propose a network model with a cascading adaptation including both retinal adaptation and short-term depression (STD) at thalamocortical synapses. In the neural network model, we compare the microsaccade-induced neural responses in the presence of STD and those without STD. It is found that the cascading with STD can give rise to faster and sharper responses to microsaccades. Moreover, STD can enhance response effectiveness and sensitivity to microsaccadic spatiotemporal changes, suggesting improved detection of small eye movements (or moving visual objects). We also explore the mechanism of the response properties in the model. Our studies strongly indicate that STD plays an important role in neural responses to microsaccades. Our model considers simultaneously retinal adaptation and STD at thalamocortical synapses in the study of microsaccade-induced neural activity, and may be useful for further investigation of the functional roles of microsaccades in visual information processing. PMID:27176307
L1-norm locally linear representation regularization multi-source adaptation learning.
Tao, Jianwen; Wen, Shiting; Hu, Wenjun
2015-09-01
In most supervised domain adaptation learning (DAL) tasks, one has access only to a small number of labeled examples from target domain. Therefore the success of supervised DAL in this "small sample" regime needs the effective utilization of the large amounts of unlabeled data to extract information that is useful for generalization. Toward this end, we here use the geometric intuition of manifold assumption to extend the established frameworks in existing model-based DAL methods for function learning by incorporating additional information about the target geometric structure of the marginal distribution. We would like to ensure that the solution is smooth with respect to both the ambient space and the target marginal distribution. In doing this, we propose a novel L1-norm locally linear representation regularization multi-source adaptation learning framework which exploits the geometry of the probability distribution, which has two techniques. Firstly, an L1-norm locally linear representation method is presented for robust graph construction by replacing the L2-norm reconstruction measure in LLE with L1-norm one, which is termed as L1-LLR for short. Secondly, considering the robust graph regularization, we replace traditional graph Laplacian regularization with our new L1-LLR graph Laplacian regularization and therefore construct new graph-based semi-supervised learning framework with multi-source adaptation constraint, which is coined as L1-MSAL method. Moreover, to deal with the nonlinear learning problem, we also generalize the L1-MSAL method by mapping the input data points from the input space to a high-dimensional reproducing kernel Hilbert space (RKHS) via a nonlinear mapping. Promising experimental results have been obtained on several real-world datasets such as face, visual video and object.
Non-linear adaptive controllers for an over-actuated pneumatic MR-compatible stepper.
Hollnagel, Christoph; Vallery, Heike; Schädler, Rainer; López, Isaac Gómez-Lor; Jaeger, Lukas; Wolf, Peter; Riener, Robert; Marchal-Crespo, Laura
2013-07-01
Pneumatics is one of the few actuation principles that can be used in an MR environment, since it can produce high forces without affecting imaging quality. However, pneumatic control is challenging, due to the air high compliance and cylinders non-linearities. Furthermore, the system's properties may change for each subject. Here, we present novel control strategies that adapt to the subject's individual anatomy and needs while performing accurate periodic gait-like movements with an MRI compatible pneumatically driven robot. In subject-passive mode, an iterative learning controller (ILC) was implemented to reduce the system's periodic disturbances. To allow the subjects to intend the task by themselves, a zero-force controller minimized the interaction forces between subject and robot. To assist patients who may be too weak, an assist-as-needed controller that adapts the assistance based on online measurement of the subject's performance was designed. The controllers were experimentally tested. The ILC successfully learned to reduce the variability and tracking errors. The zero-force controller allowed subjects to step in a transparent environment. The assist-as-needed controller adapted the assistance based on individual needs, while still challenged the subjects to perform the task. The presented controllers can provide accurate pneumatic control in MR environments to allow assessments of brain activation. PMID:23430329
NASA Astrophysics Data System (ADS)
James Li, C.; Tzeng, Tzong-Chyi
2000-11-01
The objective of this study is to establish a signal processing methodology that can infer the state of milling insert wear from translational vibration measured on the spindle housing of a milling machine. First, the tool wear signature in a translational vibration is accentuated by mapping the translational vibration into a torsional vibration using a previously identified non-linear relationship between the two, i.e. a virtual sensor. Second, a time-frequency distribution, i.e. a Choi-Williams distribution, is calculated from the torsional vibration. Third, scattering matrices and orthogonalisation are employed to identify the time-frequency components that are best correlated to the state of wear. Fourth, a neural network is trained to estimate the extent of wear from these critical time frequency components. The combination of the virtual sensor, time-frequency analysis and neural network is then validated with data obtained from real cutting tests.
NASA Astrophysics Data System (ADS)
Yang, Yang; Yue, Dong; Yuan, Deming
2016-11-01
Considering interconnections among subsystems, we propose an adaptive neural tracking control scheme for a class of multiple-input-multiple-output (MIMO) non-affine pure-feedback time-delay nonlinear systems with input saturation. Neural networks (NNs) are employed to approximate unknown functions in the design procedure, and the separation technology is introduced here to tackle the problem induced from unknown time-delay items. The adaptive neural tracking control scheme is constructed by combining Lyapunov-Krasovskii functionals, NNs, the auxiliary system, the implicit function theory and the mean value theorem along with the dynamic surface control technique. Also, it is proven that the strategy guarantees tracking errors converge to a small neighbourhood around the origin by appropriate choice of design parameters and all signals in the closed-loop system uniformly ultimately bounded. Numerical simulation results are presented to demonstrate the effectiveness of the proposed control strategy.
Gries, J M; Verotta, D
2000-08-01
In a frequently performed pharmacokinetics study, different subjects are given different doses of a drug. After each dose is given, drug concentrations are observed according to the same sampling design. The goal of the experiment is to obtain a representation for the pharmacokinetics of the drug, and to determine if drug concentrations observed at different times after a dose are linear in respect to dose. The goal of this paper is to obtain a representation for concentration as a function of time and dose, which (a) makes no assumptions on the underlying pharmacokinetics of the drug; (b) takes into account the repeated measure structure of the data; and (c) detects nonlinearities in respect to dose. To address (a) we use a multivariate adaptive regression splines representation (MARS), which we recast into a linear mixed-effects model, addressing (b). To detect nonlinearity we describe a general algorithm that obtains nested (mixed-effect) MARS representations. In the pharmacokinetics application, the algorithm obtains representations containing time, and time and dose, respectively, with the property that the bases functions of the first representation are a subset of the second. Standard statistical model selection criteria are used to select representations linear or nonlinear in respect to dose. The method can be applied to a variety of pharmacokinetics (and pharmacodynamic) preclinical and phase I-III trials. Examples of applications of the methodology to real and simulated data are reported.
Ventura, Cristina; Latino, Diogo A R S; Martins, Filomena
2013-01-01
The performance of two QSAR methodologies, namely Multiple Linear Regressions (MLR) and Neural Networks (NN), towards the modeling and prediction of antitubercular activity was evaluated and compared. A data set of 173 potentially active compounds belonging to the hydrazide family and represented by 96 descriptors was analyzed. Models were built with Multiple Linear Regressions (MLR), single Feed-Forward Neural Networks (FFNNs), ensembles of FFNNs and Associative Neural Networks (AsNNs) using four different data sets and different types of descriptors. The predictive ability of the different techniques used were assessed and discussed on the basis of different validation criteria and results show in general a better performance of AsNNs in terms of learning ability and prediction of antitubercular behaviors when compared with all other methods. MLR have, however, the advantage of pinpointing the most relevant molecular characteristics responsible for the behavior of these compounds against Mycobacterium tuberculosis. The best results for the larger data set (94 compounds in training set and 18 in test set) were obtained with AsNNs using seven descriptors (R(2) of 0.874 and RMSE of 0.437 against R(2) of 0.845 and RMSE of 0.472 in MLRs, for test set). Counter-Propagation Neural Networks (CPNNs) were trained with the same data sets and descriptors. From the scrutiny of the weight levels in each CPNN and the information retrieved from MLRs, a rational design of potentially active compounds was attempted. Two new compounds were synthesized and tested against M. tuberculosis showing an activity close to that predicted by the majority of the models.
2014-01-01
This systematic review aims to provide information about the implications of the movement-related cortical potential (MRCP) in acute and chronic responses to the counter resistance training. The structuring of the methods of this study followed the proposals of the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses). It was performed an electronically search in Pubmed/Medline and ISI Web of Knowledge data bases, from 1987 to 2013, besides the manual search in the selected references. The following terms were used: Bereitschaftspotential, MRCP, strength and force. The logical operator “AND” was used to combine descriptors and terms used to search publications. At the end, 11 studies attended all the eligibility criteria and the results demonstrated that the behavior of MRCP is altered because of different factors such as: force level, rate of force development, fatigue induced by exercise, and the specific phase of muscular action, leading to an increase in the amplitude in eccentric actions compared to concentric actions, in acute effects. The long-term adaptations demonstrated that the counter resistance training provokes an attenuation in the amplitude in areas related to the movement, which may be caused by neural adaptation occurred in the motor cortex. PMID:24602228
Modares, Hamidreza; Lewis, Frank L; Naghibi-Sistani, Mohammad-Bagher
2013-10-01
This paper presents an online policy iteration (PI) algorithm to learn the continuous-time optimal control solution for unknown constrained-input systems. The proposed PI algorithm is implemented on an actor-critic structure where two neural networks (NNs) are tuned online and simultaneously to generate the optimal bounded control policy. The requirement of complete knowledge of the system dynamics is obviated by employing a novel NN identifier in conjunction with the actor and critic NNs. It is shown how the identifier weights estimation error affects the convergence of the critic NN. A novel learning rule is developed to guarantee that the identifier weights converge to small neighborhoods of their ideal values exponentially fast. To provide an easy-to-check persistence of excitation condition, the experience replay technique is used. That is, recorded past experiences are used simultaneously with current data for the adaptation of the identifier weights. Stability of the whole system consisting of the actor, critic, system state, and system identifier is guaranteed while all three networks undergo adaptation. Convergence to a near-optimal control law is also shown. The effectiveness of the proposed method is illustrated with a simulation example. PMID:24808590
Lattari, Eduardo; Arias-Carrión, Oscar; Monteiro-Junior, Renato Sobral; Mello Portugal, Eduardo Matta; Paes, Flávia; Menéndez-González, Manuel; Silva, Adriana Cardoso; Nardi, Antonio Egidio; Machado, Sergio
2014-01-01
This systematic review aims to provide information about the implications of the movement-related cortical potential (MRCP) in acute and chronic responses to the counter resistance training. The structuring of the methods of this study followed the proposals of the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses). It was performed an electronically search in Pubmed/Medline and ISI Web of Knowledge data bases, from 1987 to 2013, besides the manual search in the selected references. The following terms were used: Bereitschaftspotential, MRCP, strength and force. The logical operator "AND" was used to combine descriptors and terms used to search publications. At the end, 11 studies attended all the eligibility criteria and the results demonstrated that the behavior of MRCP is altered because of different factors such as: force level, rate of force development, fatigue induced by exercise, and the specific phase of muscular action, leading to an increase in the amplitude in eccentric actions compared to concentric actions, in acute effects. The long-term adaptations demonstrated that the counter resistance training provokes an attenuation in the amplitude in areas related to the movement, which may be caused by neural adaptation occurred in the motor cortex. PMID:24602228
Adaptive critic neural network-based object grasping control using a three-finger gripper.
Jagannathan, S; Galan, Gustavo
2004-03-01
Grasping of objects has been a challenging task for robots. The complex grasping task can be defined as object contact control and manipulation subtasks. In this paper, object contact control subtask is defined as the ability to follow a trajectory accurately by the fingers of a gripper. The object manipulation subtask is defined in terms of maintaining a predefined applied force by the fingers on the object. A sophisticated controller is necessary since the process of grasping an object without a priori knowledge of the object's size, texture, softness, gripper, and contact dynamics is rather difficult. Moreover, the object has to be secured accurately and considerably fast without damaging it. Since the gripper, contact dynamics, and the object properties are not typically known beforehand, an adaptive critic neural network (NN)-based hybrid position/force control scheme is introduced. The feedforward action generating NN in the adaptive critic NN controller compensates the nonlinear gripper and contact dynamics. The learning of the action generating NN is performed on-line based on a critic NN output signal. The controller ensures that a three-finger gripper tracks a desired trajectory while applying desired forces on the object for manipulation. Novel NN weight tuning updates are derived for the action generating and critic NNs so that Lyapunov-based stability analysis can be shown. Simulation results demonstrate that the proposed scheme successfully allows fingers of a gripper to secure objects without the knowledge of the underlying gripper and contact dynamics of the object compared to conventional schemes.
Wang, Ying-Chung; Chien, Chiang-Ju; Teng, Ching-Cheng
2004-06-01
In this paper, a direct adaptive iterative learning control (DAILC) based on a new output-recurrent fuzzy neural network (ORFNN) is presented for a class of repeatable nonlinear systems with unknown nonlinearities and variable initial resetting errors. In order to overcome the design difficulty due to initial state errors at the beginning of each iteration, a concept of time-varying boundary layer is employed to construct an error equation. The learning controller is then designed by using the given ORFNN to approximate an optimal equivalent controller. Some auxiliary control components are applied to eliminate approximation error and ensure learning convergence. Since the optimal ORFNN parameters for a best approximation are generally unavailable, an adaptive algorithm with projection mechanism is derived to update all the consequent, premise, and recurrent parameters during iteration processes. Only one network is required to design the ORFNN-based DAILC and the plant nonlinearities, especially the nonlinear input gain, are allowed to be totally unknown. Based on a Lyapunov-like analysis, we show that all adjustable parameters and internal signals remain bounded for all iterations. Furthermore, the norm of state tracking error vector will asymptotically converge to a tunable residual set as iteration goes to infinity. Finally, iterative learning control of two nonlinear systems, inverted pendulum system and Chua's chaotic circuit, are performed to verify the tracking performance of the proposed learning scheme.
Linear-scaling symmetry-adapted perturbation theory with scaled dispersion
Maurer, Simon A.; Beer, Matthias; Lambrecht, Daniel S.; Ochsenfeld, Christian
2013-11-14
We present a linear-scaling symmetry-adapted perturbation theory (SAPT) method that is based on an atomic orbital (AO) formulation of zeroth-order SAPT (SAPT0). The non-dispersive terms are realized with linear-scaling cost using both the continuous fast multipole method (CFMM) and the linear exchange (LinK) approach for integral contractions as well as our efficient Laplace-based coupled-perturbed self-consistent field method (DL-CPSCF) for evaluating response densities. The reformulation of the dispersion term is based on our linear-scaling AO Møller-Plesset second-order perturbation theory (AO-MP2) method, that uses our recently introduced QQR-type screening [S. A. Maurer, D. S. Lambrecht, J. Kussmann, and C. Ochsenfeld, J. Chem. Phys. 138, 014101 (2013)] for preselecting numerically significant energy contributions. Similar to scaled opposite-spin MP2, we neglect the exchange-dispersion term in SAPT and introduce a scaling factor for the dispersion term, which compensates for the error and at the same time accounts for basis set incompleteness effects and intramonomer correlation. We show in extensive benchmark calculations that the new scaled-dispersion (sd-)SAPT0 approach provides reliable results for small and large interacting systems where the results with a small 6-31G** basis are roughly comparable to supermolecular MP2 calculations in a triple-zeta basis. The performance of our method is demonstrated with timings on cellulose fragments, DNA systems, and cutouts of a protein-ligand complex with up to 1100 atoms on a single computer core.
A covariance-adaptive approach for regularized inversion in linear models
NASA Astrophysics Data System (ADS)
Kotsakis, Christopher
2007-11-01
The optimal inversion of a linear model under the presence of additive random noise in the input data is a typical problem in many geodetic and geophysical applications. Various methods have been developed and applied for the solution of this problem, ranging from the classic principle of least-squares (LS) estimation to other more complex inversion techniques such as the Tikhonov-Philips regularization, truncated singular value decomposition, generalized ridge regression, numerical iterative methods (Landweber, conjugate gradient) and others. In this paper, a new type of optimal parameter estimator for the inversion of a linear model is presented. The proposed methodology is based on a linear transformation of the classic LS estimator and it satisfies two basic criteria. First, it provides a solution for the model parameters that is optimally fitted (in an average quadratic sense) to the classic LS parameter solution. Second, it complies with an external user-dependent constraint that specifies a priori the error covariance (CV) matrix of the estimated model parameters. The formulation of this constrained estimator offers a unified framework for the description of many regularization techniques that are systematically used in geodetic inverse problems, particularly for those methods that correspond to an eigenvalue filtering of the ill-conditioned normal matrix in the underlying linear model. Our study lies on the fact that it adds an alternative perspective on the statistical properties and the regularization mechanism of many inversion techniques commonly used in geodesy and geophysics, by interpreting them as a family of `CV-adaptive' parameter estimators that obey a common optimal criterion and differ only on the pre-selected form of their error CV matrix under a fixed model design.
NASA Technical Reports Server (NTRS)
Lo, Ching F.
1999-01-01
The integration of Radial Basis Function Networks and Back Propagation Neural Networks with the Multiple Linear Regression has been accomplished to map nonlinear response surfaces over a wide range of independent variables in the process of the Modem Design of Experiments. The integrated method is capable to estimate the precision intervals including confidence and predicted intervals. The power of the innovative method has been demonstrated by applying to a set of wind tunnel test data in construction of response surface and estimation of precision interval.
NASA Astrophysics Data System (ADS)
Lin, Cheng-Jian; Lee, Chi-Yung
2010-04-01
This article introduces a recurrent fuzzy neural network based on improved particle swarm optimisation (IPSO) for non-linear system control. An IPSO method which consists of the modified evolutionary direction operator (MEDO) and the Particle Swarm Optimisation (PSO) is proposed in this article. A MEDO combining the evolutionary direction operator and the migration operation is also proposed. The MEDO will improve the global search solution. Experimental results have shown that the proposed IPSO method controls the magnetic levitation system and the planetary train type inverted pendulum system better than the traditional PSO and the genetic algorithm methods.
NASA Astrophysics Data System (ADS)
Beritelli, Francesco; Capizzi, Giacomo; Lo Sciuto, Grazia; Napoli, Christian; Tramontana, Emiliano; Woźniak, Marcin
2015-09-01
Solving channel equalization problem in communication systems is based on adaptive filtering algorithms. Today, Mobile Agents (MAs) with Recurrent Neural Networks (RNNs) can be also adopted for effective interference reduction in modern wireless communication systems (WCSs). In this paper MAs with RNNs are proposed as novel computing algorithms for reducing interferences in WCSs performing an adaptive channel equalization. The method to provide it is so called MAs-RNNs. We perform the implementation of this new paradigm for interferences reduction. Simulations results and evaluations demonstrates the effectiveness of this approach and as better transmission performance in wireless communication network can be achieved by using the MAs-RNNs based adaptive filtering algorithm.
Neural network modeling of nonlinear systems based on Volterra series extension of a linear model
NASA Technical Reports Server (NTRS)
Soloway, Donald I.; Bialasiewicz, Jan T.
1992-01-01
A Volterra series approach was applied to the identification of nonlinear systems which are described by a neural network model. A procedure is outlined by which a mathematical model can be developed from experimental data obtained from the network structure. Applications of the results to the control of robotic systems are discussed.
Taravat, Alireza; Oppelt, Natascha
2014-12-02
Oil spills represent a major threat to ocean ecosystems and their environmental status. Previous studies have shown that Synthetic Aperture Radar (SAR), as its recording is independent of clouds and weather, can be effectively used for the detection and classification of oil spills. Dark formation detection is the first and critical stage in oil-spill detection procedures. In this paper, a novel approach for automated dark-spot detection in SAR imagery is presented. A new approach from the combination of adaptive Weibull Multiplicative Model (WMM) and MultiLayer Perceptron (MLP) neural networks is proposed to differentiate between dark spots and the background. The results have been compared with the results of a model combining non-adaptive WMM and pulse coupled neural networks. The presented approach overcomes the non-adaptive WMM filter setting parameters by developing an adaptive WMM model which is a step ahead towards a full automatic dark spot detection. The proposed approach was tested on 60 ENVISAT and ERS2 images which contained dark spots. For the overall dataset, an average accuracy of 94.65% was obtained. Our experimental results demonstrate that the proposed approach is very robust and effective where the non-adaptive WMM & pulse coupled neural network (PCNN) model generates poor accuracies.
Taravat, Alireza; Oppelt, Natascha
2014-01-01
Oil spills represent a major threat to ocean ecosystems and their environmental status. Previous studies have shown that Synthetic Aperture Radar (SAR), as its recording is independent of clouds and weather, can be effectively used for the detection and classification of oil spills. Dark formation detection is the first and critical stage in oil-spill detection procedures. In this paper, a novel approach for automated dark-spot detection in SAR imagery is presented. A new approach from the combination of adaptive Weibull Multiplicative Model (WMM) and MultiLayer Perceptron (MLP) neural networks is proposed to differentiate between dark spots and the background. The results have been compared with the results of a model combining non-adaptive WMM and pulse coupled neural networks. The presented approach overcomes the non-adaptive WMM filter setting parameters by developing an adaptive WMM model which is a step ahead towards a full automatic dark spot detection. The proposed approach was tested on 60 ENVISAT and ERS2 images which contained dark spots. For the overall dataset, an average accuracy of 94.65% was obtained. Our experimental results demonstrate that the proposed approach is very robust and effective where the non-adaptive WMM & pulse coupled neural network (PCNN) model generates poor accuracies. PMID:25474376
Rehault, Julien; Helbing, Jan; Zanirato, Vinicio; Olivucci, Massimo
2011-03-28
We demonstrate strong amplification of polarization-sensitive transient IR signals using a pseudo-null crossed polarizer technique first proposed by Keston and Lospalluto [Fed. Proc. 10, 207 (1951)] and applied for nanosecond flash photolysis in the visible by Che et al. [Chem. Phys. Lett. 224, 145 (1994)]. We adapted the technique to ultrafast pulsed laser spectroscopy in the infrared using photoelastic modulators, which allow us to measure amplified linear dichroism at kilohertz repetition rates. The method was applied to a photoswitch of the N-alkylated Schiff base family in order to demonstrate its potential of strongly enhancing sensitivity and signal to noise in ultrafast transient IR experiments, to simplify spectra and to determine intramolecular transition dipole orientations.
Adaptive output feedback consensus tracking for linear multi-agent systems with unknown dynamics
NASA Astrophysics Data System (ADS)
Sun, Junyong; Geng, Zhiyong
2015-09-01
In this paper, the consensus tracking problem with unknown dynamics in the leader for the linear multi-agent systems is addressed. Based on the relative output information among the agents, decentralised adaptive consensus protocols with static coupling gains are designed to guarantee that the consensus tracking errors converge to a small neighbourhood around the origin and all the signals in the closed-loop dynamics are uniformly ultimately bounded. Moreover, the result is extended to the case with dynamic coupling gains which are independent of the eigenvalues of the Laplacian matrix. Both of the protocols with static and dynamic coupling gains are designed by using the relative outputs, which are more practical than the state-feedback ones. Finally, the theoretical results are verified through an example.
NASA Astrophysics Data System (ADS)
Adamowski, Jan; Fung Chan, Hiu; Prasher, Shiv O.; Ozga-Zielinski, Bogdan; Sliusarieva, Anna
2012-01-01
Daily water demand forecasts are an important component of cost-effective and sustainable management and optimization of urban water supply systems. In this study, a method based on coupling discrete wavelet transforms (WA) and artificial neural networks (ANNs) for urban water demand forecasting applications is proposed and tested. Multiple linear regression (MLR), multiple nonlinear regression (MNLR), autoregressive integrated moving average (ARIMA), ANN and WA-ANN models for urban water demand forecasting at lead times of one day for the summer months (May to August) were developed, and their relative performance was compared using the coefficient of determination, root mean square error, relative root mean square error, and efficiency index. The key variables used to develop and validate the models were daily total precipitation, daily maximum temperature, and daily water demand data from 2001 to 2009 in the city of Montreal, Canada. The WA-ANN models were found to provide more accurate urban water demand forecasts than the MLR, MNLR, ARIMA, and ANN models. The results of this study indicate that coupled wavelet-neural network models are a potentially promising new method of urban water demand forecasting that merit further study.
Optimization of an adaptive SPECT system with the scanning linear estimator
NASA Astrophysics Data System (ADS)
Ghanbari, Nasrin; Clarkson, Eric; Kupinski, Matthew A.; Li, Xin
2015-08-01
The adaptive single-photon emission computed tomography (SPECT) system studied here acquires an initial scout image to obtain preliminary information about the object. Then the configuration is adjusted by selecting the size of the pinhole and the magnification that optimize system performance on an ensemble of virtual objects generated to be consistent with the scout data. In this study the object is a lumpy background that contains a Gaussian signal with a variable width and amplitude. The virtual objects in the ensemble are imaged by all of the available configurations and the subsequent images are evaluated with the scanning linear estimator to obtain an estimate of the signal width and amplitude. The ensemble mean squared error (EMSE) on the virtual ensemble between the estimated and the true parameters serves as the performance figure of merit for selecting the optimum configuration. The results indicate that variability in the original object background, noise and signal parameters leads to a specific optimum configuration in each case. A statistical study carried out for a number of objects show that the adaptive system on average performs better than its nonadaptive counterpart.
Wong, H S; Guan, L
2001-01-01
We address the problem of adaptive regularization in image restoration by adopting a neural-network learning approach. Instead of explicitly specifying the local regularization parameter values, they are regarded as network weights which are then modified through the supply of appropriate training examples. The desired response of the network is in the form of a gray level value estimate of the current pixel using weighted order statistic (WOS) filter. However, instead of replacing the previous value with this estimate, this is used to modify the network weights, or equivalently, the regularization parameters such that the restored gray level value produced by the network is closer to this desired response. In this way, the single WOS estimation scheme can allow appropriate parameter values to emerge under different noise conditions, rather than requiring their explicit selection in each occasion. In addition, we also consider the separate regularization of edges and textures due to their different noise masking capabilities. This in turn requires discriminating between these two feature types. Due to the inability of conventional local variance measures to distinguish these two high variance features, we propose the new edge-texture characterization (ETC) measure which performs this discrimination based on a scalar value only. This is then incorporated into a fuzzified form of the previous neural network which determines the degree of membership of each high variance pixel in two fuzzy sets, the EDGE and TEXTURE fuzzy sets, from the local ETC value, and then evaluates the appropriate regularization parameter by appropriately combining these two membership function values.
Adaptive pattern recognition by mini-max neural networks as a part of an intelligent processor
NASA Technical Reports Server (NTRS)
Szu, Harold H.
1990-01-01
In this decade and progressing into 21st Century, NASA will have missions including Space Station and the Earth related Planet Sciences. To support these missions, a high degree of sophistication in machine automation and an increasing amount of data processing throughput rate are necessary. Meeting these challenges requires intelligent machines, designed to support the necessary automations in a remote space and hazardous environment. There are two approaches to designing these intelligent machines. One of these is the knowledge-based expert system approach, namely AI. The other is a non-rule approach based on parallel and distributed computing for adaptive fault-tolerances, namely Neural or Natural Intelligence (NI). The union of AI and NI is the solution to the problem stated above. The NI segment of this unit extracts features automatically by applying Cauchy simulated annealing to a mini-max cost energy function. The feature discovered by NI can then be passed to the AI system for future processing, and vice versa. This passing increases reliability, for AI can follow the NI formulated algorithm exactly, and can provide the context knowledge base as the constraints of neurocomputing. The mini-max cost function that solves the unknown feature can furthermore give us a top-down architectural design of neural networks by means of Taylor series expansion of the cost function. A typical mini-max cost function consists of the sample variance of each class in the numerator, and separation of the center of each class in the denominator. Thus, when the total cost energy is minimized, the conflicting goals of intraclass clustering and interclass segregation are achieved simultaneously.
Neuroplasticity in dynamic neural networks comprised of neurons attached to adaptive base plate.
Joghataie, Abdolreza; Shafiei Dizaji, Mehrdad
2016-03-01
In this paper, a learning algorithm is developed for Dynamic Plastic Continuous Neural Networks (DPCNNs) to improve their learning of highly nonlinear time dependent problems. A DPCNN is comprised of a base medium, which is nonlinear and plastic, and a number of neurons that are attached to the base by wire-like connections similar to perceptrons. The information is distributed within DPCNNs gradually and through wave propagation mechanism. While a DPCNN is adaptive due to its connection weights, the material properties of its base medium can also be adjusted to improve its learning. The material of the medium is plastic and can contribute to memorizing the history of input-response similar to neuroplasticity in natural brain. The results obtained from numerical simulation of DPCNNs have been encouraging. Nonlinear plastic finite element modeling has been used for numerical simulation of dynamic behavior and wave propagation in the medium. Two significant differences of DPCNNs with other types of neural networks are that: (1) there is a medium to which the neurons are attached where the medium can contribute to the learning, (2) the input layer is not made of nodes but it is an edge terminal which is capable of receiving a continuous function over the input edge, though it is discretized in the finite element model. A DPCNN is reduced to a perceptron if the medium is removed and the neurons are connected to each other only by wires. Continuity of the input lets the discretization of data take place intrinsically within the DPCNN instead of being applied by the user.
Linearity enhancement of TVGA based on adaptive sweep optimisation in monostatic radar receiver
NASA Astrophysics Data System (ADS)
Almslmany, Amir; Wang, Caiyun; Cao, Qunsheng
2016-08-01
The limited input dynamic power range of the radar receiver and the power loss due to the targets' ranges are two potential problems in the radar receivers. This paper proposes a model based on the time-varying gain amplifier (TVGA) to compensate the power loss from the targets' ranges, and using the negative impedance compensation technique to enhance the TVGA linearity based on Volterra series. The simulation has been done based on adaptive sweep optimisation (ASO) using advanced design system (ADS) and Matlab. It shows that the suppression of the third-order intermodulation products (IMR3) was carried out for two-tone test, the high-gain accuracy improved by 3 dB, and the high linearity IMR3 improved by 14 dB. The monostatic radar system was tested to detect three targets at different ranges and to compare its probability of detection with the prior models; the results show that the probability of detection has been increased for ASO/TVGA.
