Adaptive inverse control of linear and nonlinear systems using dynamic neural networks.
Plett, G L
2003-01-01
In this paper, we see adaptive control as a three-part adaptive-filtering problem. First, the dynamical system we wish to control is modeled using adaptive system-identification techniques. Second, the dynamic response of the system is controlled using an adaptive feedforward controller. No direct feedback is used, except that the system output is monitored and used by an adaptive algorithm to adjust the parameters of the controller. Third, disturbance canceling is performed using an additional adaptive filter. The canceler does not affect system dynamics, but feeds back plant disturbance in a way that minimizes output disturbance power. The techniques work to control minimum-phase or nonminimum-phase, linear or nonlinear, single-input-single-output (SISO) or multiple-input-multiple-ouput (MIMO), stable or stabilized systems. Constraints may additionally be placed on control effort for a practical implementation. Simulation examples are presented to demonstrate that the proposed methods work very well.
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.
The Adaptive Kernel Neural Network
1989-10-01
A neural network architecture for clustering and classification is described. The Adaptive Kernel Neural Network (AKNN) is a density estimation...classification layer. The AKNN retains the inherent parallelism common in neural network models. Its relationship to the kernel estimator allows the network to
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.
A neural network for bounded linear programming
Culioli, J.C.; Protopopescu, V.; Britton, C.; Ericson, N. )
1989-01-01
The purpose of this paper is to describe a neural network implementation of an algorithm recently designed at ORNL to solve the Transportation and the Assignment Problems, and, more generally, any explicitly bounded linear program. 9 refs.
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.
Adaptive neural networks for mobile robotic control
NASA Astrophysics Data System (ADS)
Burnett, Jeff R.; Dagli, Cihan H.
2001-03-01
Movement of a differential drive robot has non-linear dependence on the current position and orientation. A controller must be able to deal with the non-linearity of the plant. The controller must either linearize the plant and deal with special cases, or be non-linear itself. Once the controller is designed, implementation on a real robotic platform presents challenges due to the varying parameters of the plant. Robots of the same model may have different motor frictions. The surface the robot maneuvers on may change e.g. carpet to tile. Batteries will drain, providing less power over time. A feed-forward neural network controller could overcome these challenges. The network could learn the non- linearities of the plant and monitor the error for parameter changes and adapt to them. In this manner, a single controller can be designed for an ideal robot, and then used to populate a multi-robot colony without manually fine tuning the controller for each robot. This paper shall demonstrate such a controller, outlining design in simulation and implementation on Khepera robotic platforms.
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.
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.
Comparative performance of linear and nonlinear neural networks to predict irregular breathing.
Murphy, Martin J; Dieterich, Sonja
2006-11-21
Breathing adaptation during external-beam radiotherapy is a matter of great concern because uncompensated tumour motion requires extended treatment margins that endanger sensitive tissue. Compensation strategies include beam gating, collimator tracking and robotic beam re-alignment. All of these schemes have a system latency of up to several hundred milliseconds, which calls in turn for predictive control loops. Irregularities in breathing make prediction difficult. We have evaluated the performance of two classes of control loop algorithms-the linear adaptive filter and the adaptive nonlinear neural network-for highly irregular patient breathing behaviours. The neural network demonstrated robust adaptability to all of the observed breathing patterns while the linear filter failed in a significant percentage of cases. For those cases where the linear filter could function, it made less accurate predictions than the neural network. Because the neural network presents no additional computational burden in the control loop we conclude that it is the preferred choice among heuristic predictive algorithms.
Neural network models for Linear Programming
Culioli, J.C.; Protopopescu, V.; Britton, C.; Ericson, N. )
1989-01-01
The purpose of this paper is to present a neural network that solves the general Linear Programming (LP) problem. In the first part, we recall Hopfield and Tank's circuit for LP and show that although it converges to stable states, it does not, in general, yield admissible solutions. This is due to the penalization treatment of the constraints. In the second part, we propose an approach based on Lagragrange multipliers that converges to primal and dual admissible solutions. We also show that the duality gap (measuring the optimality) can be rendered, in principle, as small as needed. 11 refs.
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.
Neural adaptations to electrical stimulation strength training.
Hortobágyi, Tibor; Maffiuletti, Nicola A
2011-10-01
This review provides evidence for the hypothesis that electrostimulation strength training (EST) increases the force of a maximal voluntary contraction (MVC) through neural adaptations in healthy skeletal muscle. Although electrical stimulation and voluntary effort activate muscle differently, there is substantial evidence to suggest that EST modifies the excitability of specific neural paths and such adaptations contribute to the increases in MVC force. Similar to strength training with voluntary contractions, EST increases MVC force after only a few sessions with some changes in muscle biochemistry but without overt muscle hypertrophy. There is some mixed evidence for spinal neural adaptations in the form of an increase in the amplitude of the interpolated twitch and in the amplitude of the volitional wave, with less evidence for changes in spinal excitability. Cross-sectional and exercise studies also suggest that the barrage of sensory and nociceptive inputs acts at the cortical level and can modify the motor cortical output and interhemispheric paths. The data suggest that neural adaptations mediate initial increases in MVC force after short-term EST.
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.
Linear programming for learning in neural networks
NASA Astrophysics Data System (ADS)
Raghavan, Raghu
1991-08-01
The authors have previously proposed a network of probabilistic cellular automata (PCAs) as part of an image recognition system designed to integrate model-based and data-driven approaches in a connectionist framework. The PCA arises from some natural requirements on the system which include incorporation of prior knowledge such as in inference rules, locality of inferences, and full parallelism. This network has been applied to recognize objects in both synthetic and in real data. This approach achieves recognition through the short-, rather than the long-time behavior of the dynamics of the PCA. In this paper, some methods are developed for learning the connection strengths by solving linear inequalities: the figures of merit are tendencies or directions of movement of the dynamical system. These 'dynamical' figures of merit result in inequality constraints on the connection strengths which are solved by linear (LP) or quadratic programs (QP). An algorithm is described for processing a large number of samples to determine weights for the PCA. The work may be regarded as either pointing out another application for constrained optimization, or as pointing out the need to extend the perceptron and similar methods for learning. The extension is needed because the neural network operates on a different principle from that for which the perceptron method was devised.
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.
Applications of Neural Networks to Adaptive Control
1989-12-01
DTIC ;- E py 00 NAVAL POSTGRADUATE SCHOOL Monterey, California I.$ RDTIC IELECTE fl THESIS BEG7V°U APPLICATIONS OF NEURAL NETWORKS TO ADAPTIVE CONTROL...Second keader E . Robert Wood, Chairman, Department of Aeronautics and Astronautics Gordoii E . Schacher, Dean of Faculty and Graduate Education ii ABSTRACT...23: Network Dynamic Stability for q(t) . ............................. 55 ix Figure 24: Network Dynamic Stability for e (t
Linear ubiquitination signals in adaptive immune responses.
Ikeda, Fumiyo
2015-07-01
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-κB (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.
Algebraic and adaptive learning in neural control systems
NASA Astrophysics Data System (ADS)
Ferrari, Silvia
A systematic approach is developed for designing adaptive and reconfigurable nonlinear control systems that are applicable to plants modeled by ordinary differential equations. The nonlinear controller comprising a network of neural networks is taught using a two-phase learning procedure realized through novel techniques for initialization, on-line training, and adaptive critic design. A critical observation is that the gradients of the functions defined by the neural networks must equal corresponding linear gain matrices at chosen operating points. On-line training is based on a dual heuristic adaptive critic architecture that improves control for large, coupled motions by accounting for actual plant dynamics and nonlinear effects. An action network computes the optimal control law; a critic network predicts the derivative of the cost-to-go with respect to the state. Both networks are algebraically initialized based on prior knowledge of satisfactory pointwise linear controllers and continue to adapt on line during full-scale simulations of the plant. On-line training takes place sequentially over discrete periods of time and involves several numerical procedures. A backpropagating algorithm called Resilient Backpropagation is modified and successfully implemented to meet these objectives, without excessive computational expense. This adaptive controller is as conservative as the linear designs and as effective as a global nonlinear controller. The method is successfully implemented for the full-envelope control of a six-degree-of-freedom aircraft simulation. The results show that the on-line adaptation brings about improved performance with respect to the initialization phase during aircraft maneuvers that involve large-angle and coupled dynamics, and parameter variations.
Neural Adaptation Effects in Conceptual Processing.
Marino, Barbara F M; Borghi, Anna M; Gemmi, Luca; Cacciari, Cristina; Riggio, Lucia
2015-07-31
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.
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
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.
Adaptive Control of Visually Guided Grasping in Neural Networks
1990-03-12
U01ITU S.WM NONnumsen Adaptive Control of Visually Guided Grasping in Neural Networks AFOSR-89-&CO030 88-NL-209 L AUTHOrSF 2313/A8 00 61102F (V) Dr...FINAL REPORT ADAPTIVE CONTROL OF VISUALLY GUIDED GRASPING IN NEURAL NETWORKS Neurogen Laboratories Inc. Project Summary Research performed for AFOSR...arm’s length in position and 6 degrees in orientation. Keywords: Neural Networks , Adaptive Motor Control, Sensory-Motor sensation Introduction The human
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 control using neural networks and approximate models.
Narendra, K S; Mukhopadhyay, S
1997-01-01
The NARMA model is an exact representation of the input-output behavior of finite-dimensional nonlinear discrete-time dynamical systems in a neighborhood of the equilibrium state. However, it is not convenient for purposes of adaptive control using neural networks due to its nonlinear dependence on the control input. Hence, quite often, approximate methods are used for realizing the neural controllers to overcome computational complexity. In this paper, we introduce two classes of models which are approximations to the NARMA model, and which are linear in the control input. The latter fact substantially simplifies both the theoretical analysis as well as the practical implementation of the controller. Extensive simulation studies have shown that the neural controllers designed using the proposed approximate models perform very well, and in many cases even better than an approximate controller designed using the exact NARMA model. In view of their mathematical tractability as well as their success in simulation studies, a case is made in this paper that such approximate input-output models warrant a detailed study in their own right.
Solving linear integer programming problems by a novel neural model.
Cavalieri, S
1999-02-01
The paper deals with integer linear programming problems. As is well known, these are extremely complex problems, even when the number of integer variables is quite low. Literature provides examples of various methods to solve such problems, some of which are of a heuristic nature. This paper proposes an alternative strategy based on the Hopfield neural network. The advantage of the strategy essentially lies in the fact that hardware implementation of the neural model allows for the time required to obtain a solution so as not depend on the size of the problem to be solved. The paper presents a particular class of integer linear programming problems, including well-known problems such as the Travelling Salesman Problem and the Set Covering Problem. After a brief description of this class of problems, it is demonstrated that the original Hopfield model is incapable of supplying valid solutions. This is attributed to the presence of constant bias currents in the dynamic of the neural model. A demonstration of this is given and then a novel neural model is presented which continues to be based on the same architecture as the Hopfield model, but introduces modifications thanks to which the integer linear programming problems presented can be solved. Some numerical examples and concluding remarks highlight the solving capacity of the novel neural model.
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.
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 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 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.
Cichocki, A; Unbehauen, R
1994-01-01
In this paper a new class of simplified low-cost analog artificial neural networks with on chip adaptive learning algorithms are proposed for solving linear systems of algebraic equations in real time. The proposed learning algorithms for linear least squares (LS), total least squares (TLS) and data least squares (DLS) problems can be considered as modifications and extensions of well known algorithms: the row-action projection-Kaczmarz algorithm and/or the LMS (Adaline) Widrow-Hoff algorithms. The algorithms can be applied to any problem which can be formulated as a linear regression problem. The correctness and high performance of the proposed neural networks are illustrated by extensive computer simulation results.
Unmasking the linear behaviour of slow motor adaptation to prolonged convergence.
Erkelens, Ian M; Thompson, Benjamin; Bobier, William R
2016-06-01
Adaptation to changing environmental demands is central to maintaining optimal motor system function. Current theories suggest that adaptation in both the skeletal-motor and oculomotor systems involves a combination of fast (reflexive) and slow (recalibration) mechanisms. Here we used the oculomotor vergence system as a model to investigate the mechanisms underlying slow motor adaptation. Unlike reaching with the upper limbs, vergence is less susceptible to changes in cognitive strategy that can affect the behaviour of motor adaptation. We tested the hypothesis that mechanisms of slow motor adaptation reflect early neural processing by assessing the linearity of adaptive responses over a large range of stimuli. Using varied disparity stimuli in conflict with accommodation, the slow adaptation of tonic vergence was found to exhibit a linear response whereby the rate (R(2) = 0.85, P < 0.0001) and amplitude (R(2) = 0.65, P < 0.0001) of the adaptive effects increased proportionally with stimulus amplitude. These results suggest that this slow adaptive mechanism is an early neural process, implying a fundamental physiological nature that is potentially dominated by subcortical and cerebellar substrates.
Identification of Infinite Dimensional Systems via Adaptive Wavelet Neural Networks
1993-01-01
We consider identification of distributed systems via adaptive wavelet neural networks (AWNNs). We take advantage of the multiresolution property of...wavelet systems and the computational structure of neural networks to approximate the unknown plant successively. A systematic approach is developed
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.
A Quasi-ARX Neural Network with Switching Mechanism to Adaptive Control of Nonlinear Systems
NASA Astrophysics Data System (ADS)
Wang, Lan; Cheng, Yu; Hu, Jinglu
This paper introduces an improved quasi-ARX neural network and discusses its application to adaptive control of nonlinear systems. A switching mechanism is employed to improve the performance of the quasi-ARX neural network prediction model which has linear and nonlinear parts. An adaptive controller for a nonlinear system is established based on the proposed prediction model and some stability analysis of the control system is shown. Simulations are given to show the effectiveness of the proposed method both on stability and accuracy.
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.
Study on adaptive PID algorithm of hydraulic turbine governing system based on fuzzy neural network
NASA Astrophysics Data System (ADS)
Tang, Liangbao; Bao, Jumin
2006-11-01
The conventional hydraulic turbine governing system can't automatically modulate PID parameters according to the dynamic process of the system, the generator speed is unstable and the mains frequency fluctuation results in. To solve the above problem, the fuzzy neural network (FNN) and the adaptive control are combined to design an adaptive PID algorithm based on the fuzzy neural network which can effectively control the hydraulic turbine governing system. Finally, the improved mathematic model is simulated. The simulation results are compared with the conventional hydraulic turbine's. Thus the validity and superiority of the fuzzy neural network PID algorithm have been proved. The simulation results show that the algorithm not only retains the functions of fuzzy control, but also provides the ability to approach to the non-linear system. Also the dynamic process of the system can be reflected more precisely and the on-line adaptive control is implemented. The algorithm is superior to other methods in response and control effect.
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.
PATTERN RECOGNITION AND CLASSIFICATION USING ADAPTIVE LINEAR NEURON DEVICES
adaption by an adaptive linear neuron ( Adaline ), as applied to the pattern recognition and classification problem; (2) Four possible iterative adaption...schemes which may be used to train as Adaline ; (3) Use of Multiple Adalines (Madaline) and two logic layers to increase system capability; and (4) Use...of Adaline in the practical fields of Speech Recognition, Weather Forecasting and Adaptive Control Systems and the possible use of Madaline in the Character Recognition field.
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.
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.
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.
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.
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.
Adaptive neural control of spacecraft using control moment gyros
NASA Astrophysics Data System (ADS)
Leeghim, Henzeh; Kim, Donghoon
2015-03-01
An adaptive control technique is applied to reorient spacecraft with uncertainty using control moment gyros. A nonlinear quaternion feedback law is chosen as a baseline controller. An additional adaptive control input supported by neural networks can estimate and eliminate unknown terms adaptively. The normalized input neural networks are considered for reliable computation of the adaptive input. To prove the stability of the closed-loop dynamics with the control law, the Lyapunov stability theory is considered. Accordingly, the proposed approach results in the uniform ultimate boundedness in tracking error. For reorientation maneuvers, control moment gyros are utilized with a well-known singularity problem described in this work investigated by predicting one-step ahead singularity index. A momentum vector recovery approach using magnetic torquers is also introduced to evaluate the avoidance strategies indirectly. Finally, the suggested methods are demonstrated by numerical simulation studies.
Neural adaptive control for vibration suppression in composite fin-tip of aircraft.
Suresh, S; Kannan, N; Sundararajan, N; Saratchandran, P
2008-06-01
In this paper, we present a neural adaptive control scheme for active vibration suppression of a composite aircraft fin tip. The mathematical model of a composite aircraft fin tip is derived using the finite element approach. The finite element model is updated experimentally to reflect the natural frequencies and mode shapes very accurately. Piezo-electric actuators and sensors are placed at optimal locations such that the vibration suppression is a maximum. Model-reference direct adaptive neural network control scheme is proposed to force the vibration level within the minimum acceptable limit. In this scheme, Gaussian neural network with linear filters is used to approximate the inverse dynamics of the system and the parameters of the neural controller are estimated using Lyapunov based update law. In order to reduce the computational burden, which is critical for real-time applications, the number of hidden neurons is also estimated in the proposed scheme. The global asymptotic stability of the overall system is ensured using the principles of Lyapunov approach. Simulation studies are carried-out using sinusoidal force functions of varying frequency. Experimental results show that the proposed neural adaptive control scheme is capable of providing significant vibration suppression in the multiple bending modes of interest. The performance of the proposed scheme is better than the H(infinity) control scheme.
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.
Li, Lin; Park, Il Memming; Brockmeier, Austin; Chen, Badong; Seth, Sohan; Francis, Joseph T; Sanchez, Justin C; Príncipe, José C
2013-07-01
The precise control of spiking in a population of neurons via applied electrical stimulation is a challenge due to the sparseness of spiking responses and neural system plasticity. We pose neural stimulation as a system control problem where the system input is a multidimensional time-varying signal representing the stimulation, and the output is a set of spike trains; the goal is to drive the output such that the elicited population spiking activity is as close as possible to some desired activity, where closeness is defined by a cost function. If the neural system can be described by a time-invariant (homogeneous) model, then offline procedures can be used to derive the control procedure; however, for arbitrary neural systems this is not tractable. Furthermore, standard control methodologies are not suited to directly operate on spike trains that represent both the target and elicited system response. In this paper, we propose a multiple-input multiple-output (MIMO) adaptive inverse control scheme that operates on spike trains in a reproducing kernel Hilbert space (RKHS). The control scheme uses an inverse controller to approximate the inverse of the neural circuit. The proposed control system takes advantage of the precise timing of the neural events by using a Schoenberg kernel defined directly in the space of spike trains. The Schoenberg kernel maps the spike train to an RKHS and allows linear algorithm to control the nonlinear neural system without the danger of converging to local minima. During operation, the adaptation of the controller minimizes a difference defined in the spike train RKHS between the system and the target response and keeps the inverse controller close to the inverse of the current neural circuit, which enables adapting to neural perturbations. The results on a realistic synthetic neural circuit show that the inverse controller based on the Schoenberg kernel outperforms the decoding accuracy of other models based on the conventional rate
Adaptive fuzzy-neural-network control for maglev transportation system.
Wai, Rong-Jong; Lee, Jeng-Dao
2008-01-01
A magnetic-levitation (maglev) transportation system including levitation and propulsion control is a subject of considerable scientific interest because of highly nonlinear and unstable behaviors. In this paper, the dynamic model of a maglev transportation system including levitated electromagnets and a propulsive linear induction motor (LIM) based on the concepts of mechanical geometry and motion dynamics is developed first. Then, a model-based sliding-mode control (SMC) strategy is introduced. In order to alleviate chattering phenomena caused by the inappropriate selection of uncertainty bound, a simple bound estimation algorithm is embedded in the SMC strategy to form an adaptive sliding-mode control (ASMC) scheme. However, this estimation algorithm is always a positive value so that tracking errors introduced by any uncertainty will cause the estimated bound increase even to infinity with time. Therefore, it further designs an adaptive fuzzy-neural-network control (AFNNC) scheme by imitating the SMC strategy for the maglev transportation system. In the model-free AFNNC, online learning algorithms are designed to cope with the problem of chattering phenomena caused by the sign action in SMC design, and to ensure the stability of the controlled system without the requirement of auxiliary compensated controllers despite the existence of uncertainties. The outputs of the AFNNC scheme can be directly supplied to the electromagnets and LIM without complicated control transformations for relaxing strict constrains in conventional model-based control methodologies. The effectiveness of the proposed control schemes for the maglev transportation system is verified by numerical simulations, and the superiority of the AFNNC scheme is indicated in comparison with the SMC and ASMC strategies.
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.
Diminished Neural Adaptation during Implicit Learning in Autism
Schipul, Sarah E.; Just, Marcel Adam
2015-01-01
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. PMID:26484826
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.
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.
Zou, An-Min; Dev Kumar, Krishna; Hou, Zeng-Guang
2010-09-01
This paper investigates the problem of output feedback attitude control of an uncertain spacecraft. Two robust adaptive output feedback controllers based on Chebyshev neural networks (CNN) termed adaptive neural networks (NN) controller-I and adaptive NN controller-II are proposed for the attitude tracking control of spacecraft. The four-parameter representations (quaternion) are employed to describe the spacecraft attitude for global representation without singularities. The nonlinear reduced-order observer is used to estimate the derivative of the spacecraft output, and the CNN is introduced to further improve the control performance through approximating the spacecraft attitude motion. The implementation of the basis functions of the CNN used in the proposed controllers depends only on the desired signals, and the smooth robust compensator using the hyperbolic tangent function is employed to counteract the CNN approximation errors and external disturbances. The adaptive NN controller-II can efficiently avoid the over-estimation problem (i.e., the bound of the CNNs output is much larger than that of the approximated unknown function, and hence, the control input may be very large) existing in the adaptive NN controller-I. Both adaptive output feedback controllers using CNN can guarantee that all signals in the resulting closed-loop system are uniformly ultimately bounded. For performance comparisons, the standard adaptive controller using the linear parameterization of spacecraft attitude motion is also developed. Simulation studies are presented to show the advantages of the proposed CNN-based output feedback approach over the standard adaptive output feedback approach.
Adaptive Neural Network Controller for ATM Traffic
1996-12-01
IEEE Communications Magazine (October 1995). 2. Baum, Eric B...Adaptive Control in ATM Networks," IEEE Communications Magazine (October 1995). 9. Evanowsky, John B. "Information for the Warrior," IEEE Communications Magazine (October...Network Applications in ATM," IEEE Communications Magazine (October 1995). 78 16. Imrich, et al. "A counter based congestion control for ATM
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
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 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 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.
The predictive roles of neural oscillations in speech motor adaptability.
Sengupta, Ranit; Nasir, Sazzad M
2016-06-01
The human speech system exhibits a remarkable flexibility by adapting to alterations in speaking environments. While it is believed that speech motor adaptation under altered sensory feedback involves rapid reorganization of speech motor networks, the mechanisms by which different brain regions communicate and coordinate their activity to mediate adaptation remain unknown, and explanations of outcome differences in adaption remain largely elusive. In this study, under the paradigm of altered auditory feedback with continuous EEG recordings, the differential roles of oscillatory neural processes in motor speech adaptability were investigated. The predictive capacities of different EEG frequency bands were assessed, and it was found that theta-, beta-, and gamma-band activities during speech planning and production contained significant and reliable information about motor speech adaptability. It was further observed that these bands do not work independently but interact with each other suggesting an underlying brain network operating across hierarchically organized frequency bands to support motor speech adaptation. These results provide novel insights into both learning and disorders of speech using time frequency analysis of neural oscillations.
An adaptive holographic implementation of a neural network
NASA Technical Reports Server (NTRS)
Downie, John D.; Hine, Butler P., III; Reid, Max B.
1990-01-01
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 direction. 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 the advantage of the holographic implementation with respect to the matrix-vector processor is demonstrated.
Evolving RBF neural networks for adaptive soft-sensor design.
Alexandridis, Alex
2013-12-01
This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input-output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.
Electronic realisation of recurrent neural network for solving simultaneous linear equations
NASA Astrophysics Data System (ADS)
Wang, J.
1992-02-01
An electronic neural network for solving simultaneous linear equations is presented. The proposed electronic neural network is able to generate real-time solutions to large-scale problems. The operating characteristics of an opamp based neural network is demonstrated via an illustrative example.
Self-characterization of linear and nonlinear adaptive optics systems
NASA Astrophysics Data System (ADS)
Hampton, Peter J.; Conan, Rodolphe; Keskin, Onur; Bradley, Colin; Agathoklis, Pan
2008-01-01
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.
Neural network-based adaptive controller design of robotic manipulators with an observer.
Sun, F; Sun, Z; Woo, P Y
2001-01-01
A neural network (NN)-based adaptive controller with an observer is proposed for the trajectory tracking of robotic manipulators with unknown dynamics nonlinearities. It is assumed that the robotic manipulator has only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity, while NNs are employed to further improve the control performance of the controlled system through approximating the modified robot dynamics function. The adaptive controller for robots with an observer can guarantee the uniform ultimate bounds of the tracking errors and the observer errors as well as the bounds of the NN weights. For performance comparisons, the conventional adaptive algorithm with an observer using linearity in parameters of the robot dynamics is also developed in the same control framework as the NN approach for online approximating unknown nonlinearities of the robot dynamics. Main theoretical results for designing such an observer-based adaptive controller with the NN approach using multilayer NNs with sigmoidal activation functions, as well as with the conventional adaptive approach using linearity in parameters of the robot dynamics are given. The performance comparisons between the NN approach and the conventional adaptation approach with an observer is carried out to show the advantages of the proposed control approaches through simulation studies.
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
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.
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
Fast HDR image upscaling using locally adapted linear filters
NASA Astrophysics Data System (ADS)
Talebi, Hossein; Su, Guan-Ming; Yin, Peng
2015-02-01
A new method for upscaling high dynamic range (HDR) images is introduced in this paper. Overshooting artifact is the common problem when using linear filters such as bicubic interpolation. This problem is visually more noticeable while working on HDR images where there exist more transitions from dark to bright. Our proposed method is capable of handling these artifacts by computing a simple gradient map which enables the filter to be locally adapted to the image content. This adaptation consists of first, clustering pixels into regions with similar edge structures and second, learning the shape and length of our symmetric linear filter for each of these pixel groups. This new filter can be implemented in a separable fashion which perfectly fits hardware implementations. Our experimental results show that training our filter with HDR images can effectively reduce the overshooting artifacts and improve upon the visual quality of the existing linear upscaling approaches.
Linear adaptive control of a single-tether system
NASA Technical Reports Server (NTRS)
Greene, M. E.; Carter, J. T.; Walls, J. L.
1992-01-01
A control law for a single-tether orbiting satellite system based on a reduced order linear adaptive control technique is presented. The main advantages of this technique are its design simplicity and the facts that specific system parameters and model linearization are not required when designing the controller. Two controllers are developed: one which uses only tension in the tether as control actuation and one which uses both tension and in-plane thrusters as control actuation. Both a sixth-order nonlinear and an 11th-order bead model of a tethered satellite system are used for simulation purposes, demonstrating the ability of the controller to manage an uncertain system. Retrieval and stationkeeping results using these nonlinear models and the linear adaptive controller demonstrate the feasibility of the method. The robustness of the controller with respect to parameter uncertainties is also demonstrated by changing the nonlinear model and parameters within the model without redesigning the controller.
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.
Analysis and Synthesis of Adaptive Neural Elements and Assemblies.
2007-11-02
Form Approved REPORT DOCUMENTATION PAGE OMB No. 0704-0188 u,• thc renortc bsurden 4 ,r this collection of Information s estimated to averav i -our...motivational systems can influence behaviors, in part, by acting on motor systems, such as CPGs. Fourth, motor systems possess cellular mechanisms ...motor behaviors are governed by highly adaptive neural networks and help to explain how systems of nerve cells function to produce and modulate
An adaptive neural fuzzy filter and its applications.
Lin, C T; Juang, C F
1997-01-01
A new kind of nonlinear adaptive filter, the adaptive neural fuzzy filter (ANFF), based upon a neural network's learning ability and fuzzy if-then rule structure, is proposed in this paper. The ANFF is inherently a feedforward multilayered connectionist network which can learn by itself according to numerical training data or expert knowledge represented by fuzzy if-then rules. The adaptation here includes the construction of fuzzy if-then rules (structure learning), and the tuning of the free parameters of membership functions (parameter learning). In the structure learning phase, fuzzy rules are found based on the matching of input-output clusters. In the parameter learning phase, a backpropagation-like adaptation algorithm is developed to minimize the output error. There are no hidden nodes (i.e., no membership functions and fuzzy rules) initially, and both the structure learning and parameter learning are performed concurrently as the adaptation proceeds. However, if some linguistic information about the design of the filter is available, such knowledge can be put into the ANFF to form an initial structure with hidden nodes. Two major advantages of the ANFF can thus be seen: 1) a priori knowledge can be incorporated into the ANFF which makes the fusion of numerical data and linguistic information in the filter possible; and 2) no predetermination, like the number of hidden nodes, must be given, since the ANFF can find its optimal structure and parameters automatically.
Short-Term Neural Adaptation to Simultaneous Bifocal Images
Radhakrishnan, Aiswaryah; Dorronsoro, Carlos; Sawides, Lucie; Marcos, Susana
2014-01-01
Simultaneous vision is an increasingly used solution for the correction of presbyopia (the age-related loss of ability to focus near images). Simultaneous Vision corrections, normally delivered in the form of contact or intraocular lenses, project on the patient's retina a focused image for near vision superimposed with a degraded image for far vision, or a focused image for far vision superimposed with the defocused image of the near scene. It is expected that patients with these corrections are able to adapt to the complex Simultaneous Vision retinal images, although the mechanisms or the extent to which this happens is not known. We studied the neural adaptation to simultaneous vision by studying changes in the Natural Perceived Focus and in the Perceptual Score of image quality in subjects after exposure to Simultaneous Vision. We show that Natural Perceived Focus shifts after a brief period of adaptation to a Simultaneous Vision blur, similar to adaptation to Pure Defocus. This shift strongly correlates with the magnitude and proportion of defocus in the adapting image. The magnitude of defocus affects perceived quality of Simultaneous Vision images, with 0.5 D defocus scored lowest and beyond 1.5 D scored “sharp”. Adaptation to Simultaneous Vision shifts the Perceptual Score of these images towards higher rankings. Larger improvements occurred when testing simultaneous images with the same magnitude of defocus as the adapting images, indicating that wearing a particular bifocal correction improves the perception of images provided by that correction. PMID:24664087
NASA Astrophysics Data System (ADS)
Zhao, Hui; Li, Lixiang; Peng, Haipeng; Kurths, Jürgen; Xiao, Jinghua; Yang, Yixian
2015-05-01
In this paper, exponential anti-synchronization in mean square of an uncertain memristor-based neural network is studied. The uncertain terms include non-modeled dynamics with boundary and stochastic perturbations. Based on the differential inclusions theory, linear matrix inequalities, Gronwall's inequality and adaptive control technique, an adaptive controller with update laws is developed to realize the exponential anti-synchronization. Adaptive controller can adjust itself behavior to get the best performance, according to the environment is changing or the environment has changed, which has the ability to adapt to environmental change. Furthermore, a numerical example is provided to validate the effectiveness of the proposed method.
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
Zhao, Haiquan; Zhang, Jiashu
2009-04-01
This paper proposes a novel computational efficient adaptive nonlinear equalizer based on combination of finite impulse response (FIR) filter and functional link artificial neural network (CFFLANN) to compensate linear and nonlinear distortions in nonlinear communication channel. This convex nonlinear combination results in improving the speed while retaining the lower steady-state error. In addition, since the CFFLANN needs not the hidden layers, which exist in conventional neural-network-based equalizers, it exhibits a simpler structure than the traditional neural networks (NNs) and can require less computational burden during the training mode. Moreover, appropriate adaptation algorithm for the proposed equalizer is derived by the modified least mean square (MLMS). Results obtained from the simulations clearly show that the proposed equalizer using the MLMS algorithm can availably eliminate various intensity linear and nonlinear distortions, and be provided with better anti-jamming performance. Furthermore, comparisons of the mean squared error (MSE), the bit error rate (BER), and the effect of eigenvalue ratio (EVR) of input correlation matrix are presented.
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
Visual discrimination and adaptation using non-linear unsupervised learning
NASA Astrophysics Data System (ADS)
Jiménez, Sandra; Laparra, Valero; Malo, Jesus
2013-03-01
Understanding human vision not only involves empirical descriptions of how it works, but also organization principles that explain why it does so. Identifying the guiding principles of visual phenomena requires learning algorithms to optimize specific goals. Moreover, these algorithms have to be flexible enough to account for the non-linear and adaptive behavior of the system. For instance, linear redundancy reduction transforms certainly explain a wide range of visual phenomena. However, the generality of this organization principle is still in question:10 it is not only that and additional constraints such as energy cost may be relevant as well, but also, statistical independence may not be the better solution to make optimal inferences in squared error terms. Moreover, linear methods cannot account for the non-uniform discrimination in different regions of the image and color space: linear learning methods necessarily disregard the non-linear nature of the system. Therefore, in order to account for the non-linear behavior, principled approaches commonly apply the trick of using (already non-linear) parametric expressions taken from empirical models. Therefore these approaches are not actually explaining the non-linear behavior, but just fitting it to image statistics. In summary, a proper explanation of the behavior of the system requires flexible unsupervised learning algorithms that (1) are tunable to different, perceptually meaningful, goals; and (2) make no assumption on the non-linearity. Over the last years we have worked on these kind of learning algorithms based on non-linear ICA,18 Gaussianization, 19 and principal curves. In this work we stress the fact that these methods can be tuned to optimize different design strategies, namely statistical independence, error minimization under quantization, and error minimization under truncation. Then, we show (1) how to apply these techniques to explain a number of visual phenomena, and (2) suggest the
Adaptation to New Microphones Using Artificial Neural Networks With Trainable Activation Functions.
Siniscalchi, Sabato Marco; Salerno, Valerio Mario
2016-04-14
Model adaptation is a key technique that enables a modern automatic speech recognition (ASR) system to adjust its parameters, using a small amount of enrolment data, to the nuances in the speech spectrum due to microphone mismatch in the training and test data. In this brief, we investigate four different adaptation schemes for connectionist (also known as hybrid) ASR systems that learn microphone-specific hidden unit contributions, given some adaptation material. This solution is made possible adopting one of the following schemes: 1) the use of Hermite activation functions; 2) the introduction of bias and slope parameters in the sigmoid activation functions; 3) the injection of an amplitude parameter specific for each sigmoid unit; or 4) the combination of 2) and 3). Such a simple yet effective solution allows the adapted model to be stored in a small-sized storage space, a highly desirable property of adaptation algorithms for deep neural networks that are suitable for large-scale online deployment. Experimental results indicate that the investigated approaches reduce word error rates on the standard Spoke 6 task of the Wall Street Journal corpus compared with unadapted ASR systems. Moreover, the proposed adaptation schemes all perform better than simple multicondition training and comparable favorably against conventional linear regression-based approaches while using up to 15 orders of magnitude fewer parameters. The proposed adaptation strategies are also effective when a single adaptation sentence is available.
Pipelined recurrent fuzzy neural networks for nonlinear adaptive speech prediction.
Stavrakoudis, Dimitris G; Theocharis, John B
2007-10-01
A class of pipelined recurrent fuzzy neural networks (PRFNNs) is proposed in this paper for nonlinear adaptive speech prediction. The PRFNNs are modular structures comprising a number of modules that are interconnected in a chained form. Each module is implemented by a small-scale recurrent fuzzy neural network (RFNN) with internal dynamics. Due to module nesting, the PRFNNs offer a number of desirable attributes, including decomposition of the modeling task, enhanced temporal processing capabilities, and multistage dynamic fuzzy inference. Tuning of the PRFNN adaptable parameters is accomplished by a series of gradient descent methods with different weighting of the modules and the decoupled extended Kalman filter (DEKF) algorithm, based on weight grouping. Extensive experimentation is carried out to evaluate the performance of the PRFNNs on the speech prediction platform. Comparative analysis shows that the PRFNNs outperform the single-RFNN models in terms of the prediction gains that are obtained and computational efficiency. Furthermore, PRFNNs provide considerably better performance compared to pipelined recurrent neural networks, for models with similar model complexity.
Neural network payload estimation for adaptive robot control.
Leahy, M R; Johnson, M A; Rogers, S K
1991-01-01
A concept is proposed for utilizing artificial neural networks to enhance the high-speed tracking accuracy of robotic manipulators. Tracking accuracy is a function of the controller's ability to compensate for disturbances produced by dynamical interactions between the links. A model-based control algorithm uses a nominal model of those dynamical interactions to reduce the disturbances. The problem is how to provide accurate dynamics information to the controller in the presence of payload uncertainty and modeling error. Neural network payload estimation uses a series of artificial neural networks to recognize the payload variation associated with a degradation in tracking performance. The network outputs are combined with a knowledge of nominal dynamics to produce a computationally efficient direct form of adaptive control. The concept is validated through experimentation and analysis on the first three links of a PUMA-560 manipulator. A multilayer perceptron architecture with two hidden layers is used. Integration of the principles of neural network pattern recognition and model-based control produces a tracking algorithm with enhanced robustness to incomplete dynamic information. Tracking efficacy and applicability to robust control algorithms are discussed.
Novel L1 neural network adaptive control architecture with guaranteed transient performance.
Cao, Chengyu; Hovakimyan, Naira
2007-07-01
In this paper, we present a novel neural network (NN) adaptive control architecture with guaranteed transient performance. With this new architecture, both input and output signals of an uncertain nonlinear system follow a desired linear system during the transient phase, in addition to stable tracking. This new architecture uses a low-pass filter in the feedback loop, which consequently enables to enforce the desired transient performance by increasing the adaptation gain. For the guaranteed transient performance of both input and output signals of the uncertain nonlinear system, the L1 gain of a cascaded system, comprised of the low-pass filter and the closed-loop desired reference model, is required to be less than the inverse of the Lipschitz constant of the unknown nonlinearities in the system. The tools from this paper can be used to develop a theoretically justified verification and validation framework for NN adaptive controllers. Simulation results illustrate the theoretical findings.
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.
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.
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.
Distributed Adaptive Neural Control for Stochastic Nonlinear Multiagent Systems.
Wang, Fang; Chen, Bing; Lin, Chong; Li, Xuehua
2016-11-14
In this paper, a consensus tracking problem of nonlinear multiagent systems is investigated under a directed communication topology. All the followers are modeled by stochastic nonlinear systems in nonstrict feedback form, where nonlinearities and stochastic disturbance terms are totally unknown. Based on the structural characteristic of neural networks (in Lemma 4), a novel distributed adaptive neural control scheme is put forward. The raised control method not only effectively handles unknown nonlinearities in nonstrict feedback systems, but also copes with the interactions among agents and coupling terms. Based on the stochastic Lyapunov functional method, it is indicated that all the signals of the closed-loop system are bounded in probability and all followers' outputs are convergent to a neighborhood of the output of leader. At last, the efficiency of the control method is testified by a numerical example.
Neural Network Associative Memory Using Non-Linear Holographic Storage Media
1989-12-01
T’,?T Cýy’ ( AFIT/GEO/ENG/89D-3 AD-A214 340 L NEURAL NETWORK ASSOCIATIVE MEMORY USING NON-LINEAR HOLOGRAPHIC STORAGE MEDIA I THESIS I Presented to...order approximations of the required gain were provided. - - -In= unazn A FIT/GEO/ENG/89D-3 NEURAL NETWORK ASSOCIATIVE MEMORY USING NON-LINEAR...approxi- mations of the required gain were provided. vi NEURAL NETWORK ASSOCIATIVE MEMORY USING NON-LINEAR HOLOGRAPHIC STORAGE MEDIA I. Introduction The
An Adaptive Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-ion Batteries
2010-10-01
be scheduled in advance when needed. In this paper, an adaptive recurrent neural network (ARNN) is proposed for system dynamic state forecasting. The...developed ARNN is constructed based on the adaptive/recurrent neural network architecture and the network weights are adaptively optimized using the
Adaptive H∞ nonlinear velocity tracking using RBFNN for linear DC brushless motor
NASA Astrophysics Data System (ADS)
Tsai, Ching-Chih; Chan, Cheng-Kain; Li, Yi Yu
2012-01-01
This article presents an adaptive H ∞ nonlinear velocity control for a linear DC brushless motor. A simplified model of this motor with friction is briefly recalled. The friction dynamics is described by the Lu Gre model and the online tuning radial basis function neural network (RBFNN) is used to parameterise the nonlinear friction function and un-modelled errors. An adaptive nonlinear H ∞ control method is then proposed to achieve velocity tracking, by assuming that the upper bounds of the ripple force, the changeable load and the nonlinear friction can be learned by the RBFNN. The closed-loop system is proven to be uniformly bounded using the Lyapunov stability theory. The feasibility and the efficacy of the proposed control are exemplified by conducting two velocity tracking experiments.
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.
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.
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.
Shaping Embodied Neural Networks for Adaptive Goal-directed Behavior
Chao, Zenas C.; Bakkum, Douglas J.; Potter, Steve M.
2008-01-01
The acts of learning and memory are thought to emerge from the modifications of synaptic connections between neurons, as guided by sensory feedback during behavior. However, much is unknown about how such synaptic processes can sculpt and are sculpted by neuronal population dynamics and an interaction with the environment. Here, we embodied a simulated network, inspired by dissociated cortical neuronal cultures, with an artificial animal (an animat) through a sensory-motor loop consisting of structured stimuli, detailed activity metrics incorporating spatial information, and an adaptive training algorithm that takes advantage of spike timing dependent plasticity. By using our design, we demonstrated that the network was capable of learning associations between multiple sensory inputs and motor outputs, and the animat was able to adapt to a new sensory mapping to restore its goal behavior: move toward and stay within a user-defined area. We further showed that successful learning required proper selections of stimuli to encode sensory inputs and a variety of training stimuli with adaptive selection contingent on the animat's behavior. We also found that an individual network had the flexibility to achieve different multi-task goals, and the same goal behavior could be exhibited with different sets of network synaptic strengths. While lacking the characteristic layered structure of in vivo cortical tissue, the biologically inspired simulated networks could tune their activity in behaviorally relevant manners, demonstrating that leaky integrate-and-fire neural networks have an innate ability to process information. This closed-loop hybrid system is a useful tool to study the network properties intermediating synaptic plasticity and behavioral adaptation. The training algorithm provides a stepping stone towards designing future control systems, whether with artificial neural networks or biological animats themselves. PMID:18369432
Adaptive PID control based on orthogonal endocrine neural networks.
Milovanović, Miroslav B; Antić, Dragan S; Milojković, Marko T; Nikolić, Saša S; Perić, Staniša Lj; Spasić, Miodrag D
2016-12-01
A new intelligent hybrid structure used for online tuning of a PID controller is proposed in this paper. The structure is based on two adaptive neural networks, both with built-in Chebyshev orthogonal polynomials. First substructure network is a regular orthogonal neural network with implemented artificial endocrine factor (OENN), in the form of environmental stimuli, to its weights. It is used for approximation of control signals and for processing system deviation/disturbance signals which are introduced in the form of environmental stimuli. The output values of OENN are used to calculate artificial environmental stimuli (AES), which represent required adaptation measure of a second network-orthogonal endocrine adaptive neuro-fuzzy inference system (OEANFIS). OEANFIS is used to process control, output and error signals of a system and to generate adjustable values of proportional, derivative, and integral parameters, used for online tuning of a PID controller. The developed structure is experimentally tested on a laboratory model of the 3D crane system in terms of analysing tracking performances and deviation signals (error signals) of a payload. OENN-OEANFIS performances are compared with traditional PID and 6 intelligent PID type controllers. Tracking performance comparisons (in transient and steady-state period) showed that the proposed adaptive controller possesses performances within the range of other tested controllers. The main contribution of OENN-OEANFIS structure is significant minimization of deviation signals (17%-79%) compared to other controllers. It is recommended to exploit it when dealing with a highly nonlinear system which operates in the presence of undesirable disturbances.
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.
Research on PGNAA adaptive analysis method with BP neural network
NASA Astrophysics Data System (ADS)
Peng, Ke-Xin; Yang, Jian-Bo; Tuo, Xian-Guo; Du, Hua; Zhang, Rui-Xue
2016-11-01
A new approach method to dealing with the puzzle of spectral analysis in prompt gamma neutron activation analysis (PGNAA) is developed and demonstrated. It consists of utilizing BP neural network to PGNAA energy spectrum analysis which is based on Monte Carlo (MC) simulation, the main tasks which we will accomplish as follows: (1) Completing the MC simulation of PGNAA spectrum library, we respectively set mass fractions of element Si, Ca, Fe from 0.00 to 0.45 with a step of 0.05 and each sample is simulated using MCNP. (2) Establishing the BP model of adaptive quantitative analysis of PGNAA energy spectrum, we calculate peak areas of eight characteristic gamma rays that respectively correspond to eight elements in each individual of 1000 samples and that of the standard sample. (3) Verifying the viability of quantitative analysis of the adaptive algorithm where 68 samples were used successively. Results show that the precision when using neural network to calculate the content of each element is significantly higher than the MCLLS.
Adaptive local linear regression with application to printer color management.
Gupta, Maya R; Garcia, Eric K; Chin, Erika
2008-06-01
Local learning methods, such as local linear regression and nearest neighbor classifiers, base estimates on nearby training samples, neighbors. Usually, the number of neighbors used in estimation is fixed to be a global "optimal" value, chosen by cross validation. This paper proposes adapting the number of neighbors used for estimation to the local geometry of the data, without need for cross validation. The term enclosing neighborhood is introduced to describe a set of neighbors whose convex hull contains the test point when possible. It is proven that enclosing neighborhoods yield bounded estimation variance under some assumptions. Three such enclosing neighborhood definitions are presented: natural neighbors, natural neighbors inclusive, and enclosing k-NN. The effectiveness of these neighborhood definitions with local linear regression is tested for estimating lookup tables for color management. Significant improvements in error metrics are shown, indicating that enclosing neighborhoods may be a promising adaptive neighborhood definition for other local learning tasks as well, depending on the density of training samples.
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.
Zhang, Jian-Hua; Böhme, Johann F
2007-11-01
In this paper we report an adaptive regularization network (ARN) approach to realizing fast blind separation of cerebral evoked potentials (EPs) from background electroencephalogram (EEG) activity with no need to make any explicit assumption on the statistical (or deterministic) signal model. The ARNs are proposed to construct nonlinear EEG and EP signal models. A novel adaptive regularization training (ART) algorithm is proposed to improve the generalization performance of the ARN. Two adaptive neural modeling methods based on the ARN are developed and their implementation and performance analysis are also presented. The computer experiments using simulated and measured visual evoked potential (VEP) data have shown that the proposed ARN modeling paradigm yields computationally efficient and more accurate VEP signal estimation owing to its intrinsic model-free and nonlinear processing characteristics.
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.
Optimal control of distributed parameter systems using adaptive critic neural networks
NASA Astrophysics Data System (ADS)
Padhi, Radhakant
In this dissertation, two systematic optimal control synthesis techniques are presented for distributed parameter systems based on the adaptive critic neural networks. Following the philosophy of dynamic programming, this adaptive critic optimal control synthesis approach has many desirable features, viz. having a feedback form of the control, ability for on-line implementation, no need for approximating the nonlinear system dynamics, etc. More important, unlike the dynamic programming, it can accomplish these objectives without getting overwhelmed by the computational and storage requirements. First, an approximate dynamic programming based adaptive critic control synthesis formulation was carried out assuming an approximation of the system dynamics in a discrete form. A variety of example problems were solved using this proposed general approach. Next a different formulation is presented, which is capable of directly addressing the continuous form of system dynamics for control design. This was obtained following the methodology of Galerkin projection based weighted residual approximation using a set of orthogonal basis functions. The basis functions were designed by with the help of proper orthogonal decomposition, which leads to a very low-dimensional lumped parameter representation. The regulator problems of linear and nonlinear heat equations were revisited. Optimal controllers were synthesized first assuming a continuous controller and then a set of discrete controllers in the spatial domain. Another contribution of this study is the formulation of simplified adaptive critics for a large class of problems, which can be interpreted as a significant improvement of the existing adaptive critic technique.
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
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.
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 Neural Network Nonparametric Identifier With Normalized Learning Laws.
Chairez, Isaac
2016-04-05
This paper addresses the design of a normalized convergent learning law for neural networks (NNs) with continuous dynamics. The NN is used here to obtain a nonparametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties is the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on normalized algorithms was used to adjust the weights of the NN. The adaptive algorithm was derived by means of a nonstandard logarithmic Lyapunov function (LLF). Two identifiers were designed using two variations of LLFs leading to a normalized learning law for the first identifier and a variable gain normalized learning law. In the case of the second identifier, the inclusion of normalized learning laws yields to reduce the size of the convergence region obtained as solution of the practical stability analysis. On the other hand, the velocity of convergence for the learning laws depends on the norm of errors in inverse form. This fact avoids the peaking transient behavior in the time evolution of weights that accelerates the convergence of identification error. A numerical example demonstrates the improvements achieved by the algorithm introduced in this paper compared with classical schemes with no-normalized continuous learning methods. A comparison of the identification performance achieved by the no-normalized identifier and the ones developed in this paper shows the benefits of the learning law proposed in this paper.
Zhao, Haiquan; Zhang, Jiashu
2010-02-01
A novel nonlinear adaptive filter with pipelined Chebyshev functional link artificial recurrent neural network (PCFLARNN) is presented in this paper, which uses a modification real-time recurrent learning algorithm. The PCFLARNN consists of a number of simple small-scale Chebyshev functional link artificial recurrent neural network (CFLARNN) modules. Compared to the standard recurrent neural network (RNN), those modules of PCFLARNN can simultaneously be performed in a pipelined parallelism fashion, and this would lead to a significant improvement in its total computational efficiency. Furthermore, contrasted with the architecture of a pipelined RNN (PRNN), each module of PCFLARNN is a CFLARNN whose nonlinearity is introduced by enhancing the input pattern with Chebyshev functional expansion, whereas the RNN of each module in PRNN utilizing linear input and first-order recurrent term only fails to utilize the high-order terms of inputs. Therefore, the performance of PCFLARNN can further be improved at the cost of a slightly increased computational complexity. In addition, due to the introduced nonlinear functional expansion of each module in PRNN, the number of input signals can be reduced. Computer simulations have demonstrated that the proposed filter performs better than PRNN and RNN for nonlinear colored signal prediction, nonstationary speech signal prediction, and chaotic time series prediction.
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.
A new neural network model for solving random interval linear programming problems.
Arjmandzadeh, Ziba; Safi, Mohammadreza; Nazemi, Alireza
2017-05-01
This paper presents a neural network model for solving random interval linear programming problems. The original problem involving random interval variable coefficients is first transformed into an equivalent convex second order cone programming problem. A neural network model is then constructed for solving the obtained convex second order cone problem. Employing Lyapunov function approach, it is also shown that the proposed neural network model is stable in the sense of Lyapunov and it is globally convergent to an exact satisfactory solution of the original problem. Several illustrative examples are solved in support of this technique.
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.
Semi-physical neural modeling for linear signal restoration.
Bourgois, Laurent; Roussel, Gilles; Benjelloun, Mohammed
2013-02-01
This paper deals with the design methodology of an Inverse Neural Network (INN) model. The basic idea is to carry out a semi-physical model gathering two types of information: the a priori knowledge of the deterministic rules which govern the studied system and the observation of the actual conduct of this system obtained from experimental data. This hybrid model is elaborated by being inspired by the mechanisms of a neuromimetic network whose structure is constrained by the discrete reverse-time state-space equations. In order to validate the approach, some tests are performed on two dynamic models. The first suggested model is a dynamic system characterized by an unspecified r-order Ordinary Differential Equation (ODE). The second one concerns in particular the mass balance equation for a dispersion phenomenon governed by a Partial Differential Equation (PDE) discretized on a basic mesh. The performances are numerically analyzed in terms of generalization, regularization and training effort.
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
A Bayesian regularized artificial neural network for adaptive optics forecasting
NASA Astrophysics Data System (ADS)
Sun, Zhi; Chen, Ying; Li, Xinyang; Qin, Xiaolin; Wang, Huiyong
2017-01-01
Real-time adaptive optics is a technology for enhancing the resolution of ground-based optical telescopes and overcoming the disturbance of atmospheric turbulence. The performance of the system is limited by delay errors induced by the servo system and photoelectrons noise of wavefront sensor. In order to cut these delay errors, this paper proposes a novel model to forecast the future control voltages of the deformable mirror. The predictive model is constructed by a multi-layered back propagation network with Bayesian regularization (BRBP). For the purpose of parallel computation and less disturbance, we adopt a number of sub-BP neural networks to substitute the whole network. The Bayesian regularized network assigns a probability to the network weights, allowing the network to automatically and optimally penalize excessively complex models. The simulation results show that the BRBP introduces smaller mean absolute percentage error (MAPE) and mean square errors (MSE) than other typical algorithms. Meanwhile, real data analysis results show that the BRBP model has strong generalization capability and parallelism.
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.
Hanna, Andrew I; Mandic, Danilo P
2003-03-01
A complex-valued nonlinear gradient descent (CNGD) learning algorithm for a simple finite impulse response (FIR) nonlinear neural adaptive filter with an adaptive amplitude of the complex activation function is proposed. This way the amplitude of the complex-valued analytic nonlinear activation function of a neuron in the learning algorithm is made gradient adaptive to give the complex-valued adaptive amplitude nonlinear gradient descent (CAANGD). Such an algorithm is beneficial when dealing with signals that have rich dynamical behavior. Simulations on the prediction of complex-valued coloured and nonlinear input signals show the gradient adaptive amplitude, CAANGD, outperforming the standard CNGD algorithm.
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.
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
Adaptive Neural Control of Uncertain MIMO Nonlinear Systems With State and Input Constraints.
Chen, Ziting; Li, Zhijun; Chen, C L Philip
2016-03-17
An adaptive neural control strategy for multiple input multiple output nonlinear systems with various constraints is presented in this paper. To deal with the nonsymmetric input nonlinearity and the constrained states, the proposed adaptive neural control is combined with the backstepping method, radial basis function neural network, barrier Lyapunov function (BLF), and disturbance observer. By ensuring the boundedness of the BLF of the closed-loop system, it is demonstrated that the output tracking is achieved with all states remaining in the constraint sets and the general assumption on nonsingularity of unknown control coefficient matrices has been eliminated. The constructed adaptive neural control has been rigorously proved that it can guarantee the semiglobally uniformly ultimate boundedness of all signals in the closed-loop system. Finally, the simulation studies on a 2-DOF robotic manipulator system indicate that the designed adaptive control is effective.
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
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.
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).
Research of Recurrent Dynamic Neural Networks for Adaptive Control of Complex Dynamic Systems
2010-07-08
Recognition 7.1. General description of experiment 7.2. Gesture recognition system on the base of single recurrent neural network 7.3. Experiment...results for gesture recognition system on the base of single recurrent neural network 7.4. Gesture recognition system on the base of multimodular...of non-linear effects increases an advantage of neurocontrol on linear control methods. 7. Experiments related to Gesture Recognition 7.1. General
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.
Long, Lijun; Zhao, Jun
2015-07-01
This paper investigates the problem of adaptive neural tracking control via output-feedback for a class of switched uncertain nonlinear systems without the measurements of the system states. The unknown control signals are approximated directly by neural networks. A novel adaptive neural control technique for the problem studied is set up by exploiting the average dwell time method and backstepping. A switched filter and different update laws are designed to reduce the conservativeness caused by adoption of a common observer and a common update law for all subsystems. The proposed controllers of subsystems guarantee that all closed-loop signals remain bounded under a class of switching signals with average dwell time, while the output tracking error converges to a small neighborhood of the origin. As an application of the proposed design method, adaptive output feedback neural tracking controllers for a mass-spring-damper system are constructed.
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.
An Adaptive-PSO-Based Self-Organizing RBF Neural Network.
Han, Hong-Gui; Lu, Wei; Hou, Ying; Qiao, Jun-Fei
2016-10-24
In this paper, a self-organizing radial basis function (SORBF) neural network is designed to improve both accuracy and parsimony with the aid of adaptive particle swarm optimization (APSO). In the proposed APSO algorithm, to avoid being trapped into local optimal values, a nonlinear regressive function is developed to adjust the inertia weight. Furthermore, the APSO algorithm can optimize both the network size and the parameters of an RBF neural network simultaneously. As a result, the proposed APSO-SORBF neural network can effectively generate a network model with a compact structure and high accuracy. Moreover, the analysis of convergence is given to guarantee the successful application of the APSO-SORBF neural network. Finally, multiple numerical examples are presented to illustrate the effectiveness of the proposed APSO-SORBF neural network. The results demonstrate that the proposed method is more competitive in solving nonlinear problems than some other existing SORBF neural networks.
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.
Neural network-based adaptive dynamic surface control for permanent magnet synchronous motors.
Yu, Jinpeng; Shi, Peng; Dong, Wenjie; Chen, Bing; Lin, Chong
2015-03-01
This brief considers the problem of neural networks (NNs)-based adaptive dynamic surface control (DSC) for permanent magnet synchronous motors (PMSMs) with parameter uncertainties and load torque disturbance. First, NNs are used to approximate the unknown and nonlinear functions of PMSM drive system and a novel adaptive DSC is constructed to avoid the explosion of complexity in the backstepping design. Next, under the proposed adaptive neural DSC, the number of adaptive parameters required is reduced to only one, and the designed neural controllers structure is much simpler than some existing results in literature, which can guarantee that the tracking error converges to a small neighborhood of the origin. Then, simulations are given to illustrate the effectiveness and potential of the new design technique.