NASA Astrophysics Data System (ADS)
Fazlyab, Ali Reza; Fani Saberi, Farhad; Kabganian, Mansour
2016-01-01
In this paper, an adaptive attitude control algorithm is developed based on neural network for a satellite. The proposed attitude control is based on nonlinear modified Rodrigues parameters feedback control in the presence of unknown terms like external disturbances and actuator faults. In order to eliminate the effect of the uncertainties, a multilayer neural network with a new learning rule will be designed appropriately. In this method, asymptotic stability of the proposed algorithm has been proven in the presence of unknown terms based on Lyapunov stability theorem. Finally, the performance of the designed attitude controller is investigated by simulations.
Entry Abort Determination Using Non-Adaptive Neural Networks for Mars Precision Landers
NASA Technical Reports Server (NTRS)
Graybeal, Sarah R.; Kranzusch, Kara M.
2005-01-01
The 2009 Mars Science Laboratory (MSL) will attempt the first precision landing on Mars using a modified version of the Apollo Earth entry guidance program. The guidance routine, Entry Terminal Point Controller (ETPC), commands the deployment of a supersonic parachute after converging the range to the landing target. For very dispersed cases, ETPC may not converge the range to the target and safely command parachute deployment within Mach number and dynamic pressure constraints. A full-lift up abort can save 85% of these failed trajectories while abandoning the precision landing objective. Though current MSL requirements do not call for an abort capability, an autonomous abort capability may be desired, for this mission or future Mars precision landers, to make the vehicle more robust. The application of artificial neural networks (NNs) as an abort determination technique was evaluated by personnel at the National Aeronautics and Space Administration (NASA) Johnson Space Center (JSC). In order to implement an abort, a failed trajectory needs to be recognized in real time. Abort determination is dependent upon several trajectory parameters whose relationships to vehicle survival are not well understood, and yet the lander must be trained to recognize unsafe situations. Artificial neural networks (NNs) provide a way to model these parameters and can provide MSL with the artificial intelligence necessary to independently declare an abort. Using the 2009 Mars Science Laboratory (MSL) mission as a case study, a non-adaptive NN was designed, trained and tested using Monte Carlo simulations of MSL descent and incorporated into ETPC. Neural network theory, the development history of the MSL NN, and initial testing with severe dust storm entry trajectory cases are discussed in Reference 1 and will not be repeated here. That analysis demonstrated that NNs are capable of recognizing failed descent trajectories and can significantly increase the survivability of MSL for very
NASA Astrophysics Data System (ADS)
Chen, Qiang; Ren, Xuemei; Oliver, Jesus Angel
2012-04-01
In this paper, an identifier-based adaptive neural dynamic surface control (IANDSC) is proposed for the uncertain DC-DC buck converter system with input constraint. Based on the analysis of the effect of input constraint in the buck converter, the neural network compensator is employed to ensure the controller output within the permissible range. Subsequently, the constrained adaptive control scheme combined with the neural network compensator is developed for the buck converter with uncertain load current. In this scheme, a newly presented finite-time identifier is utilized to accelerate the parameter tuning process and to heighten the accuracy of parameter estimation. By utilizing the adaptive dynamic surface control (ADSC) technique, the problem of "explosion of complexity" inherently in the traditional adaptive backstepping design can be overcome. The proposed control law can guarantee the uniformly ultimate boundedness of all signals in the closed-loop system via Lyapunov synthesis. Numerical simulations are provided to illustrate the effectiveness of the proposed control method.
The co-adaptive neural network approach to the Euclidean Travelling Salesman Problem.
Cochrane, E M; Beasley, J E
2003-12-01
In this paper we consider the Euclidean Travelling Salesman Problem (ETSP). This is the problem of finding the shortest tour around a number of cities where the cities correspond to points in the Euclidean plane and the distances between cities are given by the usual Euclidean distance metric. We present a review of the literature with respect to neural network (NN) approaches for the ETSP, and the computational results that have been reported. Based upon this review we highlight two areas that are, in our judgement, currently neglected/lacking in the literature. These are: failure to make significant use of publicly available ETSP test problems in computational work, failure to address co-operation between neurons. Drawing upon our literature survey this paper presents a new Self-Organising NN approach, called the Co-Adaptive Net, which involves not just unsupervised learning to train neurons, but also allows neurons to co-operate and compete amongst themselves depending on their situation. Our Co-Adaptive Net algorithm also includes a number of algorithmic mechanisms that, based upon our literature review, we consider to have contributed to the computational success of previous algorithms. Results for 91 publicly available standard ETSP's are presented in this paper. The largest of these problems involves 85,900 cities. This paper presents: the most extensive computational evaluation of any NN approach on publicly available ETSP test problems that has been made to date in the literature, a NN approach that performs better, with respect to solution quality and/or computation time, than other NN approaches given previously in the literature. Drawing upon computational results produced as a result of the DIMACS TSP Challenge, we highlight the fact that none of the current NN approaches for the ETSP can compete with state of the art Operations Research heuristics. We discuss why we consider continuing to study and develop NN approaches for the ETSP to be of value.
An indirect adaptive neural control of a visual-based quadrotor robot for pursuing a moving target.
Shirzadeh, Masoud; Amirkhani, Abdollah; Jalali, Aliakbar; Mosavi, Mohammad R
2015-11-01
This paper aims to use a visual-based control mechanism to control a quadrotor type aerial robot which is in pursuit of a moving target. The nonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks and other similar approaches. In addition to the two mentioned problems, another problem that emerges due to the moving nature of a target is the uncertainty that exists in the target image. By employing an artificial neural network with a Radial Basis Function (RBF) an indirect adaptive neural controller has been designed for a quadrotor robot in search of a moving target. The results of the simulation for different paths show that the quadrotor has efficiently tracked the moving target.
NASA Astrophysics Data System (ADS)
Wang, H.; Wang, D.; Peng, Z. H.
2016-01-01
This paper addresses the cooperative path-following problem of multiple marine surface vehicles subject to dynamical uncertainties and ocean disturbances induced by unknown wind, wave and ocean current. The control design falls neatly into two parts. One is to steer individual marine surface vehicle to track a predefined path and the other is to synchronise the along-path speed and path variables under the constraints of an underlying communication network. Within these two formulations, a robust adaptive path-following controller is first designed for individual vehicles based on backstepping and neural network techniques. Then, a decentralised synchronisation control law is derived by means of consensus on along-path speed and path variables based on graph theory. The distinct feature of this design lies in that synchronised path following can be reached for any undirected connected communication graphs without accurate knowledge of the model. This result is further extended to the output feedback case, where an observer-based cooperative path-following controller is developed without measuring the velocity of each vehicle. For both designs, rigorous theoretical analysis demonstrate that all signals in the closed-loop system are semi-global uniformly ultimately bounded. Simulation results validate the performance and robustness improvement of the proposed strategy.
Pedestrian tracking and navigation using an adaptive knowledge system based on neural networks
NASA Astrophysics Data System (ADS)
Grejner-Brzezinska, Dorota A.; Toth, Charles; Moafipoor, Shahram
2007-11-01
The primary objective of the research presented here is to develop theoretical foundations and implementation algorithms, which integrate the Global Positioning System (GPS), micro-electromechanical inertial measurement unit (MEMS IMU), digital barometer, electronic compass, and human pedometry to provide navigation and tracking of military and rescue ground personnel. This paper discusses the design, implementation and the performance analyses of the personal navigator prototype, with a special emphasis on dead-reckoning (DR) navigation supported by the human locomotion model. The adaptive knowledge system, based on the Artificial Neural Networks (ANN), is implemented to support this functionality. The knowledge system is trained during the GPS signal reception and is used to support navigation under GPS-denied conditions. The human locomotion parameters, step frequency (SF) and step length (SL), are extracted from GPS-timed impact switches (step frequency) and GPS/IMU data (step length), respectively, during the system calibration period. SL is correlated with several data types, such as acceleration, acceleration variation, SF, terrain slope, etc. that constitute the input parameters to the ANN-based knowledge system. The ANN-predicted SL, together with the heading information from the compass and gyro, support DR navigation. The current target accuracy of the system is 3-5 m CEP (circular error probable) 50%.
Walsh, Matthew M; Anderson, John R
2012-09-01
To behave adaptively, we must learn from the consequences of our actions. Studies using event-related potentials (ERPs) have been informative with respect to the question of how such learning occurs. These studies have revealed a frontocentral negativity termed the feedback-related negativity (FRN) that appears after negative feedback. According to one prominent theory, the FRN tracks the difference between the values of actual and expected outcomes, or reward prediction errors. As such, the FRN provides a tool for studying reward valuation and decision making. We begin this review by examining the neural significance of the FRN. We then examine its functional significance. To understand the cognitive processes that occur when the FRN is generated, we explore variables that influence its appearance and amplitude. Specifically, we evaluate four hypotheses: (1) the FRN encodes a quantitative reward prediction error; (2) the FRN is evoked by outcomes and by stimuli that predict outcomes; (3) the FRN and behavior change with experience; and (4) the system that produces the FRN is maximally engaged by volitional actions.
NASA Astrophysics Data System (ADS)
Zhao, Shitie; Gao, Xianwen
2016-08-01
A robust adaptive control is proposed for a class of single-input single-output non-affine nonlinear systems. In order to approximate the unknown nonlinear function, a novel affine-type neural network is used, and then to compensate the approximation error and external disturbance a robust control term is employed. By Lyapunov stability analysis for the closed-loop system, it is proved that tracking errors asymptotically converge to zero. Moreover, an observer is designed to estimate the system states because all the states may not be available for measurements. Furthermore, the adaptation laws of neural networks and the robust controller are given out based on the Lyapunov stability theory. Finally, two simulation examples are presented to demonstrate the effectiveness of the proposed control method.
NASA Astrophysics Data System (ADS)
Xu, Bin; Sun, Fuchun; Yang, Chenguang; Gao, Daoxiang; Ren, Jianxin
2011-09-01
In this article, the adaptive neural controller in discrete time is investigated for the longitudinal dynamics of a generic hypersonic flight vehicle. The dynamics are decomposed into the altitude subsystem and the velocity subsystem. The altitude subsystem is transformed into the strict-feedback form from which the discrete-time model is derived by the first-order Taylor expansion. The virtual control is designed with nominal feedback and neural network (NN) approximation via back-stepping. Meanwhile, one adaptive NN controller is designed for the velocity subsystem. To avoid the circular construction problem in the practical control, the design of coefficients adopts the upper bound instead of the nominal value. Under the proposed controller, the semiglobal uniform ultimate boundedness stability is guaranteed. The square and step responses are presented in the simulation studies to show the effectiveness of the proposed control approach.
NASA Astrophysics Data System (ADS)
Bu, Xiangwei; Wu, Xiaoyan; He, Guangjun; Huang, Jiaqi
2016-03-01
This paper investigates the design of a novel adaptive neural controller for the longitudinal dynamics of a flexible air-breathing hypersonic vehicle with control input constraints. To reduce the complexity of controller design, the vehicle dynamics is decomposed into the velocity subsystem and the altitude subsystem, respectively. For each subsystem, only one neural network is utilized to approach the lumped unknown function. By employing a minimal-learning parameter method to estimate the norm of ideal weight vectors rather than their elements, there are only two adaptive parameters required for neural approximation. Thus, the computational burden is lower than the ones derived from neural back-stepping schemes. Specially, to deal with the control input constraints, additional systems are exploited to compensate the actuators. Lyapunov synthesis proves that all the closed-loop signals involved are uniformly ultimately bounded. Finally, simulation results show that the adopted compensation scheme can tackle actuator constraint effectively and moreover velocity and altitude can stably track their reference trajectories even when the physical limitations on control inputs are in effect.
NASA Astrophysics Data System (ADS)
Wang, Chongchong; Wang, Yukun; Hu, Lifa; Wang, Shaoxin; Cao, Zhaoliang; Mu, Quanquan; Li, Dayu; Yang, Chengliang; Xuan, Li
2016-05-01
The intrinsic hysteresis nonlinearity of the piezo-actuators can severely degrade the positioning accuracy of a tip-tilt mirror (TTM) in an adaptive optics system. This paper focuses on compensating this hysteresis nonlinearity by feed-forward linearization with an inverse hysteresis model. This inverse hysteresis model is based on the classical Presiach model, and the neural network (NN) is used to describe the hysteresis loop. In order to apply it in the real-time adaptive correction, an analytical nonlinear function derived from the NN is introduced to compute the inverse hysteresis model output instead of the time-consuming NN simulation process. Experimental results show that the proposed method effectively linearized the TTM behavior with the static hysteresis nonlinearity of TTM reducing from 15.6% to 1.4%. In addition, the tip-tilt tracking experiments using the integrator with and without hysteresis compensation are conducted. The wavefront tip-tilt aberration rejection ability of the TTM control system is significantly improved with the -3 dB error rejection bandwidth increasing from 46 to 62 Hz.
NASA Astrophysics Data System (ADS)
Kun, David William
Unmanned aircraft systems (UASs) are gaining popularity in civil and commercial applications as their lightweight on-board computers become more powerful and affordable, their power storage devices improve, and the Federal Aviation Administration addresses the legal and safety concerns of integrating UASs in the national airspace. Consequently, many researchers are pursuing novel methods to control UASs in order to improve their capabilities, dependability, and safety assurance. The nonlinear control approach is a common choice as it offers several benefits for these highly nonlinear aerospace systems (e.g., the quadrotor). First, the controller design is physically intuitive and is derived from well known dynamic equations. Second, the final control law is valid in a larger region of operation, including far from the equilibrium states. And third, the procedure is largely methodical, requiring less expertise with gain tuning, which can be arduous for a novice engineer. Considering these facts, this thesis proposes a nonlinear controller design method that combines the advantages of adaptive robust control (ARC) with the powerful design tools of linear matrix inequalities (LMI). The ARC-LMI controller is designed with a discontinuous projection-based adaptation law, and guarantees a prescribed transient and steady state tracking performance for uncertain systems in the presence of matched disturbances. The norm of the tracking error is bounded by a known function that depends on the controller design parameters in a known form. Furthermore, the LMI-based part of the controller ensures the stability of the system while overcoming polytopic uncertainties, and minimizes the control effort. This can reduce the number of parameters that require adaptation, and helps to avoid control input saturation. These desirable characteristics make the ARC-LMI control algorithm well suited for the quadrotor UAS, which may have unknown parameters and may encounter external
Uhrig, R.E.; Emrich, M.L.
1990-01-01
The topics covered in this report are: Learning, Memory, and Artificial Neural Systems; Emerging Neural Network Technology; Neural Networks; Digital Signal Processing and Neural Networks; Application of Neural Networks to In-Core Fuel Management; Neural Networks in Process Control; Neural Network Applications in Image Processing; Neural Networks for Multi-Sensor Information Fusion; Neural Network Research in Instruments Controls Division; Neural Networks Research in the ORNL Engineering Physics and Mathematics Division; Neural Network Applications for Linear Programming; Neural Network Applications to Signal Processing and Diagnostics; Neural Networks in Filtering and Control; Neural Network Research at Tennessee Technological University; and Global Minima within the Hopfield Hypercube.
Jahandideh, Sepideh Jahandideh, Samad; Asadabadi, Ebrahim Barzegari; Askarian, Mehrdad; Movahedi, Mohammad Mehdi; Hosseini, Somayyeh; Jahandideh, Mina
2009-11-15
Prediction of the amount of hospital waste production will be helpful in the storage, transportation and disposal of hospital waste management. Based on this fact, two predictor models including artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. In this study, a 5-fold cross-validation procedure on a database containing total of 50 hospitals of Fars province (Iran) were used to verify the performance of the models. Three performance measures including MAR, RMSE and R{sup 2} were used to evaluate performance of models. The MLR as a conventional model obtained poor prediction performance measure values. However, MLR distinguished hospital capacity and bed occupancy as more significant parameters. On the other hand, ANNs as a more powerful model, which has not been introduced in predicting rate of medical waste generation, showed high performance measure values, especially 0.99 value of R{sup 2} confirming the good fit of the data. Such satisfactory results could be attributed to the non-linear nature of ANNs in problem solving which provides the opportunity for relating independent variables to dependent ones non-linearly. In conclusion, the obtained results showed that our ANN-based model approach is very promising and may play a useful role in developing a better cost-effective strategy for waste management in future.
Adaptive tracking control of leader-following linear multi-agent systems with external disturbances
NASA Astrophysics Data System (ADS)
Lin, Hanquan; Wei, Qinglai; Liu, Derong; Ma, Hongwen
2016-10-01
In this paper, the consensus problem for leader-following linear multi-agent systems with external disturbances is investigated. Brownian motions are used to describe exogenous disturbances. A distributed tracking controller based on Riccati inequalities with an adaptive law for adjusting coupling weights between neighbouring agents is designed for leader-following multi-agent systems under fixed and switching topologies. In traditional distributed static controllers, the coupling weights depend on the communication graph. However, coupling weights associated with the feedback gain matrix in our method are updated by state errors between neighbouring agents. We further present the stability analysis of leader-following multi-agent systems with stochastic disturbances under switching topology. Most traditional literature requires the graph to be connected all the time, while the communication graph is only assumed to be jointly connected in this paper. The design technique is based on Riccati inequalities and algebraic graph theory. Finally, simulations are given to show the validity of our method.
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.
Signal processing with neural networks: throwing off the yoke of linearity
NASA Astrophysics Data System (ADS)
Hecht-Nielsen, Robert
1991-11-01
During the 1930s and 1940s Norbert Wiener and others invented the core concepts of linear signal processing. These ideas quickly became popular and played a significant role in the Allies' victory in World War II. During and after the war, linear signal processing theory was greatly expanded and began to take on the character of an imposing monolith. By the mid- 1940s, Wiener (and others, such as Dennis Gabor) came to recognize that linear signal processing theory, while interesting and very useful, was only a piece of a much larger picture. In 1946 and 1958 Gabor and Wiener, respectively, attempted to address the whole picture. While they were not completely successful, they did implicitly set an agenda for a more general approach to signal processing. Although a few others have, from time to time, addressed this agenda; in terms of the signal processing community as a whole it still remains lost in the shadow of the ever-growing monolith of linear signal processing theory. The thesis of this paper is that it is now time to get on with the Wiener and Gabor agenda. It is time to make general signal processing the mainstream focus of the subject. It is argued here that the best way to do this is to abandon the transfer function/Fourier analysis/z-transform approach of the current linear signal processing regime and replace it with a much more natural intellectual framework for general signal processing--the framework offered by neurocomputing. A potential benefit of this refocusing of the field is that the detailed engineering might soon be left to machines, while human technologists will be able to concentrate on the art of signal sculpting.
NASA Astrophysics Data System (ADS)
dos Santos, T. S.; Mendes, D.; Torres, R. R.
2015-08-01
Several studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANN) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon, Northeastern Brazil and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model out- put and observed monthly precipitation. We used GCMs experiments for the 20th century (RCP Historical; 1970-1999) and two scenarios (RCP 2.6 and 8.5; 2070-2100). The model test results indicate that the ANN significantly outperforms the MLR downscaling of monthly precipitation variability.
NASA Astrophysics Data System (ADS)
Soares dos Santos, T.; Mendes, D.; Rodrigues Torres, R.
2016-01-01
Several studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANNs) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon; northeastern Brazil; and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model output and observed monthly precipitation. We used general circulation model (GCM) experiments for the 20th century (RCP historical; 1970-1999) and two scenarios (RCP 2.6 and 8.5; 2070-2100). The model test results indicate that the ANNs significantly outperform the MLR downscaling of monthly precipitation variability.
Misuse of Linear Models: Understanding Community Linkages in Family Adaptation to Unexpected Death.
ERIC Educational Resources Information Center
Murray, Colleen I.; Galligan, Richard J.
In research, the use of linear additive methods is expedient when prediction is the goal; however, when understanding is the goal, an exploration of non-linear multiplicative procedures is more appropriate. To compare the results of linear and non-linear models, data obtained from a survey of 35 bereaved mothers were compared using scattergrams,…
NASA Technical Reports Server (NTRS)
Kincaid, D. R.; Young, D. M.
1984-01-01
Adapting and designing mathematical software to achieve optimum performance on the CYBER 205 is discussed. Comments and observations are made in light of recent work done on modifying the ITPACK software package and on writing new software for vector supercomputers. The goal was to develop very efficient vector algorithms and software for solving large sparse linear systems using iterative methods.
Walther, Christian; Schweinberger, Stefan R; Kovács, Gyula
2013-01-01
Adaptation-related aftereffects (AEs) show how face perception can be altered by recent perceptual experiences. Along with contrastive behavioural biases, modulations of the early event-related potentials (ERPs) were typically reported on categorical levels. Nevertheless, the role of the adaptor stimulus per se for face identity-specific AEs is not completely understood and was therefore investigated in the present study. Participants were adapted to faces (S1s) varying systematically on a morphing continuum between pairs of famous identities (identities A and B), or to Fourier phase-randomized faces, and had to match the subsequently presented ambiguous faces (S2s; 50/50% identity A/B) to one of the respective original faces. We found that S1s identical with or near to the original identities led to strong contrastive biases with more identity B responses following A adaptation and vice versa. In addition, the closer S1s were to the 50/50% S2 on the morphing continuum, the smaller the magnitude of the AE was. The relation between S1s and AE was, however, not linear. Additionally, stronger AEs were accompanied by faster reaction times. Analyses of the simultaneously recorded ERPs revealed categorical adaptation effects starting at 100 ms post-stimulus onset, that were most pronounced at around 125-240 ms for occipito-temporal sites over both hemispheres. S1-specific amplitude modulations were found at around 300-400 ms. Response-specific analyses of ERPs showed reduced voltages starting at around 125 ms when the S1 biased perception in a contrastive way as compared to when it did not. Our results suggest that face identity AEs do not only depend on physical differences between S1 and S2, but also on perceptual factors, such as the ambiguity of S1. Furthermore, short-term plasticity of face identity processing might work in parallel to object-category processing, and is reflected in the first 400 ms of the ERP.
Walther, Christian; Schweinberger, Stefan R.; Kovács, Gyula
2013-01-01
Adaptation-related aftereffects (AEs) show how face perception can be altered by recent perceptual experiences. Along with contrastive behavioural biases, modulations of the early event-related potentials (ERPs) were typically reported on categorical levels. Nevertheless, the role of the adaptor stimulus per se for face identity-specific AEs is not completely understood and was therefore investigated in the present study. Participants were adapted to faces (S1s) varying systematically on a morphing continuum between pairs of famous identities (identities A and B), or to Fourier phase-randomized faces, and had to match the subsequently presented ambiguous faces (S2s; 50/50% identity A/B) to one of the respective original faces. We found that S1s identical with or near to the original identities led to strong contrastive biases with more identity B responses following A adaptation and vice versa. In addition, the closer S1s were to the 50/50% S2 on the morphing continuum, the smaller the magnitude of the AE was. The relation between S1s and AE was, however, not linear. Additionally, stronger AEs were accompanied by faster reaction times. Analyses of the simultaneously recorded ERPs revealed categorical adaptation effects starting at 100 ms post-stimulus onset, that were most pronounced at around 125–240 ms for occipito-temporal sites over both hemispheres. S1-specific amplitude modulations were found at around 300–400 ms. Response-specific analyses of ERPs showed reduced voltages starting at around 125 ms when the S1 biased perception in a contrastive way as compared to when it did not. Our results suggest that face identity AEs do not only depend on physical differences between S1 and S2, but also on perceptual factors, such as the ambiguity of S1. Furthermore, short-term plasticity of face identity processing might work in parallel to object-category processing, and is reflected in the first 400 ms of the ERP. PMID:23990908
An Adaptive Landscape Classification Procedure using Geoinformatics and Artificial Neural Networks
Coleman, Andre Michael
2008-06-01
The Adaptive Landscape Classification Procedure (ALCP), which links the advanced geospatial analysis capabilities of Geographic Information Systems (GISs) and Artificial Neural Networks (ANNs) and particularly Self-Organizing Maps (SOMs), is proposed as a method for establishing and reducing complex data relationships. Its adaptive and evolutionary capability is evaluated for situations where varying types of data can be combined to address different prediction and/or management needs such as hydrologic response, water quality, aquatic habitat, groundwater recharge, land use, instrumentation placement, and forecast scenarios. The research presented here documents and presents favorable results of a procedure that aims to be a powerful and flexible spatial data classifier that fuses the strengths of geoinformatics and the intelligence of SOMs to provide data patterns and spatial information for environmental managers and researchers. This research shows how evaluation and analysis of spatial and/or temporal patterns in the landscape can provide insight into complex ecological, hydrological, climatic, and other natural and anthropogenic-influenced processes. Certainly, environmental management and research within heterogeneous watersheds provide challenges for consistent evaluation and understanding of system functions. For instance, watersheds over a range of scales are likely to exhibit varying levels of diversity in their characteristics of climate, hydrology, physiography, ecology, and anthropogenic influence. Furthermore, it has become evident that understanding and analyzing these diverse systems can be difficult not only because of varying natural characteristics, but also because of the availability, quality, and variability of spatial and temporal data. Developments in geospatial technologies, however, are providing a wide range of relevant data, and in many cases, at a high temporal and spatial resolution. Such data resources can take the form of high
Neural Adaptations Associated with Interlimb Transfer in a Ballistic Wrist Flexion Task.
Ruddy, Kathy L; Rudolf, Anne K; Kalkman, Barbara; King, Maedbh; Daffertshofer, Andreas; Carroll, Timothy J; Carson, Richard G
2016-01-01
Cross education is the process whereby training of one limb gives rise to increases in the subsequent performance of its opposite counterpart. The execution of many unilateral tasks is associated with increased excitability of corticospinal projections from primary motor cortex (M1) to the opposite limb. It has been proposed that these effects are causally related. Our aim was to establish whether changes in corticospinal excitability (CSE) arising from prior training of the opposite limb determine levels of interlimb transfer. We used three vision conditions shown previously to modulate the excitability of corticospinal projections to the inactive (right) limb during wrist flexion movements performed by the training (left) limb. These were: (1) mirrored visual feedback of the training limb; (2) no visual feedback of either limb; and (3) visual feedback of the inactive limb. Training comprised 300 discrete, ballistic wrist flexion movements executed as rapidly as possible. Performance of the right limb on the same task was assessed prior to, at the mid point of, and following left limb training. There was no evidence that variations in the excitability of corticospinal projections (assessed by transcranial magnetic stimulation (TMS)) to the inactive limb were associated with, or predictive of, the extent of interlimb transfer that was expressed. There were however associations between alterations in muscle activation dynamics observed for the untrained limb, and the degree of positive transfer that arose from training of the opposite limb. The results suggest that the acute adaptations that mediate the bilateral performance gains realized through unilateral practice of this ballistic wrist flexion task are mediated by neural elements other than those within M1 that are recruited at rest by single-pulse TMS.
Neural Adaptations Associated with Interlimb Transfer in a Ballistic Wrist Flexion Task.
Ruddy, Kathy L; Rudolf, Anne K; Kalkman, Barbara; King, Maedbh; Daffertshofer, Andreas; Carroll, Timothy J; Carson, Richard G
2016-01-01
Cross education is the process whereby training of one limb gives rise to increases in the subsequent performance of its opposite counterpart. The execution of many unilateral tasks is associated with increased excitability of corticospinal projections from primary motor cortex (M1) to the opposite limb. It has been proposed that these effects are causally related. Our aim was to establish whether changes in corticospinal excitability (CSE) arising from prior training of the opposite limb determine levels of interlimb transfer. We used three vision conditions shown previously to modulate the excitability of corticospinal projections to the inactive (right) limb during wrist flexion movements performed by the training (left) limb. These were: (1) mirrored visual feedback of the training limb; (2) no visual feedback of either limb; and (3) visual feedback of the inactive limb. Training comprised 300 discrete, ballistic wrist flexion movements executed as rapidly as possible. Performance of the right limb on the same task was assessed prior to, at the mid point of, and following left limb training. There was no evidence that variations in the excitability of corticospinal projections (assessed by transcranial magnetic stimulation (TMS)) to the inactive limb were associated with, or predictive of, the extent of interlimb transfer that was expressed. There were however associations between alterations in muscle activation dynamics observed for the untrained limb, and the degree of positive transfer that arose from training of the opposite limb. The results suggest that the acute adaptations that mediate the bilateral performance gains realized through unilateral practice of this ballistic wrist flexion task are mediated by neural elements other than those within M1 that are recruited at rest by single-pulse TMS. PMID:27199722
NASA Astrophysics Data System (ADS)
Ahmadlou, M.; Delavar, M. R.; Tayyebi, A.; Shafizadeh-Moghadam, H.
2015-12-01
Land use change (LUC) models used for modelling urban growth are different in structure and performance. Local models divide the data into separate subsets and fit distinct models on each of the subsets. Non-parametric models are data driven and usually do not have a fixed model structure or model structure is unknown before the modelling process. On the other hand, global models perform modelling using all the available data. In addition, parametric models have a fixed structure before the modelling process and they are model driven. Since few studies have compared local non-parametric models with global parametric models, this study compares a local non-parametric model called multivariate adaptive regression spline (MARS), and a global parametric model called artificial neural network (ANN) to simulate urbanization in Mumbai, India. Both models determine the relationship between a dependent variable and multiple independent variables. We used receiver operating characteristic (ROC) to compare the power of the both models for simulating urbanization. Landsat images of 1991 (TM) and 2010 (ETM+) were used for modelling the urbanization process. The drivers considered for urbanization in this area were distance to urban areas, urban density, distance to roads, distance to water, distance to forest, distance to railway, distance to central business district, number of agricultural cells in a 7 by 7 neighbourhoods, and slope in 1991. The results showed that the area under the ROC curve for MARS and ANN was 94.77% and 95.36%, respectively. Thus, ANN performed slightly better than MARS to simulate urban areas in Mumbai, India.
Hybrid feedback feedforward: An efficient design of adaptive neural network control.