Chen, Mou; Ge, Shuzhi Sam
2013-08-01
In this paper, the direct adaptive neural control is proposed for a class of uncertain nonaffine nonlinear systems with unknown nonsymmetric input saturation. Based on the implicit function theorem and mean value theorem, both state feedback and output feedback direct adaptive controls are developed using neural networks (NNs) and a disturbance observer. A compounded disturbance is defined to take into account of the effect of the unknown external disturbance, the unknown nonsymmetric input saturation, and the approximation error of NN. Then, a disturbance observer is developed to estimate the unknown compounded disturbance, and it is established that the estimate error converges to a compact set if appropriate observer design parameters are chosen. Both state feedback and output feedback direct adaptive controls can guarantee semiglobal uniform boundedness of the closed-loop system signals as rigorously proved by Lyapunov analysis. Numerical simulation results are presented to illustrate the effectiveness of the proposed direct adaptive neural control techniques.
Agha, Salah R; Alnahhal, Mohammed J
2012-11-01
The current study investigates the possibility of obtaining the anthropometric dimensions, critical to school furniture design, without measuring all of them. The study first selects some anthropometric dimensions that are easy to measure. Two methods are then used to check if these easy-to-measure dimensions can predict the dimensions critical to the furniture design. These methods are multiple linear regression and neural networks. Each dimension that is deemed necessary to ergonomically design school furniture is expressed as a function of some other measured anthropometric dimensions. Results show that out of the five dimensions needed for chair design, four can be related to other dimensions that can be measured while children are standing. Therefore, the method suggested here would definitely save time and effort and avoid the difficulty of dealing with students while measuring these dimensions. In general, it was found that neural networks perform better than multiple linear regression in the current study.
A linear model for characterization of synchronization frequencies of neural networks.
Lv, Peili; Hu, Xintao; Lv, Jinglei; Han, Junwei; Guo, Lei; Liu, Tianming
2014-02-01
The synchronization frequency of neural networks and its dynamics have important roles in deciphering the working mechanisms of the brain. It has been widely recognized that the properties of functional network synchronization and its dynamics are jointly determined by network topology, network connection strength, i.e., the connection strength of different edges in the network, and external input signals, among other factors. However, mathematical and computational characterization of the relationships between network synchronization frequency and these three important factors are still lacking. This paper presents a novel computational simulation framework to quantitatively characterize the relationships between neural network synchronization frequency and network attributes and input signals. Specifically, we constructed a series of neural networks including simulated small-world networks, real functional working memory network derived from functional magnetic resonance imaging, and real large-scale structural brain networks derived from diffusion tensor imaging, and performed synchronization simulations on these networks via the Izhikevich neuron spiking model. Our experiments demonstrate that both of the network synchronization strength and synchronization frequency change according to the combination of input signal frequency and network self-synchronization frequency. In particular, our extensive experiments show that the network synchronization frequency can be represented via a linear combination of the network self-synchronization frequency and the input signal frequency. This finding could be attributed to an intrinsically-preserved principle in different types of neural systems, offering novel insights into the working mechanism of neural systems.
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)
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.
Herrmann, Guido; Turner, Matthew C; Postlethwaite, Ian
2007-03-01
This paper presents a conditioning scheme for a linear control system which is enhanced by a neural network (NN) controller and subjected to a control signal amplitude limit. The NN controller improves the performance of the linear control system by directly estimating an actuator-matched, unmodeled, nonlinear disturbance, in closed-loop, and compensating for it. As disturbances are generally known to be bounded, the nominal NN-control element is modified to keep its output below the disturbance bound. The linear control element is conditioned by an antiwindup (AW) compensator which ensures performance close to the nominal controller and swift recovery from saturation. For this, the AW compensator proposed is of low order, designed using convex linear matrix inequalities (LMIs) optimization.
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.
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.
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.
Wu, Huai-Ning; Li, Han-Xiong
2009-10-01
In this paper, an adaptive neural network (NN) control with a guaranteed L(infinity)-gain performance is proposed for a class of parabolic partial differential equation (PDE) systems with unknown nonlinearities and persistent bounded disturbances. Initially, Galerkin method is applied to the PDE system to derive a low-order ordinary differential equation (ODE) system that accurately describes the dynamics of the dominant (slow) modes of the PDE system. Subsequently, based on the low-order slow model and the Lyapunov technique, an adaptive modal feedback controller is developed such that the closed-loop slow system is semiglobally input-to-state practically stable (ISpS) with an L(infinity)-gain performance. In the proposed control scheme, a radial basis function (RBF) NN is employed to approximate the unknown term in the derivative of the Lyapunov function due to the unknown system nonlinearities. The outcome of the adaptive L(infinity)-gain control problem is formulated as a linear matrix inequality (LMI) problem. Moreover, by using the existing LMI optimization technique, a suboptimal controller is obtained in the sense of minimizing an upper bound of the L(infinity)-gain, while control constraints are respected. Furthermore, it is shown that the proposed controller can ensure the semiglobal input-to-state practical stability and L(infinity)-gain performance of the closed-loop PDE system. Finally, by applying the developed design method to the temperature profile control of a catalytic rod, the achieved simulation results show the effectiveness of the proposed controller.
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.
Analysis and Synthesis of Adaptive Neural Elements and Assembles
1993-09-30
responses. it was necessary to include elements representing recently described excitatory interneurons that elicit slow, decreased-conductance EPSPs ...incorporated into a small neural network and simulations examined the functions of interneurons and the consequences of plasticity at multiple sites. (4...complete model of the circuit underlying this reflex and simulations examined the contributions of additional interneurons and loci for plasticity to
Xia, Youshen; Sun, Changyin; Zheng, Wei Xing
2012-05-01
There is growing interest in solving linear L1 estimation problems for sparsity of the solution and robustness against non-Gaussian noise. This paper proposes a discrete-time neural network which can calculate large linear L1 estimation problems fast. The proposed neural network has a fixed computational step length and is proved to be globally convergent to an optimal solution. Then, the proposed neural network is efficiently applied to image restoration. Numerical results show that the proposed neural network is not only efficient in solving degenerate problems resulting from the nonunique solutions of the linear L1 estimation problems but also needs much less computational time than the related algorithms in solving both linear L1 estimation and image restoration problems.
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
Varying Timescales of Stimulus Integration Unite Neural Adaptation and Prototype Formation.
Mattar, Marcelo G; Kahn, David A; Thompson-Schill, Sharon L; Aguirre, Geoffrey K
2016-07-11
Human visual perception is both stable and adaptive. Perception of complex objects, such as faces, is shaped by the long-term average of experience as well as immediate, comparative context. Measurements of brain activity have demonstrated corresponding neural mechanisms, including norm-based responses reflective of stored prototype representations, and adaptation induced by the immediately preceding stimulus. Here, we consider the possibility that these apparently separate phenomena can arise from a single mechanism of sensory integration operating over varying timescales. We used fMRI to measure neural responses from the fusiform gyrus while subjects observed a rapid stream of face stimuli. Neural activity at this cortical site was best explained by the integration of sensory experience over multiple sequential stimuli, following a decaying-exponential weighting function. Although this neural activity could be mistaken for immediate neural adaptation or long-term, norm-based responses, it in fact reflected a timescale of integration intermediate to both. We then examined the timescale of sensory integration across the cortex. We found a gradient that ranged from rapid sensory integration in early visual areas, to long-term, stable representations in higher-level, ventral-temporal cortex. These findings were replicated with a new set of face stimuli and subjects. Our results suggest that a cascade of visual areas integrate sensory experience, transforming highly adaptable responses at early stages to stable representations at higher levels.
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.
Studying the neural bases of prism adaptation using fMRI: A technical and design challenge.
Bultitude, Janet H; Farnè, Alessandro; Salemme, Romeo; Ibarrola, Danielle; Urquizar, Christian; O'Shea, Jacinta; Luauté, Jacques
2016-12-30
Prism adaptation induces rapid recalibration of visuomotor coordination. The neural mechanisms of prism adaptation have come under scrutiny since the observations that the technique can alleviate hemispatial neglect following stroke, and can alter spatial cognition in healthy controls. Relative to non-imaging behavioral studies, fMRI investigations of prism adaptation face several challenges arising from the confined physical environment of the scanner and the supine position of the participants. Any researcher who wishes to administer prism adaptation in an fMRI environment must adjust their procedures enough to enable the experiment to be performed, but not so much that the behavioral task departs too much from true prism adaptation. Furthermore, the specific temporal dynamics of behavioral components of prism adaptation present additional challenges for measuring their neural correlates. We developed a system for measuring the key features of prism adaptation behavior within an fMRI environment. To validate our configuration, we present behavioral (pointing) and head movement data from 11 right-hemisphere lesioned patients and 17 older controls who underwent sham and real prism adaptation in an MRI scanner. Most participants could adapt to prismatic displacement with minimal head movements, and the procedure was well tolerated. We propose recommendations for fMRI studies of prism adaptation based on the design-specific constraints and our results.
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.
Muscular, skeletal, and neural adaptations following spinal cord injury.
Shields, Richard K
2002-02-01
Spinal cord injury is associated with adaptations to the muscular, skeletal, and spinal systems. Experimental data are lacking regarding the extent to which rehabilitative methods may influence these adaptations. An understanding of the plasticity of the muscular, skeletal, and spinal systems after paralysis may be important as new rehabilitative technologies emerge in the 21st century. Moreover, individuals injured today may become poor candidates for future scientific advancements (cure) if their neuromusculoskeletal systems are irreversibly impaired. The primary purpose of this paper is to explore the physiological properties of skeletal muscle as a result of spinal cord injury; secondarily, to consider associated changes at the skeletal and spinal levels. Muscular adaptations include a transformation to faster myosin, increased contractile speeds, shift to the right on the torque-frequency curve, increased fatigue, and enhanced doublet potentiation. These muscular adaptations may be prevented in individuals with acute paralysis and partially reversed in individuals with chronic paralysis. Moreover, the muscular changes may be coordinated with motor unit and spinal circuitry adaptations. Concurrently, skeletal adaptations, as measured by bone mineral density, show extensive loss within the first six months after paralysis. The underlying science governing neuromusculoskeletal adaptations after paralysis will help guide professionals as new rehabilitation strategies evolve in the future.
Non-linear state transitions in neural systems: from ion to networks
NASA Astrophysics Data System (ADS)
Liljenström, Hans; Braun, Hans; Århem, Peter
2001-03-01
The activity of neural systems often seems to depend on non-linear threshold effects, where microscopic fluctuations may cause rapid and large effects at a macroscopic level. Single ion channels are found to be capable of eliciting action potentials in small hippocampal interneurons. Computer simulations show that spontaneous neuronal activity can induce global oscillations in networks of neurons. For a small change in some parameter values, the global activity instead becomes chaotic-like. We use experimental as well as computational methods to investigate mechanisms by which neural systems can amplify weak signals and control the system at a larger scale. We also investigate if there are non-random processes in ion channel kinetics and use topological methods for the analysis, also of computer simulations.
[Evaluation of an adaptive filter for CT under low-CNR condition: comparison with linear filter].
Mori, Issei; Uchida, Miho; Sato, Ami; Sato, Shingo; Tamura, Hajime; Takai, Yoshihiro; Ishibashi, Tadashi; Saito, Haruo; Hosokai, Yoshiyuki; Ogura, Takahide; Chida, Koichi; Machida, Yoshio
2009-01-20
The use of an adaptive filter for CT images is becoming a common procedure and is said to reduce image noise while preserving sharpness and helping to reduce the required X-ray dose. Although many reports support this view, the validity of such evaluations is arguable. When the linearity of a system is in question, physical performance indexes should be measured under conditions similar to those of clinical use. Evaluations of diagnosis using clinical images may be fallible because the non-filtered image used as the reference might not have been optimally reconstructed. We have chosen simple, but commonly used, adaptive filters for our evaluation. As a reference for comparing performance, we designed linear filters that best approximate the noise characteristics of the adaptive filters. MTF is measured through observation of the edge-spread function. Clinical abdominal images are used to compare the performance of adaptive filters and linear filters. We conclude that the performance of the type of adaptive filter we have chosen is virtually the same as that of the linear filter, as long as the image quality of soft tissues is our interest. Both the noise SD and MTF are virtually the same if the contrast of the object is not substantially higher than 150 HU. Images of soft tissues obtained with the use of adaptive filters are also virtually the same as those obtained by linear filters. The edge-preservation characteristic of this adaptive filter is not observable for soft tissues.
Analysis and Synthesis of Adaptive Neural Elements and Assemblies
1989-12-19
learning into small neural networks, which include facilitatory and inhibitory interneurons , and we demonstrated the ability of these networks to...features of classical conditioning,. 3) to analyze the properties of facilitatory and inhibitory interneurons that might contribute to associative...individual sensory neurons represents separate pathways for conditioned stimuli (CS1 and CS2). The amplitude of the EPSPs at the sensory-to-motor synapses
Multi-Agent Reinforcement Learning and Adaptive Neural Networks.
2007-11-02
learning method. The objective was to study the utility of reinforcement learning as an approach to complex decentralized control problems. The major...accomplishment was a detailed study of multi-agent reinforcement learning applied to a large-scale decentralized stochastic control problem. This study...included a very successful demonstration that a multi-agent reinforcement learning system using neural networks could learn high-performance
A Self-Adaptive Projection and Contraction Method for Linear Complementarity Problems
Liao Lizhi Wang Shengli
2003-10-15
In this paper we develop a self-adaptive projection and contraction method for the linear complementarity problem (LCP). This method improves the practical performance of the modified projection and contraction method by adopting a self-adaptive technique. The global convergence of our new method is proved under mild assumptions. Our numerical tests clearly demonstrate the necessity and effectiveness of our proposed method.
Encoding binary neural codes in networks of threshold-linear neurons.
Curto, Carina; Degeratu, Anda; Itskov, Vladimir
2013-11-01
Networks of neurons in the brain encode preferred patterns of neural activity via their synaptic connections. Despite receiving considerable attention, the precise relationship between network connectivity and encoded patterns is still poorly understood. Here we consider this problem for networks of threshold-linear neurons whose computational function is to learn and store a set of binary patterns (e.g., a neural code) as "permitted sets" of the network. We introduce a simple encoding rule that selectively turns "on" synapses between neurons that coappear in one or more patterns. The rule uses synapses that are binary, in the sense of having only two states ("on" or "off"), but also heterogeneous, with weights drawn from an underlying synaptic strength matrix S. Our main results precisely describe the stored patterns that result from the encoding rule, including unintended "spurious" states, and give an explicit characterization of the dependence on S. In particular, we find that binary patterns are successfully stored in these networks when the excitatory connections between neurons are geometrically balanced--i.e., they satisfy a set of geometric constraints. Furthermore, we find that certain types of neural codes are natural in the context of these networks, meaning that the full code can be accurately learned from a highly undersampled set of patterns. Interestingly, many commonly observed neural codes in cortical and hippocampal areas are natural in this sense. As an application, we construct networks that encode hippocampal place field codes nearly exactly, following presentation of only a small fraction of patterns. To obtain our results, we prove new theorems using classical ideas from convex and distance geometry, such as Cayley-Menger determinants, revealing a novel connection between these areas of mathematics and coding properties of neural networks.
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 network L1 adaptive control of MIMO systems with nonlinear uncertainty.
Zhen, Hong-tao; Qi, Xiao-hui; Li, Jie; Tian, Qing-min
2014-01-01
An indirect adaptive controller is developed for a class of multiple-input multiple-output (MIMO) nonlinear systems with unknown uncertainties. This control system is comprised of an L 1 adaptive controller and an auxiliary neural network (NN) compensation controller. The L 1 adaptive controller has guaranteed transient response in addition to stable tracking. In this architecture, a low-pass filter is adopted to guarantee fast adaptive rate without generating high-frequency oscillations in control signals. The auxiliary compensation controller is designed to approximate the unknown nonlinear functions by MIMO RBF neural networks to suppress the influence of uncertainties. NN weights are tuned on-line with no prior training and the project operator ensures the weights bounded. The global stability of the closed-system is derived based on the Lyapunov function. Numerical simulations of an MIMO system coupled with nonlinear uncertainties are used to illustrate the practical potential of our theoretical results.
Backstepping Design of Adaptive Neural Fault-Tolerant Control for MIMO Nonlinear Systems.
Gao, Hui; Song, Yongduan; Wen, Changyun
2016-08-24
In this paper, an adaptive controller is developed for a class of multi-input and multioutput nonlinear systems with neural networks (NNs) used as a modeling tool. It is shown that all the signals in the closed-loop system with the proposed adaptive neural controller are globally uniformly bounded for any external input in L[₀,∞]. In our control design, the upper bound of the NN modeling error and the gains of external disturbance are characterized by unknown upper bounds, which is more rational to establish the stability in the adaptive NN control. Filter-based modification terms are used in the update laws of unknown parameters to improve the transient performance. Finally, fault-tolerant control is developed to accommodate actuator failure. An illustrative example applying the adaptive controller to control a rigid robot arm shows the validation of the proposed controller.
Neural Network L1 Adaptive Control of MIMO Systems with Nonlinear Uncertainty
Zhen, Hong-tao; Qi, Xiao-hui; Li, Jie; Tian, Qing-min
2014-01-01
An indirect adaptive controller is developed for a class of multiple-input multiple-output (MIMO) nonlinear systems with unknown uncertainties. This control system is comprised of an L1 adaptive controller and an auxiliary neural network (NN) compensation controller. The L1 adaptive controller has guaranteed transient response in addition to stable tracking. In this architecture, a low-pass filter is adopted to guarantee fast adaptive rate without generating high-frequency oscillations in control signals. The auxiliary compensation controller is designed to approximate the unknown nonlinear functions by MIMO RBF neural networks to suppress the influence of uncertainties. NN weights are tuned on-line with no prior training and the project operator ensures the weights bounded. The global stability of the closed-system is derived based on the Lyapunov function. Numerical simulations of an MIMO system coupled with nonlinear uncertainties are used to illustrate the practical potential of our theoretical results. PMID:25147871
Model reference adaptive control for linear time varying and nonlinear systems
NASA Technical Reports Server (NTRS)
Abida, L.; Kaufman, H.
1982-01-01
Model reference adaptive control is applied to linear time varying systems and to nonlinear systems amenable to virtual linearization. Asymptotic stability is guaranteed even if the perfect model following conditions do not hold, provided that some sufficient conditions are satisfied. Simulations show the scheme to be capable of effectively controlling certain nonlinear systems.
NASA Technical Reports Server (NTRS)
Bakhtiari-Nejad, Maryam; Nguyen, Nhan T.; Krishnakumar, Kalmanje Srinvas
2009-01-01
This paper presents the application of Bounded Linear Stability Analysis (BLSA) method for metrics driven adaptive control. The bounded linear stability analysis method is used for analyzing stability of adaptive control models, without linearizing the adaptive laws. Metrics-driven adaptive control introduces a notion that adaptation should be driven by some stability metrics to achieve robustness. By the application of bounded linear stability analysis method the adaptive gain is adjusted during the adaptation in order to meet certain phase margin requirements. Analysis of metrics-driven adaptive control is evaluated for a linear damaged twin-engine generic transport model of aircraft. The analysis shows that the system with the adjusted adaptive gain becomes more robust to unmodeled dynamics or time delay.
Hu, Jin; Zeng, Chunna
2017-02-01
The complex-valued Cohen-Grossberg neural network is a special kind of complex-valued neural network. In this paper, the synchronization problem of a class of complex-valued Cohen-Grossberg neural networks with known and unknown parameters is investigated. By using Lyapunov functionals and the adaptive control method based on parameter identification, some adaptive feedback schemes are proposed to achieve synchronization exponentially between the drive and response systems. The results obtained in this paper have extended and improved some previous works on adaptive synchronization of Cohen-Grossberg neural networks. Finally, two numerical examples are given to demonstrate the effectiveness of the theoretical results.
Parameter adaptation in a simplified pulse-coupled neural network
NASA Astrophysics Data System (ADS)
Szekely, Geza; Lindblad, Thomas
1999-03-01
In a general purpose pulse coupled neural network (PCNN) algorithm the following parameters are used: 2 weight matrices, 3 time constants, 3 normalization factors and 2 further parameters. In a given application, one has to determine the near optimal parameter set to achieve the desired goal. Here a simplified PCNN is described which contains a parameter fitting part, in the least squares sense. Given input and a desired output image, the program is able to determine the optimal value of a selected PCNN parameter. This method can be extended to more general PCNN algorithms, because partial derivatives are not required for the fitting. Only the sum of squares of the differences is used.
Adaptive neural network consensus based control of robot formations
NASA Astrophysics Data System (ADS)
Guzey, H. M.; Sarangapani, Jagannathan
2013-05-01
In this paper, adaptive consensus based formation control scheme is derived for mobile robots in a pre-defined formation when full dynamics of the robots which include inertia, Corolis, and friction vector are considered. It is shown that dynamic uncertainties of robots can make overall formation unstable when traditional consensus scheme is utilized. In order to estimate the affine nonlinear robot dynamics, a NN based adaptive scheme is utilized. In addition to this adaptive feedback control input, an additional control input is introduced based on the consensus approach to make the robots keep their desired formation. Subsequently, the outer consensus loop is redesigned for reduced communication. Lyapunov theory is used to show the stability of overall system. Simulation results are included at the end.
An algorithmic approach to adaptive state filtering using recurrent neural networks.
Parlos, A G; Menon, S K; Atiya, A
2001-01-01
Practical algorithms are presented for adaptive state filtering in nonlinear dynamic systems when the state equations are unknown. The state equations are constructively approximated using neural networks. The algorithms presented are based on the two-step prediction-update approach of the Kalman filter. The proposed algorithms make minimal assumptions regarding the underlying nonlinear dynamics and their noise statistics. Non-adaptive and adaptive state filtering algorithms are presented with both off-line and online learning stages. The algorithms are implemented using feedforward and recurrent neural network and comparisons are presented. Furthermore, extended Kalman filters (EKFs) are developed and compared to the filter algorithms proposed. For one of the case studies, the EKF converges but results in higher state estimation errors that the equivalent neural filters. For another, more complex case study with unknown system dynamics and noise statistics, the developed EKFs do not converge. The off-line trained neural state filters converge quite rapidly and exhibit acceptable performance. Online training further enhances the estimation accuracy of the developed adaptive filters, effectively decoupling the eventual filter accuracy from the accuracy of the process model.
NASA Technical Reports Server (NTRS)
Liu, Hua-Kuang; Diep, J.; Huang, K.
1991-01-01
Viewgraphs on multi-channel holographic bifurcative neural network system for real-time adaptive Earth Observing System (EOS) data analysis are presented. The objective is to research and develop an optical bifurcating neuromorphic pattern recognition system for making optical data array comparisons and to evaluate the use of the system for EOS data classification, reduction, analysis, and other applications.
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.
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.
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.
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 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
Sriraam, N; Eswaran, C
2008-01-01
This paper presents a comparison of the performances of neural network and linear predictors for near-lossless compression of EEG signals. Three neural network predictors, namely, single-layer perceptron (SLP), multilayer perceptron (MLP), and Elman network (EN), and two linear predictors, namely, autoregressive model (AR) and finite-impulse response filter (FIR) are used. For all the predictors, uniform quantization is applied on the residue signals obtained as the difference between the original and the predicted values. The maximum allowable reconstruction error delta is varied to determine the theoretical bound delta 0 for near-lossless compression and the corresponding bit rate rp. It is shown that among all the predictors, the SLP yields the best results in achieving the lowest values for delta 0 and rp. The corresponding values of the fidelity parameters, namely, percent of root-mean-square difference, peak SNR and cross correlation are also determined. A compression efficiency of 82.8% is achieved using the SLP with a near-lossless bound delta 0 = 3, with the diagnostic quality of the reconstructed EEG signal preserved. Thus, the proposed near-lossless scheme facilitates transmission of real time as well as offline EEG signals over network to remote interpretation center economically with less bandwidth utilization compared to other known lossless and near-lossless schemes.
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.
Fu, J C; Chen, C C; Chai, J W; Wong, S T C; Li, I C
2010-06-01
We propose an automatic hybrid image segmentation model that integrates the statistical expectation maximization (EM) model and the spatial pulse coupled neural network (PCNN) for brain magnetic resonance imaging (MRI) segmentation. In addition, an adaptive mechanism is developed to fine tune the PCNN parameters. The EM model serves two functions: evaluation of the PCNN image segmentation and adaptive adjustment of the PCNN parameters for optimal segmentation. To evaluate the performance of the adaptive EM-PCNN, we use it to segment MR brain image into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). The performance of the adaptive EM-PCNN is compared with that of the non-adaptive EM-PCNN, EM, and Bias Corrected Fuzzy C-Means (BCFCM) algorithms. The result is four sets of boundaries for the GM and the brain parenchyma (GM+WM), the two regions of most interest in medical research and clinical applications. Each set of boundaries is compared with the golden standard to evaluate the segmentation performance. The adaptive EM-PCNN significantly outperforms the non-adaptive EM-PCNN, EM, and BCFCM algorithms in gray mater segmentation. In brain parenchyma segmentation, the adaptive EM-PCNN significantly outperforms the BCFCM only. However, the adaptive EM-PCNN is better than the non-adaptive EM-PCNN and EM on average. We conclude that of the three approaches, the adaptive EM-PCNN yields the best results for gray matter and brain parenchyma segmentation.
Sympathetic neural adaptations to exercise training in humans.
Carter, Jason R; Ray, Chester A
2015-03-01
Physiological adaptations to exercise training are well recognized and contribute importantly to health and fitness. Cardiovascular diseases, such as hypertension and heart failure, are often associated with elevated activity of the sympathetic nervous system. This review aims to provide comprehensive overview on the role of exercise training on muscle sympathetic nerve activity (MSNA) regulation in humans, with a focus on recent advances in at-risk populations. Collectively, these studies converge to demonstrate that aerobic exercise training reduces resting MSNA in populations at heightened cardiovascular risk, but do not appear to alter resting MSNA in healthy adults. We provide directions for future research which might address gaps in our knowledge regarding sympathoneural adaptations to exercise training.
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.
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.
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.
A cerebellar neural network model for adaptative control of saccades implemented with MATLAB.
Rodriguez Campos, Francisco A; Enderle, John
2003-01-01
This paper describes the implementation of a neural network for the adaptative control of the saccadic system. The model shows the cerebellum plays an important role in the adaptive control of the saccadic gain. Using only eye position input through the granule cells, the cerebellum projects this signal to the other cerebellar structures and then to motor neurons responsible for the saccade. The generation of an adjustment signal occurs in the inferior olive as a result of the error sensory signal created by the open loop saccade system from propioceptive position inputs from the last eye movement generated by the network until the movement towards the target is completed. In addition, a memory component has been defined in the error system to achieve the adaptation. This neural network involves only the horizontal saccade component modeled with Matrix Laboratory language (MATLAB), in conjunction with the Simulink tool.
Neural Network Based Adaptive Flow Control for Maneuvering Vehicles
2005-09-01
effective nonlinear adaptive control of the aerodynamic flow about a dynamic body using a distributed array of synthetic jets for actuation. Design of a wind...possible coupling effects between actuation, the dynamics of flow field, and the rigid body dynamics of the model. The outcomes of simulation studies are...presented. The parameters were selected to have an adverse effect on the closed loop response, therefore representing a hypothetical worst-case
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.
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.
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.
He, Xiaoxu; Zhang, Heye; Landis, Mark; Sharma, Manas; Warrington, James; Li, Shuo
2017-02-01
As a common disease in the elderly, neural foramina stenosis (NFS) brings a significantly negative impact on the quality of life due to its symptoms including pain, disability, fall risk and depression. Accurate boundary delineation is essential to the clinical diagnosis and treatment of NFS. However, existing clinical routine is extremely tedious and inefficient due to the requirement of physicians' intensively manual delineation. Automated delineation is highly needed but faces big challenges from the complexity and variability in neural foramina images. In this paper, we propose a pure image-driven unsupervised boundary delineation framework for the automated neural foramina boundary delineation. This framework is based on a novel multi-feature and adaptive spectral segmentation (MFASS) algorithm. MFASS firstly utilizes the combination of region and edge features to generate reliable spectral features with a good separation between neural foramina and its surroundings, then estimates an optimal separation threshold for each individual image to separate neural foramina from its surroundings. This self-adjusted optimal separation threshold, estimated from spectral features, successfully overcome the diverse appearance and shape variations. With the robustness from the multi-feature fusion and the flexibility from the adaptively optimal separation threshold estimation, the proposed framework, based on MFASS, provides an automated and accurate boundary delineation. Validation was performed in 280 neural foramina MR images from 56 clinical subjects. Our method was benchmarked with manual boundary obtained by experienced physicians. Results demonstrate that the proposed method enjoys a high and stable consistency with experienced physicians (Dice: 90.58% ± 2.79%; SMAD: 0.5657 ± 0.1544 mm). Therefore, the proposed framework enables an efficient and accurate clinical tool in the diagnosis of neural foramina stenosis.
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.
Combining decoder design and neural adaptation in brain-machine interfaces.
Shenoy, Krishna V; Carmena, Jose M
2014-11-19
Brain-machine interfaces (BMIs) aim to help people with paralysis by decoding movement-related neural signals into control signals for guiding computer cursors, prosthetic arms, and other assistive devices. Despite compelling laboratory experiments and ongoing FDA pilot clinical trials, system performance, robustness, and generalization remain challenges. We provide a perspective on how two complementary lines of investigation, that have focused on decoder design and neural adaptation largely separately, could be brought together to advance BMIs. This BMI paradigm should also yield new scientific insights into the function and dysfunction of the nervous system.
Abbaspour, Alireza; Aboutalebi, Payam; Yen, Kang K; Sargolzaei, Arman
2017-03-01
A new online detection strategy is developed to detect faults in sensors and actuators of unmanned aerial vehicle (UAV) systems. In this design, the weighting parameters of the Neural Network (NN) are updated by using the Extended Kalman Filter (EKF). Online adaptation of these weighting parameters helps to detect abrupt, intermittent, and incipient faults accurately. We apply the proposed fault detection system to a nonlinear dynamic model of the WVU YF-22 unmanned aircraft for its evaluation. The simulation results show that the new method has better performance in comparison with conventional recurrent neural network-based fault detection strategies.
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.
NASA Astrophysics Data System (ADS)
Schreiter, Juerg; Ramacher, Ulrich; Heittmann, Arne; Matolin, Daniel; Schuffny, Rene
2004-05-01
We present a cellular pulse coupled neural network with adaptive weights and its analog VLSI implementation. The neural network operates on a scalar image feature, such as grey scale or the output of a spatial filter. It detects segments and marks them with synchronous pulses of the corresponding neurons. The network consists of integrate-and-fire neurons, which are coupled to their nearest neighbors via adaptive synaptic weights. Adaptation follows either one of two empirical rules. Both rules lead to spike grouping in wave like patterns. This synchronous activity binds groups of neurons and labels the corresponding image segments. Applications of the network also include feature preserving noise removal, image smoothing, and detection of bright and dark spots. The adaptation rules are insensitive for parameter deviations, mismatch and non-ideal approximation of the implied functions. That makes an analog VLSI implementation feasible. Simulations showed no significant differences in the synchronization properties between networks using the ideal adaptation rules and networks resembling implementation properties such as randomly distributed parameters and roughly implemented adaptation functions. A prototype is currently being designed and fabricated using an Infineon 130nm technology. It comprises a 128 × 128 neuron array, analog image memory, and an address event representation pulse output.
Adaptive Neural Network Algorithm for Power Control in Nuclear Power Plants
NASA Astrophysics Data System (ADS)
Masri Husam Fayiz, Al
2017-01-01
The aim of this paper is to design, test and evaluate a prototype of an adaptive neural network algorithm for the power controlling system of a nuclear power plant. The task of power control in nuclear reactors is one of the fundamental tasks in this field. Therefore, researches are constantly conducted to ameliorate the power reactor control process. Currently, in the Department of Automation in the National Research Nuclear University (NRNU) MEPhI, numerous studies are utilizing various methodologies of artificial intelligence (expert systems, neural networks, fuzzy systems and genetic algorithms) to enhance the performance, safety, efficiency and reliability of nuclear power plants. In particular, a study of an adaptive artificial intelligent power regulator in the control systems of nuclear power reactors is being undertaken to enhance performance and to minimize the output error of the Automatic Power Controller (APC) on the grounds of a multifunctional computer analyzer (simulator) of the Water-Water Energetic Reactor known as Vodo-Vodyanoi Energetichesky Reaktor (VVER) in Russian. In this paper, a block diagram of an adaptive reactor power controller was built on the basis of an intelligent control algorithm. When implementing intelligent neural network principles, it is possible to improve the quality and dynamic of any control system in accordance with the principles of adaptive control. It is common knowledge that an adaptive control system permits adjusting the controller’s parameters according to the transitions in the characteristics of the control object or external disturbances. In this project, it is demonstrated that the propitious options for an automatic power controller in nuclear power plants is a control system constructed on intelligent neural network algorithms.
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.
Mayorga, René V; Arriaga, Mariano
2007-10-01
In this article, a novel technique for non-linear global optimization is presented. The main goal is to find the optimal global solution of non-linear problems avoiding sub-optimal local solutions or inflection points. The proposed technique is based on a two steps concept: properly keep decreasing the value of the objective function, and calculating the corresponding independent variables by approximating its inverse function. The decreasing process can continue even after reaching local minima and, in general, the algorithm stops when converging to solutions near the global minimum. The implementation of the proposed technique by conventional numerical methods may require a considerable computational effort on the approximation of the inverse function. Thus, here a novel Artificial Neural Network (ANN) approach is implemented to reduce the computational requirements of the proposed optimization technique. This approach is successfully tested on some highly non-linear functions possessing several local minima. The results obtained demonstrate that the proposed approach compares favorably over some current conventional numerical (Matlab functions) methods, and other non-conventional (Evolutionary Algorithms, Simulated Annealing) optimization methods.
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)
Nguyen, Nhan
2013-01-01
This paper presents the optimal control modification for linear uncertain plants. The Lyapunov analysis shows that the modification parameter has a limiting value depending on the nature of the uncertainty. The optimal control modification exhibits a linear asymptotic property that enables it to be analyzed in a linear time invariant framework for linear uncertain plants. The linear asymptotic property shows that the closed-loop plants in the limit possess a scaled input-output mapping. Using this property, we can derive an analytical closed-loop transfer function in the limit as the adaptive gain tends to infinity. The paper revisits the Rohrs counterexample problem that illustrates the nature of non-robustness of model-reference adaptive control in the presence of unmodeled dynamics. An analytical approach is developed to compute exactly the modification parameter for the optimal control modification that stabilizes the plant in the Rohrs counterexample. The linear asymptotic property is also used to address output feedback adaptive control for non-minimum phase plants with a relative degree 1.
An adaptive observer for single-input single-output linear systems
NASA Technical Reports Server (NTRS)
Carroll, R. L.; Lindorff, D. P.
1972-01-01
It is shown that the full order adaptive observer for single input, single output, observable, continuous, stable, linear differential systems in the absence of a deterministic or random disturbance vector guarantees the vanishing of observation error, regardless of the size of the constant or slowly varying parameter ignorance. The observer parameters are directly changed in a Liapunov adaptive way so as to eventually yield the unknown full order Luenberger observer. The observer poles throughout may be placed freely in the stable region and no derivatives are required in the adaptive law.
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.
Neural self-tuning adaptive control of non-minimum phase system
NASA Technical Reports Server (NTRS)
Ho, Long T.; Bialasiewicz, Jan T.; Ho, Hai T.
1993-01-01
The motivation of this research came about when a neural network direct adaptive control scheme was applied to control the tip position of a flexible robotic arm. Satisfactory control performance was not attainable due to the inherent non-minimum phase characteristics of the flexible robotic arm tip. Most of the existing neural network control algorithms are based on the direct method and exhibit very high sensitivity, if not unstable, closed-loop behavior. Therefore, a neural self-tuning control (NSTC) algorithm is developed and applied to this problem and showed promising results. Simulation results of the NSTC scheme and the conventional self-tuning (STR) control scheme are used to examine performance factors such as control tracking mean square error, estimation mean square error, transient response, and steady state response.
Linear and Nonlinear Electrical Models of Neurons for Hopfield Neural Network
NASA Astrophysics Data System (ADS)
Sarwar, Farah; Iqbal, Shaukat; Hussain, Muhammad Waqar
2016-11-01
A novel electrical model of neuron is proposed in this presentation. The suggested neural network model has linear/nonlinear input-output characteristics. This new deterministic model has joint biological properties in excellent agreement with the earlier deterministic neuron model of Hopfield and Tank and to the stochastic neuron model of McCulloch and Pitts. It is an accurate portrayal of differential equation presented by Hopfield and Tank to mimic neurons. Operational amplifiers, resistances, capacitor, and diodes are used to design this system. The presented biological model of neurons remains to be advantageous for simulations. Impulse response is studied and conferred to certify the stability and strength of this innovative model. A simple illustration is mapped to demonstrate the exactness of the intended system. Precisely mapped illustration exhibits 100 % accurate results.
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.
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.
Study on application of adaptive fuzzy control and neural network in the automatic leveling system
NASA Astrophysics Data System (ADS)
Xu, Xiping; Zhao, Zizhao; Lan, Weiyong; Sha, Lei; Qian, Cheng
2015-04-01
This paper discusses the adaptive fuzzy control and neural network BP algorithm in large flat automatic leveling control system application. The purpose is to develop a measurement system with a flat quick leveling, Make the installation on the leveling system of measurement with tablet, to be able to achieve a level in precision measurement work quickly, improve the efficiency of the precision measurement. This paper focuses on the automatic leveling system analysis based on fuzzy controller, Use of the method of combining fuzzy controller and BP neural network, using BP algorithm improve the experience rules .Construct an adaptive fuzzy control system. Meanwhile the learning rate of the BP algorithm has also been run-rate adjusted to accelerate convergence. The simulation results show that the proposed control method can effectively improve the leveling precision of automatic leveling system and shorten the time of leveling.
Otten, Marte; Banaji, Mahzarin R
2012-01-01
A number of recent behavioral studies have shown that emotional expressions are differently perceived depending on the race of a face, and that perception of race cues is influenced by emotional expressions. However, neural processes related to the perception of invariant cues that indicate the identity of a face (such as race) are often described to proceed independently of processes related to the perception of cues that can vary over time (such as emotion). Using a visual face adaptation paradigm, we tested whether these behavioral interactions between emotion and race also reflect interdependent neural representation of emotion and race. We compared visual emotion aftereffects when the adapting face and ambiguous test face differed in race or not. Emotion aftereffects were much smaller in different race (DR) trials than same race (SR) trials, indicating that the neural representation of a facial expression is significantly different depending on whether the emotional face is black or white. It thus seems that invariable cues such as race interact with variable face cues such as emotion not just at a response level, but also at the level of perception and neural representation.
Specific neural correlates of successful learning and adaptation during social exchanges.
Smith-Collins, Adam P R; Fiorentini, Chiara; Kessler, Esther; Boyd, Harriet; Roberts, Fiona; Skuse, David H
2013-12-01
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.
Wang, Z P; Ge, S S; Lee, T H
2004-10-01
In this paper, robust adaptive neural network (NN) control is presented to solve the control problem of nonholonomic systems in chained form with unknown virtual control coefficients and strong drift nonlinearities. The robust adaptive NN control laws are developed using state scaling and backstepping. Uniform ultimate boundedness of all the signals in the closed-loop are guaranteed, and the system states are proven to converge to a small neighborhood of zero. The control performance of the closed-loop system is guaranteed by appropriately choosing the design parameters. The proposed adaptive NN control is free of control singularity problem. An adaptive control based switching strategy is used to overcome the uncontrollability problem associated with x0 (t0) = 0. The simulation results demonstrate the effectiveness of the proposed controllers.
Yoo, Sung Jin; Park, Jin Bae; Choi, Yoon Ho
2006-12-01
A new method for the robust control of flexible-joint (FJ) robots with model uncertainties in both robot dynamics and actuator dynamics is proposed. The proposed control system is a combination of the adaptive dynamic surface control (DSC) technique and the self-recurrent wavelet neural network (SRWNN). The adaptive DSC technique provides the ability to overcome the "explosion of complexity" problem in backstepping controllers. The SRWNNs are used to observe the arbitrary model uncertainties of FJ robots, and all their weights are trained online. From the Lyapunov stability analysis, their adaptation laws are induced, and the uniformly ultimately boundedness of all signals in a closed-loop adaptive system is proved. Finally, simulation results for a three-link FJ robot are utilized to validate the good position tracking performance and robustness against payload uncertainties and external disturbances of the proposed control system.
PkANN: Non-Linear Matter Power Spectrum Interpolation through Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Agarwal, Shankar
We investigate the interpolation of power spectra of matter fluctuations using artificial neural networks (ANNs). We present a new approach to confront small-scale non-linearities in the matter power spectrum. This ever-present and pernicious uncertainty is often the Achilles' heel in cosmological studies and must be reduced if we are to see the advent of precision cosmology in the late-time Universe. We detail how an accurate interpolation of the matter power spectrum is achievable with only a sparsely sampled grid of cosmological parameters. We show that an optimally trained ANN, when presented with a set of cosmological parameters (Omh2 , Obh2, ns, w0, sigma8, sum mnu and z), can provide a worst-case error ≤ 1 per cent (for redshift z ≤ 2) fit to the non-linear matter power spectrum deduced through large-scale N-body simulations, for modes up to k ≤ 0.9 hMpc-1 . Our power spectrum interpolator, which we label 'PkANN', is designed to simulate a range of cosmological models including massive neutrinos and dark energy equation of state w 0 ≠ -1. PkANN is accurate in the quasi-non-linear regime (0.1 hMpc-1 ≤ k ≤ 0.9 hMpc -1) over the entire parameter space and marks a significant improvement over some of the current power spectrum calculators. The response of the power spectrum to variations in the cosmological parameters is explored using PkANN. Using a compilation of existing peculiar velocity surveys, we investigate the cosmic Mach number statistic and show that PkANN not only successfully accounts for the non-linear motions on small scales, but also, unlike N-body simulations which are computationally expensive and/or infeasible, it can be an extremely quick and reliable tool in interpreting cosmological observations and testing theories of structure-formation.
Arévalo, Orlando; Bornschlegl, Mona A.; Eberhardt, Sven; Ernst, Udo; Pawelzik, Klaus; Fahle, Manfred
2013-01-01
In everyday life, humans interact with a dynamic environment often requiring rapid adaptation of visual perception and motor control. In particular, new visuo–motor mappings must be learned while old skills have to be kept, such that after adaptation, subjects may be able to quickly change between two different modes of generating movements (‘dual–adaptation’). A fundamental question is how the adaptation schedule determines the acquisition speed of new skills. Given a fixed number of movements in two different environments, will dual–adaptation be faster if switches (‘phase changes’) between the environments occur more frequently? We investigated the dynamics of dual–adaptation under different training schedules in a virtual pointing experiment. Surprisingly, we found that acquisition speed of dual visuo–motor mappings in a pointing task is largely independent of the number of phase changes. Next, we studied the neuronal mechanisms underlying this result and other key phenomena of dual–adaptation by relating model simulations to experimental data. We propose a simple and yet biologically plausible neural model consisting of a spatial mapping from an input layer to a pointing angle which is subjected to a global gain modulation. Adaptation is performed by reinforcement learning on the model parameters. Despite its simplicity, the model provides a unifying account for a broad range of experimental data: It quantitatively reproduced the learning rates in dual–adaptation experiments for both direct effect, i.e. adaptation to prisms, and aftereffect, i.e. behavior after removal of prisms, and their independence on the number of phase changes. Several other phenomena, e.g. initial pointing errors that are far smaller than the induced optical shift, were also captured. Moreover, the underlying mechanisms, a local adaptation of a spatial mapping and a global adaptation of a gain factor, explained asymmetric spatial transfer and generalization of
Auditory to Visual Cross-Modal Adaptation for Emotion: Psychophysical and Neural Correlates.
Wang, Xiaodong; Guo, Xiaotao; Chen, Lin; Liu, Yijun; Goldberg, Michael E; Xu, Hong
2016-01-04
Adaptation is fundamental in sensory processing and has been studied extensively within the same sensory modality. However, little is known about adaptation across sensory modalities, especially in the context of high-level processing, such as the perception of emotion. Previous studies have shown that prolonged exposure to a face exhibiting one emotion, such as happiness, leads to contrastive biases in the perception of subsequently presented faces toward the opposite emotion, such as sadness. Such work has shown the importance of adaptation in calibrating face perception based on prior visual exposure. In the present study, we showed for the first time that emotion-laden sounds, like laughter, adapt the visual perception of emotional faces, that is, subjects more frequently perceived faces as sad after listening to a happy sound. Furthermore, via electroencephalography recordings and event-related potential analysis, we showed that there was a neural correlate underlying the perceptual bias: There was an attenuated response occurring at ∼ 400 ms to happy test faces and a quickened response to sad test faces, after exposure to a happy sound. Our results provide the first direct evidence for a behavioral cross-modal adaptation effect on the perception of facial emotion, and its neural correlate.
Feasability of adaptive vibration control of a space truss using modal filters and a neural network
NASA Astrophysics Data System (ADS)
Bosse, Albert; Fisher, Shalom; Shelley, Stuart J.; Lim, Tae W.
1996-05-01
An adaptive algorithm is proposed for the control of a large space truss structure which uses modal filters for independent modal space control and a simple neural network that provides an on-line system identification capability. The modal filters are computed off-line using measured frequency response functions and estimated pole values for the modes of interest, and provide a coordinate transformation that yields modal coordinates from physical response measurements. The time histories for the modal coordinates are then processed in real time by the neural network, which models a single degree of freedom system transfer function and provides estimates of modal parameters, namely, frequency, damping ratio and modal gain. The modal filters are used to implement independent modal space control on a 3.74 meter space truss using a single reaction-mass actuator and 32 accelerometers. The performance of the modal filter based controller is compared to that of a local rate feedback controller using the same actuator. The applicability of the adaptive filter to adaptive control is demonstrated by real time estimation of the modal parameters of the truss with and without control. Because the modal filter control gain can be adjusted to maintain a desired closed loop damping ratio, which is tracked by the adaptive filter, adaptive control of individual modes in a time-varying system is possible. The goal of this work is to field a control system which can maintain desired closed loop damping ratios for mode frequency variations as high as 10%.
Ergün, Ayla; Barbieri, Riccardo; Eden, Uri T; Wilson, Matthew A; Brown, Emery N
2007-03-01
The stochastic state point process filter (SSPPF) and steepest descent point process filter (SDPPF) are adaptive filter algorithms for state estimation from point process observations that have been used to track neural receptive field plasticity and to decode the representations of biological signals in ensemble neural spiking activity. The SSPPF and SDPPF are constructed using, respectively, Gaussian and steepest descent approximations to the standard Bayes and Chapman-Kolmogorov (BCK) system of filter equations. To extend these approaches for constructing point process adaptive filters, we develop sequential Monte Carlo (SMC) approximations to the BCK equations in which the SSPPF and SDPPF serve as the proposal densities. We term the two new SMC point process filters SMC-PPFs and SMC-PPFD, respectively. We illustrate the new filter algorithms by decoding the wind stimulus magnitude from simulated neural spiking activity in the cricket cercal system. The SMC-PPFs and SMC-PPFD provide more accurate state estimates at low number of particles than a conventional bootstrap SMC filter algorithm in which the state transition probability density is the proposal density. We also use the SMC-PPFs algorithm to track the temporal evolution of a spatial receptive field of a rat hippocampal neuron recorded while the animal foraged in an open environment. Our results suggest an approach for constructing point process adaptive filters using SMC methods.
Huang, Yue; Zheng, Han; Liu, Chi; Ding, Xinghao; Rohde, Gustavo
2017-04-06
Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our work assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.
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
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
Liang, X B; Si, J
2001-01-01
This paper investigates the existence, uniqueness, and global exponential stability (GES) of the equilibrium point for a large class of neural networks with globally Lipschitz continuous activations including the widely used sigmoidal activations and the piecewise linear activations. The provided sufficient condition for GES is mild and some conditions easily examined in practice are also presented. The GES of neural networks in the case of locally Lipschitz continuous activations is also obtained under an appropriate condition. The analysis results given in the paper extend substantially the existing relevant stability results in the literature, and therefore expand significantly the application range of neural networks in solving optimization problems. As a demonstration, we apply the obtained analysis results to the design of a recurrent neural network (RNN) for solving the linear variational inequality problem (VIP) defined on any nonempty and closed box set, which includes the box constrained quadratic programming and the linear complementarity problem as the special cases. It can be inferred that the linear VIP has a unique solution for the class of Lyapunov diagonally stable matrices, and that the synthesized RNN is globally exponentially convergent to the unique solution. Some illustrative simulation examples are also given.
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.
Adaptive control of nonlinear system using online error minimum neural networks.
Jia, Chao; Li, Xiaoli; Wang, Kang; Ding, Dawei
2016-11-01
In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly.
Adaptive Neural Network Control for the Trajectory Tracking of the Furuta Pendulum.
Moreno-Valenzuela, Javier; Aguilar-Avelar, Carlos; Puga-Guzman, Sergio A; Santibanez, Victor
2016-12-01
The purpose of this paper is to introduce a novel adaptive neural network-based control scheme for the Furuta pendulum, which is a two degree-of-freedom underactuated system. Adaptation laws for the input and output weights are also provided. The proposed controller is able to guarantee tracking of a reference signal for the arm while the pendulum remains in the upright position. The key aspect of the derivation of the controller is the definition of an output function that depends on the position and velocity errors. The internal and external dynamics are rigorously analyzed, thereby proving the uniform ultimate boundedness of the error trajectories. By using real-time experiments, the new scheme is compared with other control methodologies, therein demonstrating the improved performance of the proposed adaptive algorithm.
Zhang, Hao; Sheng, Yin; Zeng, Zhigang
2017-03-15
This paper investigates the synchronization issue of coupled reaction-diffusion neural networks with directed topology via an adaptive approach. Due to the complexity of the network structure and the presence of space variables, it is difficult to design proper adaptive strategies on coupling weights to accomplish the synchronous goal. Under the assumptions of two kinds of special network structures, that is, directed spanning path and directed spanning tree, some novel edge-based adaptive laws, which utilized the local information of node dynamics fully are designed on the coupling weights for reaching synchronization. By constructing appropriate energy function, and utilizing some analytical techniques, several sufficient conditions are given. Finally, some simulation examples are given to verify the effectiveness of the obtained theoretical results.
Neural Network Aided Adaptive Extended Kalman Filtering Approach for DGPS Positioning
NASA Astrophysics Data System (ADS)
Jwo, Dah-Jing; Huang, Hung-Chih
2004-09-01
The extended Kalman filter, when employed in the GPS receiver as the navigation state estimator, provides optimal solutions if the noise statistics for the measurement and system are completely known. In practice, the noise varies with time, which results in performance degradation. The covariance matching method is a conventional adaptive approach for estimation of noise covariance matrices. The technique attempts to make the actual filter residuals consistent with their theoretical covariance. However, this innovation-based adaptive estimation shows very noisy results if the window size is small. To resolve the problem, a multilayered neural network is trained to identify the measurement noise covariance matrix, in which the back-propagation algorithm is employed to iteratively adjust the link weights using the steepest descent technique. Numerical simulations show that based on the proposed approach the adaptation performance is substantially enhanced and the positioning accuracy is substantially improved.
Digital redesign of the decentralised adaptive tracker for linear large-scale systems
NASA Astrophysics Data System (ADS)
Lin, Ming-Hong; Sheng-Hong Tsai, Jason; Chen, Chia-Wei; Guo, Shu-Mei; Chu, Che-An
2010-02-01
A novel digital redesign of the analogue model-reference-based decentralized adaptive tracker is proposed for the sampled-data large scale system consisting of N interconnected linear subsystems, so that the system output will follow any trajectory specified at sampling instant which may not be presented by the analytic reference initially, and shows that the proposed decentralized controller induces a good robustness on the decoupling of the closed-loop controlled system. The adaptation of the analogue controller gain is derived by using the model-reference adaptive control theory based on Lyapunov's method. In this article, it is shown that using the sampled-data decentralized adaptive control system it is theoretically possible to asymptotically track the desired output with a desired performance. It is assumed that all the controllers share their prior information and the principal result is derived when they cooperate implicitly. Based on the prediction-based digital redesign methodology, the optimal digital redesigned tracker for the sampled-data decentralised adaptive control systems is newly proposed. An illustrative example of interconnected linear system is presented to demonstrate the effectiveness of the proposed design methodology.
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.
Decentralized Adaptive Neural Output-Feedback DSC for Switched Large-Scale Nonlinear Systems.
Long, Lijun; Zhao, Jun
2016-03-08
In this paper, for a class of switched large-scale uncertain nonlinear systems with unknown control coefficients and unmeasurable states, a switched-dynamic-surface-based decentralized adaptive neural output-feedback control approach is developed. The approach proposed extends the classical dynamic surface control (DSC) technique for nonswitched version to switched version by designing switched first-order filters, which overcomes the problem of multiple ``explosion of complexity.'' Also, a dual common coordinates transformation of all subsystems is exploited to avoid individual coordinate transformations for subsystems that are required when applying the backstepping recursive design scheme. Nussbaum-type functions are utilized to handle the unknown control coefficients, and a switched neural network observer is constructed to estimate the unmeasurable states. Combining with the average dwell time method and backstepping and the DSC technique, decentralized adaptive neural controllers of subsystems are explicitly designed. It is proved that the approach provided can guarantee the semiglobal uniformly ultimately boundedness for all the signals in the closed-loop system under a class of switching signals with average dwell time, and the tracking errors to a small neighborhood of the origin. A two inverted pendulums system is provided to demonstrate the effectiveness of the method proposed.
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.
A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network.
Zhao, Haiquan; Zhang, Jiashu
2009-12-01
To enhance the performance and overcome the heavy computational complexity of recurrent neural networks (RNN), a novel nonlinear adaptive filter based on a pipelined second-order Volterra recurrent neural network (PSOVRNN) is proposed in this paper. A modified real-time recurrent learning (RTRL) algorithm of the proposed filter is derived in much more detail. The PSOVRNN comprises of a number of simple small-scale second-order Volterra recurrent neural network (SOVRNN) modules. In contrast to the standard RNN, these modules of a PSOVRNN can be performed simultaneously in a pipelined parallelism fashion, which can lead to a significant improvement in its total computational efficiency. Moreover, since each module of the PSOVRNN is a SOVRNN in which nonlinearity is introduced by the recursive second-order Volterra (RSOV) expansion, its performance can be further improved. Computer simulations have demonstrated that the PSOVRNN performs better than the pipelined recurrent neural network (PRNN) and RNN for nonlinear colored signals prediction and nonlinear channel equalization. However, the superiority of the PSOVRNN over the PRNN is at the cost of increasing computational complexity due to the introduced nonlinear expansion of each module.
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.
A Neural Mechanism for Time-Window Separation Resolves Ambiguity of Adaptive Coding
Hildebrandt, K. Jannis; Ronacher, Bernhard; Hennig, R. Matthias; Benda, Jan
2015-01-01
The senses of animals are confronted with changing environments and different contexts. Neural adaptation is one important tool to adjust sensitivity to varying intensity ranges. For instance, in a quiet night outdoors, our hearing is more sensitive than when we are confronted with the plurality of sounds in a large city during the day. However, adaptation also removes available information on absolute sound levels and may thus cause ambiguity. Experimental data on the trade-off between benefits and loss through adaptation is scarce and very few mechanisms have been proposed to resolve it. We present an example where adaptation is beneficial for one task—namely, the reliable encoding of the pattern of an acoustic signal—but detrimental for another—the localization of the same acoustic stimulus. With a combination of neurophysiological data, modeling, and behavioral tests, we show that adaptation in the periphery of the auditory pathway of grasshoppers enables intensity-invariant coding of amplitude modulations, but at the same time, degrades information available for sound localization. We demonstrate how focusing the response of localization neurons to the onset of relevant signals separates processing of localization and pattern information temporally. In this way, the ambiguity of adaptive coding can be circumvented and both absolute and relative levels can be processed using the same set of peripheral neurons. PMID:25761097
NASA Astrophysics Data System (ADS)
Ondra, V.; Sever, I. A.; Schwingshackl, C. W.
2017-01-01
This paper presents a method for detection and characterisation of structural non-linearities from a single frequency response function using the Hilbert transform in the frequency domain and artificial neural networks. A frequency response function is described based on its Hilbert transform using several common and newly introduced scalar parameters, termed non-linearity indexes, to create training data of the artificial neural network. This network is subsequently used to detect the existence of non-linearity and classify its type. The theoretical background of the method is given and its usage is demonstrated on different numerical test cases created by single degree of freedom non-linear systems and a lumped parameter multi degree of freedom system with a geometric non-linearity. The method is also applied to several experimentally measured frequency response functions obtained from a cantilever beam with a clearance non-linearity and an under-platform damper experimental rig with a complex friction contact interface. It is shown that the method is a fast and noise-robust means of detecting and characterising non-linear behaviour from a single frequency response function.
Adaptive Neural Control of MIMO Nonstrict-Feedback Nonlinear Systems With Time Delay.