Pan, Yongping; Liu, Yiqi; Xu, Bin; Yu, Haoyong
2016-04-01
This paper presents an efficient hybrid feedback feedforward (HFF) adaptive approximation-based control (AAC) strategy for a class of uncertain Euler-Lagrange systems. The control structure includes a proportional-derivative (PD) control term in the feedback loop and a radial-basis-function (RBF) neural network (NN) in the feedforward loop, which mimics the human motor learning control mechanism. At the presence of discontinuous friction, a sigmoid-jump-function NN is incorporated to improve control performance. The major difference of the proposed HFF-AAC design from the traditional feedback AAC (FB-AAC) design is that only desired outputs, rather than both tracking errors and desired outputs, are applied as RBF-NN inputs. Yet, such a slight modification leads to several attractive properties of HFF-AAC, including the convenient choice of an approximation domain, the decrease of the number of RBF-NN inputs, and semiglobal practical asymptotic stability dominated by control gains. Compared with previous HFF-AAC approaches, the proposed approach possesses the following two distinctive features: (i) all above attractive properties are achieved by a much simpler control scheme; (ii) the bounds of plant uncertainties are not required to be known. Consequently, the proposed approach guarantees a minimum configuration of the control structure and a minimum requirement of plant knowledge for the AAC design, which leads to a sharp decrease of implementation cost in terms of hardware selection, algorithm realization and system debugging. Simulation results have demonstrated that the proposed HFF-AAC can perform as good as or even better than the traditional FB-AAC under much simpler control synthesis and much lower computational cost. PMID:26890657
Neural Adaptations Associated with Interlimb Transfer in a Ballistic Wrist Flexion Task
Ruddy, Kathy L.; Rudolf, Anne K.; Kalkman, Barbara; King, Maedbh; Daffertshofer, Andreas; Carroll, Timothy J.; Carson, Richard G.
2016-01-01
Cross education is the process whereby training of one limb gives rise to increases in the subsequent performance of its opposite counterpart. The execution of many unilateral tasks is associated with increased excitability of corticospinal projections from primary motor cortex (M1) to the opposite limb. It has been proposed that these effects are causally related. Our aim was to establish whether changes in corticospinal excitability (CSE) arising from prior training of the opposite limb determine levels of interlimb transfer. We used three vision conditions shown previously to modulate the excitability of corticospinal projections to the inactive (right) limb during wrist flexion movements performed by the training (left) limb. These were: (1) mirrored visual feedback of the training limb; (2) no visual feedback of either limb; and (3) visual feedback of the inactive limb. Training comprised 300 discrete, ballistic wrist flexion movements executed as rapidly as possible. Performance of the right limb on the same task was assessed prior to, at the mid point of, and following left limb training. There was no evidence that variations in the excitability of corticospinal projections (assessed by transcranial magnetic stimulation (TMS)) to the inactive limb were associated with, or predictive of, the extent of interlimb transfer that was expressed. There were however associations between alterations in muscle activation dynamics observed for the untrained limb, and the degree of positive transfer that arose from training of the opposite limb. The results suggest that the acute adaptations that mediate the bilateral performance gains realized through unilateral practice of this ballistic wrist flexion task are mediated by neural elements other than those within M1 that are recruited at rest by single-pulse TMS. PMID:27199722
Tran, Anh T K; Hyne, Ross V; Pablo, Fleur; Day, W Roy; Doble, P
2007-02-28
An artificial neural network (ANN) was employed to model the chromatographic response surface for the linear gradient separation of 10 herbicides that are commonly detected in storm run-off water in agricultural catchments. The herbicides (dicamba, simazine, 2,4-D, MCPA, triclopyr, atrazine, diuron, clomazone, bensulfuron-methyl and metolachlor) were separated using reverse phase high performance liquid chromatography and detected with a photodiode array detector. The ANN was trained using the pH of the mobile phase and the slope of the acetonitrile/water gradient as input variables. A total of nine experiments were required to generate sufficient data to train the ANN to accurately describe the retention times of each of the herbicides within a defined experimental space of mobile phase pH range 3.0-4.8 and linear gradient slope 1-4% acetonitrile/min. The modelled chromatographic response surface was then used to determine the optimum separation within the experimental space. This approach allowed the rapid determination of experimental conditions for baseline resolution of all 10 herbicides. Illustrative examples of determination of these components in Milli-Q water, Sydney mains water and natural water samples spiked at 0.5-1mug/L are shown. Recoveries were over 70% for solid-phase extraction using Waters Oasis((R)) HLB 6cm(3) cartridges.
An ice-templated, linearly aligned chitosan-alginate scaffold for neural tissue engineering.
Francis, Nicola L; Hunger, Philipp M; Donius, Amalie E; Riblett, Benjamin W; Zavaliangos, Antonios; Wegst, Ulrike G K; Wheatley, Margaret A
2013-12-01
Several strategies have been investigated to enhance axonal regeneration after spinal cord injury, however, the resulting growth can be random and disorganized. Bioengineered scaffolds provide a physical substrate for guidance of regenerating axons towards their targets, and can be produced by freeze casting. This technique involves the controlled directional solidification of an aqueous solution or suspension, resulting in a linearly aligned porous structure caused by ice templating. In this study, freeze casting was used to fabricate porous chitosan-alginate (C/A) scaffolds with longitudinally oriented channels. Chick dorsal root ganglia explants adhered to and extended neurites through the scaffold in parallel alignment with the channel direction. Surface adsorption of a polycation and laminin promoted significantly longer neurite growth than the uncoated scaffold (poly-L-ornithine + Laminin = 793.2 ± 187.2 μm; poly-L-lysine + Laminin = 768.7 ± 241.2 μm; uncoated scaffold = 22.52 ± 50.14 μm) (P < 0.001). The elastic modulus of the hydrated scaffold was determined to be 5.08 ± 0.61 kPa, comparable to reported spinal cord values. The present data suggested that this C/A scaffold is a promising candidate for use as a nerve guidance scaffold, because of its ability to support neuronal attachment and the linearly aligned growth of DRG neurites.
Mehri, M
2013-04-01
Application of appropriate models to approximate the performance function warrants more precise prediction and helps to make the best decisions in the poultry industry. This study reevaluated the factors affecting hatchability in laying hens from 29 to 56 wk of age. Twenty-eight data lines representing 4 inputs consisting of egg weight, eggshell thickness, egg sphericity, and yolk/albumin ratio and 1 output, hatchability, were obtained from the literature and used to train an artificial neural network (ANN). The prediction ability of ANN was compared with that of fuzzy logic to evaluate the fitness of these 2 methods. The models were compared using R(2), mean absolute deviation (MAD), mean squared error (MSE), mean absolute percentage error (MAPE), and bias. The developed model was used to assess the relative importance of each variable on the hatchability by calculating the variable sensitivity ratio. The statistical evaluations showed that the ANN-based model predicted hatchability more accurately than fuzzy logic. The ANN-based model had a higher determination of coefficient (R(2) = 0.99) and lower residual distribution (MAD = 0.005; MSE = 0.00004; MAPE = 0.732; bias = 0.0012) than fuzzy logic (R(2) = 0.87; MAD = 0.014; MSE = 0.0004; MAPE = 2.095; bias = 0.0046). The sensitivity analysis revealed that the most important variable in the ANN-based model of hatchability was egg weight (variable sensitivity ratio, VSR = 283.11), followed by yolk/albumin ratio (VSR = 113.16), eggshell thickness (VSR = 16.23), and egg sphericity (VSR = 3.63). The results of this research showed that the universal approximation capability of ANN made it a powerful tool to approximate complex functions such as hatchability in the incubation process.
NASA Astrophysics Data System (ADS)
Wang, Gang; Wang, Chaoli; Du, Qinghui; Cai, Xuan
2016-10-01
In this paper, we address the output consensus problem of tracking a desired trajectory for a group of second-order agents on a directed graph with a fixed topology. Each agent is modelled by a second-order non-linear system with unknown non-linear dynamics and unknown non-linear control gains. Only a subset of the agents is given access to the desired trajectory information directly. A distributed adaptive consensus protocol driving all agents to track the desired trajectory is presented using the backstepping technique and approximation technique of Fourier series (FSs). The FS structure is taken not only for tracking the non-linear dynamics but also the unknown portion in the controller design procedure, which can avoid virtual controllers containing the uncertain terms. Stability analysis and parameter convergence of the proposed algorithm are conducted based on the Lyapunov theory and the algebraic graph theory. It is also demonstrated that arbitrary small tracking errors can be achieved by appropriately choosing design parameters. Though the proposed work is applicable for second-order non-linear systems containing unknown non-linear control gains, the proposed controller design can be easily extended to higher-order non-linear systems containing unknown non-linear control gains. Simulation results show the effectiveness of the proposed schemes.
Hinder, Mark R; Carroll, Timothy J; Summers, Jeffery J
2013-06-01
Bilateral movement rehabilitation is gaining popularity as an approach to improve the recovery not only of bimanual function but also of unilateral motor tasks. While the neural mechanisms mediating the transfer of bilateral training gains into unimanual contexts are not fully understood, converging evidence from behavioral, neurophysiological, and imaging studies suggests that bimanual movements are not simply the superposition of unimanual tasks undertaken with both (upper) limbs. Here we investigated the neural responses in both hemispheres to bilateral ballistic motor training and the extent to which performance improvements transferred to a unimanual task. Since aging influences interhemispheric interactions during movement production, both young (n = 9; mean age 19.4 yr; 6 women, 3 men) and older (n = 9; 66.3 yr; 7 women, 2 men) adults practiced a bilateral motor task requiring simultaneous "fast-as-possible" abductions of their left and right index fingers. Changes in bilateral and unilateral performance, and in corticospinal excitability and intracortical inhibition, were assessed. Strong transfer was observed between bimanual and unimanual contexts for both age groups. However, in contrast to previous reports of substantial bilateral cortical adaptations following unilateral training, increases in corticospinal excitability following bilateral training were not statistically reliable, and a release of intracortical inhibition was only observed for older adults. The results indicate that the neural mechanisms of motor learning for bilateral ballistic tasks differ from those that underlie unimanual ballistic performance improvement but that aging results in a greater overlap of the neural mechanisms mediating bilateral and unilateral ballistic motor performance.
Nie, Xiaobing; Zheng, Wei Xing; Cao, Jinde
2015-11-01
The problem of coexistence and dynamical behaviors of multiple equilibrium points is addressed for a class of memristive Cohen-Grossberg neural networks with non-monotonic piecewise linear activation functions and time-varying delays. By virtue of the fixed point theorem, nonsmooth analysis theory and other analytical tools, some sufficient conditions are established to guarantee that such n-dimensional memristive Cohen-Grossberg neural networks can have 5(n) equilibrium points, among which 3(n) equilibrium points are locally exponentially stable. It is shown that greater storage capacity can be achieved by neural networks with the non-monotonic activation functions introduced herein than the ones with Mexican-hat-type activation function. In addition, unlike most existing multistability results of neural networks with monotonic activation functions, those obtained 3(n) locally stable equilibrium points are located both in saturated regions and unsaturated regions. The theoretical findings are verified by an illustrative example with computer simulations.
NASA Astrophysics Data System (ADS)
Kajiwara, Yoshiyuki; Shiraishi, Junya; Kobayashi, Shoei; Yamagami, Tamotsu
2009-03-01
A digital phase-locked loop (PLL) with a linearly constrained adaptive filter (LCAF) has been studied for higher-linear-density optical discs. LCAF has been implemented before an interpolated timing recovery (ITR) PLL unit in order to improve the quality of phase error calculation by using an adaptively equalized partial response (PR) signal. Coefficient update of an asynchronous sampled adaptive FIR filter with a least-mean-square (LMS) algorithm has been constrained by a projection matrix in order to suppress the phase shift of the tap coefficients of the adaptive filter. We have developed projection matrices that are suitable for Blu-ray disc (BD) drive systems by numerical simulation. Results have shown the properties of the projection matrices. Then, we have designed the read channel system of the ITR PLL with an LCAF model on the FPGA board for experiments. Results have shown that the LCAF improves the tilt margins of 30 gigabytes (GB) recordable BD (BD-R) and 33 GB BD read-only memory (BD-ROM) with a sufficient LMS adaptation stability.
NASA Astrophysics Data System (ADS)
Czyzowska-Wisniewski, E. H.; Van Leeuwen, W. J. D.; Marsh, S. E.; Hirschboeck, K. K.; Wisniewski, W. T.
2014-12-01
Accurate estimation of Fractional Snow Cover (FSC) in complex alpine-forested terrain is now possible with appropriate remote sensing data and analysis techniques. This research examines what minimum combination of input variables are required to obtain state-of-the-art FSC estimates for heterogeneous alpine-forested terrains. Currently, one of the most accurate FSC estimators for alpine regions is based on training an Artificial Neural Network (ANN) that can deconvolve the relationships between numerous compounded and possibly non-linear bio-geophysical relations encountered in rugged terrain. Under the assumption that the ANN optimally extracts available information from its input data, we can exploit the ANN as a tool to assess the contributions toward FSC estimation of each of the data sources, and combinations thereof. By assessing the quality of the modeled FSC estimates versus ground equivalent data, suitable combinations of input variables can be identified. High spatial resolution imagery from IKONOS are used to estimate snow cover for ANN training and validation, and also for error assessment of the ANN FSC results. Input variables are initially chosen representing information already incorporated into leading snow cover estimators. Additional variables such as topographic slope, aspect, and shadow distribution are evaluated to observe the ANN as it accounts for illumination incidence and directional reflectance of surfaces affecting the viewed radiance in complex terrain. Snow usually covers vegetation and underlying geology partially, therefore the ANN also has to resolve spectral mixtures of unobscured surfaces surrounded by snow. Multispectral imagery if therefore acquired in the fall prior to the first snow of the season and are included in the ANN analyses for assessing the baseline reflectance values of the environment that later become modified by the snow. The best ANN FSC model performance was achieved when all 15 pre-selected inputs were used
Chen, Zhijia; Zhu, Yuanchang; Di, Yanqiang; Feng, Shaochong
2015-01-01
In IaaS (infrastructure as a service) cloud environment, users are provisioned with virtual machines (VMs). To allocate resources for users dynamically and effectively, accurate resource demands predicting is essential. For this purpose, this paper proposes a self-adaptive prediction method using ensemble model and subtractive-fuzzy clustering based fuzzy neural network (ESFCFNN). We analyze the characters of user preferences and demands. Then the architecture of the prediction model is constructed. We adopt some base predictors to compose the ensemble model. Then the structure and learning algorithm of fuzzy neural network is researched. To obtain the number of fuzzy rules and the initial value of the premise and consequent parameters, this paper proposes the fuzzy c-means combined with subtractive clustering algorithm, that is, the subtractive-fuzzy clustering. Finally, we adopt different criteria to evaluate the proposed method. The experiment results show that the method is accurate and effective in predicting the resource demands. PMID:25691896
Chen, Zhijia; Zhu, Yuanchang; Di, Yanqiang; Feng, Shaochong
2015-01-01
In IaaS (infrastructure as a service) cloud environment, users are provisioned with virtual machines (VMs). To allocate resources for users dynamically and effectively, accurate resource demands predicting is essential. For this purpose, this paper proposes a self-adaptive prediction method using ensemble model and subtractive-fuzzy clustering based fuzzy neural network (ESFCFNN). We analyze the characters of user preferences and demands. Then the architecture of the prediction model is constructed. We adopt some base predictors to compose the ensemble model. Then the structure and learning algorithm of fuzzy neural network is researched. To obtain the number of fuzzy rules and the initial value of the premise and consequent parameters, this paper proposes the fuzzy c-means combined with subtractive clustering algorithm, that is, the subtractive-fuzzy clustering. Finally, we adopt different criteria to evaluate the proposed method. The experiment results show that the method is accurate and effective in predicting the resource demands. PMID:25691896
San, Phyo Phyo; Ling, Sai Ho; Nguyen, Hung T
2012-01-01
Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mellitus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, an intelligent diagnostics system, using the hybrid approach of adaptive neural fuzzy inference system (ANFIS), is developed to recognize the presence of hypoglycemia. The proposed ANFIS is characterized by adaptive neural network capabilities and the fuzzy inference system. To optimize the membership functions and adaptive network parameters, a global learning optimization algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) is used. For clinical study, 15 children with Type 1 diabetes volunteered for an overnight study. All the real data sets are collected from the Department of Health, Government of Western Australia. Several experiments were conducted with 5 patients each, for a training set (184 data points), a validation set (192 data points) and a testing set (153 data points), which are randomly selected. The effectiveness of the proposed detection method is found to be satisfactory by giving better sensitivity, 79.09% and acceptable specificity, 51.82%. PMID:23367375
Lai, Guanyu; Liu, Zhi; Zhang, Yun; Chen, C L Philip
2016-01-01
This paper presents a novel adaptive controller for controlling an autonomous helicopter with unknown inertial matrix to asymptotically track the desired trajectory. To identify the unknown inertial matrix included in the attitude dynamic model, this paper proposes a new structural identifier that differs from those previously proposed in that it additionally contains a neural networks (NNs) mechanism and a robust adaptive mechanism, respectively. Using the NNs to compensate the unknown aerodynamic forces online and the robust adaptive mechanism to cancel the combination of the overlarge NNs compensation error and the external disturbances, the new robust neural identifier exhibits a better identification performance in the complex flight environment. Moreover, an optimized algorithm is included in the NNs mechanism to alleviate the burdensome online computation. By the strict Lyapunov argument, the asymptotic convergence of the inertial matrix identification error, position tracking error, and attitude tracking error to arbitrarily small neighborhood of the origin is proved. The simulation and implementation results are provided to evaluate the performance of the proposed controller. PMID:25794402
An FPGA Implementation of a Polychronous Spiking Neural Network with Delay Adaptation
Wang, Runchun; Cohen, Gregory; Stiefel, Klaus M.; Hamilton, Tara Julia; Tapson, Jonathan; van Schaik, André
2013-01-01
We present an FPGA implementation of a re-configurable, polychronous spiking neural network with a large capacity for spatial-temporal patterns. The proposed neural network generates delay paths de novo, so that only connections that actually appear in the training patterns will be created. This allows the proposed network to use all the axons (variables) to store information. Spike Timing Dependent Delay Plasticity is used to fine-tune and add dynamics to the network. We use a time multiplexing approach allowing us to achieve 4096 (4k) neurons and up to 1.15 million programmable delay axons on a Virtex 6 FPGA. Test results show that the proposed neural network is capable of successfully recalling more than 95% of all spikes for 96% of the stored patterns. The tests also show that the neural network is robust to noise from random input spikes. PMID:23408739
An FPGA Implementation of a Polychronous Spiking Neural Network with Delay Adaptation.
Wang, Runchun; Cohen, Gregory; Stiefel, Klaus M; Hamilton, Tara Julia; Tapson, Jonathan; van Schaik, André
2013-01-01
We present an FPGA implementation of a re-configurable, polychronous spiking neural network with a large capacity for spatial-temporal patterns. The proposed neural network generates delay paths de novo, so that only connections that actually appear in the training patterns will be created. This allows the proposed network to use all the axons (variables) to store information. Spike Timing Dependent Delay Plasticity is used to fine-tune and add dynamics to the network. We use a time multiplexing approach allowing us to achieve 4096 (4k) neurons and up to 1.15 million programmable delay axons on a Virtex 6 FPGA. Test results show that the proposed neural network is capable of successfully recalling more than 95% of all spikes for 96% of the stored patterns. The tests also show that the neural network is robust to noise from random input spikes.
Chan, Hui-Ling; Chen, Li-Fen; Chen, I-Tzu; Chen, Yong-Sheng
2015-07-01
Functional connectivity calculated using multiple channels of electromagnetic brain signals is often over- or underestimated due to volume conduction or field spread. Considering connectivity measures, coherence is suitable for the detection of rhythmic synchronization, whereas temporal correlation is appropriate for transient synchronization. This paper presents a beamformer-based imaging method, called spatiotemporal imaging of linearly-related source component (SILSC), which is capable of estimating connectivity at the cortical level by extracting the source component with the maximum temporal correlation between the activity of each targeted region and a reference signal. The spatiotemporal correlation dynamics can be obtained by applying SILSC at every brain region and with various time latencies. The results of six simulation studies demonstrated that SILSC is sensitive to detect the source activity correlated to the specified reference signal and is accurate and robust to noise in terms of source localization. In a facial expression imitation experiment, the correlation dynamics estimated by SILSC revealed the regions with mirror properties and the regions involved in motor control network when performing the imitation and execution tasks, respectively, with the left inferior frontal gyrus specified as the reference region.
Padhi, Radhakant; Bhardhwaj, Jayender R
2009-06-01
An adaptive drug delivery design is presented in this paper using neural networks for effective treatment of infectious diseases. The generic mathematical model used describes the coupled evolution of concentration of pathogens, plasma cells, antibodies and a numerical value that indicates the relative characteristic of a damaged organ due to the disease under the influence of external drugs. From a system theoretic point of view, the external drugs can be interpreted as control inputs, which can be designed based on control theoretic concepts. In this study, assuming a set of nominal parameters in the mathematical model, first a nonlinear controller (drug administration) is designed based on the principle of dynamic inversion. This nominal drug administration plan was found to be effective in curing "nominal model patients" (patients whose immunological dynamics conform to the mathematical model used for the control design exactly. However, it was found to be ineffective in curing "realistic model patients" (patients whose immunological dynamics may have off-nominal parameter values and possibly unwanted inputs) in general. Hence, to make the drug delivery dosage design more effective for realistic model patients, a model-following adaptive control design is carried out next by taking the help of neural networks, that are trained online. Simulation studies indicate that the adaptive controller proposed in this paper holds promise in killing the invading pathogens and healing the damaged organ even in the presence of parameter uncertainties and continued pathogen attack. Note that the computational requirements for computing the control are very minimal and all associated computations (including the training of neural networks) can be carried out online. However it assumes that the required diagnosis process can be carried out at a sufficient faster rate so that all the states are available for control computation.
NASA Technical Reports Server (NTRS)
Balas, Mark; Frost, Susan
2012-01-01
Flexible structures containing a large number of modes can benefit from adaptive control techniques which are well suited to applications that have unknown modeling parameters and poorly known operating conditions. In this paper, we focus on a direct adaptive control approach that has been extended to handle adaptive rejection of persistent disturbances. We extend our adaptive control theory to accommodate troublesome modal subsystems of a plant that might inhibit the adaptive controller. In some cases the plant does not satisfy the requirements of Almost Strict Positive Realness. Instead, there maybe be a modal subsystem that inhibits this property. This section will present new results for our adaptive control theory. We will modify the adaptive controller with a Residual Mode Filter (RMF) to compensate for the troublesome modal subsystem, or the Q modes. Here we present the theory for adaptive controllers modified by RMFs, with attention to the issue of disturbances propagating through the Q modes. We apply the theoretical results to a flexible structure example to illustrate the behavior with and without the residual mode filter.
NASA Astrophysics Data System (ADS)
Yu, Wenwu; Cao, Jinde
2006-06-01
In this paper, a new type of generalized Q-S (lag, anticipated, and complete) time-varying synchronization is defined. Adaptive Q-S (lag, anticipated, and complete) time-varying synchronization and parameters identification of uncertain delayed neural networks have been considered, where the delays are multiple time-varying delays. A novel control method is given by using the Lyapunov functional method. With this new and effective method, parameters identification and Q-S (lag, anticipated, and complete) time-varying synchronization can be achieved simultaneously. Simulation results are given to justify the theoretical analysis in this paper.
Zheng, Fang; Zhan, Max; Huang, Xiaoqin; AbdulHameed, Mohamed Diwan M.; Zhan, Chang-Guo
2013-01-01
Butyrylcholinesterase (BChE) has been an important protein used for development of anti-cocaine medication. Through computational design, BChE mutants with ~2000-fold improved catalytic efficiency against cocaine have been discovered in our lab. To study drug-enzyme interaction it is important to build mathematical model to predict molecular inhibitory activity against BChE. This report presents a neural network (NN) QSAR study, compared with multi-linear regression (MLR) and molecular docking, on a set of 93 small molecules that act as inhibitors of BChE by use of the inhibitory activities (pIC50 values) of the molecules as target values. The statistical results for the linear model built from docking generated energy descriptors were: r2 = 0.67, rmsd = 0.87, q2 = 0.65 and loormsd = 0.90; The statistical results for the ligand-based MLR model were: r2 = 0.89, rmsd = 0.51, q2 = 0.85 and loormsd = 0.58; the statistical results for the ligand-based NN model were the best: r2 = 0.95, rmsd = 0.33, q2 = 0.90 and loormsd = 0.48, demonstrating that the NN is powerful in analysis of a set of complicated data. As BChE is also an established drug target to develop new treatment for Alzheimer’s disease (AD). The developped QSAR models provide tools for rationalizing identification of potential BChE inhibitors or selection of compounds for synthesis in the discovery of novel effective inhibitors of BChE in the future. PMID:24290065
No Evidence for a Low Linear Energy Transfer Adaptive Response in Irradiated RKO Cells
Sowa, Marianne B.; Goetz, Wilfried; Baulch, Janet E.; Lewis, Adam J.; Morgan, William F.
2011-01-06
It has become increasingly evident from reports in the literature that there are many confounding factors that are capable of modulating radiation induced non-targeted responses such as the bystander effect and the adaptive response. In this paper we examine recent data that suggest that the observation of non-targeted responses may not be universally observable for differing radiation qualities. We have conducted a study of the adaptive response following low LET exposures for human colon carcinoma cells and failed to observe adaption for the endpoints of clonogenic survival or micronucleus formation.
Yang, Qinmin; Vance, Jonathan Blake; Jagannathan, S
2008-08-01
A nonaffine discrete-time system represented by the nonlinear autoregressive moving average with eXogenous input (NARMAX) representation with unknown nonlinear system dynamics is considered. An equivalent affinelike representation in terms of the tracking error dynamics is first obtained from the original nonaffine nonlinear discrete-time system so that reinforcement-learning-based near-optimal neural network (NN) controller can be developed. The control scheme consists of two linearly parameterized NNs. One NN is designated as the critic NN, which approximates a predefined long-term cost function, and an action NN is employed to derive a near-optimal control signal for the system to track a desired trajectory while minimizing the cost function simultaneously. The NN weights are tuned online. By using the standard Lyapunov approach, the stability of the closed-loop system is shown. The net result is a supervised actor-critic NN controller scheme which can be applied to a general nonaffine nonlinear discrete-time system without needing the affinelike representation. Simulation results demonstrate satisfactory performance of the controller. PMID:18632390
NASA Astrophysics Data System (ADS)
Ziemann, Amanda K.; Messinger, David W.
2014-06-01
Hyperspectral images comprise, by design, high dimensional image data. However, research has shown that for a d-dimensional hyperspectral image, it is typical for the data to inherently occupy an m-dimensional space, with m << d. In the remote sensing community, this has led to a recent increase in the use of non-linear manifold learning, which aims to characterize the embedded lower-dimensional, non-linear manifold upon which the hyperspectral data inherently lie. Classic hyperspectral data models include statistical, linear subspace, and linear mixture models, but these can place restrictive assumptions on the distribution of the data. With graph theory and manifold learning based models, the only assumption is that the data reside on an underlying manifold. In previous publications, we have shown that manifold coordinate approximation using locally linear embedding (LLE) is a viable pre-processing step for target detection with the Adaptive Cosine/Coherence Estimator (ACE) algorithm. Here, we improve upon that methodology using a more rigorous, data-driven implementation of LLE that incorporates the injection of a cloud" of target pixels and the Spectral Angle Mapper (SAM) detector. The LLE algorithm, which holds that the data is locally linear, is typically governed by a user defined parameter k, indicating the number of nearest neighbors to use in the initial graph model. We use an adaptive approach to building the graph that is governed by the data itself and does not rely upon user input. This implementation of LLE can yield greater separation between the target pixels and the background pixels in the manifold space. We present an analysis of target detection performance in the manifold coordinates using scene-derived target spectra and laboratory-measured target spectra across two different data sets.
An indirect adaptive neural control of a visual-based quadrotor robot for pursuing a moving target.