Zhao, Xudong; Yang, Haijiao; Karimi, Hamid Reza; Zhu, Yanzheng
2016-06-01
In this paper, an adaptive neural output-feedback tracking controller is designed for a class of multiple-input and multiple-output nonstrict-feedback nonlinear systems with time delay. The system coefficient and uncertain functions of our considered systems are both unknown. By employing neural networks to approximate the unknown function entries, and constructing a new input-driven filter, a backstepping design method of tracking controller is developed for the systems under consideration. The proposed controller can guarantee that all the signals in the closed-loop systems are ultimately bounded, and the time-varying target signal can be tracked within a small error as well. The main contributions of this paper lie in that the systems under consideration are more general, and an effective design procedure of output-feedback controller is developed for the considered systems, which is more applicable in practice. Simulation results demonstrate the efficiency of the proposed algorithm.
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.
Multi-layer holographic bifurcative neural network system for real-time adaptive EOS data analysis
NASA Technical Reports Server (NTRS)
Liu, Hua-Kuang; Huang, K.; Diep, J.
1992-01-01
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 photorefractive 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 feed forward 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.
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.
NASA Astrophysics Data System (ADS)
Tang, Song; Ye, Mao; Zhu, Ce; Liu, Yiguang
2017-01-01
How to transfer the trained detector into the target scenarios has been an important topic for a long time in the field of computer vision. Unfortunately, most of the existing transfer methods need to keep source samples or label target samples in the detection phase. Therefore, they are difficult to apply to real applications. For this problem, we propose a framework that consists of a controlled convolutional neural network (CCNN) and a modulating neural network (MNN). In a CCNN, the parameters of the last layer, i.e., the classifier, are dynamically adjusted by a MNN. For each target sample, the CCNN adaptively generates a proprietary classifier. Our contributions include (1) the first detector-based unsupervised transfer method that is very suitable for real applications and (2) a new scheme of a dynamically adjusting classifier in which a new object function is invented. Experimental results confirm that our method can achieve state-of-the-art results on two pedestrian datasets.
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.
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
An adaptive locally linear embedding manifold learning approach for hyperspectral target detection
NASA Astrophysics Data System (ADS)
Ziemann, Amanda K.; Messinger, David W.
2015-05-01
Algorithms for spectral analysis commonly use parametric or linear models of the data. Research has shown, however, that hyperspectral data -- particularly in materially cluttered scenes -- are not always well-modeled by statistical or linear methods. Here, we propose an approach to hyperspectral target detection that is based on a graph theory model of the data and a manifold learning transformation. An adaptive nearest neighbor (ANN) graph is built on the data, and then used to implement an adaptive version of locally linear embedding (LLE). We artificially induce a target manifold and incorporate it into the adaptive LLE transformation. The artificial target manifold helps to guide the separation of the target data from the background data in the new, transformed manifold coordinates. Then, target detection is performed in the manifold space using Spectral Angle Mapper. This methodology is an improvement over previous iterations of this approach due to the incorporation of ANN, the artificial target manifold, and the choice of detector in the transformed space. We implement our approach in a spatially local way: the image is delineated into square tiles, and the detection maps are normalized across the entire image. Target detection results will be shown using laboratory-measured and scene-derived target data from the SHARE 2012 collect.
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.
Neural signatures of adaptive post-error adjustments in visual search.
Steinhauser, Robert; Maier, Martin E; Steinhauser, Marco
2017-02-22
Errors in speeded choice tasks can lead to post-error adjustments both on the behavioral and on the neural level. There is an ongoing debate whether such adjustments result from adaptive processes that serve to optimize performance or whether they reflect interference from error monitoring or attentional orientation. The present study aimed at identifying adaptive adjustments in a two-stage visual search task, in which participants had to select and subsequently identify a target stimulus presented to the left or right visual hemifield. Target selection and identification can be measured by two distinct event-related potentials, the N2pc and the SPCN. Using a decoder analysis based on multivariate pattern analysis, we were able to isolate the processing stages related to error sources and post-error adjustments. Whereas errors were linked to deviations in the N2pc and the SPCN, only for the N2pc we identified a post-error adjustment, which exhibits key features of source-specific adaptivity. While errors were associated with an increased N2pc, post-error adjustments consisted in an N2pc decrease. We interpret this as an adaptive adjustment of target selection to prevent errors due to disproportionate processing of the task-irrelevant target location. Our study thus provides evidence for adaptive post-error adjustments in visual search.
Discrete-time adaptive backstepping nonlinear control via high-order neural networks.
Alanis, Alma Y; Sanchez, Edgar N; Loukianov, Alexander G
2007-07-01
This paper deals with adaptive tracking for discrete-time multiple-input-multiple-output (MIMO) nonlinear systems in presence of bounded disturbances. In this paper, a high-order neural network (HONN) structure is used to approximate a control law designed by the backstepping technique, applied to a block strict feedback form (BSFF). This paper also includes the respective stability analysis, on the basis of the Lyapunov approach, for the whole controlled system, including the extended Kalman filter (EKF)-based NN learning algorithm. Applicability of the scheme is illustrated via simulation for a discrete-time nonlinear model of an electric induction motor.
da Fonseca Neto, João Viana; Abreu, Ivanildo Silva; da Silva, Fábio Nogueira
2010-04-01
Toward the synthesis of state-space controllers, a neural-genetic model based on the linear quadratic regulator design for the eigenstructure assignment of multivariable dynamic systems is presented. The neural-genetic model represents a fusion of a genetic algorithm and a recurrent neural network (RNN) to perform the selection of the weighting matrices and the algebraic Riccati equation solution, respectively. A fourth-order electric circuit model is used to evaluate the convergence of the computational intelligence paradigms and the control design method performance. The genetic search convergence evaluation is performed in terms of the fitness function statistics and the RNN convergence, which is evaluated by landscapes of the energy and norm, as a function of the parameter deviations. The control problem solution is evaluated in the time and frequency domains by the impulse response, singular values, and modal analysis.
Han, Honggui; Wu, Xiao-Long; Qiao, Jun-Fei
2014-04-01
In this paper, a self-organizing fuzzy-neural-network with adaptive computation algorithm (SOFNN-ACA) is proposed for modeling a class of nonlinear systems. This SOFNN-ACA is constructed online via simultaneous structure and parameter learning processes. In structure learning, a set of fuzzy rules can be self-designed using an information-theoretic methodology. The fuzzy rules with high spiking intensities (SI) are divided into new ones. And the fuzzy rules with a small relative mutual information (RMI) value will be pruned in order to simplify the FNN structure. In parameter learning, the consequent part parameters are learned through the use of an ACA that incorporates an adaptive learning rate strategy into the learning process to accelerate the convergence speed. Then, the convergence of SOFNN-ACA is analyzed. Finally, the proposed SOFNN-ACA is used to model nonlinear systems. The modeling results demonstrate that this proposed SOFNN-ACA can model nonlinear systems effectively.
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
Liu, Yan-Jun; Li, Jing; Tong, Shaocheng; Chen, C L Philip
2016-07-01
In order to stabilize a class of uncertain nonlinear strict-feedback systems with full-state constraints, an adaptive neural network control method is investigated in this paper. The state constraints are frequently emerged in the real-life plants and how to avoid the violation of state constraints is an important task. By introducing a barrier Lyapunov function (BLF) to every step in a backstepping procedure, a novel adaptive backstepping design is well developed to ensure that the full-state constraints are not violated. At the same time, one remarkable feature is that the minimal learning parameters are employed in BLF backstepping design. By making use of Lyapunov analysis, we can prove that all the signals in the closed-loop system are semiglobal uniformly ultimately bounded and the output is well driven to follow the desired output. Finally, a simulation is given to verify the effectiveness of the method.
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.
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.
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. PMID:22163872
Measor, Kevin R.; Leavell, Brian C.; Brewton, Dustin H.; Rumschlag, Jeffrey; Barber, Jesse R.
2017-01-01
Abstract In active sensing, animals make motor adjustments to match sensory inputs to specialized neural circuitry. Here, we describe an active sensing system for sound level processing. The pallid bat uses downward frequency-modulated (FM) sweeps as echolocation calls for general orientation and obstacle avoidance. The bat’s auditory cortex contains a region selective for these FM sweeps (FM sweep-selective region, FMSR). We show that the vast majority of FMSR neurons are sensitive and strongly selective for relatively low levels (30-60 dB SPL). Behavioral testing shows that when a flying bat approaches a target, it reduces output call levels to keep echo levels between ∼30 and 55 dB SPL. Thus, the pallid bat behaviorally matches echo levels to an optimized neural representation of sound levels. FMSR neurons are more selective for sound levels of FM sweeps than tones, suggesting that across-frequency integration enhances level tuning. Level-dependent timing of high-frequency sideband inhibition in the receptive field shapes increased level selectivity for FM sweeps. Together with previous studies, these data indicate that the same receptive field properties shape multiple filters (sweep direction, rate, and level) for FM sweeps, a sound common in multiple vocalizations, including human speech. The matched behavioral and neural adaptations for low-intensity echolocation in the pallid bat will facilitate foraging with reduced probability of acoustic detection by prey. PMID:28275715
Kumar, Rajesh; Srivastava, Smriti; Gupta, J R P
2017-03-01
In this paper adaptive control of nonlinear dynamical systems using diagonal recurrent neural network (DRNN) is proposed. The structure of DRNN is a modification of fully connected recurrent neural network (FCRNN). Presence of self-recurrent neurons in the hidden layer of DRNN gives it an ability to capture the dynamic behaviour of the nonlinear plant under consideration (to be controlled). To ensure stability, update rules are developed using lyapunov stability criterion. These rules are then used for adjusting the various parameters of DRNN. The responses of plants obtained with DRNN are compared with those obtained when multi-layer feed forward neural network (MLFFNN) is used as a controller. Also, in example 4, FCRNN is also investigated and compared with DRNN and MLFFNN. Robustness of the proposed control scheme is also tested against parameter variations and disturbance signals. Four simulation examples including one-link robotic manipulator and inverted pendulum are considered on which the proposed controller is applied. The results so obtained show the superiority of DRNN over MLFFNN as a controller.
On adaptive trajectory tracking of a robot manipulator using inversion of its neural emulator.
Behera, L; Gopal, M; Chaudhury, S
1996-01-01
This paper is concerned with the design of a neuro-adaptive trajectory tracking controller. The paper presents a new control scheme based on inversion of a feedforward neural model of a robot arm. The proposed control scheme requires two modules. The first module consists of an appropriate feedforward neural model of forward dynamics of the robot arm that continuously accounts for the changes in the robot dynamics. The second module implements an efficient network inversion algorithm that computes the control action by inverting the neural model. In this paper, a new extended Kalman filter (EKF) based network inversion scheme is proposed. The scheme is evaluated through comparison with two other schemes of network inversion: gradient search in input space and Lyapunov function approach. Using these three inversion schemes the proposed controller was implemented for trajectory tracking control of a two-link manipulator. Simulation results in all cases confirm the efficacy of control input prediction using network inversion. Comparison of the inversion algorithms in terms of tracking accuracy showed the superior performance of the EKF based inversion scheme over others.
NASA Astrophysics Data System (ADS)
Young, R. J.; Ritthaler, M. Healy, M.; Caudell, T. P. Zimmer, P.; McGraw, J.
2007-10-01
While learning algorithms have been used for astronomical data analysis, the vast majority of those algorithms have used supervised learning. We examine the use of two types of Adaptive Resonance Theory (ART) (Carpenter & Grossberg 1987) neural networks which use unsupervised learning for this task. Using synthetic astronomical data from SkyMaker which was designed to mimic the dynamic range of the CTI-II telescope, we compared the ability of the ART-1 neural network and the ART-1 neural network with a category theoretic modification to detect regions of interest and to characterize noise. We use the program SExtractor to pinpoint clusters that contain either many or no object hits. We then show that there are more targets in the clusters with many SExtractor hits than SExtractor finds. We also show that ART clusters together input regions that are dominated by noise that can be used to characterize the noise in an image. The results provided show that unsupervised learning algorithms should not be overlooked for astronomical data analysis.
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)
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…
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.
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.
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.
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.
Motor learning and cross-limb transfer rely upon distinct neural adaptation processes.
Stöckel, Tino; Carroll, Timothy J; Summers, Jeffery J; Hinder, Mark R
2016-08-01
Performance benefits conferred in the untrained limb after unilateral motor practice are termed cross-limb transfer. Although the effect is robust, the neural mechanisms remain incompletely understood. In this study we used noninvasive brain stimulation to reveal that the neural adaptations that mediate motor learning in the trained limb are distinct from those that underlie cross-limb transfer to the opposite limb. Thirty-six participants practiced a ballistic motor task with their right index finger (150 trials), followed by intermittent theta-burst stimulation (iTBS) applied to the trained (contralateral) primary motor cortex (cM1 group), the untrained (ipsilateral) M1 (iM1 group), or the vertex (sham group). After stimulation, another 150 training trials were undertaken. Motor performance and corticospinal excitability were assessed before motor training, pre- and post-iTBS, and after the second training bout. For all groups, training significantly increased performance and excitability of the trained hand, and performance, but not excitability, of the untrained hand, indicating transfer at the level of task performance. The typical facilitatory effect of iTBS on MEPs was reversed for cM1, suggesting homeostatic metaplasticity, and prior performance gains in the trained hand were degraded, suggesting that iTBS interfered with learning. In stark contrast, iM1 iTBS facilitated both performance and excitability for the untrained hand. Importantly, the effects of cM1 and iM1 iTBS on behavior were exclusive to the hand contralateral to stimulation, suggesting that adaptations within the untrained M1 contribute to cross-limb transfer. However, the neural processes that mediate learning in the trained hemisphere vs. transfer in the untrained hemisphere appear distinct.
Wang, Huanqing; Chen, Bing; Liu, Kefu; Liu, Xiaoping; Lin, Chong
2014-05-01
This paper considers the problem of adaptive neural control of stochastic nonlinear systems in nonstrict-feedback form with unknown backlash-like hysteresis nonlinearities. To overcome the design difficulty of nonstrict-feedback structure, variable separation technique is used to decompose the unknown functions of all state variables into a sum of smooth functions of each error dynamic. By combining radial basis function neural networks' universal approximation capability with an adaptive backstepping technique, an adaptive neural control algorithm is proposed. It is shown that the proposed controller guarantees that all the signals in the closed-loop system are four-moment semiglobally uniformly ultimately bounded, and the tracking error eventually converges to a small neighborhood of the origin in the sense of mean quartic value. Simulation results further show the effectiveness of the presented control scheme.
Model-free adaptive fractional order control of stable linear time-varying systems.
Yakoub, Z; Amairi, M; Chetoui, M; Saidi, B; Aoun, M
2017-03-01
This paper presents a new model-free adaptive fractional order control approach for linear time-varying systems. An online algorithm is proposed to determine some frequency characteristics using a selective filtering and to design a fractional PID controller based on the numerical optimization of the frequency-domain criterion. When the system parameters are time-varying, the controller is updated to keep the same desired performances. The main advantage of the proposed approach is that the controller design depends only on the measured input and output signals of the process. The effectiveness of the proposed method is assessed through a numerical example.
Stability of Wilkinson's linear model of prism adaptation over time for various targets.
Wallace, B
1977-01-01
Prism adaptation as measured by negative aftereffects (NA), proprioceptive shifts (PS), and visual shifts (VS) was assessed as a function of amount of exposure time and target specificity, whether an exposure and a test target background were the same or different, to determine the validity of Wilkinson's linear model (NA = PS + VS). With few exceptions the model was found to hold well up to 40 min of prism viewing regardless of type of exposure background. In addition target specificity affected magnitude of the NA component of adapation but not the PS and the VS components.
NASA Technical Reports Server (NTRS)
Balas, M. J.; Kaufman, H.; Wen, J.
1985-01-01
A command generator tracker approach to model following contol of linear distributed parameter systems (DPS) whose dynamics are described on infinite dimensional Hilbert spaces is presented. This method generates finite dimensional controllers capable of exponentially stable tracking of the reference trajectories when certain ideal trajectories are known to exist for the open loop DPS; we present conditions for the existence of these ideal trajectories. An adaptive version of this type of controller is also presented and shown to achieve (in some cases, asymptotically) stable finite dimensional control of the infinite dimensional DPS.
Optimisation of substrate blends in anaerobic co-digestion using adaptive linear programming.
García-Gen, Santiago; Rodríguez, Jorge; Lema, Juan M
2014-12-01
Anaerobic co-digestion of multiple substrates has the potential to enhance biogas productivity by making use of the complementary characteristics of different substrates. A blending strategy based on a linear programming optimisation method is proposed aiming at maximising COD conversion into methane, but simultaneously maintaining a digestate and biogas quality. The method incorporates experimental and heuristic information to define the objective function and the linear restrictions. The active constraints are continuously adapted (by relaxing the restriction boundaries) such that further optimisations in terms of methane productivity can be achieved. The feasibility of the blends calculated with this methodology was previously tested and accurately predicted with an ADM1-based co-digestion model. This was validated in a continuously operated pilot plant, treating for several months different mixtures of glycerine, gelatine and pig manure at organic loading rates from 1.50 to 4.93 gCOD/Ld and hydraulic retention times between 32 and 40 days at mesophilic conditions.
NASA Astrophysics Data System (ADS)
Li, Yuan; Lv, Hui; Jiao, Dongxiu
2017-03-01
In this study, an adaptive neural network synchronization (NNS) approach, capable of guaranteeing prescribed performance (PP), is designed for non-identical fractional-order chaotic systems (FOCSs). For PP synchronization, we mean that the synchronization error converges to an arbitrary small region of the origin with convergence rate greater than some function given in advance. Neural networks are utilized to estimate unknown nonlinear functions in the closed-loop system. Based on the integer-order Lyapunov stability theorem, a fractional-order adaptive NNS controller is designed, and the PP can be guaranteed. Finally, simulation results are presented to confirm our results.
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
The Neural Dynamics of Conflict Adaptation within a Look-to-Do Transition
Tang, Dandan; Hu, Li; Li, Hong; Zhang, Qinglin; Chen, Antao
2013-01-01
Background For optimal performance in conflict situations, conflict adaptation (conflict detection and adjustment) is necessary. However, the neural dynamics of conflict adaptation is still unclear. Methods In the present study, behavioral and electroencephalography (EEG) data were recorded from seventeen healthy participants during performance of a color-word Stroop task with a novel look-to-do transition. Within this transition, participants looked at the Stroop stimuli but no responses were required in the ‘look’ trials; or made manual responses to the Stroop stimuli in the ‘do’ trials. Results In the ‘look’ trials, the amplitude modulation of N450 occurred exclusively in the right-frontal region. Subsequently, the amplitude modulation of sustained potential (SP) emerged in the posterior parietal and right-frontal regions. A significantly positive correlation between the modulation of reconfiguration in the ‘look’ trials and the behavioral conflict adaptation in the ‘do’ trials was observed. Specially, a stronger information flow from right-frontal region to posterior parietal region in the beta band was observed for incongruent condition than for congruent condition. In the ‘do’ trials, the conflict of ‘look’ trials enhanced the amplitude modulations of N450 in the right-frontal and posterior parietal regions, but decreased the amplitude modulations of SP in these regions. Uniquely, a stronger information flow from centro-parietal region to right-frontal region in the theta band was observed for iI condition than for cI condition. Conclusion All these findings showed that top-down conflict adaptation is implemented by: (1) enhancing the sensitivity to conflict detection and the adaptation to conflict resolution; (2) modulating the effective connectivity between parietal region and right-frontal region. PMID:23469102
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
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.
Hoogi, Assaf; Subramaniam, Arjun; Veerapaneni, Rishi; Rubin, Daniel
2016-11-11
In this paper, we propose a generalization of the level set segmentation approach by supplying a novel method for adaptive estimation of active contour parameters. The presented segmentation method is fully automatic once the lesion has been detected. First, the location of the level set contour relative to the lesion is estimated using a convolutional neural network (CNN). The CNN has two convolutional layers for feature extraction, which lead into dense layers for classification. Second, the output CNN probabilities are then used to adaptively calculate the parameters of the active contour functional during the segmentation process. Finally, the adaptive window size surrounding each contour point is re-estimated by an iterative process that considers lesion size and spatial texture. We demonstrate the capabilities of our method on a dataset of 164 MRI and 112 CT images of liver lesions that includes low contrast and heterogeneous lesions as well as noisy images. To illustrate the strength of our method, we evaluated it against state of the art CNNbased and active contour techniques. For all cases, our method, as assessed by Dice similarity coefficients, performed significantly better than currently available methods. An average Dice improvement of 0.27 was found across the entire dataset over all comparisons. We also analyzed two challenging subsets of lesions and obtained a significant Dice improvement of ����.�������� with our method (p < 0.001, Wilcoxon).
Hoogi, Assaf; Subramaniam, Arjun; Veerapaneni, Rishi; Rubin, Daniel
2016-11-11
In this paper, we propose a generalization of the level set segmentation approach by supplying a novel method for adaptive estimation of active contour parameters. The presented segmentation method is fully automatic once the lesion has been detected. First, the location of the level set contour relative to the lesion is estimated using a convolutional neural network (CNN). The CNN has two convolutional layers for feature extraction, which lead into dense layers for classification. Second, the output CNN probabilities are then used to adaptively calculate the parameters of the active contour functional during the segmentation process. Finally, the adaptive window size surrounding each contour point is re-estimated by an iterative process that considers lesion size and spatial texture. We demonstrate the capabilities of our method on a dataset of 164 MRI and 112 CT images of liver lesions that includes low contrast and heterogeneous lesions as well as noisy images. To illustrate the strength of our method, we evaluated it against state of the art CNNbased and active contour techniques. For all cases, our method, as assessed by Dice similarity coefficients, performed significantly better than currently available methods. An average Dice improvement of 0.27 was found across the entire dataset over all comparisons. We also analyzed two challenging subsets of lesions and obtained a significant Dice improvement of 0.24 with our method (p < 0.001, Wilcoxon).
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.
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.
Allen, J; Murray, A
1999-08-01
The relationships between peripheral blood pressure and blood volume pulse waveforms can provide valuable physiological data about the peripheral vascular system, and are the subject of this study. Blood pressure and volume pulse waveforms were collected from 12 normal male subjects using non-invasive optical techniques, finger arterial blood pressure (BP, Finapres: Datex-Ohmeda) and photoelectric plethysmography (PPG) respectively, and captured to computer for three equal (1 min) measurement phases: baseline, hand raising and hand elevated. This simple physiological challenge was designed to induce a significant drop in peripheral blood pressure. A simple first order lag transfer function was chosen to study the relationship between blood pressure (system input) and blood volume pulse waveforms (system output), with parameters describing the dynamics (time constant, tau) and input-output gain (K). Tau and K were estimated for each subject using two different system identification techniques: a recursive parameter estimation algorithm which calculated tau and K from a linear auto-regressive with exogenous variable (ARX) model, and an artificial neural network which was trained to learn the non-linear process input-output relationships and then derive a linearized ARX model of the system. The identification techniques allowed the relationship between the blood pressure and blood volume pulses to be described simply, with the neural network technique providing a better model fit overall (p < 0.05, Wilcoxon). The median falls in tau following the hand raise challenge were 26% and 31% for the linear and neural network based techniques respectively (both p < 0.05, Wilcoxon). This preliminary study has shown that the time constant and gain parameters obtained using these techniques can provide physiological data for the clinical assessment of the peripheral circulation.
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.
Neural adaptations to resistive exercise: mechanisms and recommendations for training practices.
Gabriel, David A; Kamen, Gary; Frost, Gail
2006-01-01
It is generally accepted that neural factors play an important role in muscle strength gains. This article reviews the neural adaptations in strength, with the goal of laying the foundations for practical applications in sports medicine and rehabilitation. An increase in muscular strength without noticeable hypertrophy is the first line of evidence for neural involvement in acquisition of muscular strength. The use of surface electromyographic (SEMG) techniques reveal that strength gains in the early phase of a training regimen are associated with an increase in the amplitude of SEMG activity. This has been interpreted as an increase in neural drive, which denotes the magnitude of efferent neural output from the CNS to active muscle fibres. However, SEMG activity is a global measure of muscle activity. Underlying alterations in SEMG activity are changes in motor unit firing patterns as measured by indwelling (wire or needle) electrodes. Some studies have reported a transient increase in motor unit firing rate. Training-related increases in the rate of tension development have also been linked with an increased probability of doublet firing in individual motor units. A doublet is a very short interspike interval in a motor unit train, and usually occurs at the onset of a muscular contraction. Motor unit synchronisation is another possible mechanism for increases in muscle strength, but has yet to be definitely demonstrated. There are several lines of evidence for central control of training-related adaptation to resistive exercise. Mental practice using imagined contractions has been shown to increase the excitability of the cortical areas involved in movement and motion planning. However, training using imagined contractions is unlikely to be as effective as physical training, and it may be more applicable to rehabilitation. Retention of strength gains after dissipation of physiological effects demonstrates a strong practice effect. Bilateral contractions are
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.
Adaptive neural network control for a class of low-triangular-structured nonlinear systems.
Du, Hongbin; Shao, Huihe; Yao, Pingjing
2006-03-01
In this paper, a class of unknown perturbed nonlinear systems is theoretically stabilized by using adaptive neural network control. The systems, with disturbances and nonaffine unknown functions, have low triangular structure, which generalizes both strict-feedback uncertain systems and pure-feedback ones. There do not exist any effective methods to stabilize this kind of systems. With some new conclusions for Nussbaum-Gain functions (NGF) and the idea of backstepping, semiglobal, uniformal, and ultimate boundedness of all the signals in the closed-loop is proved at equilibrium point. The two problems, control directions and control singularity, are well dealt with. The effectiveness of proposed scheme is shown by simulation on a proper nonlinear system.
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
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.
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.
Neural adaptive chaotic control with constrained input using state and output feedback
NASA Astrophysics Data System (ADS)
Gao, Shi-Gen; Dong, Hai-Rong; Sun, Xu-Bin; Ning, Bin
2015-01-01
This paper presents neural adaptive control methods for a class of chaotic nonlinear systems in the presence of constrained input and unknown dynamics. To attenuate the influence of constrained input caused by actuator saturation, an effective auxiliary system is constructed to prevent the stability of closed loop system from being destroyed. Radial basis function neural networks (RBF-NNs) are used in the online learning of the unknown dynamics, which do not require an off-line training phase. Both state and output feedback control laws are developed. In the output feedback case, high-order sliding mode (HOSM) observer is utilized to estimate the unmeasurable system states. Simulation results are presented to verify the effectiveness of proposed schemes. Project supported by the National High Technology Research and Development Program of China (Grant No. 2012AA041701), the Fundamental Research Funds for Central Universities of China (Grant No. 2013JBZ007), the National Natural Science Foundation of China (Grant Nos. 61233001, 61322307, 61304196, and 61304157), and the Research Program of Beijing Jiaotong University, China (Grant No. RCS2012ZZ003).
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.
Nonlinear model identification and adaptive model predictive control using neural networks.
Akpan, Vincent A; Hassapis, George D
2011-04-01
This paper presents two new adaptive model predictive control algorithms, both consisting of an on-line process identification part and a predictive control part. Both parts are executed at each sampling instant. The predictive control part of the first algorithm is the Nonlinear Model Predictive Control strategy and the control part of the second algorithm is the Generalized Predictive Control strategy. In the identification parts of both algorithms the process model is approximated by a series-parallel neural network structure which is trained by a recursive least squares (ARLS) method. The two control algorithms have been applied to: 1) the temperature control of a fluidized bed furnace reactor (FBFR) of a pilot plant and 2) the auto-pilot control of an F-16 aircraft. The training and validation data of the neural network are obtained from the open-loop simulation of the FBFR and the nonlinear F-16 aircraft models. The identification and control simulation results show that the first algorithm outperforms the second one at the expense of extra computation time.
NASA Astrophysics Data System (ADS)
Ticchi, Alessandro; Faisal, Aldo A.; Brain; Behaviour Lab Team
2015-03-01
Experimental evidence at the behavioural-level shows that the brains are able to make Bayes-optimal inference and decisions (Kording and Wolpert 2004, Nature; Ernst and Banks, 2002, Nature), yet at the circuit level little is known about how neural circuits may implement Bayesian learning and inference (but see (Ma et al. 2006, Nat Neurosci)). Molecular sources of noise are clearly established to be powerful enough to pose limits to neural function and structure in the brain (Faisal et al. 2008, Nat Rev Neurosci; Faisal et al. 2005, Curr Biol). We propose a spking neuron model where we exploit molecular noise as a useful resource to implement close-to-optimal inference by sampling. Specifically, we derive a synaptic plasticity rule which, coupled with integrate-and-fire neural dynamics and recurrent inhibitory connections, enables a neural population to learn the statistical properties of the received sensory input (prior). Moreover, the proposed model allows to combine prior knowledge with additional sources of information (likelihood) from another neural population, and to implement in spiking neurons a Markov Chain Monte Carlo algorithm which generates samples from the inferred posterior distribution.
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.
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.
Chase, Steven M; Kass, Robert E; Schwartz, Andrew B
2012-07-01
Brain-computer interfaces (BCIs) provide a defined link between neural activity and devices, allowing a detailed study of the neural adaptive responses generating behavioral output. We trained monkeys to perform two-dimensional center-out movements of a computer cursor using a BCI. We then applied a perturbation by randomly selecting a subset of the recorded units and rotating their directional contributions to cursor movement by a consistent angle. Globally, this perturbation mimics a visuomotor transformation, and in the first part of this article we characterize the psychophysical indications of motor adaptation and compare them with known results from adaptation of natural reaching movements. Locally, however, only a subset of the neurons in the population actually contributes to error, allowing us to probe for signatures of neural adaptation that might be specific to the subset of neurons we perturbed. One compensation strategy would be to selectively adapt the subset of cells responsible for the error. An alternate strategy would be to globally adapt the entire population to correct the error. Using a recently developed mathematical technique that allows us to differentiate these two mechanisms, we found evidence of both strategies in the neural responses. The dominant strategy we observed was global, accounting for ∼86% of the total error reduction. The remaining 14% came from local changes in the tuning functions of the perturbed units. Interestingly, these local changes were specific to the details of the applied rotation: in particular, changes in the depth of tuning were only observed when the percentage of perturbed cells was small. These results imply that there may be constraints on the network's adaptive capabilities, at least for perturbations lasting only a few hundreds of trials.
Sabesan, Ramkumar; Barbot, Antoine; Yoon, Geunyoung
2017-03-01
Highly aberrated keratoconic (KC) eyes do not elicit the expected visual advantage from customized optical corrections. This is attributed to the neural insensitivity arising from chronic visual experience with poor retinal image quality, dominated by low spatial frequencies. The goal of this study was to investigate if targeted perceptual learning with adaptive optics (AO) can stimulate neural plasticity in these highly aberrated eyes. The worse eye of 2 KC subjects was trained in a contrast threshold test under AO correction. Prior to training, tumbling 'E' visual acuity and contrast sensitivity at 4, 8, 12, 16, 20, 24 and 28 c/deg were measured in both the trained and untrained eyes of each subject with their routine prescription and with AO correction for a 6mm pupil. The high spatial frequency requiring 50% contrast for detection with AO correction was picked as the training frequency. Subjects were required to train on a contrast detection test with AO correction for 1h for 5 consecutive days. During each training session, threshold contrast measurement at the training frequency with AO was conducted. Pre-training measures were repeated after the 5 training sessions in both eyes (i.e., post-training). After training, contrast sensitivity under AO correction improved on average across spatial frequency by a factor of 1.91 (range: 1.77-2.04) and 1.75 (1.22-2.34) for the two subjects. This improvement in contrast sensitivity transferred to visual acuity with the two subjects improving by 1.5 and 1.3 lines respectively with AO following training. One of the two subjects denoted an interocular transfer of training and an improvement in performance with their routine prescription post-training. This training-induced visual benefit demonstrates the potential of AO as a tool for neural rehabilitation in patients with abnormal corneas. Moreover, it reveals a sufficient degree of neural plasticity in normally developed adults who have a long history of abnormal visual
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.
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)
Yadmellat, Peyman; Nikravesh, S. Kamaleddin Yadavar
2011-01-01
In this paper, a recursive delayed output-feedback control strategy is considered for stabilizing unstable periodic orbit of unknown nonlinear chaotic systems. An unknown nonlinearity is directly estimated by a linear-in-parameter neural network which is then used in an observer structure. An on-line modified back propagation algorithm with e-modification is used to update the weights of the network. The globally uniformly ultimately boundedness of overall closed-loop system response is analytically ensured using Razumikhin lemma. To verify the effectiveness of the proposed observer-based controller, a set of simulations is performed on a Rossler system in comparison with several previous methods.
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.
Adaptive FIR neural model for centroid learning in self-organizing maps.
Tucci, Mauro; Raugi, Marco
2010-06-01
In this paper, a training method for the formation of topology preserving maps is introduced. The proposed approach presents a sequential formulation of the self-organizing map (SOM), which is based on a new model of the neuron, or processing unit. Each neuron acts as a finite impulse response (FIR) system, and the coefficients of the filters are adaptively estimated during the sequential learning process, in order to minimize a distortion measure of the map. The proposed FIR-SOM model deals with static distributions and it computes an ordered set of centroids. Additionally, the FIR-SOM estimates the learning dynamic of each prototype using an adaptive FIR model. A noteworthy result is that the optimized coefficients of the FIR processes tend to represent a moving average filter, regardless of the underlying input distribution. The convergence of the resulting model is analyzed numerically and shows good properties with respect to the classic SOM and other unsupervised neural models. Finally, the optimal FIR coefficients are shown to be useful for visualizing the cluster densities.
An adaptive wavelet neural network for spatio-temporal system identification.
Wei, H L; Billings, S A; Zhao, Y F; Guo, L Z
2010-12-01
Starting from the basic concept of coupled map lattices, a new family of adaptive wavelet neural networks (AWNN) is introduced for spatio-temporal system identification, by combining an efficient wavelet representation with a coupled map lattice model. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the orthogonal projection pursuit algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, may however be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. The proposed two-stage hybrid training procedure can generally produce a parsimonious network model, where a ranked list of wavelet neurons, according to the capability of each neuron to represent the total variance in the system output signal is produced. Two spatio-temporal system identification examples are presented to demonstrate the performance of the proposed new modelling framework.
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
2014-03-06
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.
Adaptive Movable Neural Interfaces for Monitoring Single Neurons in the Brain
Muthuswamy, Jit; Anand, Sindhu; Sridharan, Arati
2011-01-01
Implantable microelectrodes that are currently used to monitor neuronal activity in the brain in vivo have serious limitations both in acute and chronic experiments. Movable microelectrodes that adapt their position in the brain to maximize the quality of neuronal recording have been suggested and tried as a potential solution to overcome the challenges with the current fixed implantable microelectrodes. While the results so far suggest that movable microelectrodes improve the quality and stability of neuronal recordings from the brain in vivo, the bulky nature of the technologies involved in making these movable microelectrodes limits the throughput (number of neurons that can be recorded from at any given time) of these implantable devices. Emerging technologies involving the use of microscale motors and electrodes promise to overcome this limitation. This review summarizes some of the most recent efforts in developing movable neural interfaces using microscale technologies that adapt their position in response to changes in the quality of the neuronal recordings. Key gaps in our understanding of the brain–electrode interface are highlighted. Emerging discoveries in these areas will lead to success in the development of a reliable and stable interface with single neurons that will impact basic neurophysiological studies and emerging cortical prosthetic technologies. PMID:21927593
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
Alahyane, N; Fonteille, V; Urquizar, C; Salemme, R; Nighoghossian, N; Pelisson, D; Tilikete, C
2008-01-01
Sensory-motor adaptation processes are critically involved in maintaining accurate motor behavior throughout life. Yet their underlying neural substrates and task-dependency bases are still poorly understood. We address these issues here by studying adaptation of saccadic eye movements, a well-established model of sensory-motor plasticity. The cerebellum plays a major role in saccadic adaptation but it has not yet been investigated whether this role can account for the known specificity of adaptation to the saccade type (e.g., reactive versus voluntary). Two patients with focal lesions in different parts of the cerebellum were tested using the double-step target paradigm. Each patient was submitted to two separate sessions: one for reactive saccades (RS) triggered by the sudden appearance of a visual target and the second for scanning voluntary saccades (SVS) performed when exploring a more complex scene. We found that a medial cerebellar lesion impaired adaptation of reactive-but not of voluntary-saccades, whereas a lateral lesion affected adaptation of scanning voluntary saccades, but not of reactive saccades. These findings provide the first evidence of an involvement of the lateral cerebellum in saccadic adaptation, and extend the demonstrated role of the cerebellum in RS adaptation to adaptation of SVS. The double dissociation of adaptive abilities is also consistent with our previous hypothesis of the involvement in saccadic adaptation of partially separated cerebellar areas specific to the reactive or voluntary task (Alahyane et al. Brain Res 1135:107-121 (2007)).
Joiner, Wilsaan M; Ajayi, Obafunso; Sing, Gary C; Smith, Maurice A
2011-01-01
The ability to generalize learned motor actions to new contexts is a key feature of the motor system. For example, the ability to ride a bicycle or swing a racket is often first developed at lower speeds and later applied to faster velocities. A number of previous studies have examined the generalization of motor adaptation across movement directions and found that the learned adaptation decays in a pattern consistent with the existence of motor primitives that display narrow Gaussian tuning. However, few studies have examined the generalization of motor adaptation across movement speeds. Following adaptation to linear velocity-dependent dynamics during point-to-point reaching arm movements at one speed, we tested the ability of subjects to transfer this adaptation to short-duration higher-speed movements aimed at the same target. We found near-perfect linear extrapolation of the trained adaptation with respect to both the magnitude and the time course of the velocity profiles associated with the high-speed movements: a 69% increase in movement speed corresponded to a 74% extrapolation of the trained adaptation. The close match between the increase in movement speed and the corresponding increase in adaptation beyond what was trained indicates linear hypergeneralization. Computational modeling shows that this pattern of linear hypergeneralization across movement speeds is not compatible with previous models of adaptation in which motor primitives display isotropic Gaussian tuning of motor output around their preferred velocities. Instead, we show that this generalization pattern indicates that the primitives involved in the adaptation to viscous dynamics display anisotropic tuning in velocity space and encode the gain between motor output and motion state rather than motor output itself.
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 Predictor-Based Output Feedback Control for a Class of Unknown MIMO Linear Systems
NASA Astrophysics Data System (ADS)
Nguyen, Chuong Hoang; Leonessa, Alexander
2017-02-01
In this paper, the problem of characterizing adaptive output feedback control laws for a general class of unknown MIMO linear systems is considered. Specifically, the presented control approach relies on three components, i.e., a predictor, a reference model and a controller. The predictor is designed to predict the system's output with arbitrary accuracy, for any admissible control input. Subsequently, a full state feedback control law is designed to control the predictor output to approach the reference system, while the reference system tracks the desired trajectory. Ultimately, the control objective of driving the actual system output to track the desired trajectories is achieved by showing that the system output, the predictor output and the reference system trajectories all converge to each other.
Long-range accelerated BOTDA sensor using adaptive linear prediction and cyclic coding.
Muanenda, Yonas; Taki, Mohammad; Pasquale, Fabrizio Di
2014-09-15
We propose and experimentally demonstrate a long-range accelerated Brillouin optical time domain analysis (BOTDA) sensor that exploits the complementary noise reduction benefits of adaptive linear prediction and optical pulse coding. The combined technique allows using orders of magnitude less the number of averages of the backscattered BOTDA traces compared to a standard single pulse BOTDA, enabling distributed strain measurement over 10 km of a standard single mode fiber with meter-scale spatial resolution and 1.8 MHz Brillouin frequency shift resolution. By optimizing the system parameters, the measurement is achieved with only 20 averages for each Brillouin gain spectrum scanned frequency, allowing for an eight times faster strain measurement compared to the use of cyclic pulse coding alone.
NASA Astrophysics Data System (ADS)
Tai, Shen-Chuan; Chen, Peng-Yu; Chao, Chian-Yen
2016-07-01
The Consultative Committee for Space Data Systems proposed an efficient image compression standard that can do lossless compression (CCSDS-ICS). CCSDS-ICS is the most widely utilized standard for satellite communications. However, the original CCSDS-ICS is weak in terms of error resilience with even a single incorrect bit possibly causing numerous missing pixels. A restoration algorithm based on the neighborhood similar pixel interpolator is proposed to fill in missing pixels. The linear regression model is used to generate the reference image from other panchromatic or multispectral images. Furthermore, an adaptive search window is utilized to sieve out similar pixels from the pixels in the search region defined in the neighborhood similar pixel interpolator. The experimental results show that the proposed methods are capable of reconstructing missing regions with good visual quality.
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.
NASA Astrophysics Data System (ADS)
Gupta, Kinjal Dhar; Vilalta, Ricardo; Asadourian, Vicken; Macri, Lucas
2014-05-01
We describe an approach to automate the classification of Cepheid variable stars into two subtypes according to their pulsation mode. Automating such classification is relevant to obtain a precise determination of distances to nearby galaxies, which in addition helps reduce the uncertainty in the current expansion of the universe. One main difficulty lies in the compatibility of models trained using different galaxy datasets; a model trained using a training dataset may be ineffectual on a testing set. A solution to such difficulty is to adapt predictive models across domains; this is necessary when the training and testing sets do not follow the same distribution. The gist of our methodology is to train a predictive model on a nearby galaxy (e.g., Large Magellanic Cloud), followed by a model-adaptation step to make the model operable on other nearby galaxies. We follow a parametric approach to density estimation by modeling the training data (anchor galaxy) using a mixture of linear models. We then use maximum likelihood to compute the right amount of variable displacement, until the testing data closely overlaps the training data. At that point, the model can be directly used in the testing data (target galaxy).
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.
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.
Bergersen, L H; Bramham, C R; Hugdahl, K; Sander, M; Storm-Mathisen, J
2013-09-05
The Kavli Prize in Neuroscience was awarded for the third time in September 2012, by the Norwegian Academy of Science and Letters in Oslo. The accompanying Kavli Prize Symposium on Neuroscience, held in Bergen and Trondheim, was a showcase of excellence in neuroscience research. The common theme of the Symposium presentations was the mechanisms by which animals adapt to their environment. The symposium speakers--Michael Greenberg, Erin Schuman, Chiara Cirelli, Michael Meaney, Catherine Dulac, Hopi Hoekstra, and Stanislas Dehaene--covered topics ranging from the molecular and cellular levels to the systems level and behavior. Thus a single amino acid change in a transcriptional repressor can disrupt gene regulation through neural activity (Greenberg). Deep sequencing analysis of the neuropil transcriptome indicates that a large fraction of the synaptic proteome is synthesized in situ in axons and dendrites, permitting local regulation (Schuman). The nature of the 'reset' function that makes animals dependent of sleep is being revealed (Cirelli). Maternal behavior can cause changes in gene expression that stably modify behavior in the offspring (Meaney). Removal of a single sensory channel protein in the vomero-nasal organ can switch off male-specific and switch on female-specific innate behavior of mice in response to environmental stimulation (Dulac). Innate behaviors can be stably transmitted from parent to offspring through generations even when those behaviors cannot be expressed, as illustrated by the elaborate burrowing behavior in a rodent species, in which independent genetic regions regulate distinct modules of the burrowing pattern (Hoekstra). Finally, at the other extreme of the nature-nurture scale, functional magnetic resonance imaging (fMRI) analysis in children and adults identified a brain area specifically involved in reading (Dehaene). As the area must originally have developed for a purpose other than reading, such as shape recognition, this
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
Small-Aperture Monovision and the Pulfrich Experience: Absence of Neural Adaptation Effects
Plainis, Sotiris; Petratou, Dionysia; Giannakopoulou, Trisevgeni; Radhakrishnan, Hema; Pallikaris, Ioannis G.; Charman, W. Neil
2013-01-01
Purpose To explore whether adaptation reduces the interocular visual latency differences and the induced Pulfrich effect caused by the anisocoria implicit in small-aperture monovision. Methods Anisocoric vision was simulated in two adults by wearing in the non-dominant eye for 7 successive days, while awake, an opaque soft contact lens (CL) with a small, central, circular aperture. This was repeated with aperture diameters of 1.5 and 2.5 mm. Each day, monocular and binocular pattern-reversal Visual Evoked Potentials (VEP) were recorded. Additionally, the Pulfrich effect was measured: the task of the subject was to state whether a a 2-deg spot appeared in front or behind the plane of a central cross when moved left-to-right or right-to-left on a display screen. The retinal illuminance of the dominant eye was varied using neutral density (ND) filters to establish the ND value which eliminated the Pulfrich effect for each lens. All experiments were performed at luminance levels of 5 and 30 cd/m2. Results Interocular differences in monocular VEP latency (at 30 cd/m2) rose to about 12–15 ms and 20–25 ms when the CL aperture was 2.5 and 1.5 mm, respectively. The effect was more pronounced at 5 cd/m2 (i.e. with larger natural pupils). A strong Pulfrich effect was observed under all conditions, with the effect being less striking for the 2.5 mm aperture. No neural adaptation appeared to occur: neither the interocular differences in VEP latency nor the ND value required to null the Pulfrich effect reduced over each 7-day period of anisocoric vision. Conclusions Small-aperture monovision produced marked interocular differences in visual latency and a Pulfrich experience. These were not reduced by adaptation, perhaps because the natural pupil diameter of the dominant eye was continually changing throughout the day due to varying illumination and other factors, making adaptation difficult. PMID:24155881
An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems
1991-12-01
Recurrent and feedforward artificial neural networks are developed as wavefront reconstructors. The recurrent neural network studied is the Hopfield...input features are just the wavefront sensor slope outputs. Both artificial neural networks use their inputs to calculate deformable mirror actuator commands. The effects of training are examined.
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.
Narayanan, Arun; Wang, DeLiang
2015-01-01
Although deep neural network (DNN) acoustic models are known to be inherently noise robust, especially with matched training and testing data, the use of speech separation as a frontend and for deriving alternative feature representations has been shown to improve performance in challenging environments. We first present a supervised speech separation system that significantly improves automatic speech recognition (ASR) performance in realistic noise conditions. The system performs separation via ratio time-frequency masking; the ideal ratio mask (IRM) is estimated using DNNs. We then propose a framework that unifies separation and acoustic modeling via joint adaptive training. Since the modules for acoustic modeling and speech separation are implemented using DNNs, unification is done by introducing additional hidden layers with fixed weights and appropriate network architecture. On the CHiME-2 medium-large vocabulary ASR task, and with log mel spectral features as input to the acoustic model, an independently trained ratio masking frontend improves word error rates by 10.9% (relative) compared to the noisy baseline. In comparison, the jointly trained system improves performance by 14.4%. We also experiment with alternative feature representations to augment the standard log mel features, like the noise and speech estimates obtained from the separation module, and the standard feature set used for IRM estimation. Our best system obtains a word error rate of 15.4% (absolute), an improvement of 4.6 percentage points over the next best result on this corpus. PMID:26973851
Neural self-adapting architecture for video-on-radio devices
NASA Astrophysics Data System (ADS)
Basti, Gianfranco; Perrone, Antonio L.
2002-03-01
In this paper we have sketched some technical details of an FM sub-carrier technology called Multi Purpose Radio Communication Channel (MPRC). This technology delivers actually data at maximum data rate of around 40 kbs using a proprietary codec algorithm: Subsidiary Communication Channel (SCC). A core device of this codec algorithm is a DWT compressor with a proprietary pre-processing, constituted by a neural self-adapting filter, the Dynamic Perceptron Algorithm (DPA), able to detect edges and to extract objects from the moving images flow, so to optimize the overall compression rate and the image quality. As a result it is possible to obtain video transmission in QCIF format at roughly 8/12 fps using 35 kHz of the 100 kHz available for a commercial FM radio station in Europe. This allows transmitting video on FM radio together with the usual radio broadcasting. On the contrary, if we use all the available 100 kHz., we obtain, after the charge related to the error protocol, a channel for compressed video transmission of about 113 kbit, allowing high quality 640x480 (zoomed or not zoomed) video images.
Measures of complexity in neural spike-trains of the slowly adapting stretch receptor organs.
Jiménez-Montaño, M A; Penagos, H; Hernández Torres, A; Diez-Martínez, O
2000-01-01
Discrete sequence analysis methods were applied to study spike-trains generated by the isolated neuron of the slowly adapting stretch receptor organ. Calculation of the algorithmic complexity and block entropies of digitized individual spike-train forms allowed us to distinguish different classes of neural behavior. While some spike-trains exhibited significant structure, others displayed diverse degrees of randomness. The sequences recorded during the stimulated portions of the intermittent and walk-through forms, differed considerably from their randomly shuffled surrogates. Informational and grammar complexity measures (in two, four and eight-letter alphabets), tell us things about the structure of spike-trains that are not obtained with conventional spike analysis. Comparison of the conditional entropies for the digitized signals showed that the method distinguishes between different stimulated conditions. Additionally, comparison of the different stimulated conditions with their corresponding surrogates showed that, both, conditional entropies and complexities were significantly different for the two groups. Although the original and the randomly shuffled sequences had the same distribution and average firing rate, their complexity values were different. The results obtained with both measures of sequence structure were quite consistent.
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.
Walsh, Matthew M.; Anderson, John R.
2012-01-01
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. PMID:22683741
Indoor location system based on discriminant-adaptive neural network in IEEE 802.11 environments.
Fang, Shih-Hau; Lin, Tsung-Nan
2008-11-01
This brief paper presents a novel localization algorithm, named discriminant-adaptive neural network (DANN), which takes the received signal strength (RSS) from the access points (APs) as inputs to infer the client position in the wireless local area network (LAN) environment. We extract the useful information into discriminative components (DCs) for network learning. The nonlinear relationship between RSS and the position is then accurately constructed by incrementally inserting the DCs and recursively updating the weightings in the network until no further improvement is required. Our localization system is developed in a real-world wireless LAN WLAN environment, where the realistic RSS measurement is collected. We implement the traditional approaches on the same test bed, including weighted kappa-nearest neighbor (WKNN), maximum likelihood (ML), and multilayer perceptron (MLP), and compare the results. The experimental results indicate that the proposed algorithm is much higher in accuracy compared with other examined techniques. The improvement can be attributed to that only the useful information is efficiently extracted for positioning while the redundant information is regarded as noise and discarded. Finally, the analysis shows that our network intelligently accomplishes learning while the inserted DCs provide sufficient information.
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%.
NASA Technical Reports Server (NTRS)
Balas, Mark; Kaufman, Howard; Wen, John
1984-01-01
The topics are presented in view graph form and include the following: an adaptive model following control; adaptive control of a distributed parameter system (DPS) with a finite-dimensional controller; a direct adaptive controller; a closed-loop adaptively controlled DPS; Lyapunov stability; the asymptotic stability of the closed loop; and model control of a simply supported beam.
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
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)
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.
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.
Jahandideh, Sepideh; Jahandideh, Samad; Asadabadi, Ebrahim Barzegari; Askarian, Mehrdad; Movahedi, Mohammad Mehdi; Hosseini, Somayyeh; Jahandideh, Mina
2009-11-01
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(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(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.
NASA Technical Reports Server (NTRS)
Yu, Xiaolong; Lewis, Edwin R.
1989-01-01
It is shown that noise can be an important element in the translation of neuronal generator potentials (summed inputs) to neuronal spike trains (outputs), creating or expanding a range of amplitudes over which the spike rate is proportional to the generator potential amplitude. Noise converts the basically nonlinear operation of a spike initiator into a nearly linear modulation process. This linearization effect of noise is examined in a simple intuitive model of a static threshold and in a more realistic computer simulation of spike initiator based on the Hodgkin-Huxley (HH) model. The results are qualitatively similar; in each case larger noise amplitude results in a larger range of nearly linear modulation. The computer simulation of the HH model with noise shows linear and nonlinear features that were earlier observed in spike data obtained from the VIIIth nerve of the bullfrog. This suggests that these features can be explained in terms of spike initiator properties, and it also suggests that the HH model may be useful for representing basic spike initiator properties in vertebrates.
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.
2014-11-01
into more-realistic multitasking environments. Behind the work are basic questions about the utility of rapid serial visual presentation (RSVP) and... multitasking simulator with integrated real-time electroencephalogram (EEG) processing, RSVP performance was measured. Figure 2a shows the display for the...classification of their neural signals, all within the multitasking simulation environment. These studies and the results are described in the following
Wu, Jingheng; Mei, Juan; Wen, Sixiang; Liao, Siyan; Chen, Jincan; Shen, Yong
2010-07-30
Based on the quantitative structure-activity relationships (QSARs) models developed by artificial neural networks (ANNs), genetic algorithm (GA) was used in the variable-selection approach with molecule descriptors and helped to improve the back-propagation training algorithm as well. The cross validation techniques of leave-one-out investigated the validity of the generated ANN model and preferable variable combinations derived in the GAs. A self-adaptive GA-ANN model was successfully established by using a new estimate function for avoiding over-fitting phenomenon in ANN training. Compared with the variables selected in two recent QSAR studies that were based on stepwise multiple linear regression (MLR) models, the variables selected in self-adaptive GA-ANN model are superior in constructing ANN model, as they revealed a higher cross validation (CV) coefficient (Q(2)) and a lower root mean square deviation both in the established model and biological activity prediction. The introduced methods for validation, including leave-multiple-out, Y-randomization, and external validation, proved the superiority of the established GA-ANN models over MLR models in both stability and predictive power. Self-adaptive GA-ANN showed us a prospect of improving QSAR model.
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.
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.
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.
Lin, Chuan-Kai; Wang, Sheng-De
2004-11-01
A new autopilot design for bank-to-turn (BTT) missiles is presented. In the design of autopilot, a ridge Gaussian neural network with local learning capability and fewer tuning parameters than Gaussian neural networks is proposed to model the controlled nonlinear systems. We prove that the proposed ridge Gaussian neural network, which can be a universal approximator, equals the expansions of rotated and scaled Gaussian functions. Although ridge Gaussian neural networks can approximate the nonlinear and complex systems accurately, the small approximation errors may affect the tracking performance significantly. Therefore, by employing the Hinfinity control theory, it is easy to attenuate the effects of the approximation errors of the ridge Gaussian neural networks to a prescribed level. Computer simulation results confirm the effectiveness of the proposed ridge Gaussian neural networks-based autopilot with Hinfinity stabilization.
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
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.
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. PMID:27199722
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.
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.
Wen, Yuntong; Ren, Xuemei
2011-10-01
This paper investigates a neural network (NN) state observer-based adaptive control for a class of time-varying delays nonlinear systems with unknown control direction. An adaptive neural memoryless observer, in which the knowledge of time-delay is not used, is designed to estimate the system states. Furthermore, by applying the property of the function tanh(2)(ϑ/ε)/ϑ (the function can be defined at ϑ = 0) and introducing a novel type appropriate Lyapunov-Krasovskii functional, an adaptive output feedback controller is constructed via backstepping method which can efficiently avoid the problem of controller singularity and compensate for the time-delay. It is highly proven that the closed-loop systems controller designed by the NN-basis function property, new kind parameter adaptive law and Nussbaum function in detecting the control direction is able to guarantee the semi-global uniform ultimate boundedness of all signals and the tracking error can converge to a small neighborhood of zero. The characteristic of the proposed approach is that it relaxes any restrictive assumptions of Lipschitz condition for the unknown nonlinear continuous functions. And the proposed scheme is suitable for the systems with mismatching conditions and unmeasurable states. Finally, two simulation examples are given to illustrate the effectiveness and applicability of the proposed approach.
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.
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.
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)
Kim, G.; Singh, R.
1995-01-01
Passive hydraulic mounts exhibit excitation frequency variant and deflection amplitude sensitive stiffness and damping properties. Such non-linear dynamic characteristics are examined by using analytical and experimental methods, both at the device level and within the context of a simplified vehicle model. A new lumped parameter non-linear mathematical model of the hydraulic mount is developed by simulating its decoupler switching mechanism and inertia track dynamics. The low frequency performance features and limitations of several passive mounts are made clear through the non-linear vehicle model simulation and comparable laboratory vibration tests. The high frequency performance problems of the passive hydraulic mount are identified by applying the quasi-linear analysis method. Based on these results, a new adaptive mount system is developed which exhibits broad bandwidth performance features up to 250 Hz. It implements an on-off damping control mode by using engine intake manifold vacuum and a microprocessor based solenoid valve controller. A laboratory bench set-up has already demonstrated its operational feasibility. Through analytical methods, it is observed that our adaptive mount provides superior dynamic performance to passive engine mounts and comparable performance to a small scale active mount over a wide frequency range, given the engine mounting resonance control, shock absorption and vibration isolation performance requirements. Although technical prospects of the proposed adaptive system appear promising, the in situperformance needs to be evaluated.