Shirzadeh, Masoud; Amirkhani, Abdollah; Jalali, Aliakbar; Mosavi, Mohammad R
2015-11-01
This paper aims to use a visual-based control mechanism to control a quadrotor type aerial robot which is in pursuit of a moving target. The nonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks and other similar approaches. In addition to the two mentioned problems, another problem that emerges due to the moving nature of a target is the uncertainty that exists in the target image. By employing an artificial neural network with a Radial Basis Function (RBF) an indirect adaptive neural controller has been designed for a quadrotor robot in search of a moving target. The results of the simulation for different paths show that the quadrotor has efficiently tracked the moving target. PMID:26521725
Kobravi, Hamid Reza; Ali, Sara Hemmati; Vatandoust, Masood; Marvi, Rasoul
2016-01-01
The prediction of the joint angle position, especially during tremor bursts, can be useful for detecting, tracking, and forecasting tremors. Thus, this research proposes a new model for predicting the wrist joint position during rhythmic bursts and inter-burst intervals. Since a tremor is an approximately rhythmic and roughly sinusoidal movement, neural oscillators have been selected to underlie the proposed model. Two neural oscillators were adopted. Electromyogram (EMG) signals were recorded from the extensor carpi radialis and flexor carpi radialis muscles concurrent with the joint angle signals of a stroke subject in an arm constant-posture. The output frequency of each oscillator was equal to the frequency corresponding to the maximum value of power spectrum related to the rhythmic wrist joint angle signals which had been recorded during a postural tremor. The phase shift between the outputs of the two oscillators was equal to the phase shift between the muscle activation of the wrist flexor and extensor muscles. The difference between the two oscillators' output signals was considered the main pattern. Along with a proportional compensator, an adaptive neural controller has adjusted the amplitude of the main pattern in such a way so as to minimize the wrist joint prediction error during a stroke patient's tremor burst and a healthy subject's generated artificial tremor. In regard to the range of wrist joint movement during the observed rhythmic motions, a calculated prediction error is deemed acceptable. PMID:27186540
Kobravi, Hamid Reza; Ali, Sara Hemmati; Vatandoust, Masood; Marvi, Rasoul
2016-01-01
The prediction of the joint angle position, especially during tremor bursts, can be useful for detecting, tracking, and forecasting tremors. Thus, this research proposes a new model for predicting the wrist joint position during rhythmic bursts and inter-burst intervals. Since a tremor is an approximately rhythmic and roughly sinusoidal movement, neural oscillators have been selected to underlie the proposed model. Two neural oscillators were adopted. Electromyogram (EMG) signals were recorded from the extensor carpi radialis and flexor carpi radialis muscles concurrent with the joint angle signals of a stroke subject in an arm constant-posture. The output frequency of each oscillator was equal to the frequency corresponding to the maximum value of power spectrum related to the rhythmic wrist joint angle signals which had been recorded during a postural tremor. The phase shift between the outputs of the two oscillators was equal to the phase shift between the muscle activation of the wrist flexor and extensor muscles. The difference between the two oscillators’ output signals was considered the main pattern. Along with a proportional compensator, an adaptive neural controller has adjusted the amplitude of the main pattern in such a way so as to minimize the wrist joint prediction error during a stroke patient's tremor burst and a healthy subject's generated artificial tremor. In regard to the range of wrist joint movement during the observed rhythmic motions, a calculated prediction error is deemed acceptable. PMID:27186540
Armony, Jorge L; Aubé, William; Angulo-Perkins, Arafat; Peretz, Isabelle; Concha, Luis
2015-04-23
Several studies have identified, using functional magnetic resonance imaging (fMRI), a region within the superior temporal gyrus that preferentially responds to musical stimuli. However, in most cases, significant responses to other complex stimuli, particularly human voice, were also observed. Thus, it remains unknown if the same neurons respond to both stimulus types, albeit with different strengths, or whether the responses observed with fMRI are generated by distinct, overlapping neural populations. To address this question, we conducted an fMRI experiment in which short music excerpts and human vocalizations were presented in a pseudo-random order. Critically, we performed an adaptation-based analysis in which responses to the stimuli were analyzed taking into account the category of the preceding stimulus. Our results confirm the presence of a region in the anterior STG that responds more strongly to music than voice. Moreover, we found a music-specific adaptation effect in this area, consistent with the existence of music-preferred neurons. Lack of differences between musicians and non-musicians argues against an expertise effect. These findings provide further support for neural separability between music and speech within the temporal lobe.
Tong, Shaocheng; Wang, Tong; Li, Yongming; Zhang, Huaguang
2014-06-01
This paper discusses the problem of adaptive neural network output feedback control for a class of stochastic nonlinear strict-feedback systems. The concerned systems have certain characteristics, such as unknown nonlinear uncertainties, unknown dead-zones, unmodeled dynamics and without the direct measurements of state variables. In this paper, the neural networks (NNs) are employed to approximate the unknown nonlinear uncertainties, and then by representing the dead-zone as a time-varying system with a bounded disturbance. An NN state observer is designed to estimate the unmeasured states. Based on both backstepping design technique and a stochastic small-gain theorem, a robust adaptive NN output feedback control scheme is developed. It is proved that all the variables involved in the closed-loop system are input-state-practically stable in probability, and also have robustness to the unmodeled dynamics. Meanwhile, the observer errors and the output of the system can be regulated to a small neighborhood of the origin by selecting appropriate design parameters. Simulation examples are also provided to illustrate the effectiveness of the proposed approach.
Hauser, Tobias U.; Iannaccone, Reto; Walitza, Susanne; Brandeis, Daniel; Brem, Silvia
2015-01-01
Adolescence is associated with quickly changing environmental demands which require excellent adaptive skills and high cognitive flexibility. Feedback-guided adaptive learning and cognitive flexibility are driven by reward prediction error (RPE) signals, which indicate the accuracy of expectations and can be estimated using computational models. Despite the importance of cognitive flexibility during adolescence, only little is known about how RPE processing in cognitive flexibility deviates between adolescence and adulthood. In this study, we investigated the developmental aspects of cognitive flexibility by means of computational models and functional magnetic resonance imaging (fMRI). We compared the neural and behavioral correlates of cognitive flexibility in healthy adolescents (12–16 years) to adults performing a probabilistic reversal learning task. Using a modified risk-sensitive reinforcement learning model, we found that adolescents learned faster from negative RPEs than adults. The fMRI analysis revealed that within the RPE network, the adolescents had a significantly altered RPE-response in the anterior insula. This effect seemed to be mainly driven by increased responses to negative prediction errors. In summary, our findings indicate that decision making in adolescence goes beyond merely increased reward-seeking behavior and provides a developmental perspective to the behavioral and neural mechanisms underlying cognitive flexibility in the context of reinforcement learning. PMID:25234119
Mortazavi, S.M.J.; Motamedifar, M.; Namdari, G.; Taheri, M.; Mortazavi, A.R.; Shokrpour, N.
2014-01-01
Substantial evidence indicates that adaptive response induced by low doses of ionizing radiation can result in resistance to the damage caused by a subsequently high-dose radiation or cause cross-resistance to other non-radiation stressors. Adaptive response contradicts the linear-non-threshold (LNT) dose-response model for ionizing radiation. We have previously reported that exposure of laboratory animals to radiofrequency radiation can induce a survival adaptive response. Furthermore, we have indicated that pre-exposure of mice to radiofrequency radiation emitted by a GSM mobile phone increased their resistance to a subsequent Escherichia coli infection. In this study, the survival rates in animals receiving both adapting (radiofrequency) and challenge dose (bacteria) and the animals receiving only the challenge dose (bacteria) were 56% and 20%, respectively. In this light, our findings contribute to the assumption that radiofrequency-induced adaptive response can be used as an efficient method for decreasing the risk of infection in immunosuppressed irradiated individuals. The implication of this phenomenon in human’s long term stay in the space is also discussed. PMID:24910582
Tommasi, C.; May, C.
2010-09-30
The DKL-optimality criterion has been recently proposed for the dual problem of model discrimination and parameter estimation, for the case of two rival models. A sequential version of the DKL-optimality criterion is herein proposed in order to discriminate and efficiently estimate more than two nested non-linear models. Our sequential method is inspired by the procedure of Biswas and Chaudhuri (2002), which is however useful only in the set up of nested linear models.
Biohybrid Control of General Linear Systems Using the Adaptive Filter Model of Cerebellum
Wilson, Emma D.; Assaf, Tareq; Pearson, Martin J.; Rossiter, Jonathan M.; Dean, Paul; Anderson, Sean R.; Porrill, John
2015-01-01
The adaptive filter model of the cerebellar microcircuit has been successfully applied to biological motor control problems, such as the vestibulo-ocular reflex (VOR), and to sensory processing problems, such as the adaptive cancelation of reafferent noise. It has also been successfully applied to problems in robotics, such as adaptive camera stabilization and sensor noise cancelation. In previous applications to inverse control problems, the algorithm was applied to the velocity control of a plant dominated by viscous and elastic elements. Naive application of the adaptive filter model to the displacement (as opposed to velocity) control of this plant results in unstable learning and control. To be more generally useful in engineering problems, it is essential to remove this restriction to enable the stable control of plants of any order. We address this problem here by developing a biohybrid model reference adaptive control (MRAC) scheme, which stabilizes the control algorithm for strictly proper plants. We evaluate the performance of this novel cerebellar-inspired algorithm with MRAC scheme in the experimental control of a dielectric electroactive polymer, a class of artificial muscle. The results show that the augmented cerebellar algorithm is able to accurately control the displacement response of the artificial muscle. The proposed solution not only greatly extends the practical applicability of the cerebellar-inspired algorithm, but may also shed light on cerebellar involvement in a wider range of biological control tasks. PMID:26257638
Accuracy requirements of optical linear algebra processors in adaptive optics imaging systems
NASA Technical Reports Server (NTRS)
Downie, John D.
1990-01-01
A ground-based adaptive optics imaging telescope system attempts to improve image quality by detecting and correcting for atmospherically induced wavefront aberrations. The required control computations during each cycle will take a finite amount of time. Longer time delays result in larger values of residual wavefront error variance since the atmosphere continues to change during that time. Thus an optical processor may be well-suited for this task. This paper presents a study of the accuracy requirements in a general optical processor that will make it competitive with, or superior to, a conventional digital computer for the adaptive optics application. An optimization of the adaptive optics correction algorithm with respect to an optical processor's degree of accuracy is also briefly discussed.
Spike history neural response model.
Kameneva, Tatiana; Abramian, Miganoosh; Zarelli, Daniele; Nĕsić, Dragan; Burkitt, Anthony N; Meffin, Hamish; Grayden, David B
2015-06-01
There is a potential for improved efficacy of neural stimulation if stimulation levels can be modified dynamically based on the responses of neural tissue in real time. A neural model is developed that describes the response of neurons to electrical stimulation and that is suitable for feedback control neuroprosthetic stimulation. Experimental data from NZ white rabbit retinae is used with a data-driven technique to model neural dynamics. The linear-nonlinear approach is adapted to incorporate spike history and to predict the neural response of ganglion cells to electrical stimulation. To validate the fitness of the model, the penalty term is calculated based on the time difference between each simulated spike and the closest spike in time in the experimentally recorded train. The proposed model is able to robustly predict experimentally observed spike trains.
Luo, Shaohua; Wu, Songli; Gao, Ruizhen
2015-07-15
This paper investigates chaos control for the brushless DC motor (BLDCM) system by adaptive dynamic surface approach based on neural network with the minimum weights. The BLDCM system contains parameter perturbation, chaotic behavior, and uncertainty. With the help of radial basis function (RBF) neural network to approximate the unknown nonlinear functions, the adaptive law is established to overcome uncertainty of the control gain. By introducing the RBF neural network and adaptive technology into the dynamic surface control design, a robust chaos control scheme is developed. It is proved that the proposed control approach can guarantee that all signals in the closed-loop system are globally uniformly bounded, and the tracking error converges to a small neighborhood of the origin. Simulation results are provided to show that the proposed approach works well in suppressing chaos and parameter perturbation.
Accuracy requirements of optical linear algebra processors in adaptive optics imaging systems.
Downie, J D; Goodman, J W
1989-10-15
A ground-based adaptive optics imaging telescope system attempts to improve image quality by measuring and correcting for atmospherically induced wavefront aberrations. The necessary control computations during each cycle will take a finite amount of time, which adds to the residual error variance since the atmosphere continues to change during that time. Thus an optical processor may be well-suited for this task. This paper investigates this possibility by studying the accuracy requirements in a general optical processor that will make it competitive with, or superior to, a conventional digital computer for adaptive optics use.
NASA Technical Reports Server (NTRS)
Bautista, Abigail B.
1994-01-01
Twenty-four observers looked through a pair of 20 diopter wedge prisms and pointed to an image of a target which was displaced vertically from eye level by 6 cm at a distance of 30 cm. Observers pointed 40 times, using only their right hand, and received error-corrective feedback upon termination of each pointing response (terminal visual feedback). At three testing distances, 20, 30, and 40 cm, ten pre-exposure and ten post-exposure pointing responses were recorded for each hand as observers reached to a mirror-viewed target located at eye level. The difference between pre- and post-exposure pointing response (adaptive shift) was compared for both Exposed and Unexposed hands across all three testing distances. The data were assessed according to the results predicted by two alternative models for processing spatial-information: one using angular displacement information and another using linear displacement information. The angular model of spatial mapping best predicted the observer's pointing response for the Exposed hand. Although the angular adaptive shift did not change significantly as a function of distance (F(2,44) = 1.12, n.s.), the linear adaptive shift increased significantly over the three testing distances 02 44) = 4.90 p less than 0.01).
Neural Time Course of Conflict Adaptation Effects on the Stroop Task
ERIC Educational Resources Information Center
Larson, Michael J.; Kaufman, David A. S.; Perlstein, William M.
2009-01-01
Cognitive control theory suggests conflict effects are reduced following high- relative to low-conflict trials. Such reactive adjustments in control, frequently termed "conflict adaptation effects," indicate a dynamic interplay between regulative and evaluative components of cognitive control necessary for adaptable goal-directed behavior. The…
NASA Technical Reports Server (NTRS)
Burken, John J.
2005-01-01
This viewgraph presentation reviews the use of a Robust Servo Linear Quadratic Regulator (LQR) and a Radial Basis Function (RBF) Neural Network in reconfigurable flight control designs in adaptation to a aircraft part failure. The method uses a robust LQR servomechanism design with model Reference adaptive control, and RBF neural networks. During the failure the LQR servomechanism behaved well, and using the neural networks improved the tracking.
Adaptive probabilistic neural networks for pattern classification in time-varying environment.
Rutkowski, Leszek
2004-07-01
In this paper, we propose a new class of probabilistic neural networks (PNNs) working in nonstationary environment. The novelty is summarized as follows: 1) We formulate the problem of pattern classification in nonstationary environment as the prediction problem and design a probabilistic neural network to classify patterns having time-varying probability distributions. We note that the problem of pattern classification in the nonstationary case is closely connected with the problem of prediction because on the basis of a learning sequence of the length n, a pattern in the moment n + k, k > or = 1 should be classified. 2) We present, for the first time in literature, definitions of optimality of PNNs in time-varying environment. Moreover, we prove that our PNNs asymptotically approach the Bayes-optimal (time-varying) decision surface. 3) We investigate the speed of convergence of constructed PNNs. 4) We design in detail PNNs based on Parzen kernels and multivariate Hermite series.
He, Shouling
2002-10-01
In this paper multilayer neural networks (MNNs) are used to control the balancing of a class of inverted pendulums. Unlike normal inverted pendulums, the pendulum discussed here has two degrees of rotational freedom and the base-point moves randomly in three-dimensional space. The goal is to apply control torques to keep the pendulum in a prescribed position in spite of the random movement at the base-point. Since the inclusion of the base-point motion leads to a non-autonomous dynamic system with time-varying parametric excitation, the design of the control system is a challenging task. A feedback control algorithm is proposed that utilizes a set of neural networks to compensate for the effect of the system's nonlinearities. The weight parameters of neural networks updated on-line, according to a learning algorithm that guarantees the Lyapunov stability of the control system. Furthermore, since the base-point movement is considered unmeasurable, a neural inverse model is employed to estimate it from only measured state variables. The estimate is then utilized within the main control algorithm to produce compensating control signals. The examination of the proposed control system, through simulations, demonstrates the promise of the methodology and exhibits positive aspects, which cannot be achieved by the previously developed techniques on the same problem. These aspects include fast, yet well-maintained damped responses with reasonable control torques and no requirement for knowledge of the model or the model parameters. The work presented here can benefit practical problems such as the study of stable locomotion of human upper body and bipedal robots.
Zhang, Hao; Liu, Jia; Zhang, Qinglin
2014-01-01
Inventive conceptions amount to creative ideas for designing devices that are both original and useful. The generation of inventive conceptions is a key element of the inventive process. However, neural mechanisms of the inventive process remain poorly understood. Here we employed functional feature association tasks and event-related functional magnetic resonance imaging (MRI) to investigate neural substrates for the generation of inventive conceptions. The functional MRI (fMRI) data revealed significant activations at Brodmann area (BA) 47 in the left inferior frontal gyrus and at BA 18 in the left lingual gyrus, when participants performed biological functional feature association tasks compared with non-biological functional feature association tasks. Our results suggest that the left inferior frontal gyrus (BA 47) is associated with novelty-based representations formed by the generation and selection of semantic relatedness, and the left lingual gyrus (BA 18) is involved in relevant visual imagery in processing of semantic relatedness. The findings might shed light on neural mechanisms underlying the inventive process. PMID:23582377
Closed loop adaptive control of spectrum-producing step using neural networks
Fu, C.Y.
1998-11-24
Characteristics of the plasma in a plasma-based manufacturing process step are monitored directly and in real time by observing the spectrum which it produces. An artificial neural network analyzes the plasma spectrum and generates control signals to control one or more of the process input parameters in response to any deviation of the spectrum beyond a narrow range. In an embodiment, a plasma reaction chamber forms a plasma in response to input parameters such as gas flow, pressure and power. The chamber includes a window through which the electromagnetic spectrum produced by a plasma in the chamber, just above the subject surface, may be viewed. The spectrum is conducted to an optical spectrometer which measures the intensity of the incoming optical spectrum at different wavelengths. The output of optical spectrometer is provided to an analyzer which produces a plurality of error signals, each indicating whether a respective one of the input parameters to the chamber is to be increased or decreased. The microcontroller provides signals to control respective controls, but these lines are intercepted and first added to the error signals, before being provided to the controls for the chamber. The analyzer can include a neural network and an optional spectrum preprocessor to reduce background noise, as well as a comparator which compares the parameter values predicted by the neural network with a set of desired values provided by the microcontroller. 7 figs.
Closed loop adaptive control of spectrum-producing step using neural networks
Fu, Chi Yung
1998-01-01
Characteristics of the plasma in a plasma-based manufacturing process step are monitored directly and in real time by observing the spectrum which it produces. An artificial neural network analyzes the plasma spectrum and generates control signals to control one or more of the process input parameters in response to any deviation of the spectrum beyond a narrow range. In an embodiment, a plasma reaction chamber forms a plasma in response to input parameters such as gas flow, pressure and power. The chamber includes a window through which the electromagnetic spectrum produced by a plasma in the chamber, just above the subject surface, may be viewed. The spectrum is conducted to an optical spectrometer which measures the intensity of the incoming optical spectrum at different wavelengths. The output of optical spectrometer is provided to an analyzer which produces a plurality of error signals, each indicating whether a respective one of the input parameters to the chamber is to be increased or decreased. The microcontroller provides signals to control respective controls, but these lines are intercepted and first added to the error signals, before being provided to the controls for the chamber. The analyzer can include a neural network and an optional spectrum preprocessor to reduce background noise, as well as a comparator which compares the parameter values predicted by the neural network with a set of desired values provided by the microcontroller.
NASA Astrophysics Data System (ADS)
Akhunov, R. R.; Gazizov, T. R.; Kuksenko, S. P.
2016-08-01
The mean time needed to solve a series of systems of linear algebraic equations (SLAEs) as a function of the number of SLAEs is investigated. It is proved that this function has an extremum point. An algorithm for adaptively determining the time when the preconditioner matrix should be recalculated when a series of SLAEs is solved is developed. A numerical experiment with multiply solving a series of SLAEs using the proposed algorithm for computing 100 capacitance matrices with two different structures—microstrip when its thickness varies and a modal filter as the gap between the conductors varies—is carried out. The speedups turned out to be close to the optimal ones.
Adaptive optical radial basis function neural network for handwritten digit recognition
NASA Astrophysics Data System (ADS)
Foor, Wesley E.; Neifeld, Mark A.
1994-06-01
An adaptive optical radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially- multiplexed system incorporating on-line adaptation of weights and basis function widths to provide robustness to optical system imperfections and system noise. The optical system computes the Euclidean distances between a 100-dimensional input and 198 stored reference patterns in parallel using dual vector-matrix multipliers. For this experimental software is used to perform the on-line learning of the weights and basis function widths. An experimental recognition rate of 86.7% correct out of 300 testing samples is achieved with the adaptive training versus 52.3% correct for non-adaptive training. The experimental results from the optical system are compared with data from a computer model of the system in order to identify noise sources and indicate possible improvements for system performance.
Not Available
1991-01-01
The present conference discusses such topics as the self-organization of nonnumeric data sets, higher-order data compression with neural networks, approaches to connectionist pattern synthesis, a time-varying recurrent neural system for convex programming, a fuzzy associative memory for conceptual design, sensor failure detection and recovery via neural networks, genetic optimization of self-organizing feature maps, a maximum neural network for the max-cut problem, a neural-network LSI chip with on-chip learning, an optoelectronic adaptive resonance unit, an adaptive fuzzy system for transform image coding, a neural model of image velocity encoding, and incremental learning with rule-based neural networks. Also discussed are the induction of neural networks for parallel binary operations, hybrid learning in expert networks, self-organizing modular neural networks, connectionist category formation, period-doublings to chaos in a simple neural network, the optimal adaptive classifier design criterion, fuzzy neuron models, associative memory networks, adaptive transfer functions, spatiotemporal correlation in the cerebellum, prejuditial searches and the pole balancer, linear quadratic regulation via neural networks, the global optimization of a neural network, neural network analysis of DNA sequences, map learning using an associative-memory neural network, a pairing strategy in an associative memory classifier, neural networks for music composition, and a neural network for motion computation.
Sun, W Y
1993-04-01
This thesis solves the problem of finding the optimal linear noise-reduction filter for linear tomographic image reconstruction. The optimization is data dependent and results in minimizing the mean-square error of the reconstructed image. The error is defined as the difference between the result and the best possible reconstruction. Applications for the optimal filter include reconstructions of positron emission tomographic (PET), X-ray computed tomographic, single-photon emission tomographic, and nuclear magnetic resonance imaging. Using high resolution PET as an example, the optimal filter is derived and presented for the convolution backprojection, Moore-Penrose pseudoinverse, and the natural-pixel basis set reconstruction methods. Simulations and experimental results are presented for the convolution backprojection method.
Neural-Network Controller For Vibration Suppression
NASA Technical Reports Server (NTRS)
Boussalis, Dhemetrios; Wang, Shyh Jong
1995-01-01
Neural-network-based adaptive-control system proposed for vibration suppression of flexible space structures. Controller features three-layer neural network and utilizes output feedback. Measurements generated by various sensors on structure. Feed forward path also included to speed up response in case plant exhibits predominantly linear dynamic behavior. System applicable to single-input single-output systems. Work extended to multiple-input multiple-output systems as well.
Liu, Zhi; Chen, Ci; Zhang, Yun; Chen, C L P
2015-03-01
To achieve an excellent dual-arm coordination of the humanoid robot, it is essential to deal with the nonlinearities existing in the system dynamics. The literatures so far on the humanoid robot control have a common assumption that the problem of output hysteresis could be ignored. However, in the practical applications, the output hysteresis is widely spread; and its existing limits the motion/force performances of the robotic system. In this paper, an adaptive neural control scheme, which takes the unknown output hysteresis and computational efficiency into account, is presented and investigated. In the controller design, the prior knowledge of system dynamics is assumed to be unknown. The motion error is guaranteed to converge to a small neighborhood of the origin by Lyapunov's stability theory. Simultaneously, the internal force is kept bounded and its error can be made arbitrarily small.
Liu, Zhi; Chen, Ci; Zhang, Yun; Chen, C L P
2015-03-01
To achieve an excellent dual-arm coordination of the humanoid robot, it is essential to deal with the nonlinearities existing in the system dynamics. The literatures so far on the humanoid robot control have a common assumption that the problem of output hysteresis could be ignored. However, in the practical applications, the output hysteresis is widely spread; and its existing limits the motion/force performances of the robotic system. In this paper, an adaptive neural control scheme, which takes the unknown output hysteresis and computational efficiency into account, is presented and investigated. In the controller design, the prior knowledge of system dynamics is assumed to be unknown. The motion error is guaranteed to converge to a small neighborhood of the origin by Lyapunov's stability theory. Simultaneously, the internal force is kept bounded and its error can be made arbitrarily small. PMID:24968367
Powder, Kara E.; Cousin, Hélène; McLinden, Gretchen P.; Craig Albertson, R.
2014-01-01
Since the time of Darwin, biologists have sought to understand the origins and maintenance of life’s diversity of form. However, the nature of the exact DNA mutations and molecular mechanisms that result in morphological differences between species remains unclear. Here, we characterize a nonsynonymous mutation in a transcriptional coactivator, limb bud and heart homolog (lbh), which is associated with adaptive variation in the lower jaw of cichlid fishes. Using both zebrafish and Xenopus, we demonstrate that lbh mediates migration of cranial neural crest cells, the cellular source of the craniofacial skeleton. A single amino acid change that is alternatively fixed in cichlids with differing facial morphologies results in discrete shifts in migration patterns of this multipotent cell type that are consistent with both embryological and adult craniofacial phenotypes. Among animals, this polymorphism in lbh represents a rare example of a coding change that is associated with continuous morphological variation. This work offers novel insights into the development and evolution of the craniofacial skeleton, underscores the evolutionary potential of neural crest cells, and extends our understanding of the genetic nature of mutations that underlie divergence in complex phenotypes. PMID:25234704
NASA Astrophysics Data System (ADS)
Lang, Jun; Hao, Zhengchao
2014-01-01
In this paper, we first propose the discrete multi-parameter fractional random transform (DMPFRNT), which can make the spectrum distributed randomly and uniformly. Then we introduce this new spectrum transform into the image fusion field and present a new approach for the remote sensing image fusion, which utilizes both adaptive pulse coupled neural network (PCNN) and the discrete multi-parameter fractional random transform in order to meet the requirements of both high spatial resolution and low spectral distortion. In the proposed scheme, the multi-spectral (MS) and panchromatic (Pan) images are converted into the discrete multi-parameter fractional random transform domains, respectively. In DMPFRNT spectrum domain, high amplitude spectrum (HAS) and low amplitude spectrum (LAS) components carry different informations of original images. We take full advantage of the synchronization pulse issuance characteristics of PCNN to extract the HAS and LAS components properly, and give us the PCNN ignition mapping images which can be used to determine the fusion parameters. In the fusion process, local standard deviation of the amplitude spectrum is chosen as the link strength of pulse coupled neural network. Numerical simulations are performed to demonstrate that the proposed method is more reliable and superior than several existing methods based on Hue Saturation Intensity representation, Principal Component Analysis, the discrete fractional random transform etc.
Bu, Xiangwei; Wu, Xiaoyan; Tian, Mingyan; Huang, Jiaqi; Zhang, Rui; Ma, Zhen
2015-09-01
In this paper, an adaptive neural controller is exploited for a constrained flexible air-breathing hypersonic vehicle (FAHV) based on high-order tracking differentiator (HTD). By utilizing functional decomposition methodology, the dynamic model is reasonably decomposed into the respective velocity subsystem and altitude subsystem. For the velocity subsystem, a dynamic inversion based neural controller is constructed. By introducing the HTD to adaptively estimate the newly defined states generated in the process of model transformation, a novel neural based altitude controller that is quite simpler than the ones derived from back-stepping is addressed based on the normal output-feedback form instead of the strict-feedback formulation. Based on minimal-learning parameter scheme, only two neural networks with two adaptive parameters are needed for neural approximation. Especially, a novel auxiliary system is explored to deal with the problem of control inputs constraints. Finally, simulation results are presented to test the effectiveness of the proposed control strategy in the presence of system uncertainties and actuators constraints.
Automated detection of semagram-laden images using adaptive neural networks
NASA Astrophysics Data System (ADS)
Cerkez, Paul S.; Cannady, James D.
2010-04-01
Digital steganography has been used extensively for electronic copyright stamping, but also for criminal or covert activities. While a variety of techniques exist for detecting steganography the identification of semagrams, messages transmitted visually in a non-textual format remain elusive. The work that will be presented describes the creation of a novel application which uses hierarchical neural network architectures to detect the likely presence of a semagram message in an image. The application was used to detect semagrams containing Morse Code messages with over 80% accuracy. These preliminary results indicate a significant advance in the detection of complex semagram patterns.
Uppal, Neha; Foxe, John J; Butler, John S; Acluche, Frantzy; Molholm, Sophie
2016-03-01
Young children are often hyperreactive to somatosensory inputs hardly noticed by adults, as exemplified by irritation to seams or labels in clothing. The neurodevelopmental mechanisms underlying changes in sensory reactivity are not well understood. Based on the idea that neurodevelopmental changes in somatosensory processing and/or changes in sensory adaptation might underlie developmental differences in somatosensory reactivity, high-density electroencephalography was used to examine how the nervous system responds and adapts to repeated vibrotactile stimulation over childhood. Participants aged 6-18 yr old were presented with 50-ms vibrotactile stimuli to the right wrist over the median nerve at 5 blocked interstimulus intervals (ranging from ∼7 to ∼1 stimulus per second). Somatosensory evoked potentials (SEPs) revealed three major phases of activation within the first 200 ms, with scalp topographies suggestive of neural generators in contralateral somatosensory cortex. Although overall SEPs were highly similar for younger, middle, and older age groups (6.1-9.8, 10.0-12.9, and 13.0-17.8 yr old), there were significant age-related amplitude differences in initial and later phases of the SEP. In contrast, robust adaptation effects for fast vs. slow presentation rates were observed that did not differ as a function of age. A greater amplitude response in the later portion of the SEP was observed for the youngest group and may be related to developmental changes in responsivity to somatosensory stimuli. These data suggest the protracted development of the somatosensory system over childhood, whereas adaptation, as assayed in this study, is largely in place by ∼7 yr of age. PMID:26763781
Adaptive, optical, radial basis function neural network for handwritten digit recognition
NASA Astrophysics Data System (ADS)
Foor, Wesley E.; Neifeld, Mark A.
1995-11-01
An adaptive, optical, radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially multiplexed system that incorporates an on-line adaptation of weights and basis function widths to provide robustness to optical system imperfections and system noise. The optical system computes the Euclidean distances between a 100-dimensional input vector and 198 stored reference patterns in parallel by using dual vector-matrix multipliers and a contrast-reversing spatial light modulator. Software is used to emulate an electronic chip that performs the on-line learning of the weights and basis function widths. An experimental recognition rate of 92.7% correct out of 300 testing samples is achieved with the adaptive training, versus 31.0% correct for nonadaptive training. We compare the experimental results with a detailed computer model of the system in order to analyze the influence of various noise sources on the system performance.
Adaptive distance protection of double-circuit lines using artificial neural networks
Jongepier, A.G.; Sluis, L. van der
1997-01-01
Because of the zero sequence mutual coupling of parallel circuits, the distance calculation performed by a ground distance relay is incorrect. This error is influenced by the actual power system condition. Although accounted for by using a large safety margin in the zone boundaries, unexpected overreach can still occur and the operation speed is decreased. Adaptive protection offers an approach to compensate for the influence of the variable power system conditions. By adapting the relay settings to the actual power system condition, the relay will respond more accurately to power system faults. The selectivity of the protection system is increased, as is the power system reliability. In this paper, an adaptive distance relaying concept is presented. In order to minimize the required communication, local measurements are used to estimate the entire power system condition. An artificial neutral network is used to estimate the actual power system condition and to calculate the appropriate tripping impedance.
Oscillatory dynamics in an attractor neural network with firing rate adaptation
NASA Astrophysics Data System (ADS)
Rathore, S.; Bush, D.; Latham, P.; Burgess, N.
2013-01-01
We develop a framework for generating oscillations in ring attractor networks with firing rate adaptation. We show the relationship between the frequency of rotation around the ring of the shifting bump of activity, the adaptation variable and other model parameters using perturbation theory. The analytic solutions are validated against simulations of such networks. Further preliminary findings indicate that the frequency of these networks can be simply controlled using an external stimulus. The mechanism developed here could potentially be used for temporal coding of position through interference of oscillators of different frequencies.
Back-propagation neural network adaptive control of a continuous wastewater treatment process
Syu, J.J.; Chen, B.C.
1998-09-01
Wastewater treatment processes and technology have been investigated for several decades and have almost been completed up to date. In this study, a chemical method was applied to treat the wastewater. Instead of real wastewater, benzoic acid and water were mixed as the wastewater since different concentrations of dissolved benzoic acid could result in different chemical oxygen demands (COD). Hydrogen peroxide and ferrous chloride were both added to treat the wastewater in order to meet the standards of 1998 environmental regulation in Taiwan. pH was found to be a major factor affecting the coagulation condition of the suspended particles during the treatment process. Back-propagation neural network was applied, and the purpose of the control was to provide the minimum amount of reagents to reach the required COD. The pump rates for adding hydrogen peroxide and ferrous chloride were controlled. The neural network was of a time-delayed mode, and its structure was properly determined, with the only output node being the predicted H{sub 2}O{sub 2}. The concentration of the added reagents was compared as well.
Minerals detection for hyperspectral images using adapted linear unmixing: LinMin
NASA Astrophysics Data System (ADS)
Schmidt, Frédéric; Legendre, Maxime; Le Mouëlic, Stéphane
2014-07-01
Minerals detection over large volume of spectra is the challenge addressed by current hyperspectral imaging spectrometer in Planetary Science. Instruments such OMEGA (Mars Express), CRISM (Mars Reconnaissance Orbiter), M3 (Chandrayaan-1), VIRTIS (Rosetta) and many more, have been producing very large datasets since one decade. We propose here a fast supervised detection algorithm called LinMin, in the framework of linear unmixing, with innovative arrangement in order to treat non-linear cases due to radiative transfer in both atmosphere and surface. We use reference laboratory and synthetic spectral library. Additional spectra are used in order to mimic the effect of Martian aerosols, grain size, and observation geometry discrepancies between reference and observed spectra. The proposed algorithm estimates the uncertainty on “mixing coefficient” from the uncertainty of observed spectra. Both numerical and observational tests validate the approach. Fast parallel implementation of the best algorithm (IPLS) on Graphics Processing Units (GPU) allows to significantly reduce the computation cost by a factor of ∼40.
Neural Substrates Related to Motor Memory with Multiple Timescales in Sensorimotor Adaptation
Lv, Jinchi; Schweighofer, Nicolas; Imamizu, Hiroshi
2015-01-01
Recent computational and behavioral studies suggest that motor adaptation results from the update of multiple memories with different timescales. Here, we designed a model-based functional magnetic resonance imaging (fMRI) experiment in which subjects adapted to two opposing visuomotor rotations. A computational model of motor adaptation with multiple memories was fitted to the behavioral data to generate time-varying regressors of brain activity. We identified regional specificity to timescales: in particular, the activity in the inferior parietal region and in the anterior-medial cerebellum was associated with memories for intermediate and long timescales, respectively. A sparse singular value decomposition analysis of variability in specificities to timescales over the brain identified four components, two fast, one middle, and one slow, each associated with different brain networks. Finally, a multivariate decoding analysis showed that activity patterns in the anterior-medial cerebellum progressively represented the two rotations. Our results support the existence of brain regions associated with multiple timescales in adaptation and a role of the cerebellum in storing multiple internal models. PMID:26645916
King, Bradley R; Fogel, Stuart M; Albouy, Geneviève; Doyon, Julien
2013-01-01
As the world's population ages, a deeper understanding of the relationship between aging and motor learning will become increasingly relevant in basic research and applied settings. In this context, this review aims to address the effects of age on motor sequence learning (MSL) and motor adaptation (MA) with respect to behavioral, neurological, and neuroimaging findings. Previous behavioral research investigating the influence of aging on motor learning has consistently reported the following results. First, the initial acquisition of motor sequences is not altered, except under conditions of increased task complexity. Second, older adults demonstrate deficits in motor sequence memory consolidation. And, third, although older adults demonstrate deficits during the exposure phase of MA paradigms, the aftereffects following removal of the sensorimotor perturbation are similar to young adults, suggesting that the adaptive ability of older adults is relatively intact. This paper will review the potential neural underpinnings of these behavioral results, with a particular emphasis on the influence of age-related dysfunctions in the cortico-striatal system on motor learning.
Zheng, Huiru; Wang, Haiying; Azuaje, Francisco
2008-07-01
Serial analysis of gene expression (SAGE) allows a detailed, simultaneous analysis of thousands of genes without the need for prior, complete gene sequence information. However, due to its inherent complexity and the lack of complete structural and function knowledge, mining vast collections of SAGE data to extract useful knowledge poses great challenges to traditional analytical techniques. Moreover, SAGE data are characterized by a specific statistical model that has not been incorporated into traditional data analysis techniques. The analysis of SAGE data requires advanced, intelligent computational techniques, which consider the underlying biology and the statistical nature of SAGE data. By addressing the statistical properties demonstrated by SAGE data, this paper presents a new self-adaptive neural network, Poisson-based growing self-organizing map (PGSOM), which implements novel weight adaptation and neuron growing strategies. An empirical study of key dynamic mechanisms of PGSOM is presented. It was tested on three datasets, including synthetic and experimental SAGE data. The results indicate that, in comparison to traditional techniques, the PGSOM offers significant advantages in the context of pattern discovery and visualization in SAGE data. The pattern discovery and visualization platform discussed in this paper can be applied to other problem domains where the data are better approximated by a Poisson distribution.
Popova, Yekaterina; Boyle, Richard
2015-07-01
Gravity plays a key role in shaping the vestibular sensitivity (VS) of terrestrial organisms. We studied VS changes in the statocyst of the gastropod Helix aspersa immediately after 4-, 16-, and 32-day exposures to a 1.4G hypergravic field or following a 7-day recovery period. In the same animals we measured latencies of behavioral "negative gravitaxis" responses to a head-down pitch before and after centrifugation and found significant delays after 16- and 32-day runs. In an isolated neural preparation we recorded the electrophysiological responses of the statocyst nerve to static tilt (±19°) and sinusoids (±12°; 0.1 Hz). Spike sorting software was used to separate individual sensory cells' patterns out of a common trace. In correspondence with behavior we observed a VS decrease in animals after 16- (p < 0.05) and 32-day (p < 0.01) centrifugations. These findings reveal the capability of statoreceptors to adjust their sensitivity in response to a prolonged change in the force of gravity. Interestingly, background discharge rate increased after 16 and 32 days in hypergravity and continued to rise through the recovery period. This result indicates that adaptive mechanisms to novel gravity levels were long lasting, and re-adaptation from hypergravity is a more complex process than just "return to normal".
Neural network-based optimal adaptive output feedback control of a helicopter UAV.
Nodland, David; Zargarzadeh, Hassan; Jagannathan, Sarangapani
2013-07-01
Helicopter unmanned aerial vehicles (UAVs) are widely used for both military and civilian operations. Because the helicopter UAVs are underactuated nonlinear mechanical systems, high-performance controller design for them presents a challenge. This paper introduces an optimal controller design via an output feedback for trajectory tracking of a helicopter UAV, using a neural network (NN). The output-feedback control system utilizes the backstepping methodology, employing kinematic and dynamic controllers and an NN observer. The online approximator-based dynamic controller learns the infinite-horizon Hamilton-Jacobi-Bellman equation in continuous time and calculates the corresponding optimal control input by minimizing a cost function, forward-in-time, without using the value and policy iterations. Optimal tracking is accomplished by using a single NN utilized for the cost function approximation. The overall closed-loop system stability is demonstrated using Lyapunov analysis. Finally, simulation results are provided to demonstrate the effectiveness of the proposed control design for trajectory tracking.
Automatic spike detection based on adaptive template matching for extracellular neural recordings.
Kim, Sunghan; McNames, James
2007-09-30
Recordings of extracellular neural activity are used in many clinical applications and scientific studies. In most cases, these signals are analyzed as a point process, and a spike detection algorithm is required to estimate the times at which action potentials occurred. Recordings from high-density microelectrode arrays (MEAs) and low-impedance microelectrodes often have a low signal-to-noise ratio (SNR<10) and contain action potentials from more than one neuron. We describe a new detection algorithm based on template matching that only requires the user to specify the minimum and maximum firing rates of the neurons. The algorithm iteratively estimates the morphology of the most prominent action potentials. It is able to achieve a sensitivity of >90% with a false positive rate of <5Hz in recordings with an estimated SNR=3, and it performs better than an optimal threshold detector in recordings with an estimated SNR>2.5.
NASA Astrophysics Data System (ADS)
Zhao, Lin; Jia, Yingmin
2016-06-01
In this paper, a distributed output feedback consensus tracking control scheme is proposed for second-order multi-agent systems in the presence of uncertain nonlinear dynamics, external disturbances, input constraints, and partial loss of control effectiveness. The proposed controllers incorporate reduced-order filters to account for the unmeasured states, and the neural networks technique is implemented to approximate the uncertain nonlinear dynamics in the synthesis of control algorithms. In order to compensate the partial loss of actuator effectiveness faults, fault-tolerant parts are included in controllers. Using the Lyapunov approach and graph theory, it is proved that the controllers guarantee a group of agents that simultaneously track a common time-varying state of leader, even when the state of leader is available only to a subset of the members of a group. Simulation results are provided to demonstrate the effectiveness of the proposed consensus tracking method.
Automated detection of semagram-laden images using adaptive neural networks
NASA Astrophysics Data System (ADS)
Cerkez, Paul S.; Cannady, James D.
2012-04-01
Digital steganography is gaining wide acceptance in the world of electronic copyright stamping. Digital media that are easy to steal, such as graphics, photos and audio files, are being tagged with both visible and invisible copyright stamps (known as digital watermarking). However, these same techniques can also be used to hide communications between actors in criminal or covert activities. An inherent difficulty in detecting steganography is overcoming the variety of methods for hiding a message and the multitude of choices of available media. Another problem in steganography defense is the issue of detection speed since the encoded data is frequently time-sensitive. When a message is visually transmitted in a non-textual format (i.e., in an image) it is referred to as a semagram. Semagrams are relatively easy to create, but very difficult to detect. While steganography can often be identified by detecting digital modifications to an image's structure, an image-based semagram is more difficult because the message is the image itself. The work presented describes the creation of a novel, computer-based application, which uses hybrid hierarchical neural network architecture to detect the likely presence of a semagram message in an image. The prototype system was used to detect semagrams containing Morse Code messages. Based on the results of these experiments our approach provides a significant advance in the detection of complex semagram patterns. Specific results of the experiments and the potential practical applications of the neural network-based technology are discussed. This presentation provides the final results of our research experiments.
Behavioral and neural Darwinism: selectionist function and mechanism in adaptive behavior dynamics.
McDowell, J J
2010-05-01
An evolutionary theory of behavior dynamics and a theory of neuronal group selection share a common selectionist framework. The theory of behavior dynamics instantiates abstractly the idea that behavior is selected by its consequences. It implements Darwinian principles of selection, reproduction, and mutation to generate adaptive behavior in virtual organisms. The behavior generated by the theory has been shown to be quantitatively indistinguishable from that of live organisms. The theory of neuronal group selection suggests a mechanism whereby the abstract principles of the evolutionary theory may be implemented in the nervous systems of biological organisms. According to this theory, groups of neurons subserving behavior may be selected by synaptic modifications that occur when the consequences of behavior activate value systems in the brain. Together, these theories constitute a framework for a comprehensive account of adaptive behavior that extends from brain function to the behavior of whole organisms in quantitative detail.
Stress, sex and neural adaptation to a changing environment: mechanisms of neuronal remodeling
McEwen, Bruce S.
2010-01-01
The adult brain is much more resilient and adaptable than previously believed, and adaptive structural plasticity involves growth and shrinkage of dendritic trees, turnover of synapses and limited amounts of neurogenesis in the forebrain, especially the dentate gyrus of the hippocampal formation. Stress and sex hormones help to mediate adaptive structural plasticity, which has been extensively investigated in hippocampus and to a lesser extent in prefrontal cortex and amygdala, all brain regions that are involved in cognitive and emotional functions. Stress and sex hormones exert their effects on brain structural remodeling through both classical genomic as well as non-genomic mechanisms, and they do so in collaboration with neurotransmitters and other intra- and extracellular mediators. This review will illustrate the actions of estrogen on synapse formation in the hippocampus and the process of stress-induced remodelling of dendrites and synapses in the hippocampus, amygdala and prefrontal cortex. The influence of early developmental epigenetic events, such as early life stress and brain sexual differentiation, is noted along with the interactions between sex hormones and the effects of stress on the brain. Because hormones influence brain structure and function and because hormone secretion is governed by the brain, applied molecular neuroscience techniques can begin to reveal the role of hormones in brain-related disorders and the treatment of these diseases. A better understanding of hormone-brain interactions should promote more flexible approaches to the treatment of psychiatric disorders, as well as their prevention through both behavioral and pharmaceutical interventions. PMID:20840167
Fragkaki, A G; Farmaki, E; Thomaidis, N; Tsantili-Kakoulidou, A; Angelis, Y S; Koupparis, M; Georgakopoulos, C
2012-09-21
The comparison among different modelling techniques, such as multiple linear regression, partial least squares and artificial neural networks, has been performed in order to construct and evaluate models for prediction of gas chromatographic relative retention times of trimethylsilylated anabolic androgenic steroids. The performance of the quantitative structure-retention relationship study, using the multiple linear regression and partial least squares techniques, has been previously conducted. In the present study, artificial neural networks models were constructed and used for the prediction of relative retention times of anabolic androgenic steroids, while their efficiency is compared with that of the models derived from the multiple linear regression and partial least squares techniques. For overall ranking of the models, a novel procedure [Trends Anal. Chem. 29 (2010) 101-109] based on sum of ranking differences was applied, which permits the best model to be selected. The suggested models are considered useful for the estimation of relative retention times of designer steroids for which no analytical data are available.
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. PMID:25532213
Knowledge-based adaptive neural control of drum level in a boiler system
NASA Astrophysics Data System (ADS)
Tripathi, Nishith; Tran, Michael; VanLandingham, Hugh
1995-11-01
A boiler system is an integral component of a thermal power plant, and control of the water level in the drum of the boiler system is a critical operational consideration. For the drum level control, a 3-element proportional-integral-derivative (PID) control is a popular conventional approach. This scheme works satisfactorily in the absence of any process disturbances. However, when there are significant process disturbances, the 3-element PID control scheme does not perform well because of lack of knowledge of proper controller gains to cope with such disturbances. Inevitably over time and use, PID controllers get detuned. Hence, there is good motivation to investigate alternatives to this control scheme. Multivariable control of drum boiler systems has been studied by many researchers. However, these approaches assume some process model equations (to a more or less extent) to design a controller. This paper presents a model-free approach in the sense that no plant equations are assumed. Only data is used to gain knowledge about the process, and the performance of the existing PID control scheme is observed. Based on this process knowledge, an intelligent control technique is developed, (artificial) neural network control (NNC). The technique proposed in this paper was tested on a process simulator. This paper shows that an intelligent control scheme such as NNC gives better performance in rejecting process disturbances when compared to 3-element PID control scheme.
Neural network-based optimal adaptive output feedback control of a helicopter UAV.
Nodland, David; Zargarzadeh, Hassan; Jagannathan, Sarangapani
2013-07-01
Helicopter unmanned aerial vehicles (UAVs) are widely used for both military and civilian operations. Because the helicopter UAVs are underactuated nonlinear mechanical systems, high-performance controller design for them presents a challenge. This paper introduces an optimal controller design via an output feedback for trajectory tracking of a helicopter UAV, using a neural network (NN). The output-feedback control system utilizes the backstepping methodology, employing kinematic and dynamic controllers and an NN observer. The online approximator-based dynamic controller learns the infinite-horizon Hamilton-Jacobi-Bellman equation in continuous time and calculates the corresponding optimal control input by minimizing a cost function, forward-in-time, without using the value and policy iterations. Optimal tracking is accomplished by using a single NN utilized for the cost function approximation. The overall closed-loop system stability is demonstrated using Lyapunov analysis. Finally, simulation results are provided to demonstrate the effectiveness of the proposed control design for trajectory tracking. PMID:24808521
Huarte, Alicia; Ramos, Angel; Morera, Constantino; Garcia-Ibáñez, Luis; Battmer, Rolf; Dillier, Norbert; Wesarg, Thomas; Müller-Deile, Joachim; Hey, Mattias; Offeciers, Erwin; von Wallenberg, Ernst; Coudert, Chrystelle; Killian, Matthijs
2014-05-01
Custom Sound EP™ (CSEP) is an advanced flexible software tool dedicated to recording of electrically evoked compound action potentials (ECAPs) in Nucleus® recipients using Neural Response Telemetry™ (NRT™). European multi-centre studies of the Freedom™ cochlear implant system confirmed that CSEP offers tools to effectively record ECAP thresholds, amplitude growth functions, recovery functions, spread of excitation functions, and rate adaptation functions and an automated algorithm (AutoNRT™) to measure threshold profiles. This paper reports on rate adaptation measurements. Rate adaptation of ECAP amplitudes can successfully be measured up to rates of 495 pulses per second (pps) by repeating conventional ECAP measurements and over a wide range of rates up to 8000 pps using the masked response extraction technique. Rate adaptation did not show a predictable relationship with speech perception and coding strategy channel rate preference. The masked response extraction method offers opportunities to study long-term rate adaptation with well-defined and controlled stimulation paradigms. PMID:24559068
Uga, Minako; Dan, Ippeita; Sano, Toshifumi; Dan, Haruka; Watanabe, Eiju
2014-01-01
Abstract. An increasing number of functional near-infrared spectroscopy (fNIRS) studies utilize a general linear model (GLM) approach, which serves as a standard statistical method for functional magnetic resonance imaging (fMRI) data analysis. While fMRI solely measures the blood oxygen level dependent (BOLD) signal, fNIRS measures the changes of oxy-hemoglobin (oxy-Hb) and deoxy-hemoglobin (deoxy-Hb) signals at a temporal resolution severalfold higher. This suggests the necessity of adjusting the temporal parameters of a GLM for fNIRS signals. Thus, we devised a GLM-based method utilizing an adaptive hemodynamic response function (HRF). We sought the optimum temporal parameters to best explain the observed time series data during verbal fluency and naming tasks. The peak delay of the HRF was systematically changed to achieve the best-fit model for the observed oxy- and deoxy-Hb time series data. The optimized peak delay showed different values for each Hb signal and task. When the optimized peak delays were adopted, the deoxy-Hb data yielded comparable activations with similar statistical power and spatial patterns to oxy-Hb data. The adaptive HRF method could suitably explain the behaviors of both Hb parameters during tasks with the different cognitive loads during a time course, and thus would serve as an objective method to fully utilize the temporal structures of all fNIRS data. PMID:26157973
NASA Astrophysics Data System (ADS)
Wang, I.-Ting; Chang, Chih-Cheng; Chiu, Li-Wen; Chou, Teyuh; Hou, Tuo-Hung
2016-09-01
The implementation of highly anticipated hardware neural networks (HNNs) hinges largely on the successful development of a low-power, high-density, and reliable analog electronic synaptic array. In this study, we demonstrate a two-layer Ta/TaO x /TiO2/Ti cross-point synaptic array that emulates the high-density three-dimensional network architecture of human brains. Excellent uniformity and reproducibility among intralayer and interlayer cells were realized. Moreover, at least 50 analog synaptic weight states could be precisely controlled with minimal drifting during a cycling endurance test of 5000 training pulses at an operating voltage of 3 V. We also propose a new state-independent bipolar-pulse-training scheme to improve the linearity of weight updates. The improved linearity considerably enhances the fault tolerance of HNNs, thus improving the training accuracy.
Goicoechea, Héctor C; Collado, María S; Satuf, María L; Olivieri, Alejandro C
2002-10-01
The complementary use of partial least-squares (PLS) multivariate calibration and artificial neural networks (ANNs) for the simultaneous spectrophotometric determination of three active components in a pharmaceutical formulation has been explored. The presence of non-linearities caused by chemical interactions was confirmed by a recently discussed methodology based on Mallows augmented partial residual plots. Ternary mixtures of chlorpheniramine, naphazoline and dexamethasone in a matrix of excipients have been resolved by using PLS for the two major analytes (chlorpheniramine and naphazoline) and ANNs for the minor one (dexamethasone). Notwithstanding the large number of constituents, their high degree of spectral overlap and the occurrence of non-linearities, rapid and simultaneous analysis has been achieved, with reasonably good accuracy and precision. No extraction procedures using non-aqueous solvents are required.
Wang, I-Ting; Chang, Chih-Cheng; Chiu, Li-Wen; Chou, Teyuh; Hou, Tuo-Hung
2016-09-01
The implementation of highly anticipated hardware neural networks (HNNs) hinges largely on the successful development of a low-power, high-density, and reliable analog electronic synaptic array. In this study, we demonstrate a two-layer Ta/TaO x /TiO2/Ti cross-point synaptic array that emulates the high-density three-dimensional network architecture of human brains. Excellent uniformity and reproducibility among intralayer and interlayer cells were realized. Moreover, at least 50 analog synaptic weight states could be precisely controlled with minimal drifting during a cycling endurance test of 5000 training pulses at an operating voltage of 3 V. We also propose a new state-independent bipolar-pulse-training scheme to improve the linearity of weight updates. The improved linearity considerably enhances the fault tolerance of HNNs, thus improving the training accuracy. PMID:27483492
Azadi, Sama; Karimi-Jashni, Ayoub
2016-02-01
Predicting the mass of solid waste generation plays an important role in integrated solid waste management plans. In this study, the performance of two predictive models, Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) was verified to predict mean Seasonal Municipal Solid Waste Generation (SMSWG) rate. The accuracy of the proposed models is illustrated through a case study of 20 cities located in Fars Province, Iran. Four performance measures, MAE, MAPE, RMSE and R were used to evaluate the performance of these models. The MLR, as a conventional model, showed poor prediction performance. On the other hand, the results indicated that the ANN model, as a non-linear model, has a higher predictive accuracy when it comes to prediction of the mean SMSWG rate. As a result, in order to develop a more cost-effective strategy for waste management in the future, the ANN model could be used to predict the mean SMSWG rate. PMID:26482809
Azadi, Sama; Karimi-Jashni, Ayoub
2016-02-01
Predicting the mass of solid waste generation plays an important role in integrated solid waste management plans. In this study, the performance of two predictive models, Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) was verified to predict mean Seasonal Municipal Solid Waste Generation (SMSWG) rate. The accuracy of the proposed models is illustrated through a case study of 20 cities located in Fars Province, Iran. Four performance measures, MAE, MAPE, RMSE and R were used to evaluate the performance of these models. The MLR, as a conventional model, showed poor prediction performance. On the other hand, the results indicated that the ANN model, as a non-linear model, has a higher predictive accuracy when it comes to prediction of the mean SMSWG rate. As a result, in order to develop a more cost-effective strategy for waste management in the future, the ANN model could be used to predict the mean SMSWG rate.
Adaptive independent component analysis to analyze electrocardiograms
NASA Astrophysics Data System (ADS)
Yim, Seong-Bin; Szu, Harold H.
2001-03-01
In this work, we apply adaptive version independent component analysis (ADAPTIVE ICA) to the nonlinear measurement of electro-cardio-graphic (ECG) signals for potential detection of abnormal conditions in the heart. In principle, unsupervised ADAPTIVE ICA neural networks can demix the components of measured ECG signals. However, the nonlinear pre-amplification and post measurement processing make the linear ADAPTIVE ICA model no longer valid. This is possible because of a proposed adaptive rectification pre-processing is used to linearize the preamplifier of ECG, and then linear ADAPTIVE ICA is used in iterative manner until the outputs having their own stable Kurtosis. We call such a new approach adaptive ADAPTIVE ICA. Each component may correspond to individual heart function, either normal or abnormal. Adaptive ADAPTIVE ICA neural networks have the potential to make abnormal components more apparent, even when they are masked by normal components in the original measured signals. This is particularly important for diagnosis well in advance of the actual onset of heart attack, in which abnormalities in the original measured ECG signals may be difficult to detect. This is the first known work that applies Adaptive ADAPTIVE ICA to ECG signals beyond noise extraction, to the detection of abnormal heart function.
Roberto, Baccoli; Ubaldo, Carlini; Stefano, Mariotti; Roberto, Innamorati; Elisa, Solinas; Paolo, Mura
2010-06-15
This paper deals with the development of methods for non steady state test of solar thermal collectors. Our goal is to infer performances in steady-state conditions in terms of the efficiency curve when measures in transient conditions are the only ones available. We take into consideration the method of identification of a system in dynamic conditions by applying a Graybox Identification Model and a Dynamic Adaptative Linear Neural Network (ALNN) model. The study targets the solar collector with evacuated pipes, such as Dewar pipes. The mathematical description that supervises the functioning of the solar collector in transient conditions is developed using the equation of the energy balance, with the aim of determining the order and architecture of the two models. The input and output vectors of the two models are constructed, considering the measures of 4 days of solar radiation, flow mass, environment and heat-transfer fluid temperature in the inlet and outlet from the thermal solar collector. The efficiency curves derived from the two models are detected in correspondence to the test and validation points. The two synthetic simulated efficiency curves are compared with the actual efficiency curve certified by the Swiss Institute Solartechnik Puffung Forschung which tested the solar collector performance in steady-state conditions according to the UNI-EN 12975 standard. An acquisition set of measurements of only 4 days in the transient condition was enough to trace through a Graybox State Space Model the efficiency curve of the tested solar thermal collector, with a relative error of synthetic values with respect to efficiency certified by SPF, lower than 0.5%, while with the ALNN model the error is lower than 2.2% with respect to certified one. (author)
Jalali-Heravi, Mehdi; Kyani, Anahita
2008-06-01
The purpose of this study was to develop the structure-toxicity relationships for a large group of 268 substituted benzene to the ciliate Tetrahymena pyriformis using mechanistically interpretable descriptors. The shuffling-adaptive neuro fuzzy inference system (Shuffling-ANFIS) has been successfully applied to select the important factors affecting the toxicity of substituted benzenes to T. pyriformis. The results of the proposed model were compared with the model of linear-free energy response surface and also the principal component analysis Bayesian-regularized neural network (PCA-BRANN) trained using the same data. The presented model shows a better statistical parameter in comparison with the previous models. The results of the model are promising and descriptive. Five descriptors of octanol-water partition coefficient (logP), bond information content (BIC0), number of R-CX-R (C-026), eigenvalue sum from Z weighted distance matrix (SEigZ) and fragment based polar surface area (PSA) selected by Shuffling-ANFIS reveal the role of hydrophobicity, electronic and steric interactions in the mechanism of toxic action. Sequential zeroing of weights (SZW) as a sensitivity analysis method revealed that the hydrophobicity and electronic interactions play a major role in toxicity of these compounds. Satisfactory results (q(2)=0.828 and RMSE=0.348) in comparison with the previous works indicate that the Shuffling-ANFIS-ANN technique is able to model a diverse chemical class with more than one mechanism of toxicity by using simple and interpretable descriptors. Shuffling-ANFIS can be used as powerful feature selection technique, because its application in prediction of toxicity potency results in good statistical and interpretable physiochemical parameters. PMID:18499226
Smalt, Christopher J; Talavage, Thomas M; Pisoni, David B; Svirsky, Mario A
2011-01-01
A portable real-time speech processor that implements an acoustic simulation model of a cochlear implant (CI) has been developed on the Apple iPhone / iPod Touch to permit testing and experimentation under extended exposure in real-world environments. This simulator allows for both a variable number of noise band channels and electrode insertion depth. Utilizing this portable CI simulator, we tested perceptual learning in normal hearing listeners by measuring word and sentence comprehension behaviorally before and after 2 weeks of exposure. To evaluate changes in neural activation related to adaptation to transformed speech, fMRI was also conducted. Differences in brain activation after training occurred in the inferior frontal gyrus and areas related to language processing. A 15-20% improvement in word and sentence comprehension of cochlear implant simulated speech was also observed. These results demonstrate the effectiveness of a portable CI simulator as a research tool and provide new information about the physiological changes that accompany perceptual learning of degraded auditory input. PMID:22254517
Amiri, Mohammad J; Abedi-Koupai, Jahangir; Eslamian, Sayed S; Mousavi, Sayed F; Hasheminejad, Hasti
2013-01-01
To evaluate the performance of Adaptive Neural-Based Fuzzy Inference System (ANFIS) model in estimating the efficiency of Pb (II) ions removal from aqueous solution by ostrich bone ash, a batch experiment was conducted. Five operational parameters including adsorbent dosage (C(s)), initial concentration of Pb (II) ions (C(o)), initial pH, temperature (T) and contact time (t) were taken as the input data and the adsorption efficiency (AE) of bone ash as the output. Based on the 31 different structures, 5 ANFIS models were tested against the measured adsorption efficiency to assess the accuracy of each model. The results showed that ANFIS5, which used all input parameters, was the most accurate (RMSE = 2.65 and R(2) = 0.95) and ANFIS1, which used only the contact time input, was the worst (RMSE = 14.56 and R(2) = 0.46). In ranking the models, ANFIS4, ANFIS3 and ANFIS2 ranked second, third and fourth, respectively. The sensitivity analysis revealed that the estimated AE is more sensitive to the contact time, followed by pH, initial concentration of Pb (II) ions, adsorbent dosage, and temperature. The results showed that all ANFIS models overestimated the AE. In general, this study confirmed the capabilities of ANFIS model as an effective tool for estimation of AE. PMID:23383640
NASA Astrophysics Data System (ADS)
Pagani, M.; Iellamo, F.; Lucini, D.; Pizzinelli, P.; Castrucci, F.; Peruzzi, G.; Malliani, A.