Carrillo, Snaider; Harkin, Jim; McDaid, Liam; Pande, Sandeep; Cawley, Seamus; McGinley, Brian; Morgan, Fearghal
2012-09-01
The brain is highly efficient in how it processes information and tolerates faults. Arguably, the basic processing units are neurons and synapses that are interconnected in a complex pattern. Computer scientists and engineers aim to harness this efficiency and build artificial neural systems that can emulate the key information processing principles of the brain. However, existing approaches cannot provide the dense interconnect for the billions of neurons and synapses that are required. Recently a reconfigurable and biologically inspired paradigm based on network-on-chip (NoC) and spiking neural networks (SNNs) has been proposed as a new method of realising an efficient, robust computing platform. However, the use of the NoC as an interconnection fabric for large-scale SNNs demands a good trade-off between scalability, throughput, neuron/synapse ratio and power consumption. This paper presents a novel traffic-aware, adaptive NoC router, which forms part of a proposed embedded mixed-signal SNN architecture called EMBRACE (EMulating Biologically-inspiRed ArChitectures in hardwarE). The proposed adaptive NoC router provides the inter-neuron connectivity for EMBRACE, maintaining router communication and avoiding dropped router packets by adapting to router traffic congestion. Results are presented on throughput, power and area performance analysis of the adaptive router using a 90 nm CMOS technology which outperforms existing NoCs in this domain. The adaptive behaviour of the router is also verified on a Stratix II FPGA implementation of a 4 × 2 router array with real-time traffic congestion. The presented results demonstrate the feasibility of using the proposed adaptive NoC router within the EMBRACE architecture to realise large-scale SNNs on embedded hardware.
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.
Bulea, Thomas C.; Stanley, Christopher J.; Damiano, Diane L.
2017-01-01
Motor adaptation, or alteration of neural control in response to a perturbation, is a potential mechanism to facilitate motor learning for rehabilitation. Central nervous system deficits are known to affect locomotor adaptation; yet we demonstrated that similar to adults following stroke, children with unilateral brain injuries can adapt step length in response to unilateral leg weighting. Here, we extend our analysis to explore kinematic strategies underlying step length adaptation and utilize dynamical systems approaches to elucidate how neural control may differ in those with hemiplegic CP across legs and compared to typically developing controls. Ten participants with hemiplegic CP and ten age-matched controls participated in this study. Knee and hip joint kinematics were analyzed during unilateral weighting of each leg in treadmill walking to assess adaptation and presence and persistence of after-effects. Peak joint angle displacement was used to represent changes in joint angles during walking. We examined baseline and task-specific variability and local dynamic stability to evaluate neuromuscular control across groups and legs. In contrast to controls, children with unilateral CP had asymmetries in joint angle variability and local dynamic stability at baseline, showing increased variability and reduced stability in the dominant limb. Kinematic variability increased and local stability decreased during weighting of ipsilateral and contralateral limbs in both groups compared to baseline. After weight removal both measures returned to baseline. Analogous to the temporal-spatial results, children with unilateral CP demonstrated similar capability as controls to adapt kinematics to unilateral leg weighting, however, the group with CP differed across sides after weight removal with dominant limb after-effects fading more quickly than in controls. The change in kinematics did not completely return to baseline in the non-dominant limb of the CP group, producing a
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.
NASA Astrophysics Data System (ADS)
Elkoteshy, Yasser; Jiao, L. C.; Chen, Weisheng
2014-05-01
In this work, the adaptive backstepping neural control technique is proposed for a class of uncertain multi-input multi-output nonlinear systems in block-triangular form with the ultimate tracking accuracy assumed to be known a priori. The stability analysis of the closed-loop control system is derived based on Barbalat's Lemma instead of Lyapunov stability theory. Semi-global uniform ultimate boundedness of all the signals in the closed-loop system is achieved and after a sufficiently large interval of time, the outputs of the system are proven to converge to the predefined value. A single hidden layer feed-forward neural network based on the extreme learning machine is used in this work to approximate the unknown nonlinear functions in the control laws. Two simulation examples, including a mathematical one and a practical one, are given to verify the effectiveness of the proposed controller and its superiority over the existing techniques.
Optimal linear compression under unreliable representation and robust PCA neural models.
Diamantaras, K I; Hornik, K; Strintzis, M G
1999-01-01
In a typical linear data compression system the representation variables resulting from the coding operation are assumed totally reliable and therefore the solution in the mean-squared-error sense is an orthogonal projector to the so-called principal component subspace. When the representation variables are contaminated by additive noise which is uncorrelated with the signal, the problem is called noisy principal component analysis (NPCA) and the optimal MSE solution is not a trivial extension of PCA. We first show that the problem is not well defined unless we impose explicit or implicit constraints on either the coding or the decoding operator. Second, orthogonality is not a property of the optimal solution under most constraints. Third, the signal components may or may not be reconstructed depending on the noise level. As the noise power increases, we observe rank reduction in the optimal solution under most reasonable constraints. In these cases it appears that it is preferable to omit the smaller signal components rather than attempting to reconstruct them. This phenomenon has similarities with classical information theoretical results, notably the water-filling analogy, found in parallel additive Gaussian noise channels. Finally, we show that standard Hebbian-type PCA learning algorithms are not optimally robust to noise, and propose a new Hebbian-type learning algorithm which is optimally robust in the NPCA sense.
2012-07-01
2.1 SAIC Applied and Transitional Research In contrast to the basic research developed at ICB, SAIC’s applied research and neurotechnology is based...application, a much higher level of performance is required. Under the Defense Advanced Research Project Agency’s (DARPA)’s Neurotechnology for...Biotechnologies LDA linear discriminant analysis MGV manned ground vehicles NIA Neurotechnology for Intelligence Analysts NTG non-target P3 P300
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.
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.
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.
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.
NASA Astrophysics Data System (ADS)
Ebrahimi, Hadi; Rajaee, Taher
2017-01-01
Simulation of groundwater level (GWL) fluctuations is an important task in management of groundwater resources. In this study, the effect of wavelet analysis on the training of the artificial neural network (ANN), multi linear regression (MLR) and support vector regression (SVR) approaches was investigated, and the ANN, MLR and SVR along with the wavelet-ANN (WNN), wavelet-MLR (WLR) and wavelet-SVR (WSVR) models were compared in simulating one-month-ahead of GWL. The only variable used to develop the models was the monthly GWL data recorded over a period of 11 years from two wells in the Qom plain, Iran. The results showed that decomposing GWL time series into several sub-time series, extremely improved the training of the models. For both wells 1 and 2, the Meyer and Db5 wavelets produced better results compared to the other wavelets; which indicated wavelet types had similar behavior in similar case studies. The optimal number of delays was 6 months, which seems to be due to natural phenomena. The best WNN model, using Meyer mother wavelet with two decomposition levels, simulated one-month-ahead with RMSE values being equal to 0.069 m and 0.154 m for wells 1 and 2, respectively. The RMSE values for the WLR model were 0.058 m and 0.111 m, and for WSVR model were 0.136 m and 0.060 m for wells 1 and 2, respectively.
NASA Astrophysics Data System (ADS)
Cheng, Chao-Jung; Cheng, Chi-Bin
2013-10-01
Chaotic dynamics provide a fast and simple means to create an excellent image cryptosystem, because it is extremely sensitive to initial conditions and system parameters, pseudorandomness, and non-periodicity. However, most chaos-based image encryption schemes are symmetric cryptographic techniques, which have been proven to be more vulnerable, compared to an asymmetric cryptosystem. This paper develops an asymmetric image cryptosystem, based on the adaptive synchronization of two different chaotic systems, namely a unified chaotic system and a cellular neural network. An adaptive controller with parameter update laws is formulated, using the Lyapunov stability theory, to asymptotically synchronize the two chaotic systems. The synchronization controller is embedded in the image cryptosystem and generates a pair of asymmetric keys, for image encryption and decryption. Using numerical simulations, three sets of experiments are conducted to evaluate the feasibility and reliability of the proposed chaos-based image cryptosystem.
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
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 (12-16years) 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.
Dewhirst, Oliver P; Angarita-Jaimes, Natalia; Simpson, David M; Allen, Robert; Newland, Philip L
2013-02-01
Nonlinear type system identification models coupled with white noise stimulation provide an experimentally convenient and quick way to investigate the often complex and nonlinear interactions between the mechanical and neural elements of reflex limb control systems. Previous steady state analysis has allowed the neurons in such systems to be categorised by their sensitivity to position, velocity or acceleration (dynamics) and has improved our understanding of network function. These neurons, however, are known to adapt their output amplitude or spike firing rate during repetitive stimulation and this transient response may be more important than the steady state response for reflex control. In the current study previously used system identification methods are developed and applied to investigate both steady state and transient dynamic and nonlinear changes in the neural circuit responsible for controlling reflex movements of the locust hind limbs. Through the use of a parsimonious model structure and Monte Carlo simulations we conclude that key system dynamics remain relatively unchanged during repetitive stimulation while output amplitude adaptation is occurring. Whilst some evidence of a significant change was found in parts of the systems nonlinear response, the effect was small and probably of little physiological relevance. Analysis using biologically more realistic stimulation reinforces this conclusion.
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.
Jing, Luyang; Wang, Taiyong; Zhao, Ming; Wang, Peng
2017-01-01
A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment. PMID:28230767
Jing, Luyang; Wang, Taiyong; Zhao, Ming; Wang, Peng
2017-02-21
A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment.
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
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.
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.
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.
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.
NASA Astrophysics Data System (ADS)
Luo, Shaohua; Wu, Songli; Gao, Ruizhen
2015-07-01
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.
Luo, Shaohua; Wu, Songli; Gao, Ruizhen
2015-07-01
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.
An Adaptive Neural Mechanism for Acoustic Motion Perception with Varying Sparsity
Shaikh, Danish; Manoonpong, Poramate
2017-01-01
Biological motion-sensitive neural circuits are quite adept in perceiving the relative motion of a relevant stimulus. Motion perception is a fundamental ability in neural sensory processing and crucial in target tracking tasks. Tracking a stimulus entails the ability to perceive its motion, i.e., extracting information about its direction and velocity. Here we focus on auditory motion perception of sound stimuli, which is poorly understood as compared to its visual counterpart. In earlier work we have developed a bio-inspired neural learning mechanism for acoustic motion perception. The mechanism extracts directional information via a model of the peripheral auditory system of lizards. The mechanism uses only this directional information obtained via specific motor behaviour to learn the angular velocity of unoccluded sound stimuli in motion. In nature however the stimulus being tracked may be occluded by artefacts in the environment, such as an escaping prey momentarily disappearing behind a cover of trees. This article extends the earlier work by presenting a comparative investigation of auditory motion perception for unoccluded and occluded tonal sound stimuli with a frequency of 2.2 kHz in both simulation and practice. Three instances of each stimulus are employed, differing in their movement velocities–0.5°/time step, 1.0°/time step and 1.5°/time step. To validate the approach in practice, we implement the proposed neural mechanism on a wheeled mobile robot and evaluate its performance in auditory tracking. PMID:28337137
An Adaptive Neural Mechanism for Acoustic Motion Perception with Varying Sparsity.
Shaikh, Danish; Manoonpong, Poramate
2017-01-01
Biological motion-sensitive neural circuits are quite adept in perceiving the relative motion of a relevant stimulus. Motion perception is a fundamental ability in neural sensory processing and crucial in target tracking tasks. Tracking a stimulus entails the ability to perceive its motion, i.e., extracting information about its direction and velocity. Here we focus on auditory motion perception of sound stimuli, which is poorly understood as compared to its visual counterpart. In earlier work we have developed a bio-inspired neural learning mechanism for acoustic motion perception. The mechanism extracts directional information via a model of the peripheral auditory system of lizards. The mechanism uses only this directional information obtained via specific motor behaviour to learn the angular velocity of unoccluded sound stimuli in motion. In nature however the stimulus being tracked may be occluded by artefacts in the environment, such as an escaping prey momentarily disappearing behind a cover of trees. This article extends the earlier work by presenting a comparative investigation of auditory motion perception for unoccluded and occluded tonal sound stimuli with a frequency of 2.2 kHz in both simulation and practice. Three instances of each stimulus are employed, differing in their movement velocities-0.5°/time step, 1.0°/time step and 1.5°/time step. To validate the approach in practice, we implement the proposed neural mechanism on a wheeled mobile robot and evaluate its performance in auditory tracking.
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.
Error-based adaptive non-linear control and regions of feasibility
NASA Technical Reports Server (NTRS)
Teel, Andrew R.
1992-01-01
The nonlinear adaptive algorithm of Kanellakopoulos et al. (1991) was modified to produce an error-based algorithm. This permits global stabilizability for a large subset of pure-feedback nonlinear systems. The algorithm was demonstrated on the single-input stabilization problem, but extends easily to the multiple input tracking problems.
Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems
2003-06-01
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...Fault identification, isolation. and accommodation 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
Mixed linear model approach adapted for genome-wide association studies
Technology Transfer Automated Retrieval System (TEKTRAN)
Mixed linear model (MLM) methods have proven useful in controlling for population structure and relatedness within genome-wide association studies. However, MLM-based methods can be computationally challenging for large datasets. We report a compression approach, called ‘compressed MLM,’ that decrea...
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.
NASA Astrophysics Data System (ADS)
Qin, Chunbin; Zhang, Huaguang; Luo, Yanhong
2014-05-01
In this paper, a novel theoretic formulation based on adaptive dynamic programming (ADP) is developed to solve online the optimal tracking problem of the continuous-time linear system with unknown dynamics. First, the original system dynamics and the reference trajectory dynamics are transformed into an augmented system. Then, under the same performance index with the original system dynamics, an augmented algebraic Riccati equation is derived. Furthermore, the solutions for the optimal control problem of the augmented system are proven to be equal to the standard solutions for the optimal tracking problem of the original system dynamics. Moreover, a new online algorithm based on the ADP technique is presented to solve the optimal tracking problem of the linear system with unknown system dynamics. Finally, simulation results are given to verify the effectiveness of the theoretic results.
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.
Adapting for endocytosis: roles for endocytic sorting adaptors in directing neural development
Yap, Chan Choo; Winckler, Bettina
2015-01-01
Proper cortical development depends on the orchestrated actions of a multitude of guidance receptors and adhesion molecules and their downstream signaling. The levels of these receptors on the surface and their precise locations can greatly affect guidance outcomes. Trafficking of receptors to a particular surface locale and removal by endocytosis thus feed crucially into the final guidance outcomes. In addition, endocytosis of receptors can affect downstream signaling (both quantitatively and qualitatively) and regulated endocytosis of guidance receptors is thus an important component of ensuring proper neural development. We will discuss the cell biology of regulated endocytosis and the impact on neural development. We focus our discussion on endocytic accessory proteins (EAPs) (such as numb and disabled) and how they regulate endocytosis and subsequent post-endocytic trafficking of their cognate receptors (such as Notch, TrkB, β-APP, VLDLR, and ApoER2). PMID:25904845
Adapting for endocytosis: roles for endocytic sorting adaptors in directing neural development.
Yap, Chan Choo; Winckler, Bettina
2015-01-01
Proper cortical development depends on the orchestrated actions of a multitude of guidance receptors and adhesion molecules and their downstream signaling. The levels of these receptors on the surface and their precise locations can greatly affect guidance outcomes. Trafficking of receptors to a particular surface locale and removal by endocytosis thus feed crucially into the final guidance outcomes. In addition, endocytosis of receptors can affect downstream signaling (both quantitatively and qualitatively) and regulated endocytosis of guidance receptors is thus an important component of ensuring proper neural development. We will discuss the cell biology of regulated endocytosis and the impact on neural development. We focus our discussion on endocytic accessory proteins (EAPs) (such as numb and disabled) and how they regulate endocytosis and subsequent post-endocytic trafficking of their cognate receptors (such as Notch, TrkB, β-APP, VLDLR, and ApoER2).
A mixed-signal implementation of a polychronous spiking neural network with delay adaptation
Wang, Runchun M.; Hamilton, Tara J.; Tapson, Jonathan C.; van Schaik, André
2014-01-01
We present a mixed-signal implementation of a re-configurable polychronous spiking neural network capable of storing and recalling spatio-temporal patterns. The proposed neural network contains one neuron array and one axon array. Spike Timing Dependent Delay Plasticity is used to fine-tune delays and add dynamics to the network. In our mixed-signal implementation, the neurons and axons have been implemented as both analog and digital circuits. The system thus consists of one FPGA, containing the digital neuron array and the digital axon array, and one analog IC containing the analog neuron array and the analog axon array. The system can be easily configured to use different combinations of each. We present and discuss the experimental results of all combinations of the analog and digital axon arrays and the analog and digital neuron arrays. The test results show that the proposed neural network is capable of successfully recalling more than 85% of stored patterns using both analog and digital circuits. PMID:24672422
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.
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.
Norman, Sharon E; Butera, Robert J; Canavier, Carmen C
2016-09-01
Oscillatory neurons integrate their synaptic inputs in fundamentally different ways than normally quiescent neurons. We show that the oscillation period of invertebrate endogenous pacemaker neurons wanders, producing random fluctuations in the interspike intervals (ISI) on a time scale of seconds to minutes, which decorrelates pairs of neurons in hybrid circuits constructed using the dynamic clamp. The autocorrelation of the ISI sequence remained high for many ISIs, but the autocorrelation of the ΔISI series had on average a single nonzero value, which was negative at a lag of one interval. We reproduced these results using a simple integrate and fire (IF) model with a stochastic population of channels carrying an adaptation current with a stochastic component that was integrated with a slow time scale, suggesting that a similar population of channels underlies the observed wander in the period. Using autoregressive integrated moving average (ARIMA) models, we found that a single integrator and a single moving average with a negative coefficient could simulate both the experimental data and the IF model. Feeding white noise into an integrator with a slow time constant is sufficient to produce the autocorrelation structure of the ISI series. Moreover, the moving average clearly accounted for the autocorrelation structure of the ΔISI series and is biophysically implemented in the IF model using slow stochastic adaptation. The observed autocorrelation structure may be a neural signature of slow stochastic adaptation, and wander generated in this manner may be a general mechanism for limiting episodes of synchronized activity in the nervous system.
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.
NASA Astrophysics Data System (ADS)
Karimi, Gholamreza; Banitalebi, Roza; Babaei Sedaghat, Sedigheh
2013-07-01
In this article, the small-signal equivalent circuit model of SiGe:C heterojunction bipolar transistors (HBTs) has directly been extracted from S-parameter data. Moreover, in this article, we present a new modelling approach using ANFIS (adaptive neuro-fuzzy inference system), which in general has a high degree of accuracy, simplicity and novelty (independent approach). Then measured and model-calculated data show an excellent agreement with less than 1.68 × 10-5% discrepancy in the frequency range of higher than 300 GHz over a wide range of bias points in ANFIS. The results show ANFIS model is better than ANN (artificial neural network) for redeveloping the model and increasing the input parameters.
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.
Jaffe-Dax, Sagi; Frenkel, Or; Ahissar, Merav
2017-01-01
Dyslexia is a prevalent reading disability whose underlying mechanisms are still disputed. We studied the neural mechanisms underlying dyslexia using a simple frequency-discrimination task. Though participants were asked to compare the two tones in each trial, implicit memory of previous trials affected their responses. We hypothesized that implicit memory decays faster among dyslexics. We tested this by increasing the temporal intervals between consecutive trials, and by measuring the behavioral impact and ERP responses from the auditory cortex. Dyslexics showed a faster decay of implicit memory effects on both measures, with similar time constants. Finally, faster decay of implicit memory also characterized the impact of sound regularities in benefitting dyslexics' oral reading rate. Their benefit decreased faster as a function of the time interval from the previous reading of the same non-word. We propose that dyslexics’ shorter neural adaptation paradoxically accounts for their longer reading times, since it reduces their temporal window of integration of past stimuli, resulting in noisier and less reliable predictions for both simple and complex stimuli. Less reliable predictions limit their acquisition of reading expertise. DOI: http://dx.doi.org/10.7554/eLife.20557.001 PMID:28115055
Powder, Kara E; Cousin, Hélène; McLinden, Gretchen P; Craig Albertson, R
2014-12-01
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.
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.
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
Wai, Rong-Jong; Yang, Zhi-Wei
2008-10-01
This paper focuses on the development of adaptive fuzzy neural network control (AFNNC), including indirect and direct frameworks for an n-link robot manipulator, to achieve high-precision position tracking. In general, it is difficult to adopt a model-based design to achieve this control objective due to the uncertainties in practical applications, such as friction forces, external disturbances, and parameter variations. In order to cope with this problem, an indirect AFNNC (IAFNNC) scheme and a direct AFNNC (DAFNNC) strategy are investigated without the requirement of prior system information. In these model-free control topologies, a continuous-time Takagi-Sugeno (T-S) dynamic fuzzy model with online learning ability is constructed to represent the system dynamics of an n-link robot manipulator. In the IAFNNC, an FNN estimator is designed to tune the nonlinear dynamic function vector in fuzzy local models, and then, the estimative vector is used to indirectly develop a stable IAFNNC law. In the DAFNNC, an FNN controller is directly designed to imitate a predetermined model-based stabilizing control law, and then, the stable control performance can be achieved by only using joint position information. All the IAFNNC and DAFNNC laws and the corresponding adaptive tuning algorithms for FNN weights are established in the sense of Lyapunov stability analyses to ensure the stable control performance. Numerical simulations and experimental results of a two-link robot manipulator actuated by dc servomotors are given to verify the effectiveness and robustness of the proposed methodologies. In addition, the superiority of the proposed control schemes is indicated in comparison with proportional-differential control, fuzzy-model-based control, T-S-type FNN control, and robust neural fuzzy network control systems.
Uppal, Neha; Foxe, John J.; Butler, John S.; Acluche, Frantzy
2016-01-01
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
Asynchronous BCI and local neural classifiers: an overview of the Adaptive Brain Interface project.
Millán, José del R; Mouriño, Josep
2003-06-01
In this communication, we give an overview of our work on an asynchronous brain-computer interface (where the subject makes self-paced decisions on when to switch from one mental task to the next) that responds every 0.5 s. A local neural classifier tries to recognize three different mental tasks; it may also respond "unknown" for uncertain samples as the classifier has incorporated statistical rejection criteria. We report our experience with 15 subjects. We also briefly describe two brain-actuated applications we have developed: a virtual keyboard and a mobile robot (emulating a motorized wheelchair).
Ermentrout, B; Pascal, M; Gutkin, B
2001-06-01
There are several different biophysical mechanisms for spike frequency adaptation observed in recordings from cortical neurons. The two most commonly used in modeling studies are a calcium-dependent potassium current I(ahp) and a slow voltage-dependent potassium current, I(m). We show that both of these have strong effects on the synchronization properties of excitatorily coupled neurons. Furthermore, we show that the reasons for these effects are different. We show through an analysis of some standard models, that the M-current adaptation alters the mechanism for repetitive firing, while the afterhyperpolarization adaptation works via shunting the incoming synapses. This latter mechanism applies with a network that has recurrent inhibition. The shunting behavior is captured in a simple two-variable reduced model that arises near certain types of bifurcations. A one-dimensional map is derived from the simplified model.
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.
Adaptive vision-based control of an unmanned aerial vehicle without linear velocity measurements.
Jabbari Asl, Hamed; Yoon, Jungwon
2016-11-01
In this paper, an image-based visual servo controller is designed for an unmanned aerial vehicle. The main objective is to use flow of image features as the velocity cue to compensate for the low quality of linear velocity information obtained from accelerometers. Nonlinear observers are designed to estimate this flow. The proposed controller is bounded, which can help to keep the target points in the field of view of the camera. The main advantages over the previous full dynamic observer-based methods are that, the controller is robust with respect to unknown image depth, and also no yaw information is required. The complete stability analysis is presented and asymptotic convergence of the error signals is guaranteed. Simulation results show the effectiveness of the proposed approach.
Performance analysis of structured gradient algorithm. [for adaptive beamforming linear arrays
NASA Technical Reports Server (NTRS)
Godara, Lal C.
1990-01-01
The structured gradient algorithm uses a structured estimate of the array correlation matrix (ACM) to estimate the gradient required for the constrained least-mean-square (LMS) algorithm. This structure reflects the structure of the exact array correlation matrix for an equispaced linear array and is obtained by spatial averaging of the elements of the noisy correlation matrix. In its standard form the LMS algorithm does not exploit the structure of the array correlation matrix. The gradient is estimated by multiplying the array output with the receiver outputs. An analysis of the two algorithms is presented to show that the covariance of the gradient estimated by the structured method is less sensitive to the look direction signal than that estimated by the standard method. The effect of the number of elements on the signal sensitivity of the two algorithms is studied.
1990-01-01
FUNDING NUMBERS PROGRAM PROJECT TASK WORK UNIT ELEMENT NO. NO. NO. ACCESSION NO 11 TITLE (Include Security Classification) NEURAL NETWORKS 12. PERSONAL...SUB-GROUP Neural Networks Optical Architectures Nonlinear Optics Adaptation 19. ABSTRACT (Continue on reverse if necessary and identify by block number...341i Y C-odes , lo iii/(iv blank) 1. INTRODUCTION Neural networks are a type of distributed processing system [1
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
A new adaptation of linear reservoir models in parallel sets to assess actual hydrological events
NASA Astrophysics Data System (ADS)
Mateo Lázaro, Jesús; Sánchez Navarro, José Ángel; García Gil, Alejandro; Edo Romero, Vanesa
2015-05-01
A methodology based on Parallel Linear Reservoir (PLR) models is presented. To carry it out has been implemented within the software SHEE (Simulation of Hydrological Extreme Events), which is a tool for the analysis of hydrological processes in catchments with the management and display of DEM and datasets. The algorithms of the models pass throughout the cells and drainage network, by means of the Watershed Traversal Algorithm (WTA) that runs the entire drainage network of a basin in both directions, upwards and downwards, which is ideal for incorporating the models of the hydrological processes of the basins into its structure. The WTA methodology is combined with another one based on models of Parallel Linear Reservoirs (PLR) whose main qualities include: (1) the models are defined by observing the recession curves of actual hydrographs, i.e., the watershed actual responses; (2) the models serve as a way to simulate the routing through the watershed and its different reservoirs; and (3) the models allow calculating the water balance, which is essential to the study of actual events in the watershed. A complete hydrometeorological event needs the combination of several models, each one of which represents a hydrological process. The PLR model is a routing model, but it also contributes to the adjustment of other models (e.g., the rainfall-runoff model) and allows establishing a distributed model of effective rainfall for an actual event occurred in a basin. On the other hand, the proposed formulation solves the rainfall distribution problem for each deposit in the reservoir combination models.
Yoo, Yun Joo; Sun, Lei; Poirier, Julia G.; Paterson, Andrew D.
2016-01-01
ABSTRACT By jointly analyzing multiple variants within a gene, instead of one at a time, gene‐based multiple regression can improve power, robustness, and interpretation in genetic association analysis. We investigate multiple linear combination (MLC) test statistics for analysis of common variants under realistic trait models with linkage disequilibrium (LD) based on HapMap Asian haplotypes. MLC is a directional test that exploits LD structure in a gene to construct clusters of closely correlated variants recoded such that the majority of pairwise correlations are positive. It combines variant effects within the same cluster linearly, and aggregates cluster‐specific effects in a quadratic sum of squares and cross‐products, producing a test statistic with reduced degrees of freedom (df) equal to the number of clusters. By simulation studies of 1000 genes from across the genome, we demonstrate that MLC is a well‐powered and robust choice among existing methods across a broad range of gene structures. Compared to minimum P‐value, variance‐component, and principal‐component methods, the mean power of MLC is never much lower than that of other methods, and can be higher, particularly with multiple causal variants. Moreover, the variation in gene‐specific MLC test size and power across 1000 genes is less than that of other methods, suggesting it is a complementary approach for discovery in genome‐wide analysis. The cluster construction of the MLC test statistics helps reveal within‐gene LD structure, allowing interpretation of clustered variants as haplotypic effects, while multiple regression helps to distinguish direct and indirect associations. PMID:27885705
Nie, Xiaobing; Zheng, Wei Xing; Cao, Jinde
2016-12-01
In this paper, the coexistence and dynamical behaviors of multiple equilibrium points are discussed for a class of memristive neural networks (MNNs) with unbounded time-varying delays and nonmonotonic piecewise linear activation functions. By means of the fixed point theorem, nonsmooth analysis theory and rigorous mathematical analysis, it is proven that under some conditions, such n-neuron MNNs can have 5(n) equilibrium points located in ℜ(n), and 3(n) of them are locally μ-stable. As a direct application, some criteria are also obtained on the multiple exponential stability, multiple power stability, multiple log-stability and multiple log-log-stability. All these results reveal that the addressed neural networks with activation functions introduced in this paper can generate greater storage capacity than the ones with Mexican-hat-type activation function. Numerical simulations are presented to substantiate the theoretical results.
Baldwin, Carryl L; Penaranda, B N
2012-01-02
Adaptive training using neurophysiological measures requires efficient classification of mental workload in real time as a learner encounters new and increasingly difficult levels of tasks. Previous investigations have shown that artificial neural networks (ANNs) can accurately classify workload, but only when trained on neurophysiological exemplars from experienced operators on specific tasks. The present study examined classification accuracies for ANNs trained on electroencephalographic (EEG) activity recorded while participants performed the same (within task) and different (cross) tasks for short periods of time with little or no prior exposure to the tasks. Participants performed three working memory tasks at two difficulty levels with order of task and difficulty level counterbalanced. Within-task classification accuracies were high when ANNs were trained on exemplars from the same task or a set containing the to-be-classified task, (M=87.1% and 85.3%, respectively). Cross-task classification accuracies were significantly lower (average 44.8%) indicating consistent systematic misclassification for certain tasks in some individuals. Results are discussed in terms of their implications for developing neurophysiologically driven adaptive training platforms.