The goal of the study was to characterize the changes in neurovegetative control of the circulation, attending the presumed physiological and psychological stress originated by the isolation and confinement typical of the living condition of space stations, as simulated in a ground based unit, using time and frequency domain analysis. As a secondary goal we sought to verify the implementation of real time data acquisition, for off line spectral analisys of R-R interval, systolic arterial pressure (by Finapres) and respiration (by PVF2 piezoelectric sensors). We addressed the cardiorespiratory and neurovegetative responses to standardized, simple Stressors (active standing, dynamic and static handgrip) on the EXEMSI 92 crew, before, during and after the isolation period. On average the appropriate excitatory responses (to stand, dynamic and static handgrip) were elicited also in isolation and confinement. Active standing and small masses muscular exercises are easy to be performed in a confined and isolated environment and provide a valuable tool for investigating the adaptational changes in neural control mechanisms. The possibility there exists of using this time and frequency domain approach to monitor the level of performance and well being of the space crew in (quasi) real time.
NASA Astrophysics Data System (ADS)
Salehi, Mohammad Reza; Noori, Leila; Abiri, Ebrahim
2016-11-01
In this paper, a subsystem consisting of a microstrip bandpass filter and a microstrip low noise amplifier (LNA) is designed for WLAN applications. The proposed filter has a small implementation area (49 mm2), small insertion loss (0.08 dB) and wide fractional bandwidth (FBW) (61%). To design the proposed LNA, the compact microstrip cells, an field effect transistor, and only a lumped capacitor are used. It has a low supply voltage and a low return loss (-40 dB) at the operation frequency. The matching condition of the proposed subsystem is predicted using subsystem analysis, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). To design the proposed filter, the transmission matrix of the proposed resonator is obtained and analysed. The performance of the proposed ANN and ANFIS models is tested using the numerical data by four performance measures, namely the correlation coefficient (CC), the mean absolute error (MAE), the average percentage error (APE) and the root mean square error (RMSE). The obtained results show that these models are in good agreement with the numerical data, and a small error between the predicted values and numerical solution is obtained.
NASA Astrophysics Data System (ADS)
Roach, James; Sander, Leonard; Zochowski, Michal
Auto-associative memory is the ability to retrieve a pattern from a small fraction of the pattern and is an important function of neural networks. Within this context, memories that are stored within the synaptic strengths of networks act as dynamical attractors for network firing patterns. In networks with many encoded memories, some attractors will be stronger than others. This presents the problem of how networks switch between attractors depending on the situation. We suggest that regulation of neuronal spike-frequency adaptation (SFA) provides a universal mechanism for network-wide attractor selectivity. Here we demonstrate in a Hopfield type attractor network that neurons minimal SFA will reliably activate in the pattern corresponding to a local attractor and that a moderate increase in SFA leads to the network to converge to the strongest attractor state. Furthermore, we show that on long time scales SFA allows for temporal sequences of activation to emerge. Finally, using a model of cholinergic modulation within the cortex we argue that dynamic regulation of attractor preference by SFA could be critical for the role of acetylcholine in attention or for arousal states in general. This work was supported by: NSF Graduate Research Fellowship Program under Grant No. DGE 1256260 (JPR), NSF CMMI 1029388 (MRZ) and NSF PoLS 1058034 (MRZ & LMS).
Krusemark, Elizabeth A; Novak, Lucas R; Gitelman, Darren R; Li, Wen
2013-09-25
Phylogenetically the most ancient sense, olfaction is characterized by a unique intimacy with the emotion system. However, mechanisms underlying olfaction-emotion interaction remain unclear, especially in an ever-changing environment and dynamic internal milieu. Perturbing the internal state with anxiety induction in human subjects, we interrogated emotion-state-dependent olfactory processing in a functional magnetic resonance imaging (fMRI) study. Following anxiety induction, initially neutral odors become unpleasant and take longer to detect, accompanied by augmented response to these odors in the olfactory (anterior piriform and orbitofrontal) cortices and emotion-relevant pregenual anterior cingulate cortex. In parallel, the olfactory sensory relay adapts with increased anxiety, incorporating amygdala as an integral step via strengthened (afferent or efferent) connections between amygdala and all levels of the olfactory cortical hierarchy. This anxiety-state-dependent neural circuitry thus enables cumulative infusion of limbic affective information throughout the olfactory sensory progression, thereby driving affectively charged olfactory perception. These findings could constitute an olfactory etiology model of emotional disorders, as exaggerated emotion-olfaction interaction in negative mood states turns innocuous odors aversive, fueling anxiety and depression with rising ambient sensory stress.
Neural Mechanisms Behind Identification of Leptokurtic Noise and Adaptive Behavioral Response.
d'Acremont, Mathieu; Bossaerts, Peter
2016-04-01
Large-scale human interaction through, for example, financial markets causes ceaseless random changes in outcome variability, producing frequent and salient outliers that render the outcome distribution more peaked than the Gaussian distribution, and with longer tails. Here, we study how humans cope with this evolutionary novel leptokurtic noise, focusing on the neurobiological mechanisms that allow the brain, 1) to recognize the outliers as noise and 2) to regulate the control necessary for adaptive response. We used functional magnetic resonance imaging, while participants tracked a target whose movements were affected by leptokurtic noise. After initial overreaction and insufficient subsequent correction, participants improved performance significantly. Yet, persistently long reaction times pointed to continued need for vigilance and control. We ran a contrasting treatment where outliers reflected permanent moves of the target, as in traditional mean-shift paradigms. Importantly, outliers were equally frequent and salient. There, control was superior and reaction time was faster. We present a novel reinforcement learning model that fits observed choices better than the Bayes-optimal model. Only anterior insula discriminated between the 2 types of outliers. In both treatments, outliers initially activated an extensive bottom-up attention and belief network, followed by sustained engagement of the fronto-parietal control network.
Neural Mechanisms Behind Identification of Leptokurtic Noise and Adaptive Behavioral Response
d'Acremont, Mathieu; Bossaerts, Peter
2016-01-01
Large-scale human interaction through, for example, financial markets causes ceaseless random changes in outcome variability, producing frequent and salient outliers that render the outcome distribution more peaked than the Gaussian distribution, and with longer tails. Here, we study how humans cope with this evolutionary novel leptokurtic noise, focusing on the neurobiological mechanisms that allow the brain, 1) to recognize the outliers as noise and 2) to regulate the control necessary for adaptive response. We used functional magnetic resonance imaging, while participants tracked a target whose movements were affected by leptokurtic noise. After initial overreaction and insufficient subsequent correction, participants improved performance significantly. Yet, persistently long reaction times pointed to continued need for vigilance and control. We ran a contrasting treatment where outliers reflected permanent moves of the target, as in traditional mean-shift paradigms. Importantly, outliers were equally frequent and salient. There, control was superior and reaction time was faster. We present a novel reinforcement learning model that fits observed choices better than the Bayes-optimal model. Only anterior insula discriminated between the 2 types of outliers. In both treatments, outliers initially activated an extensive bottom-up attention and belief network, followed by sustained engagement of the fronto-parietal control network. PMID:26850528
Wolf, Susanne A; Steiner, Barbara; Wengner, Antje; Lipp, Martin; Kammertoens, Thomas; Kempermann, Gerd
2009-09-01
To understand the link between peripheral immune activation and neuronal precursor biology, we investigated the effect of T-cell activation on adult hippocampal neurogenesis in female C57Bl/6 mice. A peripheral adaptive immune response triggered by adjuvant-induced rheumatoid arthritis (2 microg/microl methylated BSA) or staphylococcus enterotoxin B (EC(50) of 0.25 microg/ml per 20 g body weight) was associated with a transient increase in hippocampal precursor cell proliferation and neurogenesis as assessed by immunohistochemistry and confocal microscopy. Both treatments were paralleled by an increase in corticosterone levels in the hippocampus 1- to 2-fold over the physiological amount measured by quantitative radioimmunoassay. In contrast, intraperitoneal administration of the innate immune response activator lipopolysaccaride (EC(50) of 0.5 microg/ml per 20 g body weight) led to a chronic 5-fold increase of hippocampal glucocorticoid levels and a decrease of adult neurogenesis. In vitro exposure of murine neuronal progenitor cells to corticosterone triggered either cell death at high (1.5 nM) or proliferation at low (0.25 nM) concentrations. This effect could be blocked using a viral vector system expressing a transdomain of the glucocorticoid receptor. We suggest an evolutionary relevant communication route for the brain to respond to environmental stressors like inflammation mediated by glucocorticoid levels in the hippocampus.
de Boer, Maarten D; Maganaris, Constantinos N; Seynnes, Olivier R; Rennie, Michael J; Narici, Marco V
2007-09-15
Muscles and tendons are highly adaptive to changes in chronic loading, though little is known about the adaptative time course. We tested the hypothesis that, in response to unilateral lower limb suspension (ULLS), the magnitude of tendon mechanical adaptations would match or exceed those of skeletal muscle. Seventeen men (1.79 +/- 0.05 m, 76.6 +/- 10.3 kg, 22.3 +/- 3.8 years) underwent ULLS for 23 days (n = 9) or acted as controls (n = 8). Knee extensor (KE) torque, voluntary activation (VA), cross-sectional area (CSA) (by magnetic resonance imaging), vastus lateralis fascicle length (L(f)) and pennation angle (), patellar tendon stiffness and Young's modulus (by ultrasonography) were measured before, during and at the end of ULLS. After 14 and 23 days (i) KE torque decreased by 14.8 +/- 5.5% (P < 0.001) and 21.0 +/- 7.1% (P < 0.001), respectively; (ii) VA did not change; (iii) KE CSA decreased by 5.2 +/- 0.7% (P < 0.001) and 10.0 +/- 2.0% (P < 0.001), respectively; L(f) decreased by 5.9% (n.s.) and 7.7% (P < 0.05), respectively, and by 3.2% (P < 0.05) and 7.6% (P < 0.01); (iv) tendon stiffness decreased by 9.8 +/- 8.2% (P < 0.05) and 29.3 +/- 11.5% (P < 0.005), respectively, and Young's modulus by 9.2 +/- 8.2% (P < 0.05) and 30.1 +/- 11.9% (P < 0.01), respectively, with no changes in the controls. Hence, ULLS induces rapid losses of KE muscle size, architecture and function, but not in neural drive. Significant deterioration in tendon mechanical properties also occurs within 2 weeks, exacerbating in the third week of ULLS. Rehabilitation to limit muscle and tendon deterioration should probably start within 2 weeks of unloading.
NASA Astrophysics Data System (ADS)
Kamran, M. Ahmad; Hong, Keum-Shik
2013-10-01
Objective. Functional near-infrared spectroscopy (fNIRS) is an emerging non-invasive brain imaging technique that measures brain activities by using near-infrared light of 650-950 nm wavelength. The major advantages of fNIRS are its low cost, portability, and good temporal resolution as a plausible solution to real-time imaging. Recent research has shown the great potential of fNIRS as a tool for brain-computer interfaces. Approach. This paper presents the first novel technique for fNIRS-based modelling of brain activities using the linear parameter-varying (LPV) method and adaptive signal processing. The output signal of each channel is assumed to be an output of an LPV system with unknown coefficients that are optimally estimated by the affine projection algorithm. The parameter vector is assumed to be Gaussian. Main results. The general linear model (GLM) is very popular and is a commonly used method for the analysis of functional MRI data, but it has certain limitations in the case of optical signals. The proposed model is more efficient in the sense that it allows the user to define more states. Moreover, unlike most previous models, it is online. The present results, showing improvement, were verified by random finger-tapping tasks in extensive experiments. We used 24 states, which can be reduced or increased depending on the cost of computation and requirements. Significance. The t-statistics were employed to determine the activation maps and to verify the significance of the results. Comparison of the proposed technique and two existing GLM-based algorithms shows an improvement in the estimation of haemodynamic response. Additionally, the convergence of the proposed algorithm is shown by error reduction in consecutive iterations.
Lee, Dongyul; Lee, Chaewoo
2014-01-01
The advancement in wideband wireless network supports real time services such as IPTV and live video streaming. However, because of the sharing nature of the wireless medium, efficient resource allocation has been studied to achieve a high level of acceptability and proliferation of wireless multimedia. Scalable video coding (SVC) with adaptive modulation and coding (AMC) provides an excellent solution for wireless video streaming. By assigning different modulation and coding schemes (MCSs) to video layers, SVC can provide good video quality to users in good channel conditions and also basic video quality to users in bad channel conditions. For optimal resource allocation, a key issue in applying SVC in the wireless multicast service is how to assign MCSs and the time resources to each SVC layer in the heterogeneous channel condition. We formulate this problem with integer linear programming (ILP) and provide numerical results to show the performance under 802.16 m environment. The result shows that our methodology enhances the overall system throughput compared to an existing algorithm.
Lee, Chaewoo
2014-01-01
The advancement in wideband wireless network supports real time services such as IPTV and live video streaming. However, because of the sharing nature of the wireless medium, efficient resource allocation has been studied to achieve a high level of acceptability and proliferation of wireless multimedia. Scalable video coding (SVC) with adaptive modulation and coding (AMC) provides an excellent solution for wireless video streaming. By assigning different modulation and coding schemes (MCSs) to video layers, SVC can provide good video quality to users in good channel conditions and also basic video quality to users in bad channel conditions. For optimal resource allocation, a key issue in applying SVC in the wireless multicast service is how to assign MCSs and the time resources to each SVC layer in the heterogeneous channel condition. We formulate this problem with integer linear programming (ILP) and provide numerical results to show the performance under 802.16 m environment. The result shows that our methodology enhances the overall system throughput compared to an existing algorithm. PMID:25276862
Babapour, R; Naghdi, R; Ghajar, I; Ghodsi, R
2015-07-01
Rock proportion of subsoil directly influences the cost of embankment in forest road construction. Therefore, developing a reliable framework for rock ratio estimation prior to the road planning could lead to more light excavation and less cost operations. Prediction of rock proportion was subjected to statistical analyses using the application of Artificial Neural Network (ANN) in MATLAB and five link functions of ordinal logistic regression (OLR) according to the rock type and terrain slope properties. In addition to bed rock and slope maps, more than 100 sample data of rock proportion were collected, observed by geologists, from any available bed rock of every slope class. Four predictive models were developed for rock proportion, employing independent variables and applying both the selected probit link function of OLR and Layer Recurrent and Feed forward back propagation networks of Neural Networks. In ANN, different numbers of neurons are considered for the hidden layer(s). Goodness of the fit measures distinguished that ANN models produced better results than OLR with R (2) = 0.72 and Root Mean Square Error = 0.42. Furthermore, in order to show the applicability of the proposed approach, and to illustrate the variability of rock proportion resulted from the model application, the optimum models were applied to a mountainous forest in where forest road network had been constructed in the past.
Pehlevan, Cengiz; Hu, Tao; Chklovskii, Dmitri B
2015-07-01
Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis, by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost function, these rules are nonlocal and hence biologically implausible. At the same time, biologically plausible local rules have been postulated rather than derived from a principled cost function. Here, to bridge this gap, we derive a biologically plausible network for subspace learning on streaming data by minimizing a principled cost function. In a departure from previous work, where cost was quantified by the representation, or reconstruction, error, we adopt a multidimensional scaling cost function for streaming data. The resulting algorithm relies only on biologically plausible Hebbian and anti-Hebbian local learning rules. In a stochastic setting, synaptic weights converge to a stationary state, which projects the input data onto the principal subspace. If the data are generated by a nonstationary distribution, the network can track the principal subspace. Thus, our result makes a step toward an algorithmic theory of neural computation.
Wang, Hsing-Kuo; Un, Chi-Pang; Lin, Kwan-Hwa; Chang, En-Chung; Shiang, Tzyy-Yuang; Su, Sheng-Chu
2014-01-01
This study investigated and compared the effects of an eight-week program of whole body vibration combined with counter-movement jumping (WBV + CMJ) or counter-movement jumping (CMJ) alone on players. Twenty-four men's volleyball players of league A or B were randomized to the WBV + CMJ or CMJ groups (n = 12 and 12; mean [SD] age of 21.4 [2.2] and 21.7 [2.2] y; height of 175.6 [4.6] and 177.6 [3.9] cm; and weight, 69.9 [12.8] and 70.5 [10.7] kg, respectively). The pre- and post-training values of the following measurements were compared: H-reflex, first volitional (V)-wave, rate of electromyography rise (RER) in the triceps surae and absolute rate of force development (RFD) in plantarflexion and vertical jump height. After training, the WBV + CMJ group exhibited increases in H reflexes (p = 0.029 and <0.001); V-wave (p < 0.001); RER (p = 0.003 and <0.001); jump height (p < 0.001); and RFD (p = 0.006 and <0.001). The post-training values of V wave (p = 0.006) and RFD at 0-50 (p = 0.009) and 0-200 ms (p = 0.008) in the WBV + CMJ group were greater than those in the CMJ group. This study shows that a combination of WBV and power exercise could impact neural adaptation and leads to greater fast force capacity than power exercise alone in male players.
NASA Astrophysics Data System (ADS)
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.
NASA Astrophysics Data System (ADS)
Vítková, Gabriela; Novotný, Karel; Prokeš, Lubomír; Hrdlička, Aleš; Kaiser, Jozef; Novotný, Jan; Malina, Radomír; Prochazka, David
2012-07-01
The goal of this paper is to compare two selected statistical techniques used for identification of archeological materials merely on the base of their spectra obtained by stand-off laser-induced breakdown spectroscopy (stand-off LIBS). Data processing using linear discriminant analysis (LDA) and artificial neural networks (ANN) were applied on spectra of 18 different samples, some of them archeological and some recent, containing 7 types of material (i.e. shells, mortar, bricks, soil pellets, ceramic, teeth and bones). As the input data PCA scores were taken. The intended aim of this work is to create a database for simple and fast identification of archeological or paleontological materials in situ. This approach can speed up and simplify the sampling process during archeological excavations that nowadays tend to be quite damaging and time-consuming.
NASA Astrophysics Data System (ADS)
Bargatze, L. F.
2015-12-01
Active Data Archive Product Tracking (ADAPT) is a collection of software routines that permits one to generate XML metadata files to describe and register data products in support of the NASA Heliophysics Virtual Observatory VxO effort. ADAPT is also a philosophy. The ADAPT concept is to use any and all available metadata associated with scientific data to produce XML metadata descriptions in a consistent, uniform, and organized fashion to provide blanket access to the full complement of data stored on a targeted data server. In this poster, we present an application of ADAPT to describe all of the data products that are stored by using the Common Data File (CDF) format served out by the CDAWEB and SPDF data servers hosted at the NASA Goddard Space Flight Center. These data servers are the primary repositories for NASA Heliophysics data. For this purpose, the ADAPT routines have been used to generate data resource descriptions by using an XML schema named Space Physics Archive, Search, and Extract (SPASE). SPASE is the designated standard for documenting Heliophysics data products, as adopted by the Heliophysics Data and Model Consortium. The set of SPASE XML resource descriptions produced by ADAPT includes high-level descriptions of numerical data products, display data products, or catalogs and also includes low-level "Granule" descriptions. A SPASE Granule is effectively a universal access metadata resource; a Granule associates an individual data file (e.g. a CDF file) with a "parent" high-level data resource description, assigns a resource identifier to the file, and lists the corresponding assess URL(s). The CDAWEB and SPDF file systems were queried to provide the input required by the ADAPT software to create an initial set of SPASE metadata resource descriptions. Then, the CDAWEB and SPDF data repositories were queried subsequently on a nightly basis and the CDF file lists were checked for any changes such as the occurrence of new, modified, or deleted
Rotstein, Horacio G; Nadim, Farzan
2014-08-01
Many neuron types exhibit preferred frequency responses in their voltage amplitude (resonance) or phase shift to subthreshold oscillatory currents, but the effect of biophysical parameters on these properties is not well understood. We propose a general framework to analyze the role of different ionic currents and their interactions in shaping the properties of impedance amplitude and phase in linearized biophysical models and demonstrate this approach in a two-dimensional linear model with two effective conductances g L and g1. We compute the key attributes of impedance and phase (resonance frequency and amplitude, zero-phase frequency, selectivity, etc.) in the g(L) - g1 parameter space. Using these attribute diagrams we identify two basic mechanisms for the generation of resonance: an increase in the resonance amplitude as g1 increases while the overall impedance is decreased, and an increase in the maximal impedance, without any change in the input resistance, as the ionic current time constant increases. We use the attribute diagrams to analyze resonance and phase of the linearization of two biophysical models that include resonant (I h or slow potassium) and amplifying currents (persistent sodium). In the absence of amplifying currents, the two models behave similarly as the conductances of the resonant currents is increased whereas, with the amplifying current present, the two models have qualitatively opposite responses. This work provides a general method for decoding the effect of biophysical parameters on linear membrane resonance and phase by tracking trajectories, parametrized by the relevant biophysical parameter, in pre-constructed attribute diagrams. PMID:24254440
Ghose, Kaushik; Moss, Cynthia F
2006-02-01
Adaptive behaviors require sensorimotor computations that convert information represented initially in sensory coordinates to commands for action in motor coordinates. Fundamental to these computations is the relationship between the region of the environment sensed by the animal (gaze) and the animal's locomotor plan. Studies of visually guided animals have revealed an anticipatory relationship between gaze direction and the locomotor plan during target-directed locomotion. Here, we study an acoustically guided animal, an echolocating bat, and relate acoustic gaze (direction of the sonar beam) to flight planning as the bat searches for and intercepts insect prey. We show differences in the relationship between gaze and locomotion as the bat progresses through different phases of insect pursuit. We define acoustic gaze angle, theta(gaze), to be the angle between the sonar beam axis and the bat's flight path. We show that there is a strong linear linkage between acoustic gaze angle at time t [theta(gaze)(t)] and flight turn rate at time t + tau into the future [theta(flight) (t + tau)], which can be expressed by the formula theta(flight) (t + tau) = ktheta(gaze)(t). The gain, k, of this linkage depends on the bat's behavioral state, which is indexed by its sonar pulse rate. For high pulse rates, associated with insect attacking behavior, k is twice as high compared with low pulse rates, associated with searching behavior. We suggest that this adjustable linkage between acoustic gaze and motor output in a flying echolocating bat simplifies the transformation of auditory information to flight motor commands.
Jung, JeYoung; Lambon Ralph, Matthew A.
2016-01-01
Higher cognitive function reflects the interaction of a network of multiple brain regions. Previous investigations have plotted out these networks using functional or structural connectivity approaches. While these map the topography of the regions involved, they do not explore the key aspect of this neuroscience principle—namely that the regions interact in a dynamic fashion. Here, we achieved this aim with respect to semantic memory. Although converging evidence implicates the anterior temporal lobes (ATLs), bilaterally, as a crucial component in semantic representation, the underlying neural interplay between the ATLs remains unclear. By combining continuous theta-burst stimulation (cTBS) with functional magnetic resonance imaging (fMRI), we perturbed the left ventrolateral ATL (vATL) and investigated acute changes in neural activity and effective connectivity of the semantic system. cTBS resulted in decreased activity at the target region and compensatory, increased activity at the contralateral vATL. In addition, there were task-specific increases in effective connectivity between the vATLs, reflecting an increased facilitatory intrinsic connectivity from the right to left vATL. Our results suggest that semantic representation is founded on a flexible, adaptive bilateral neural system and reveals an adaptive plasticity-based mechanism that might support functional recovery after unilateral damage in neurological patients. PMID:27242027
Liu, Yan-Jun; Zhou, Ning
2010-10-01
Based on the universal approximation property of the fuzzy-neural networks, an adaptive fuzzy-neural observer design algorithm is studied for a class of nonlinear SISO systems with both a completely unknown function and an unknown dead-zone input. The fuzzy-neural networks are used to approximate the unknown nonlinear function. Because it is assumed that the system states are unmeasured, an observer needs to be designed to estimate those unmeasured states. In the previous works with the observer design based on the universal approximator, when the dead-zone input appears it is ignored and the stability of the closed-loop system will be affected. In this paper, the proposed algorithm overcomes the affections of dead-zone input for the stability of the systems. Moreover, the dead-zone parameters are assumed to be unknown and will be adjusted adaptively as well as the sign function being introduced to compensate the dead-zone. With the aid of the Lyapunov analysis method, the stability of the closed-loop system is proven. A simulation example is provided to illustrate the feasibility of the control algorithm presented in this paper.
Multiobjective algebraic synthesis of neural control systems by implicit model following.
Ferrari, Silvia
2009-03-01
The advantages brought about by using classical linear control theory in conjunction with neural approximators have long been recognized in the literature. In particular, using linear controllers to obtain the starting neural control design has been shown to be a key step for the successful development and implementation of adaptive-critic neural controllers. Despite their adaptive capabilities, neural controllers are often criticized for not providing the same performance and stability guarantees as classical linear designs. Therefore, this paper develops an algebraic synthesis procedure for designing dynamic output-feedback neural controllers that are closed-loop stable and meet the same performance objectives as any classical linear design. The performance synthesis problem is addressed by deriving implicit model-following algebraic relationships between model matrices, obtained from the classical design, and the neural control parameters. Additional linear matrix inequalities (LMIs) conditions for closed-loop exponential stability of the neural controller are derived using existing integral quadratic constraints (IQCs) for operators with repeated slope-restricted nonlinearities. The approach is demonstrated by designing a recurrent neural network controller for a highly maneuverable tailfin-controlled missile that meets multiple design objectives, including pole placement for transient tuning, H(infinity) and H(2) performance in the presence of parameter uncertainty, and command-input tracking. PMID:19203887
Carré, Arnaud; Gierski, Fabien; Lemogne, Cédric; Tran, Eric; Raucher-Chéné, Delphine; Béra-Potelle, Céline; Portefaix, Christophe; Kaladjian, Arthur; Pierot, Laurent; Besche-Richard, Chrystel; Limosin, Frédéric
2014-06-01
Social anxiety disorder (SAD), which is characterized by the fear of being rejected and negatively evaluated, involves altered brain activation during the processing of negative emotions in a social context. Although associated temperament traits, such as shyness or behavioral inhibition, have been studied, there is still insufficient knowledge to support the dimensional approach, which assumes a continuum from subclinical to clinical levels of social anxiety symptoms. This study used functional magnetic resonance imaging (fMRI) to examine the neural bases of individual differences in social anxiety. Our sample included participants with both healthy/subclinical as well as clinical levels of social anxiety. Forty-six participants with a wide range of social anxiety levels performed a gender decision task with emotional facial expressions during fMRI scanning. Activation in the left anterior insula and right lateral prefrontal cortex in response to angry faces was positively correlated with the level of social anxiety in a regression analysis. The results substantiate, with a dimensional approach, those obtained in previous studies that involved SAD patients or healthy and subclinical participants. It may help to refine further therapeutic strategies based on markers of social anxiety.
Avci, Derya; Leblebicioglu, Mehmet Kemal; Poyraz, Mustafa; Dogantekin, Esin
2014-02-01
So far, analysis and classification of urine cells number has become an important topic for medical diagnosis of some diseases. Therefore, in this study, we suggest a new technique based on Adaptive Discrete Wavelet Entropy Energy and Neural Network Classifier (ADWEENN) for Recognition of Urine Cells from Microscopic Images Independent of Rotation and Scaling. Some digital image processing methods such as noise reduction, contrast enhancement, segmentation, and morphological process are used for feature extraction stage of this ADWEENN in this study. Nowadays, the image processing and pattern recognition topics have come into prominence. The image processing concludes operation and design of systems that recognize patterns in data sets. In the past years, very difficulty in classification of microscopic images was the deficiency of enough methods to characterize. Lately, it is seen that, multi-resolution image analysis methods such as Gabor filters, discrete wavelet decompositions are superior to other classic methods for analysis of these microscopic images. In this study, the structure of the ADWEENN method composes of four stages. These are preprocessing stage, feature extraction stage, classification stage and testing stage. The Discrete Wavelet Transform (DWT) and adaptive wavelet entropy and energy is used for adaptive feature extraction in feature extraction stage to strengthen the premium features of the Artificial Neural Network (ANN) classifier in this study. Efficiency of the developed ADWEENN method was tested showing that an avarage of 97.58% recognition succes was obtained.
Wang, Chun-Hao; Tsai, Chia-Liang; Tseng, Philip; Yang, Albert C; Lo, Men-Tzung; Peng, Chung-Kang; Wang, Hsin-Yi; Muggleton, Neil G; Juan, Chi-Hung; Liang, Wei-Kuang
2014-10-29
Physical activity has been shown to benefit brain and cognition in late adulthood. However, this effect is still unexplored in terms of brain signal complexity, which reflects the level of neural adaptability and efficiency during cognitive processing that cannot be acquired via averaged neuroelectric signals. Here we employed multiscale entropy analysis (MSE) of electroencephalography (EEG), a new approach that conveys important information related to the temporal dynamics of brain signal complexity across multiple time scales, to reveal the association of physical activity with neural adaptability and efficiency in elderly adults. A between-subjects design that included 24 participants (aged 66.63±1.31years; female=12) with high physical activity and 24 age- and gender-matched low physical activity participants (aged 67.29±1.20years) was conducted to examine differences related to physical activity in performance and MSE of EEG signals during a visuo-spatial cognition task. We observed that physically active elderly adults had better accuracy on both visuo-spatial attention and working memory conditions relative to their sedentary counterparts. Additionally, these physically active elderly adults displayed greater MSE values at larger time scales at the Fz electrode in both attention and memory conditions. The results suggest that physical activity may be beneficial for adaptability of brain systems in tasks involving visuo-spatial information. MSE thus might be a promising approach to test the effects of the benefits of exercise on cognition.
Chen, Ji; Fan, Cunxiu; Li, Jinqiang; Han, Qiaoqing; Lin, Jianzhong; Yang, Tianhe; Zhang, Jiaxing
2016-03-01
The human brain is intrinsically plastic such that its functional architecture can be reorganized in response to environmental pressures and physiological changes. However, it remains unclear whether a compensatory modification of spontaneous neural activity occurs in adult brain during prolonged high-altitude (HA) adaptation. In this study, we obtained resting-state functional magnetic resonance (MR) images in 16 adults who have immigrated to Qinghai-Tibet Plateau (2300-4400 m) for 2 years and in 16 age-matched sea level (SL) controls. A validated regional homogeneity (Reho) method was employed to investigate the local synchronization of resting-state functional magnetic resonance imaging (fMRI) signals. Seed connectivity analysis was carried out subsequently. Cognitive and physiological assessments were made and correlated with the image metrics. Compared with SL controls, global mean Reho was significantly increased in HA immigrants as well as a regional increase in the right inferolateral sensorimotor cortex. Furthermore, mean z-Reho value extracted within the inferolateral sensorimotor area showed trend-level significant inverse correlation with memory search reaction time in HA immigrants. These observations, for the first time, provide evidence of adult brain resilience of spontaneous neural activity after long-term HA exposure without inherited and developmental effects. Resting-state fMRI could yield valuable information for central mechanisms underlying respiratory and cognitive compensations in adults during prolonged environmentally hypoxic adaptation, paving the way for future HA-adaptive training.
NASA Astrophysics Data System (ADS)
Qiao, Wei
Worldwide concern about the environmental problems and a possible energy crisis has led to increasing interest in clean and renewable energy generation. Among various renewable energy sources, wind power is the most rapidly growing one. Therefore, how to provide efficient, reliable, and high-performance wind power generation and distribution has become an important and practical issue in the power industry. In addition, because of the new constraints placed by the environmental and economical factors, the trend of power system planning and operation is toward maximum utilization of the existing infrastructure with tight system operating and stability margins. This trend, together with the increased penetration of renewable energy sources, will bring new challenges to power system operation, control, stability and reliability which require innovative solutions. Flexible ac transmission system (FACTS) devices, through their fast, flexible, and effective control capability, provide one possible solution to these challenges. To fully utilize the capability of individual power system components, e.g., wind turbine generators (WTGs) and FACTS devices, their control systems must be suitably designed with high reliability. Moreover, in order to optimize local as well as system-wide performance and stability of the power system, real-time local and wide-area coordinated control is becoming an important issue. Power systems containing conventional synchronous generators, WTGs, and FACTS devices are large-scale, nonlinear, nonstationary, stochastic and complex systems distributed over large geographic areas. Traditional mathematical tools and system control techniques have limitations to control such complex systems to achieve an optimal performance. Intelligent and bio-inspired techniques, such as swarm intelligence, neural networks, and adaptive critic designs, are emerging as promising alternative technologies for power system control and performance optimization. This
NASA Astrophysics Data System (ADS)
Wu, Yimin; Lv, Hui
2016-08-01
In this paper, we consider the control problem of a class of uncertain fractional-order chaotic systems preceded by unknown backlash-like hysteresis nonlinearities based on backstepping control algorithm. We model the hysteresis by using a differential equation. Based on the fractional Lyapunov stability criterion and the backstepping algorithm procedures, an adaptive neural network controller is driven. No knowledge of the upper bound of the disturbance and system uncertainty is required in our controller, and the asymptotical convergence of the tracking error can be guaranteed. Finally, we give two simulation examples to confirm our theoretical results.
An Adaptive Critic Approach to Reference Model Adaptation
NASA Technical Reports Server (NTRS)
Krishnakumar, K.; Limes, G.; Gundy-Burlet, K.; Bryant, D.
2003-01-01
Neural networks have been successfully used for implementing control architectures for different applications. In this work, we examine a neural network augmented adaptive critic as a Level 2 intelligent controller for a C- 17 aircraft. This intelligent control architecture utilizes an adaptive critic to tune the parameters of a reference model, which is then used to define the angular rate command for a Level 1 intelligent controller. The present architecture is implemented on a high-fidelity non-linear model of a C-17 aircraft. The goal of this research is to improve the performance of the C-17 under degraded conditions such as control failures and battle damage. Pilot ratings using a motion based simulation facility are included in this paper. The benefits of using an adaptive critic are documented using time response comparisons for severe damage situations.
On neural networks in identification and control of dynamic systems
NASA Technical Reports Server (NTRS)
Phan, Minh; Juang, Jer-Nan; Hyland, David C.
1993-01-01
This paper presents a discussion of the applicability of neural networks in the identification and control of dynamic systems. Emphasis is placed on the understanding of how the neural networks handle linear systems and how the new approach is related to conventional system identification and control methods. Extensions of the approach to nonlinear systems are then made. The paper explains the fundamental concepts of neural networks in their simplest terms. Among the topics discussed are feed forward and recurrent networks in relation to the standard state-space and observer models, linear and nonlinear auto-regressive models, linear, predictors, one-step ahead control, and model reference adaptive control for linear and nonlinear systems. Numerical examples are presented to illustrate the application of these important concepts.
Lundström, T; Jonas, T; Volkwein, A
2008-01-01
Thirteen Norway spruce [Picea abies (L.) Karst.] trees of different size, age, and social status, and grown under varying conditions, were investigated to see how they react to complex natural static loading under summer and winter conditions, and how they have adapted their growth to such combinations of load and tree state. For this purpose a non-linear finite-element model and an extensive experimental data set were used, as well as a new formulation describing the degree to which the exploitation of the bending stress capacity is uniform. The three main findings were: material and geometric non-linearities play important roles when analysing tree deflections and critical loads; the strengths of the stem and the anchorage mutually adapt to the local wind acting on the tree crown in the forest canopy; and the radial stem growth follows a mechanically high-performance path because it adapts to prevailing as well as acute seasonal combinations of the tree state (e.g. frozen or unfrozen stem and anchorage) and load (e.g. wind and vertical and lateral snow pressure). Young trees appeared to adapt to such combinations in a more differentiated way than older trees. In conclusion, the mechanical performance of the Norway spruce studied was mostly very high, indicating that their overall growth had been clearly influenced by the external site- and tree-specific mechanical stress.
NASA Astrophysics Data System (ADS)
Land, Walker H., Jr.; Masters, Timothy D.; Lo, Joseph Y.; McKee, Dan
2001-07-01
A new neural network technology was developed for improving the benign/malignant diagnosis of breast cancer using mammogram findings. A new paradigm, Adaptive Boosting (AB), uses a markedly different theory in solutioning Computational Intelligence (CI) problems. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than random performance (i.e., approximately 55%) when processing a mammogram training set. Then, by successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves the performance of the basic Evolutionary Programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization focused on improving specificity and positive predictive value at very high sensitivities, where an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, on average this hybrid was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.
Parinet, Julien; Julien, Maxime; Nun, Pierrick; Robins, Richard J; Remaud, Gerald; Höhener, Patrick
2015-09-01
We aim at predicting the effect of structure and isotopic substitutions on the equilibrium vapour pressure isotope effect of various organic compounds (alcohols, acids, alkanes, alkenes and aromatics) at intermediate temperatures. We attempt to explore quantitative structure property relationships by using artificial neural networks (ANN); the multi-layer perceptron (MLP) and compare the performances of it with multi-linear regression (MLR). These approaches are based on the relationship between the molecular structure (organic chain, polar functions, type of functions, type of isotope involved) of the organic compounds, and their equilibrium vapour pressure. A data set of 130 equilibrium vapour pressure isotope effects was used: 112 were used in the training set and the remaining 18 were used for the test/validation dataset. Two sets of descriptors were tested, a set with all the descriptors: number of(12)C, (13)C, (16)O, (18)O, (1)H, (2)H, OH functions, OD functions, CO functions, Connolly Solvent Accessible Surface Area (CSA) and temperature and a reduced set of descriptors. The dependent variable (the output) is the natural logarithm of the ratios of vapour pressures (ln R), expressed as light/heavy as in classical literature. Since the database is rather small, the leave-one-out procedure was used to validate both models. Considering higher determination coefficients and lower error values, it is concluded that the multi-layer perceptron provided better results compared to multi-linear regression. The stepwise regression procedure is a useful tool to reduce the number of descriptors. To our knowledge, a Quantitative Structure Property Relationship (QSPR) approach for isotopic studies is novel.
Parinet, Julien; Julien, Maxime; Nun, Pierrick; Robins, Richard J; Remaud, Gerald; Höhener, Patrick
2015-09-01
We aim at predicting the effect of structure and isotopic substitutions on the equilibrium vapour pressure isotope effect of various organic compounds (alcohols, acids, alkanes, alkenes and aromatics) at intermediate temperatures. We attempt to explore quantitative structure property relationships by using artificial neural networks (ANN); the multi-layer perceptron (MLP) and compare the performances of it with multi-linear regression (MLR). These approaches are based on the relationship between the molecular structure (organic chain, polar functions, type of functions, type of isotope involved) of the organic compounds, and their equilibrium vapour pressure. A data set of 130 equilibrium vapour pressure isotope effects was used: 112 were used in the training set and the remaining 18 were used for the test/validation dataset. Two sets of descriptors were tested, a set with all the descriptors: number of(12)C, (13)C, (16)O, (18)O, (1)H, (2)H, OH functions, OD functions, CO functions, Connolly Solvent Accessible Surface Area (CSA) and temperature and a reduced set of descriptors. The dependent variable (the output) is the natural logarithm of the ratios of vapour pressures (ln R), expressed as light/heavy as in classical literature. Since the database is rather small, the leave-one-out procedure was used to validate both models. Considering higher determination coefficients and lower error values, it is concluded that the multi-layer perceptron provided better results compared to multi-linear regression. The stepwise regression procedure is a useful tool to reduce the number of descriptors. To our knowledge, a Quantitative Structure Property Relationship (QSPR) approach for isotopic studies is novel. PMID:25559176
Fairbank, Michael; Li, Shuhui; Fu, Xingang; Alonso, Eduardo; Wunsch, Donald
2014-01-01
We present a recurrent neural-network (RNN) controller designed to solve the tracking problem for control systems. We demonstrate that a major difficulty in training any RNN is the problem of exploding gradients, and we propose a solution to this in the case of tracking problems, by introducing a stabilization matrix and by using carefully constrained context units. This solution allows us to achieve consistently lower training errors, and hence allows us to more easily introduce adaptive capabilities. The resulting RNN is one that has been trained off-line to be rapidly adaptive to changing plant conditions and changing tracking targets. The case study we use is a renewable-energy generator application; that of producing an efficient controller for a three-phase grid-connected converter. The controller we produce can cope with the random variation of system parameters and fluctuating grid voltages. It produces tracking control with almost instantaneous response to changing reference states, and virtually zero oscillation. This compares very favorably to the classical proportional integrator (PI) controllers, which we show produce a much slower response and settling time. In addition, the RNN we propose exhibits better learning stability and convergence properties, and can exhibit faster adaptation, than has been achieved with adaptive critic designs.
NASA Astrophysics Data System (ADS)
Helama, S.; Makarenko, N. G.; Karimova, L. M.; Kruglun, O. A.; Timonen, M.; Holopainen, J.; Meriläinen, J.; Eronen, M.
2009-03-01
Tree-rings tell of past climates. To do so, tree-ring chronologies comprising numerous climate-sensitive living-tree and subfossil time-series need to be "transferred" into palaeoclimate estimates using transfer functions. The purpose of this study is to compare different types of transfer functions, especially linear and nonlinear algorithms. Accordingly, multiple linear regression (MLR), linear scaling (LSC) and artificial neural networks (ANN, nonlinear algorithm) were compared. Transfer functions were built using a regional tree-ring chronology and instrumental temperature observations from Lapland (northern Finland and Sweden). In addition, conventional MLR was compared with a hybrid model whereby climate was reconstructed separately for short- and long-period timescales prior to combining the bands of timescales into a single hybrid model. The fidelity of the different reconstructions was validated against instrumental climate data. The reconstructions by MLR and ANN showed reliable reconstruction capabilities over the instrumental period (AD 1802-1998). LCS failed to reach reasonable verification statistics and did not qualify as a reliable reconstruction: this was due mainly to exaggeration of the low-frequency climatic variance. Over this instrumental period, the reconstructed low-frequency amplitudes of climate variability were rather similar by MLR and ANN. Notably greater differences between the models were found over the actual reconstruction period (AD 802-1801). A marked temperature decline, as reconstructed by MLR, from the Medieval Warm Period (AD 931-1180) to the Little Ice Age (AD 1601-1850), was evident in all the models. This decline was approx. 0.5°C as reconstructed by MLR. Different ANN based palaeotemperatures showed simultaneous cooling of 0.2 to 0.5°C, depending on algorithm. The hybrid MLR did not seem to provide further benefit above conventional MLR in our sample. The robustness of the conventional MLR over the calibration
Neural predictive control for active buffet alleviation
NASA Astrophysics Data System (ADS)
Pado, Lawrence E.; Lichtenwalner, Peter F.; Liguore, Salvatore L.; Drouin, Donald
1998-06-01
The adaptive neural control of aeroelastic response (ANCAR) and the affordable loads and dynamics independent research and development (IRAD) programs at the Boeing Company jointly examined using neural network based active control technology for alleviating undesirable vibration and aeroelastic response in a scale model aircraft vertical tail. The potential benefits of adaptive control includes reducing aeroelastic response associated with buffet and atmospheric turbulence, increasing flutter margins, and reducing response associated with nonlinear phenomenon like limit cycle oscillations. By reducing vibration levels and thus loads, aircraft structures can have lower acquisition cost, reduced maintenance, and extended lifetimes. Wind tunnel tests were undertaken on a rigid 15% scale aircraft in Boeing's mini-speed wind tunnel, which is used for testing at very low air speeds up to 80 mph. The model included a dynamically scaled flexible fail consisting of an aluminum spar with balsa wood cross sections with a hydraulically powered rudder. Neural predictive control was used to actuate the vertical tail rudder in response to strain gauge feedback to alleviate buffeting effects. First mode RMS strain reduction of 50% was achieved. The neural predictive control system was developed and implemented by the Boeing Company to provide an intelligent, adaptive control architecture for smart structures applications with automated synthesis, self-optimization, real-time adaptation, nonlinear control, and fault tolerance capabilities. It is designed to solve complex control problems though a process of automated synthesis, eliminating costly control design and surpassing it in many instances by accounting for real world non-linearities.
Koh, Doo-Yeol; Kim, Young-Kook; Kim, Kyung-Soo; Kim, Soohyun
2013-08-01
In mobile robotics, obtaining stable image of a mounted camera is crucial for operating a mobile system to complete given tasks. This note presents the development of a high-speed image stabilizing device using linear shaft actuator, and a new image stabilization method inspired by human gaze stabilization process known as vestibulo-ocular reflex (VOR). In the proposed control, the reference is adaptively adjusted by the VOR adaptation control to reject residual vibration of a camera as the VOR gain converges to optimal state. Through experiments on a pneumatic vibrator, it will be shown that the proposed system is capable of stabilizing 10 Hz platform vibration, which shows potential applicability of the device to a high-speed mobile robot.
NASA Astrophysics Data System (ADS)
Koh, Doo-Yeol; Kim, Young-Kook; Kim, Kyung-Soo; Kim, Soohyun
2013-08-01
In mobile robotics, obtaining stable image of a mounted camera is crucial for operating a mobile system to complete given tasks. This note presents the development of a high-speed image stabilizing device using linear shaft actuator, and a new image stabilization method inspired by human gaze stabilization process known as vestibulo-ocular reflex (VOR). In the proposed control, the reference is adaptively adjusted by the VOR adaptation control to reject residual vibration of a camera as the VOR gain converges to optimal state. Through experiments on a pneumatic vibrator, it will be shown that the proposed system is capable of stabilizing 10 Hz platform vibration, which shows potential applicability of the device to a high-speed mobile robot.
Koh, Doo-Yeol; Kim, Young-Kook; Kim, Kyung-Soo; Kim, Soohyun
2013-08-01
In mobile robotics, obtaining stable image of a mounted camera is crucial for operating a mobile system to complete given tasks. This note presents the development of a high-speed image stabilizing device using linear shaft actuator, and a new image stabilization method inspired by human gaze stabilization process known as vestibulo-ocular reflex (VOR). In the proposed control, the reference is adaptively adjusted by the VOR adaptation control to reject residual vibration of a camera as the VOR gain converges to optimal state. Through experiments on a pneumatic vibrator, it will be shown that the proposed system is capable of stabilizing 10 Hz platform vibration, which shows potential applicability of the device to a high-speed mobile robot. PMID:24007125
NASA Astrophysics Data System (ADS)
Matéo, Tony; Mofid, Yassine; Grégoire, Jean-Marc; Ossant, Frédéric
In ophtalmic ultrasonography, axial B-scans are seriously deteriorated owing to the presence of the crystalline lens. This strongly aberrating medium affects both spatial and contrast resolution and causes important distortions. To deal with this issue, an adapted beamforming (BF) has been developed and experimented with a 20 MHz linear array working with a custom US research scanner. The adapted BF computes focusing delays that compensate for crystalline phase aberration, including refraction effects. This BF was tested in vitro by imaging a wire phantom through an eye phantom consisting of a synthetic gelatin lens, shaped according to the unaccommodated state of an adult human crystalline lens, anatomically set up in an appropriate liquid (turpentine) to approach the in vivo velocity ratio. Both image quality and fidelity from the adapted BF were assessed and compared with conventional delay-and-sum BF over the aberrating medium. Results showed 2-fold improvement of the lateral resolution, greater sensitivity and 90% reduction of the spatial error (from 758 μm to 76 μm) with adapted BF compared to conventional BF. Finally, promising first ex vivo axial B-scans of a human eye are presented.
Evolvable Neural Software System
NASA Technical Reports Server (NTRS)
Curtis, Steven A.
2009-01-01
The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.
Mariani, L; Coradini, D; Biganzoli, E; Boracchi, P; Marubini, E; Pilotti, S; Salvadori, B; Silvestrini, R; Veronesi, U; Zucali, R; Rilke, F
1997-06-01
The purpose of the present study was to assess prognostic factor for metachronous contralateral recurrence of breast cancer (CBC). Two factors were of particular interest, namely estrogen (ER) and progesterone (PgR) receptors assayed with the biochemical method in primary tumor tissue. Information was obtained from a prospective clinical database for 1763 axillary node-negative women who had received curative surgery, mostly of the conservative type, and followed-up for a median of 82 months. The analysis was performed based on both a standard (linear) Cox model and an artificial neural network (ANN) extension of this model proposed by Faraggi and Simon. Furthermore, to assess the prognostic importance of the factors considered, model predictive ability was computed. In agreement with already published studies, the results of our analysis confirmed the prognostic role of age at surgery, histology, and primary tumor site, in that young patients (< or = 45 years) with tumors of lobular histology or located at inner/central mammary quadrants were at greater risk of developing CBC. ER and PgR were also shown to have a prognostic role. Their effect, however, was not simple in relation to the presence of interactions between ER and age, and between PgR and histology. In fact, ER appeared to play a protective role in young patients, whereas the opposite was true in older women. Higher levels of PgR implied a greater hazard of CBC occurrence in infiltrating duct carcinoma or tumors with an associated extensive intraductal component, and a lower hazard in infiltrating lobular carcinoma or other histotypes. In spite of the above findings, the predictive value of both the standard and ANN Cox models was relatively low, thus suggesting an intrinsic limitation of the prognostic variables considered, rather than their suboptimal modeling. Research for better prognostic variables should therefore continue.
NASA Astrophysics Data System (ADS)
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
NASA Astrophysics Data System (ADS)
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.
Neural networks for aircraft control
NASA Technical Reports Server (NTRS)
Linse, Dennis
1990-01-01
Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.
NASA Technical Reports Server (NTRS)
Gundy-Burlet, Karen
2003-01-01
The Neural Flight Control System (NFCS) was developed to address the need for control systems that can be produced and tested at lower cost, easily adapted to prototype vehicles and for flight systems that can accommodate damaged control surfaces or changes to aircraft stability and control characteristics resulting from failures or accidents. NFCS utilizes on a neural network-based flight control algorithm which automatically compensates for a broad spectrum of unanticipated damage or failures of an aircraft in flight. Pilot stick and rudder pedal inputs are fed into a reference model which produces pitch, roll and yaw rate commands. The reference model frequencies and gains can be set to provide handling quality characteristics suitable for the aircraft of interest. The rate commands are used in conjunction with estimates of the aircraft s stability and control (S&C) derivatives by a simplified Dynamic Inverse controller to produce virtual elevator, aileron and rudder commands. These virtual surface deflection commands are optimally distributed across the aircraft s available control surfaces using linear programming theory. Sensor data is compared with the reference model rate commands to produce an error signal. A Proportional/Integral (PI) error controller "winds up" on the error signal and adds an augmented command to the reference model output with the effect of zeroing the error signal. In order to provide more consistent handling qualities for the pilot, neural networks learn the behavior of the error controller and add in the augmented command before the integrator winds up. In the case of damage sufficient to affect the handling qualities of the aircraft, an Adaptive Critic is utilized to reduce the reference model frequencies and gains to stay within a flyable envelope of the aircraft.
Moser, Jason S; Schroder, Hans S; Heeter, Carrie; Moran, Tim P; Lee, Yu-Hao
2011-12-01
How well people bounce back from mistakes depends on their beliefs about learning and intelligence. For individuals with a growth mind-set, who believe intelligence develops through effort, mistakes are seen as opportunities to learn and improve. For individuals with a fixed mind-set, who believe intelligence is a stable characteristic, mistakes indicate lack of ability. We examined performance-monitoring event-related potentials (ERPs) to probe the neural mechanisms underlying these different reactions to mistakes. Findings revealed that a growth mind-set was associated with enhancement of the error positivity component (Pe), which reflects awareness of and allocation of attention to mistakes. More growth-minded individuals also showed superior accuracy after mistakes compared with individuals endorsing a more fixed mind-set. It is critical to note that Pe amplitude mediated the relationship between mind-set and posterror accuracy. These results suggest that neural mechanisms indexing on-line awareness of and attention to mistakes are intimately involved in growth-minded individuals' ability to rebound from mistakes.
Is neural Darwinism Darwinism?
van Belle, T
1997-01-01
Neural Darwinism is a theory of cognition developed by Gerald Edelman along with George Reeke and Olaf Sporns at Rockefeller University. As its name suggests, neural Darwinism is modeled after biological Darwinism, and its authors assert that the two processes are strongly analogous. both operate on variation in a population, amplifying the more adaptive individuals. However, from a computational perspective, neural Darwinism is quite different from other models of natural selection, such as genetic algorithms. The individuals of neural Darwinism do not replicate, thus robbing the process of the capacity to explore new solutions over time and ultimately reducing it to a random search. Because neural Darwinism does not have the computational power of a truly Darwinian process, it is misleading to label it as such. to illustrate this disparity in adaptive power, one of Edelman's early computer experiments, Darwin I, is revisited, and it is shown that adding replication greatly improves the adaptive power of the system.
NASA Astrophysics Data System (ADS)
Chiou, J.-S.; Liu, M.-T.
2008-02-01
As a powerful machine-learning approach to pattern recognition problems, the support vector machine (SVM) is known to easily allow generalization. More importantly, it works very well in a high-dimensional feature space. This paper presents a nonlinear active suspension controller which achieves a high level performance by compensating for actuator dynamics. We use a linear quadratic regulator (LQR) to ensure optimal control of nonlinear systems. An LQR is used to solve the problem of state feedback and an SVM is used to address the question of the estimation and examination of the state. These two are then combined and designed in a way that outputs feedback control. The real-time simulation demonstrates that an active suspension using the combined SVM-LQR controller provides passengers with a much more comfortable ride and better road handling.
Buño, W; Bustamante, J; Fuentes, J
1984-01-01
Input-output relations were investigated in the slowly adapting stretch receptor organ of crayfish using a Gaussian white noise length input with a 0.03-12.5 Hz band width and the resulting action potential output. The noise input was presented to the de-efferented receptor in situ, at three mean elongations and at four different amplitudes. The three mean elongations were set within the normal range in vivo, two at the extremes close to the minimum and maximum physiological lengths and the other in the mid-range. With white noise inputs there is a finite probability that the system will be tested in all possible conditions within the chosen band width because white noise has the advantage that it contains, with a finite probability, all possible stimulus wave forms at random. The analysis indicated similarities between the effects of the input variables, namely white noise amplitude and mean elongation. With low input variables the activity was periodic. With larger inputs, impulse rates were higher and irregular. The average length trajectories leading to a spike (i.e. the average stimulus) were either biphasic with high inputs or multiphasic and periodic with lower input variables. The frequency of periodicity increased with mean elongation. Although for a given length and noise amplitude a variety of individual length trajectories preceded spikes, the final biphasic shortening-lengthening average stimulus sequence before a spike was similar in all cases irrespective of the input variables. The number of possible trajectories decreased with increments in the input variables. The standard deviation of length values for each average stimulus was computed and displayed as a function of time relative to the spike. It was first constant, and decreased gradually to a minimum value at the spike reference. Standard deviation values were lower for higher white noise amplitudes and mean elongation. Simple, short-lasting stimulus wave forms in the white noise were isolated
Bagherpoor, H M; Salmasi, Farzad R
2015-07-01
In this paper, robust model reference adaptive tracking controllers are considered for Single-Input Single-Output (SISO) and Multi-Input Multi-Output (MIMO) linear systems containing modeling uncertainties, unknown additive disturbances and actuator fault. Two new lemmas are proposed for both SISO and MIMO, under which dead-zone modification rule is improved such that the tracking error for any reference signal tends to zero in such systems. In the conventional approach, adaption of the controller parameters is ceased inside the dead-zone region which results tracking error, while preserving the system stability. In the proposed scheme, control signal is reinforced with an additive term based on tracking error inside the dead-zone which results in full reference tracking. In addition, no Fault Detection and Diagnosis (FDD) unit is needed in the proposed approach. Closed loop system stability and zero tracking error are proved by considering a suitable Lyapunov functions candidate. It is shown that the proposed control approach can assure that all the signals of the close loop system are bounded in faulty conditions. Finally, validity and performance of the new schemes have been illustrated through numerical simulations of SISO and MIMO systems in the presence of actuator faults, modeling uncertainty and output disturbance.
Encoding of event timing in the phase of neural oscillations.
Kösem, Anne; Gramfort, Alexandre; van Wassenhove, Virginie
2014-05-15
Time perception is a critical component of conscious experience. To be in synchrony with the environment, the brain must deal not only with differences in the speed of light and sound but also with its computational and neural transmission delays. Here, we asked whether the brain could actively compensate for temporal delays by changing its processing time. Specifically, can changes in neural timing or in the phase of neural oscillation index perceived timing? For this, a lag-adaptation paradigm was used to manipulate participants' perceived audiovisual (AV) simultaneity of events while they were recorded with magnetoencephalography (MEG). Desynchronized AV stimuli were presented rhythmically to elicit a robust 1 Hz frequency-tagging of auditory and visual cortical responses. As participants' perception of AV simultaneity shifted, systematic changes in the phase of entrained neural oscillations were observed. This suggests that neural entrainment is not a passive response and that the entrained neural oscillation shifts in time. Crucially, our results indicate that shifts in neural timing in auditory cortices linearly map participants' perceived AV simultaneity. To our knowledge, these results provide the first mechanistic evidence for active neural compensation in the encoding of sensory event timing in support of the emergence of time awareness. PMID:24531044
NASA Astrophysics Data System (ADS)
Hortos, William S.
1999-03-01
A hybrid neural network approach is presented to estimate radio propagation characteristics and multiuser interference and to evaluate their combined impact on throughput, latency and information loss in third-generation (3G) wireless networks. The latter three performance parameters influence the quality of service (QoS) for multimedia services under consideration for 3G networks. These networks, based on a hierarchical architecture of overlaying macrocells on top of micro- and picocells, are planned to operate in mobile urban and indoor environments with service demands emanating from circuit-switched, packet-switched and satellite-based traffic sources. Candidate radio interfaces for these networks employ a form of wideband CDMA in 5-MHz and wider-bandwidth channels, with possible asynchronous operation of the mobile subscribers. The proposed neural network (NN) architecture allocates network resources to optimize QoS metrics. Parameters of the radio propagation channel are estimated, followed by control of an adaptive antenna array at the base station to minimize interference, and then joint multiuser detection is performed at the base station receiver. These adaptive processing stages are implemented as a sequence of NN techniques that provide their estimates as inputs to a final- stage Kohonen self-organizing feature map (SOFM). The SOFM optimizes the allocation of available network resources to satisfy QoS requirements for variable-rate voice, data and video services. As the first stage of the sequence, a modified feed-forward multilayer perceptron NN is trained on the pilot signals of the mobile subscribers to estimate the parameters of shadowing, multipath fading and delays on the uplinks. A recurrent NN (RNN) forms the second stage to control base stations' adaptive antenna arrays to minimize intra-cell interference. The third stage is based on a Hopfield NN (HNN), modified to detect multiple users on the uplink radio channels to mitigate multiaccess
Active control of vibration using a neural network.
Snyder, S D; Tanaka, N
1995-01-01
Feedforward control of sound and vibration using a neural network-based control system is considered, with the aim being to derive an architecture/algorithm combination which is capable of supplanting the commonly used finite impulse response filter/filtered-x least mean square (LMS) linear arrangement for certain nonlinear problems. An adaptive algorithm is derived which enables stable adaptation of the neural controller for this purpose, while providing the capacity to maintain causality within the control scheme. The algorithm is shown to be simply a generalization of the linear filtered-x LMS algorithm. Experiments are undertaken which demonstrate the utility of the proposed arrangement, showing that it performs as well as a linear control system for a linear control problem and better for a nonlinear control problem. The experiments also lead to the conclusion that more work is required to improve the predictability and consistency of the performance before the neural network controller becomes a practical alternative to the current linear feedforward systems.
Neural net based MRAC for a class of nonlinear plants.
Ahmed, M S
2000-01-01
A neural net based state feedback model reference adaptive control scheme is presented for a class of nonlinear plants. The proposed scheme employs a time varying pseudo-linear state feedback control, where the state feedback gain being generated from the output of artificial neural networks. The plant need not be in a feedback linearizable form. Both regulation and tracking control have been considered. Global stability of the scheme has been proved through Lyapunov theory. The extension of the scheme to MIMO plants is also included. Simulation studies have been conducted on an industrial robot to validate and illustrate the proposed method.
Barrett, Harrison H.; Furenlid, Lars R.; Freed, Melanie; Hesterman, Jacob Y.; Kupinski, Matthew A.; Clarkson, Eric; Whitaker, Meredith K.
2008-01-01
Adaptive imaging systems alter their data-acquisition configuration or protocol in response to the image information received. An adaptive pinhole single-photon emission computed tomography (SPECT) system might acquire an initial scout image to obtain preliminary information about the radiotracer distribution and then adjust the configuration or sizes of the pinholes, the magnifications, or the projection angles in order to improve performance. This paper briefly describes two small-animal SPECT systems that allow this flexibility and then presents a framework for evaluating adaptive systems in general, and adaptive SPECT systems in particular. The evaluation is in terms of the performance of linear observers on detection or estimation tasks. Expressions are derived for the ideal linear (Hotelling) observer and the ideal linear (Wiener) estimator with adaptive imaging. Detailed expressions for the performance figures of merit are given, and possible adaptation rules are discussed. PMID:18541485
Yolmeh, Mahmoud; Habibi Najafi, Mohammad B; Salehi, Fakhreddin
2014-01-01
Annatto is commonly used as a coloring agent in the food industry and has antimicrobial and antioxidant properties. In this study, genetic algorithm-artificial neural network (GA-ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used to predict the effect of annatto dye on Salmonella enteritidis in mayonnaise. The GA-ANN and ANFIS were fed with 3 inputs of annatto dye concentration (0, 0.1, 0.2 and 0.4%), storage temperature (4 and 25°C) and storage time (1-20 days) for prediction of S. enteritidis population. Both models were trained with experimental data. The results showed that the annatto dye was able to reduce of S. enteritidis and its effect was stronger at 25°C than 4°C. The developed GA-ANN, which included 8 hidden neurons, could predict S. enteritidis population with correlation coefficient of 0.999. The overall agreement between ANFIS predictions and experimental data was also very good (r=0.998). Sensitivity analysis results showed that storage temperature was the most sensitive factor for prediction of S. enteritidis population. PMID:24566279
Wang, Chi-Hsu; Chen, Chun-Yao; Hung, Kun-Neng
2015-06-01
In this paper, a new adaptive self-organizing map (SOM) with recurrent neural network (RNN) controller is proposed for task assignment and path evolution of missile defense system (MDS). We address the problem of N agents (defending missiles) and D targets (incoming missiles) in MDS. A new RNN controller is designed to force an agent (or defending missile) toward a target (or incoming missile), and a monitoring controller is also designed to reduce the error between RNN controller and ideal controller. A new SOM with RNN controller is then designed to dispatch agents to their corresponding targets by minimizing total damaging cost. This is actually an important application of the multiagent system. The SOM with RNN controller is the main controller. After task assignment, the weighting factors of our new SOM with RNN controller are activated to dispatch the agents toward their corresponding targets. Using the Lyapunov constraints, the weighting factors for the proposed SOM with RNN controller are updated to guarantee the stability of the path evolution (or planning) system. Excellent simulations are obtained using this new approach for MDS, which show that our RNN has the lowest average miss distance among the several techniques.
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.
Tolkunov, Denis; Rubin, Denis; Mujica-Parodi, LR
2010-01-01
In a well-regulated control system, excitatory and inhibitory components work closely together with minimum lag; in response to inputs of finite duration, outputs should show rapid rise and, following the input's termination, immediate return to baseline. The efficiency of this response can be quantified using the power spectrum density's scaling parameter β, a measure of self-similarity, applied to the first-derivative of the raw signal. In this study, we adapted power spectrum density methods, previously used to quantify autonomic dysregulation (heart rate variability), to neural time-series obtained via functional MRI. The negative feedback loop we investigated was the limbic system, using affect-valent faces as stimuli. We hypothesized that trait anxiety would be related to efficiency of regulation of limbic responses, as quantified by power law scaling of fMRI time series. Our results supported this hypothesis, showing moderate to strong correlations of β (r = 0.4–0.54) for the amygdala, orbitofrontal cortex, hippocampus, superior temporal gyrus, posterior insula, and anterior cingulate. Strong anticorrelations were also found between the amygdala's β and wake heart rate variability (r = −0.61), suggesting a robust relationship between dysregulated limbic outputs and their autonomic consequences. PMID:20025979
Reed, William R.; Cao, Dong-Yuan; Long, Cynthia R.; Kawchuk, Gregory N.; Pickar, Joel G.
2013-01-01
High velocity low amplitude spinal manipulation (HVLA-SM) is used frequently to treat musculoskeletal complaints. Little is known about the intervention's biomechanical characteristics that determine its clinical benefit. Using an animal preparation, we determined how neural activity from lumbar muscle spindles during a lumbar HVLA-SM is affected by the type of thrust control and by the thrust's amplitude, duration, and rate. A mechanical device was used to apply a linear increase in thrust displacement or force and to control thrust duration. Under displacement control, neural responses during the HVLA-SM increased in a fashion graded with thrust amplitude. Under force control neural responses were similar regardless of the thrust amplitude. Decreasing thrust durations at all thrust amplitudes except the smallest thrust displacement had an overall significant effect on increasing muscle spindle activity during the HVLA-SMs. Under force control, spindle responses specifically and significantly increased between thrust durations of 75 and 150 ms suggesting the presence of a threshold value. Thrust velocities greater than 20–30 mm/s and thrust rates greater than 300 N/s tended to maximize the spindle responses. This study provides a basis for considering biomechanical characteristics of an HVLA-SM that should be measured and reported in clinical efficacy studies to help define effective clinical dosages. PMID:23401713
Reed, William R; Cao, Dong-Yuan; Long, Cynthia R; Kawchuk, Gregory N; Pickar, Joel G
2013-01-01
High velocity low amplitude spinal manipulation (HVLA-SM) is used frequently to treat musculoskeletal complaints. Little is known about the intervention's biomechanical characteristics that determine its clinical benefit. Using an animal preparation, we determined how neural activity from lumbar muscle spindles during a lumbar HVLA-SM is affected by the type of thrust control and by the thrust's amplitude, duration, and rate. A mechanical device was used to apply a linear increase in thrust displacement or force and to control thrust duration. Under displacement control, neural responses during the HVLA-SM increased in a fashion graded with thrust amplitude. Under force control neural responses were similar regardless of the thrust amplitude. Decreasing thrust durations at all thrust amplitudes except the smallest thrust displacement had an overall significant effect on increasing muscle spindle activity during the HVLA-SMs. Under force control, spindle responses specifically and significantly increased between thrust durations of 75 and 150 ms suggesting the presence of a threshold value. Thrust velocities greater than 20-30 mm/s and thrust rates greater than 300 N/s tended to maximize the spindle responses. This study provides a basis for considering biomechanical characteristics of an HVLA-SM that should be measured and reported in clinical efficacy studies to help define effective clinical dosages.
Nonlinear signal processing using neural networks: Prediction and system modelling
Lapedes, A.; Farber, R.
1987-06-01
The backpropagation learning algorithm for neural networks is developed into a formalism for nonlinear signal processing. We illustrate the method by selecting two common topics in signal processing, prediction and system modelling, and show that nonlinear applications can be handled extremely well by using neural networks. The formalism is a natural, nonlinear extension of the linear Least Mean Squares algorithm commonly used in adaptive signal processing. Simulations are presented that document the additional performance achieved by using nonlinear neural networks. First, we demonstrate that the formalism may be used to predict points in a highly chaotic time series with orders of magnitude increase in accuracy over conventional methods including the Linear Predictive Method and the Gabor-Volterra-Weiner Polynomial Method. Deterministic chaos is thought to be involved in many physical situations including the onset of turbulence in fluids, chemical reactions and plasma physics. Secondly, we demonstrate the use of the formalism in nonlinear system modelling by providing a graphic example in which it is clear that the neural network has accurately modelled the nonlinear transfer function. It is interesting to note that the formalism provides explicit, analytic, global, approximations to the nonlinear maps underlying the various time series. Furthermore, the neural net seems to be extremely parsimonious in its requirements for data points from the time series. We show that the neural net is able to perform well because it globally approximates the relevant maps by performing a kind of generalized mode decomposition of the maps. 24 refs., 13 figs.
Sieh Kiong, Tiong; Tariqul Islam, Mohammad; Ismail, Mahamod; Salem, Balasem
2014-01-01
Linear constraint minimum variance (LCMV) is one of the adaptive beamforming techniques that is commonly applied to cancel interfering signals and steer or produce a strong beam to the desired signal through its computed weight vectors. However, weights computed by LCMV usually are not able to form the radiation beam towards the target user precisely and not good enough to reduce the interference by placing null at the interference sources. It is difficult to improve and optimize the LCMV beamforming technique through conventional empirical approach. To provide a solution to this problem, artificial intelligence (AI) technique is explored in order to enhance the LCMV beamforming ability. In this paper, particle swarm optimization (PSO), dynamic mutated artificial immune system (DM-AIS), and gravitational search algorithm (GSA) are incorporated into the existing LCMV technique in order to improve the weights of LCMV. The simulation result demonstrates that received signal to interference and noise ratio (SINR) of target user can be significantly improved by the integration of PSO, DM-AIS, and GSA in LCMV through the suppression of interference in undesired direction. Furthermore, the proposed GSA can be applied as a more effective technique in LCMV beamforming optimization as compared to the PSO technique. The algorithms were implemented using Matlab program. PMID:25147859
Darzi, Soodabeh; Kiong, Tiong Sieh; Islam, Mohammad Tariqul; Ismail, Mahamod; Kibria, Salehin; Salem, Balasem
2014-01-01
Linear constraint minimum variance (LCMV) is one of the adaptive beamforming techniques that is commonly applied to cancel interfering signals and steer or produce a strong beam to the desired signal through its computed weight vectors. However, weights computed by LCMV usually are not able to form the radiation beam towards the target user precisely and not good enough to reduce the interference by placing null at the interference sources. It is difficult to improve and optimize the LCMV beamforming technique through conventional empirical approach. To provide a solution to this problem, artificial intelligence (AI) technique is explored in order to enhance the LCMV beamforming ability. In this paper, particle swarm optimization (PSO), dynamic mutated artificial immune system (DM-AIS), and gravitational search algorithm (GSA) are incorporated into the existing LCMV technique in order to improve the weights of LCMV. The simulation result demonstrates that received signal to interference and noise ratio (SINR) of target user can be significantly improved by the integration of PSO, DM-AIS, and GSA in LCMV through the suppression of interference in undesired direction. Furthermore, the proposed GSA can be applied as a more effective technique in LCMV beamforming optimization as compared to the PSO technique. The algorithms were implemented using Matlab program.
Lau, Condon; Zhang, Jevin W; McPherson, Bradley; Pienkowski, Martin; Wu, Ed X
2015-02-15
Exposure to loud sounds can lead to permanent hearing loss, i.e., the elevation of hearing thresholds. Exposure at more moderate sound pressure levels (SPLs) (non-traumatic and within occupational limits) may not elevate thresholds, but could in the long-term be detrimental to speech intelligibility by altering its spectrotemporal representation in the central auditory system. In support of this, electrophysiological and behavioral changes following long-term, passive (no conditioned learning) exposure at moderate SPLs have recently been observed in adult animals. To assess the potential effects of moderately loud noise on the entire auditory brain, we employed functional magnetic resonance imaging (fMRI) to study noise-exposed adult rats. We find that passive, pulsed broadband noise exposure for two months at 65 dB SPL leads to a decrease of the sound-evoked blood oxygenation level-dependent fMRI signal in the thalamic medial geniculate body (MGB) and in the auditory cortex (AC). This points to the thalamo-cortex as the site of the neural adaptation to the moderately noisy environment. The signal reduction is statistically significant during 10 Hz pulsed acoustic stimulation (MGB: p<0.05, AC: p<10(-4)), but not during 5 Hz stimulation. This indicates that noise exposure has a greater effect on the processing of higher pulse rate sounds. This study has enhanced our understanding of functional changes following exposure by mapping changes across the entire auditory brain. These findings have important implications for speech processing, which depends on accurate processing of sounds with a wide spectrum of pulse rates.
NASA Astrophysics Data System (ADS)
He, Zhibin; Wen, Xiaohu; Liu, Hu; Du, Jun
2014-02-01
Data driven models are very useful for river flow forecasting when the underlying physical relationships are not fully understand, but it is not clear whether these data driven models still have a good performance in the small river basin of semiarid mountain regions where have complicated topography. In this study, the potential of three different data driven methods, artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and support vector machine (SVM) were used for forecasting river flow in the semiarid mountain region, northwestern China. The models analyzed different combinations of antecedent river flow values and the appropriate input vector has been selected based on the analysis of residuals. The performance of the ANN, ANFIS and SVM models in training and validation sets are compared with the observed data. The model which consists of three antecedent values of flow has been selected as the best fit model for river flow forecasting. To get more accurate evaluation of the results of ANN, ANFIS and SVM models, the four quantitative standard statistical performance evaluation measures, the coefficient of correlation (R), root mean squared error (RMSE), Nash-Sutcliffe efficiency coefficient (NS) and mean absolute relative error (MARE), were employed to evaluate the performances of various models developed. The results indicate that the performance obtained by ANN, ANFIS and SVM in terms of different evaluation criteria during the training and validation period does not vary substantially; the performance of the ANN, ANFIS and SVM models in river flow forecasting was satisfactory. A detailed comparison of the overall performance indicated that the SVM model performed better than ANN and ANFIS in river flow forecasting for the validation data sets. The results also suggest that ANN, ANFIS and SVM method can be successfully applied to establish river flow with complicated topography forecasting models in the semiarid mountain regions.
NASA Technical Reports Server (NTRS)
Moebes, T. A.
1994-01-01
To locate the accessory pathway(s) in preexicitation syndromes, epicardial and endocardial ventricular mapping is performed during anterograde ventricular activation via accessory pathway(s) from data originally received in signal form. As the number of channels increases, it is pertinent that more automated detection of coherent/incoherent signals is achieved as well as the prediction and prognosis of ventricular tachywardia (VT). Today's computers and computer program algorithms are not good in simple perceptual tasks such as recognizing a pattern or identifying a sound. This discrepancy, among other things, has been a major motivating factor in developing brain-based, massively parallel computing architectures. Neural net paradigms have proven to be effective at pattern recognition tasks. In signal processing, the picking of coherent/incoherent signals represents a pattern recognition task for computer systems. The picking of signals representing the onset ot VT also represents such a computer task. We attacked this problem by defining four signal attributes for each potential first maximal arrival peak and one signal attribute over the entire signal as input to a back propagation neural network. One attribute was the predicted amplitude value after the maximum amplitude over a data window. Then, by using a set of known (user selected) coherent/incoherent signals, and signals representing the onset of VT, we trained the back propagation network to recognize coherent/incoherent signals, and signals indicating the onset of VT. Since our output scheme involves a true or false decision, and since the output unit computes values between 0 and 1, we used a Fuzzy Arithmetic approach to classify data as coherent/incoherent signals. Furthermore, a Mean-Square Error Analysis was used to determine system stability. The neural net based picking coherent/incoherent signal system achieved high accuracy on picking coherent/incoherent signals on different patients. The system
NASA Technical Reports Server (NTRS)
Clancy, John P.
1988-01-01
The object of the invention is to provide a mechanical force actuator which is lightweight and manipulatable and utilizes linear motion for push or pull forces while maintaining a constant overall length. The mechanical force producing mechanism comprises a linear actuator mechanism and a linear motion shaft mounted parallel to one another. The linear motion shaft is connected to a stationary or fixed housing and to a movable housing where the movable housing is mechanically actuated through actuator mechanism by either manual means or motor means. The housings are adapted to releasably receive a variety of jaw or pulling elements adapted for clamping or prying action. The stationary housing is adapted to be pivotally mounted to permit an angular position of the housing to allow the tool to adapt to skewed interfaces. The actuator mechanisms is operated by a gear train to obtain linear motion of the actuator mechanism.
An adaptive neuro-control system of synchronous generator for power system stabilization
Kobayashi, Takenori; Yokoyama, Akihiko
1996-09-01
This paper proposes a nonlinear adaptive generator control system using neural networks, called an adaptive neuro-control system (ANCS). This system generates supplementary control signals to conventional controllers and works adaptively in response to changes in operating conditions and network configuration. Through digital time simulations for a one-machine infinite bus test power system, the control performance of the ANCS and advanced controllers such as a linear optimal regulator and a self-tuning regulator is evaluated from the viewpoint of stability enhancement. As a result, the proposed ANCS using neural networks with nonlinear characteristics improves system damping more effectively and more adaptively than the other two controllers designed for the linearized model of the power system.
2011-01-01
Background Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test. Results Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed
Ghose, Kaushik; Moss, Cynthia F.
2012-01-01
Adaptive behaviors require sensorimotor computations that convert information represented initially in sensory coordinates to commands for action in motor coordinates. Fundamental to these computations is the relationship between the region of the environment sensed by the animal (gaze) and the animal’s locomotor plan. Studies of visually guided animals have revealed an anticipatory relationship between gaze direction and the locomotor plan during target-directed locomotion. Here, we study an acoustically guided animal, an echolocating bat, and relate acoustic gaze (direction of the sonar beam) to flight planning as the bat searches for and intercepts insect prey. We show differences in the relationship between gaze and locomotion as the bat progresses through different phases of insect pursuit. We define acoustic gaze angle, θgaze, to be the angle between the sonar beam axis and the bat’s flight path. We show that there is a strong linear linkage between acoustic gaze angle at time t [θgaze(t)] and flight turn rate at time t + τ into the future [θ̇flight (t + τ)], which can be expressed by the formula θ̇flight (t + τ) = kθgaze(t). The gain, k, of this linkage depends on the bat’s behavioral state, which is indexed by its sonar pulse rate. For high pulse rates, associated with insect attacking behavior, k is twice as high compared with low pulse rates, associated with searching behavior. We suggest that this adjustable linkage between acoustic gaze and motor output in a flying echolocating bat simplifies the transformation of auditory information to flight motor commands. PMID:16467518
An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems.
Ranganayaki, V; Deepa, S N
2016-01-01
Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature.
An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems.
Ranganayaki, V; Deepa, S N
2016-01-01
Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature. PMID:27034973
An Intelligent Ensemble Neural Network Model for Wind Speed Prediction in Renewable Energy Systems
Ranganayaki, V.; Deepa, S. N.
2016-01-01
Various criteria are proposed to select the number of hidden neurons in artificial neural network (ANN) models and based on the criterion evolved an intelligent ensemble neural network model is proposed to predict wind speed in renewable energy applications. The intelligent ensemble neural model based wind speed forecasting is designed by averaging the forecasted values from multiple neural network models which includes multilayer perceptron (MLP), multilayer adaptive linear neuron (Madaline), back propagation neural network (BPN), and probabilistic neural network (PNN) so as to obtain better accuracy in wind speed prediction with minimum error. The random selection of hidden neurons numbers in artificial neural network results in overfitting or underfitting problem. This paper aims to avoid the occurrence of overfitting and underfitting problems. The selection of number of hidden neurons is done in this paper employing 102 criteria; these evolved criteria are verified by the computed various error values. The proposed criteria for fixing hidden neurons are validated employing the convergence theorem. The proposed intelligent ensemble neural model is applied for wind speed prediction application considering the real time wind data collected from the nearby locations. The obtained simulation results substantiate that the proposed ensemble model reduces the error value to minimum and enhances the accuracy. The computed results prove the effectiveness of the proposed ensemble neural network (ENN) model with respect to the considered error factors in comparison with that of the earlier models available in the literature. PMID:27034973
Yu, Huichun; Wang, Yongwei; Wang, Jun
2009-01-01
An electronic nose (E-nose) was employed to detect the aroma of green tea after different storage times. Longjing green tea dry leaves, beverages and residues were detected with an E-nose, respectively. In order to decrease the data dimensionality and optimize the feature vector, the E-nose sensor response data were analyzed by principal components analysis (PCA) and the five main principal components values were extracted as the input for the discrimination analysis. The storage time (0, 60, 120, 180 and 240 days) was better discriminated by linear discrimination analysis (LDA) and was predicted by the back-propagation neural network (BPNN) method. The results showed that the discrimination and testing results based on the tea leaves were better than those based on tea beverages and tea residues. The mean errors of the tea leaf data were 9, 2.73, 3.93, 6.33 and 6.8 days, respectively. PMID:22408494
Retrieval of atmospheric properties with radiometric measurements using neural network
NASA Astrophysics Data System (ADS)
Chakraborty, Rohit; Maitra, Animesh
2016-11-01
Microwave radiometer is an effective instrument to monitor the atmosphere continuously in different weather conditions. It measures brightness temperatures at different frequency bands which are subjected to standard retrieval methods to obtain real time profiles of various atmospheric parameters such as temperature and humidity. But the retrieval techniques used by radiometer have to be adaptive to changing weather condition and location. In the present study, three retrieval techniques have been used to obtain the temperature and relative humidity profiles from brightness temperatures, namely; piecewise linear regression, feed forward neural network and neural back propagation network. The simulated results are compared with radiosonde observations using correlation analysis and error distribution. The analysis reveals that neural network with back propagation is the most accurate technique amongst the three retrieval methods utilized in this study.
Mizera, Mikołaj; Talaczyńska, Alicja; Zalewski, Przemysław; Skibiński, Robert; Cielecka-Piontek, Judyta
2015-05-01
A sensitive and fast HPLC method using ultraviolet diode-array detector (DAD)/electrospray ionization tandem mass spectrometry (Q-TOF-MS/MS) was developed for the determination of tebipenem pivoxyl and in the presence of degradation products formed during thermolysis. The chromatographic separations were performed on stationary phases produced in core-shell technology with particle diameter of 5.0 µm. The mobile phases consisted of formic acid (0.1%) and acetonitrile at different ratios. The flow rate was 0.8 mL/min while the wavelength was set at 331 nm. The stability characteristics of tebipenem pivoxyl were studied by performing stress tests in the solid state in dry air (RH=0%) and at an increased relative air humidity (RH=90%). The validation parameters such as selectivity, accuracy, precision and sensitivity were found to be satisfying. The satisfied selectivity and precision of determination were obtained for the separation of tebipenem pivoxyl from its degradation products using a stationary phase with 5.0 µm particles. The evaluation of the chemical structure of the 9 degradation products of tebipenem pivoxyl was conducted following separation based on the stationary phase with a 5.0 µm particle size by applying a Q-TOF-MS/MS detector. The main degradation products of tebipenem pivoxyl were identified: a product resulting from the condensation of the substituents of 1-(4,5-dihydro-1,3-thiazol-2-yl)-3-azetidinyl]sulfanyl and acid and ester forms of tebipenem with an open β-lactam ring in dry air at an increased temperature (RH=0%, T=393 K) as well as acid and ester forms of tebipenem with an open β-lactam ring at an increased relative air humidity and an elevated temperature (RH=90%, T=333 K). Retention times of tebipenem pivoxyl and its degradation products were used as training data set for predictive model of quantitative structure-retention relationship. An artificial neural network with adaptation protocol and extensive feature selection process
Neural network applications in telecommunications
NASA Technical Reports Server (NTRS)
Alspector, Joshua
1994-01-01
Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.
Adaptive Inner-Loop Rover Control
NASA Technical Reports Server (NTRS)
Kulkarni, Nilesh; Ippolito, Corey; Krishnakumar, Kalmanje; Al-Ali, Khalid M.
2006-01-01
Adaptive control technology is developed for the inner-loop speed and steering control of the MAX Rover. MAX, a CMU developed rover, is a compact low-cost 4-wheel drive, 4-wheel steer (double Ackerman), high-clearance agile durable chassis, outfitted with sensors and electronics that make it ideally suited for supporting research relevant to intelligent teleoperation and as a low-cost autonomous robotic test bed and appliance. The design consists of a feedback linearization based controller with a proportional - integral (PI) feedback that is augmented by an online adaptive neural network. The adaptation law has guaranteed stability properties for safe operation. The control design is retrofit in nature so that it fits inside the outer-loop path planning algorithms. Successful hardware implementation of the controller is illustrated for several scenarios consisting of actuator failures and modeling errors in the nominal design.
Adaptive Control for Microgravity Vibration Isolation System
NASA Technical Reports Server (NTRS)
Yang, Bong-Jun; Calise, Anthony J.; Craig, James I.; Whorton, Mark S.
2005-01-01
Most active vibration isolation systems that try to a provide quiescent acceleration environment for space science experiments have utilized linear design methods. In this paper, we address adaptive control augmentation of an existing classical controller that employs a high-gain acceleration feedback together with a low-gain position feedback to center the isolated platform. The control design feature includes parametric and dynamic uncertainties because the hardware of the isolation system is built as a payload-level isolator, and the acceleration Sensor exhibits a significant bias. A neural network is incorporated to adaptively compensate for the system uncertainties, and a high-pass filter is introduced to mitigate the effect of the measurement bias. Simulations show that the adaptive control improves the performance of the existing acceleration controller and keep the level of the isolated platform deviation to that of the existing control system.
Neural networks in clinical medicine.
Penny, W; Frost, D
1996-01-01
Neural networks are parallel, distributed, adaptive information-processing systems that develop their functionality in response to exposure to information. This paper is a tutorial for researchers intending to use neural nets for medical decision-making applications. It includes detailed discussion of the issues particularly relevant to medical data as well as wider issues relevant to any neural net application. The article is restricted to back-propagation learning in multilayer perceptrons, as this is the neural net model most widely used in medical applications.
Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems
NASA Technical Reports Server (NTRS)
Innocenti, M.; Napolitano, M.
2003-01-01
Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.
From neural-based object recognition toward microelectronic eyes
NASA Technical Reports Server (NTRS)
Sheu, Bing J.; Bang, Sa Hyun
1994-01-01
Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.
NASA Astrophysics Data System (ADS)
Hortos, William S.
2000-03-01
Third-generation (3G) wireless networks, based on a hierarchical cellular structure, support tiered levels of multimedia services. These services can be categorized as real-time and delay-sensitive, or non-real-time and delay- insensitive. Each call carries demand for one or more services in parallel; each with a guaranteed quality of service (QoS). Roaming is handled by handoff procedures between base stations (BSs) and the mobile subscribers (MSs) within the network. Metrics such as the probabilities of handoff failure, dropped calls and blocked calls; handoff transition time; and handoff rate are used to evaluate the handoff schemes, which also directly affects QoS. Previous researchers have proposed a fuzzy logic system (FLS) with neural encoding of the rule base and probabilistic neural network to solve the handoff decision as a pattern recognition problem in the set of MS signal measurements and mobility amid fading path uncertainties. Both neural approaches evalute only voice traffic in a closed, single- layer network of uniform cells. This paper proposed a new topology-preserving, self-organizing neural network (SONN) for both handoff and admission control as part of an overall resource allocation (RA) problem to support QoS in a three- layer, wideband CDMA HCS with dynamic loading of multimedia services. MS profiles include simultaneous service requirements, which are mapped to a new set of variables, defined in terms of the network radio resources (RRs). Simulations of the new SONN-based algorithms under various operating scenarios of MS mobility, dynamic loading, active set size, and RR bounds, using published traffic models of 3G services, compare their performance with earlier approaches.
Identification of nonlinear optical systems using adaptive kernel methods
NASA Astrophysics Data System (ADS)
Wang, Xiaodong; Zhang, Changjiang; Zhang, Haoran; Feng, Genliang; Xu, Xiuling
2005-12-01
An identification approach of nonlinear optical dynamic systems, based on adaptive kernel methods which are modified version of least squares support vector machine (LS-SVM), is presented in order to obtain the reference dynamic model for solving real time applications such as adaptive signal processing of the optical systems. The feasibility of this approach is demonstrated with the computer simulation through identifying a Bragg acoustic-optical bistable system. Unlike artificial neural networks, the adaptive kernel methods possess prominent advantages: over fitting is unlikely to occur by employing structural risk minimization criterion, the global optimal solution can be uniquely obtained owing to that its training is performed through the solution of a set of linear equations. Also, the adaptive kernel methods are still effective for the nonlinear optical systems with a variation of the system parameter. This method is robust with respect to noise, and it constitutes another powerful tool for the identification of nonlinear optical systems.
NASA Technical Reports Server (NTRS)
Rodriguez, Guillermo (Editor)
1990-01-01
Various papers on intelligent control and adaptive systems are presented. Individual topics addressed include: control architecture for a Mars walking vehicle, representation for error detection and recovery in robot task plans, real-time operating system for robots, execution monitoring of a mobile robot system, statistical mechanics models for motion and force planning, global kinematics for manipulator planning and control, exploration of unknown mechanical assemblies through manipulation, low-level representations for robot vision, harmonic functions for robot path construction, simulation of dual behavior of an autonomous system. Also discussed are: control framework for hand-arm coordination, neural network approach to multivehicle navigation, electronic neural networks for global optimization, neural network for L1 norm linear regression, planning for assembly with robot hands, neural networks in dynamical systems, control design with iterative learning, improved fuzzy process control of spacecraft autonomous rendezvous using a genetic algorithm.