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".
Towler, John; Gosling, Angela; Duchaine, Bradley; Eimer, Martin
2016-03-01
Individuals with developmental prosopagnosia (DP) have a severe difficulty recognizing the faces of known individuals in the absence of any history of neurological damage. These recognition problems may be linked to selective deficits in the holistic/configural processing of faces. We used two-tone Mooney images to study the processing of faces versus non-face objects in DP when it is based on holistic information (or the facial gestalt) in the absence of obvious local cues about facial features. A rapid adaptation procedure was employed for a group of 16 DPs. Naturalistic photographs of upright faces were preceded by upright or inverted Mooney faces or by Mooney houses. DPs showed face-sensitive N170 components in response to Mooney faces versus houses, and N170 amplitude reductions for inverted as compared to upright Mooney faces. They also showed the typical pattern of N170 adaptation effects, with reduced N170 components when upright naturalistic test faces were preceded by upright Mooney faces, demonstrating that the perception of Mooney and naturalistic faces recruits shared neural populations. Our findings demonstrate that individuals with DP can utilize global information about face configurations for categorical discriminations between faces and non-face objects, and suggest that face processing deficits emerge primarily at more fine-grained higher level stages of face perception.
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.
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.
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.
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
Linder, Mats; Ranganathan, Anirudh; Brinck, Tore
2013-02-12
We present a structure-based parametrization of the Linear Interaction Energy (LIE) method and show that it allows for the prediction of absolute protein-ligand binding energies. We call the new model "Adapted" LIE (ALIE) because the α and β coefficients are defined by system-dependent descriptors and do therefore not require any empirical γ term. The best formulation attains a mean average deviation of 1.8 kcal/mol for a diverse test set and depends on only one fitted parameter. It is robust with respect to additional fitting and cross-validation. We compare this new approach with standard LIE by Åqvist and co-workers and the LIE + γSASA model (initially suggested by Jorgensen and co-workers) against in-house and external data sets and discuss their applicabilities.
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
Neural correlates of adaptive working memory training in a glycogen storage disease type-IV patient.
Lee, Kristin; Ernst, Thomas; Løhaugen, Gro; Zhang, Xin; Chang, Linda
2017-03-01
Glycogen storage disease type-IV has varied clinical presentations and subtypes. We evaluated a 38-year-old man with memory complaints, common symptoms in adult polyglucosan body disease subtype, and investigated cognitive and functional MRI changes associated with two 25-sessions of adaptive working memory training. He showed improved trained and nontrained working memory up to 6-months after the training sessions. On functional MRI, he showed increased cortical activation 1-3 months after training, but both increased and decreased activation 6-months later. Working memory training appears to be beneficial to patients with adult polyglucosan body disease, although continued training may be required to maintain improvements.
Narins, P M; Capranica, R R
1980-01-01
Male Puerto Rican treefrogs, Eleutherodactylus coqui, produce a two-note call: a 100-msec constant frequency 'Co' note, followed by a longer, upward sweeping 'Qui' note. Previous behavioral studies have shown that males respond selectively to natural and synthetic call notes of 100 msec duration, whereas preliminary results suggest that females respond preferentially to the second note in the male's call. In the present study, we first show that the basilar papilla in the inner ear is tuned differentially in males and females. Comparisons were next made between cells in the eighth nerve and midbrain torus semicircularis of firing rate vs. duration functions in order to help determine the underlying neural mechanisms responsible for the behavioral selectivity to notes of 100 msec duration. A model for detection of vocalizations of specific durations is postulated and discussed in the light of the observed calling behavior of the male as well as the response properties of a class of cells found in the torus semicircularis.
Neural-network-based adaptive UPFC for improving transient stability performance of power system.
Mishra, Sukumar
2006-03-01
This paper uses the recently proposed H(infinity)-learning method, for updating the parameter of the radial basis function neural network (RBFNN) used as a control scheme for the unified power flow controller (UPFC) to improve the transient stability performance of a multimachine power system. The RBFNN uses a single neuron architecture whose input is proportional to the difference in error and the updating of its parameters is carried via a proportional value of the error. Also, the coefficients of the difference of error, error, and auxiliary signal used for improving damping performance are depicted by a genetic algorithm. The performance of the newly designed controller is evaluated in a four-machine power system subjected to different types of disturbances. The newly designed single-neuron RBFNN-based UPFC exhibits better damping performance compared to the conventional PID as well as the extended Kalman filter (EKF) updating-based RBFNN scheme, making the unstable cases stable. Its simple architecture reduces the computational burden, thereby making it attractive for real-time implementation. Also, all the machines are being equipped with the conventional power system stabilizer (PSS) to study the coordinated effect of UPFC and PSS in the system.
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.
Brandenburg, Jason P; Docherty, David
2002-02-01
The purpose of this study was to compare the strength and neuromuscular adaptations for dynamic constant external resistance (DCER) training and dynamic accentuated external resistance (DAER) training (resistance training employing an accentuated load during eccentric actions). Male subjects active in resistance training were assigned to either a DCER training group (n = 10) or a DAER training group (n = 8) for 9 weeks. Subjects in the DCER group performed 4 sets of 10 repetitions with a load of 75% concentric 1 repetition maximum (RM). Subjects in the DAER group performed 3 sets of 10 repetitions with a concentric load of 75% of 1RM and an eccentric load of approximately 120% of concentric 1RM. Three measures reflecting adaptation of elbow flexors and extensors were recorded pretraining and posttraining: concentric 1RM, muscle cross-sectional area (CSA), and specific tension. Strength was assessed at midtraining periods. No significant changes in muscle CSA were observed in either group. Both training groups experienced significant increases in concentric 1RM and specific tension of both the elbow flexors and extensors, but compared with DCER training, DAER training produced significantly greater increases in concentric 1RM of the elbow extensors. These results suggest that, for some exercises, DAER training may be more effective than DCER training in developing strength within a 9-week training phase. However, for trained subjects, neither protocol is effective in eliciting muscle hypertrophy.
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.
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.
Métris, Aline; George, Susie M; Ropers, Delphine
2017-01-02
Addition of salt to food is one of the most ancient and most common methods of food preservation. However, little is known of how bacterial cells adapt to such conditions. We propose to use piecewise linear approximations to model the regulatory adaptation of Escherichiacoli to osmotic stress. We apply the method to eight selected genes representing the functions known to be at play during osmotic adaptation. The network is centred on the general stress response factor, sigma S, and also includes a module representing the catabolic repressor CRP-cAMP. Glutamate, potassium and supercoiling are combined to represent the intracellular regulatory signal during osmotic stress induced by salt. The output is a module where growth is represented by the concentration of stable RNAs and the transcription of the osmotic gene osmY. The time course of gene expression of transport of osmoprotectant represented by the symporter proP and of the osmY is successfully reproduced by the network. The behaviour of the rpoS mutant predicted by the model is in agreement with experimental data. We discuss the application of the model to food-borne pathogens such as Salmonella; although the genes considered have orthologs, it seems that supercoiling is not regulated in the same way. The model is limited to a few selected genes, but the regulatory interactions are numerous and span different time scales. In addition, they seem to be condition specific: the links that are important during the transition from exponential to stationary phase are not all needed during osmotic stress. This model is one of the first steps towards modelling adaptation to stress in food safety and has scope to be extended to other genes and pathways, other stresses relevant to the food industry, and food-borne pathogens. The method offers a good compromise between systems of ordinary differential equations, which would be unmanageable because of the size of the system and for which insufficient data are available
"DRY" immersion induces neural and contractile adaptations in the human triceps surae muscle.
Koryak, Yuri
2002-12-01
The effects of 7-days of simulated spaceflight, achieved with the technique of "dry" water immersion, on human triceps surae muscle function have been investigated in six subjects. After immersion, the maximal voluntary contraction (MVC) was reduced by 19% (p<0.01), and the electrically evoked (150 Hz) maximal tetanic contraction (Po) was reduced by 8% (p>0.05). The difference between Po and MVC expressed as a percentage of Po and referred to as force deficiency has also been calculated. The force deficiency increased by 44% (p<0.01) after immersion. The decrease in Po was associated with increased maximal rates of tension development (7.2%) and of tension relaxation. The twitch time-to-peak was not significantly changed, and half relaxation and total contraction time were decreased by 5% and 3%, respectively, but the twitch tension (Pt) was not significantly changed and the Pt/Po ratio was decreased by 9%. The 60-s intermittent contractions (50 Hz) decreased tetanic force to 57% (p<0.05) of initial values, but force reduction was not significantly different in the two fatigue tests: fatigue index was 36.2 +/- 5.4% vs. 38.6 +/- 2.8%, respectively (p>0.05). While identical force reduction was present in the two fatigue test it would appear that concomitant electrical failure was considerably different. Comparison of the electrical and mechanical responses alterations recorded during voluntary contractions, and in contractions evoked by electrical stimulation of the motor nerve, suggests that immersion not only modifies the peripheral processes associated with contraction, but also changes central and/or neural command of the contraction. At peripheral sites, it is proposed that the intracellular processes of contraction play a role in the contractile impairment recorded during immersion.
Peng, Zhouhua; Wang, Dan; Zhang, Hongwei; Sun, Gang
2014-08-01
This paper addresses the leader-follower synchronization problem of uncertain dynamical multiagent systems with nonlinear dynamics. Distributed adaptive synchronization controllers are proposed based on the state information of neighboring agents. The control design is developed for both undirected and directed communication topologies without requiring the accurate model of each agent. This result is further extended to the output feedback case where a neighborhood observer is proposed based on relative output information of neighboring agents. Then, distributed observer-based synchronization controllers are derived and a parameter-dependent Riccati inequality is employed to prove the stability. This design has a favorable decouple property between the observer and the controller designs for nonlinear multiagent systems. For both cases, the developed controllers guarantee that the state of each agent synchronizes to that of the leader with bounded residual errors. Two illustrative examples validate the efficacy of the proposed methods.
Dashtbozorgi, Zahra; Golmohammadi, Hassan
2010-12-01
The main aim of this study was the development of a quantitative structure-property relationship method using an artificial neural network (ANN) for predicting the water-to-wet butyl acetate partition coefficients of organic solutes. As a first step, a genetic algorithm-multiple linear regression model was developed; the descriptors appearing in this model were considered as inputs for the ANN. These descriptors are principal moment of inertia C (I(C)), area-weighted surface charge of hydrogen-bonding donor atoms (HACA-2), Kier and Hall index (order 2) ((2)χ), Balaban index (J), minimum bond order of a C atom (P(C)) and relative negative-charged SA (RNCS). Then a 6-4-1 neural network was generated for the prediction of water-to-wet butyl acetate partition coefficients of 76 organic solutes. By comparing the results obtained from multiple linear regression and ANN models, it can be seen that statistical parameters (Fisher ratio, correlation coefficient and standard error) of the ANN model are better than that regression model, which indicates that nonlinear model can simulate the relationship between the structural descriptors and the partition coefficients of the investigated molecules more accurately.
Ge, Shuzhi Sam; Yang, Chenguang; Lee, Tong Heng
2008-09-01
In this paper, adaptive neural network (NN) control is investigated for a class of nonlinear pure-feedback discrete-time systems. By using prediction functions of future states, the pure-feedback system is transformed into an n-step-ahead predictor, based on which state feedback NN control is synthesized. Next, by investigating the relationship between outputs and states, the system is transformed into an input-output predictor model, and then, output feedback control is constructed. To overcome the difficulty of nonaffine appearance of the control input, implicit function theorem is exploited in the control design and NN is employed to approximate the unknown function in the control. In both state feedback and output feedback control, only a single NN is used and the controller singularity is completely avoided. The closed-loop system achieves semiglobal uniform ultimate boundedness (SGUUB) stability and the output tracking error is made within a neighborhood around zero. Simulation results are presented to show the effectiveness of the proposed control approach.
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.
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.
Niu, Ben; Liu, Yanjun; Zong, Guangdeng; Han, Zhaoyu; Fu, Jun
2017-01-16
In this paper, a new adaptive approximation-based tracking controller design approach is developed for a class of uncertain nonlinear switched lower-triangular systems with an output constraint using neural networks (NNs). By introducing a novel barrier Lyapunov function (BLF), the constrained switched system is first transformed into a new system without any constraint, which means the control objectives of the both systems are equivalent. Then command filter technique is applied to solve the so-called "explosion of complexity" problem in traditional backstepping procedure, and radial basis function NNs are directly employed to model the unknown nonlinear functions. The designed controller ensures that all the closed-loop variables are ultimately boundedness, while the output limit is not transgressed and the output tracking error can be reduced arbitrarily small. Furthermore, the use of an asymmetric BLF is also explored to handle the case of asymmetric output constraint as a generalization result. Finally, the control performance of the presented control schemes is illustrated via two examples.
NASA Astrophysics Data System (ADS)
Sbarufatti, Claudio; Corbetta, Matteo; Giglio, Marco; Cadini, Francesco
2017-03-01
Lithium-Ion rechargeable batteries are widespread power sources with applications to consumer electronics, electrical vehicles, unmanned aerial and spatial vehicles, etc. The failure to supply the required power levels may lead to severe safety and economical consequences. Thus, in view of the implementation of adequate maintenance strategies, the development of diagnostic and prognostic tools for monitoring the state of health of the batteries and predicting their remaining useful life is becoming a crucial task. Here, we propose a method for predicting the end of discharge of Li-Ion batteries, which stems from the combination of particle filters with radial basis function neural networks. The major innovation lies in the fact that the radial basis function model is adaptively trained on-line, i.e., its parameters are identified in real time by the particle filter as new observations of the battery terminal voltage become available. By doing so, the prognostic algorithm achieves the flexibility needed to provide sound end-of-discharge time predictions as the charge-discharge cycles progress, even in presence of anomalous behaviors due to failures or unforeseen operating conditions. The method is demonstrated with reference to actual Li-Ion battery discharge data contained in the prognostics data repository of the NASA Ames Research Center database.
NASA Technical Reports Server (NTRS)
Dewan, Mohammad W.; Huggett, Daniel J.; Liao, T. Warren; Wahab, Muhammad A.; Okeil, Ayman M.
2015-01-01
Friction-stir-welding (FSW) is a solid-state joining process where joint properties are dependent on welding process parameters. In the current study three critical process parameters including spindle speed (??), plunge force (????), and welding speed (??) are considered key factors in the determination of ultimate tensile strength (UTS) of welded aluminum alloy joints. A total of 73 weld schedules were welded and tensile properties were subsequently obtained experimentally. It is observed that all three process parameters have direct influence on UTS of the welded joints. Utilizing experimental data, an optimized adaptive neuro-fuzzy inference system (ANFIS) model has been developed to predict UTS of FSW joints. A total of 1200 models were developed by varying the number of membership functions (MFs), type of MFs, and combination of four input variables (??,??,????,??????) utilizing a MATLAB platform. Note EFI denotes an empirical force index derived from the three process parameters. For comparison, optimized artificial neural network (ANN) models were also developed to predict UTS from FSW process parameters. By comparing ANFIS and ANN predicted results, it was found that optimized ANFIS models provide better results than ANN. This newly developed best ANFIS model could be utilized for prediction of UTS of FSW joints.
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.
Kusy, Maciej; Zajdel, Roman
2015-09-01
In this paper, we propose new methods for the choice and adaptation of the smoothing parameter of the probabilistic neural network (PNN). These methods are based on three reinforcement learning algorithms: Q(0)-learning, Q(λ)-learning, and stateless Q-learning. We regard three types of PNN classifiers: the model that uses single smoothing parameter for the whole network, the model that utilizes single smoothing parameter for each data attribute, and the model that possesses the matrix of smoothing parameters different for each data variable and data class. Reinforcement learning is applied as the method of finding such a value of the smoothing parameter, which ensures the maximization of the prediction ability. PNN models with smoothing parameters computed according to the proposed algorithms are tested on eight databases by calculating the test error with the use of the cross validation procedure. The results are compared with state-of-the-art methods for PNN training published in the literature up to date and, additionally, with PNN whose sigma is determined by means of the conjugate gradient approach. The results demonstrate that the proposed approaches can be used as alternative PNN training procedures.
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.
Broom, Donald M
2006-01-01
The term adaptation is used in biology in three different ways. It may refer to changes which occur at the cell and organ level, or at the individual level, or at the level of gene action and evolutionary processes. Adaptation by cells, especially nerve cells helps in: communication within the body, the distinguishing of stimuli, the avoidance of overload and the conservation of energy. The time course and complexity of these mechanisms varies. Adaptive characters of organisms, including adaptive behaviours, increase fitness so this adaptation is evolutionary. The major part of this paper concerns adaptation by individuals and its relationships to welfare. In complex animals, feed forward control is widely used. Individuals predict problems and adapt by acting before the environmental effect is substantial. Much of adaptation involves brain control and animals have a set of needs, located in the brain and acting largely via motivational mechanisms, to regulate life. Needs may be for resources but are also for actions and stimuli which are part of the mechanism which has evolved to obtain the resources. Hence pigs do not just need food but need to be able to carry out actions like rooting in earth or manipulating materials which are part of foraging behaviour. The welfare of an individual is its state as regards its attempts to cope with its environment. This state includes various adaptive mechanisms including feelings and those which cope with disease. The part of welfare which is concerned with coping with pathology is health. Disease, which implies some significant effect of pathology, always results in poor welfare. Welfare varies over a range from very good, when adaptation is effective and there are feelings of pleasure or contentment, to very poor. A key point concerning the concept of individual adaptation in relation to welfare is that welfare may be good or poor while adaptation is occurring. Some adaptation is very easy and energetically cheap and
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
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.
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
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.
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.
Brasquet, C.; Bourges, B.; Le Cloirec, P.
1999-12-01
The adsorption of 55 organic compounds is carried out onto a recently discovered adsorbent, activated carbon cloth. Isotherms are modeled using the Freundlich classical model, and the large database generated allows qualitative assumptions about the adsorption mechanism. However, to confirm these assumptions, a quantitative structure-property relationship methodology is used to assess the correlations between an adsorbability parameter (expressed using the Freundlich parameter K) and topological indices related to the compounds molecular structure (molecular connectivity indices, MCI). This correlation is set up by mean of two different statistical tools, multiple linear regression (MLR) and neural network (NN). A principal component analysis is carried out to generate new and uncorrelated variables. It enables the relations between the MCI to be analyzed, but the multiple linear regression assessed using the principal components (PCs) has a poor statistical quality and introduces high order PCs, too inaccurate for an explanation of the adsorption mechanism. The correlations are thus set up using the original variables (MCI), and both statistical tools, multiple linear regression and neutral network, are compared from a descriptive and predictive point of view. To compare the predictive ability of both methods, a test database of 10 organic compounds is used.
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.
Jalali-Heravi, M; Parastar, F
2000-12-01
A new series of six comprehensive descriptors that represent different features of the gas-liquid partition coefficient, K(L), for commonly used stationary phases is developed. These descriptors can be considered as counterparts of the parameters in the Abraham solvatochromic model of solution. A separate multiple linear regression (MLR) model was developed by using the six descriptors for each stationary phase of poly(ethylene glycol adipate) (EGAD), N,N,N',N'-tetrakis(2-hydroxypropyl) ethylenediamine (THPED), poly(ethylene glycol) (Ucon 50 HB 660) (U50HB), di(2-ethylhexyl)phosphoric acid (DEHPA) and tetra-n-butylammonium N,N-(bis-2-hydroxylethyl)-2-aminoethanesulfonate (QBES). The results obtained using these models are in good agreement with the experiment and with the results of the empirical model based on the solvatochromic theory. A 6-6-5 neural network was developed using the descriptors appearing in the MLR models as inputs. Comparison of the mean square errors (MSEs) shows the superiority of the artificial neural network (ANN) over that of the MLR. This indicates that the retention behavior of the molecules on different columns show some nonlinear characteristics. The experimental solvatochromic parameters proposed by Abraham can be replaced by the calculated descriptors in this work.
Golmohammadi, Hassan
2009-11-30
A quantitative structure-property relationship (QSPR) study was performed to develop models those relate the structure of 141 organic compounds to their octanol-water partition coefficients (log P(o/w)). A genetic algorithm was applied as a variable selection tool. Modeling of log P(o/w) of these compounds as a function of theoretically derived descriptors was established by multiple linear regression (MLR), partial least squares (PLS), and artificial neural network (ANN). The best selected descriptors that appear in the models are: atomic charge weighted partial positively charged surface area (PPSA-3), fractional atomic charge weighted partial positive surface area (FPSA-3), minimum atomic partial charge (Qmin), molecular volume (MV), total dipole moment of molecule (mu), maximum antibonding contribution of a molecule orbital in the molecule (MAC), and maximum free valency of a C atom in the molecule (MFV). The result obtained showed the ability of developed artificial neural network to prediction of partition coefficients of organic compounds. Also, the results revealed the superiority of ANN over the MLR and PLS models.
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.
The neural code for taste in the nucleus of the solitary tract of the rat: effects of adaptation.
Di Lorenzo, P M; Lemon, C H
2000-01-10
Adaptation of the tongue to NaCl, HCl, quinine or sucrose was used as a tool to study the stability and organization of response profiles in the nucleus of the solitary tract (NTS). Taste responses in the NTS were recorded in anesthetized rats before and after adaptation of the tongue to NaCl, HCl, sucrose or quinine. Results showed that the magnitude of response to test stimuli following adaptation was a function of the context, i.e., adaptation condition, in which the stimuli were presented. Over half of all taste responses were either attenuated or enhanced following the adaptation procedure: NaCl adaptation produced the most widespread, non-stimulus-selective cross-adaptation and sucrose adaptation produced the least frequent cross-adaptation and the most frequent enhancement of taste responses. Adaptation to quinine cross-adapted to sucrose and adaptation to HCl cross-adapted to quinine in over half of the units tested. The adaptation procedure sometimes unmasked taste responses where none were present beforehand and sometimes altered taste responses to test stimuli even though the adapting stimulus did not itself produce a response. These effects demonstrated a form of context-dependency of taste responsiveness in the NTS and further suggest a broad potentiality in the sensitivity of NTS units across taste stimuli. Across unit patterns of response remained distinct from each other under all adaptation conditions. Discriminability of these patterns may provide a neurophysiological basis for residual psychophysical abilities following adaptation.
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
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.
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
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.
NASA Astrophysics Data System (ADS)
Bonelli, Maria Grazia; Ferrini, Mauro; Manni, Andrea
2016-12-01
The assessment of metals and organic micropollutants contamination in agricultural soils is a difficult challenge due to the extensive area used to collect and analyze a very large number of samples. With Dioxins and dioxin-like PCBs measurement methods and subsequent the treatment of data, the European Community advises the develop low-cost and fast methods allowing routing analysis of a great number of samples, providing rapid measurement of these compounds in the environment, feeds and food. The aim of the present work has been to find a method suitable to describe the relations occurring between organic and inorganic contaminants and use the value of the latter in order to forecast the former. In practice, the use of a metal portable soil analyzer coupled with an efficient statistical procedure enables the required objective to be achieved. Compared to Multiple Linear Regression, the Artificial Neural Networks technique has shown to be an excellent forecasting method, though there is no linear correlation between the variables to be analyzed.
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.
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.
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.
Applications of Neural Networks in Fault Detection of Rotating Machinery
1993-05-17
based on the ADALINE (ADAptive LINear Element) perceptron [Ref #4]. They correctly theorized that it would be possible for their 7 network to...Marvin Minski and Seymour Pappert [Ref #5]. After extensive mathematical study, Minski and Pappert concluded that a neural network based on the ADALINE
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.
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.
Face-selective regions show invariance to linear, but not to non-linear, changes in facial images.
Baseler, Heidi A; Young, Andrew W; Jenkins, Rob; Mike Burton, A; Andrews, Timothy J
2016-12-01
Familiar face recognition is remarkably invariant across huge image differences, yet little is understood concerning how image-invariant recognition is achieved. To investigate the neural correlates of invariance, we localized the core face-responsive regions and then compared the pattern of fMR-adaptation to different stimulus transformations in each region to behavioural data demonstrating the impact of the same transformations on familiar face recognition. In Experiment 1, we compared linear transformations of size and aspect ratio to a non-linear transformation affecting only part of the face. We found that adaptation to facial identity in face-selective regions showed invariance to linear changes, but there was no invariance to non-linear changes. In Experiment 2, we measured the sensitivity to non-linear changes that fell within the normal range of variation across face images. We found no adaptation to facial identity for any of the non-linear changes in the image, including to faces that varied in different levels of caricature. These results show a compelling difference in the sensitivity to linear compared to non-linear image changes in face-selective regions of the human brain that is only partially consistent with their effect on behavioural judgements of identity. We conclude that while regions such as the FFA may well be involved in the recognition of face identity, they are more likely to contribute to some form of normalisation that underpins subsequent recognition than to form the neural substrate of recognition per se.
1997-06-01
Transactions on Systems, Man and Cybernetics, vol.SMC- 13, no.5, p. 815-26 (1983). 14. Crick , F. and C. Kosch. "The problem of consciousness." Mind and Brain...cortical maps via synchronization," Parallel Pro- cessing in Neural Systems and Computers, p. xv+626, 101-4 (1990). 25. Francis , Gregory and Stephen
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
NASA Astrophysics Data System (ADS)
Samhouri, M.; Al-Ghandoor, A.; Fouad, R. H.
2009-08-01
In this study two techniques, for modeling electricity consumption of the Jordanian industrial sector, are presented: (i) multivariate linear regression and (ii) neuro-fuzzy models. Electricity consumption is modeled as function of different variables such as number of establishments, number of employees, electricity tariff, prevailing fuel prices, production outputs, capacity utilizations, and structural effects. It was found that industrial production and capacity utilization are the most important variables that have significant effect on future electrical power demand. The results showed that both the multivariate linear regression and neuro-fuzzy models are generally comparable and can be used adequately to simulate industrial electricity consumption. However, comparison that is based on the square root average squared error of data suggests that the neuro-fuzzy model performs slightly better for future prediction of electricity consumption than the multivariate linear regression model. Such results are in full agreement with similar work, using different methods, for other countries.
ERIC Educational Resources Information Center
Allen, William T., Jr.; Hunsaker, Scott L.
2016-01-01
Curriculum ideologies are educational theories applied in everyday pedagogical practice. In this study, to better meet the learning needs of their students, four middle school teachers used a variety of ideologies as a professional toolbox. When confronted with school district standardization, these teachers adapted; however, as predicted by…
NASA Astrophysics Data System (ADS)
Orra, Kashfull; Choudhury, Sounak K.
2016-12-01
The purpose of this paper is to build an adaptive feedback linear control system to check the variation of cutting force signal to improve the tool life. The paper discusses the use of transfer function approach in improving the mathematical modelling and adaptively controlling the process dynamics of the turning operation. The experimental results shows to be in agreement with the simulation model and error obtained is less than 3%. The state space approach model used in this paper successfully check the adequacy of the control system through controllability and observability test matrix and can be transferred from one state to another by appropriate input control in a finite time. The proposed system can be implemented to other machining process under varying range of cutting conditions to improve the efficiency and observability of the system.
Stasiunas, Antanas; Verikas, Antanas; Bacauskiene, Marija; Miliauskas, Rimvydas
2012-03-01
Outer hair cells in the cochlea of the ear, together with the local structures of the basilar membrane, reticular lamina and tectorial membrane constitute the adaptive primary filters (PF) of the second order. We used them for designing a serial-parallel signal filtering system. We determined a rational number of the PF included in Gaussian channels of the system, summation weights of the output signals, and distribution of the PF along the basilar membrane. A Gaussian panoramic filter bank each channel of which consists of five PF is presented as an example. The properties of the PF, the channel and the filter bank operating in the linear and nonlinear modes are determined during adaptation and under efferent control. The results suggest that application of biological filtering principles can be useful for designing cochlear implants with new speech encoding strategies.
NASA Astrophysics Data System (ADS)
Skeberis, C.; Xenos, T. D.; Hadjileontiadis, L.; Contadakis, M. E.; Arabelos, D.
2012-04-01
This paper investigates the development and application of artificial neural networks (ANN) based on Predictive Modular Neural Networks (PREMONNs) to provide a self adaptive unsupervised method for detecting disturbances that can be attributed to seismic-ionospheric precursor phenomena using VLF radio signals. As such, the neural network is applied to bring forth and adaptively discriminate different characteristics in the received signals, in real time, in order to provide data segments of interest that can be correlated to subsequent seismic phenomena. PREMONNs have been developed for time series prediction and through that for source switching detection in a time series; they are constituted by two modules. The first tier is a module consisting of a dynamic array of neural networks following the data stream in order to predict the next value of a time series whereas the second is a decision one utilizing a Bayes probability equation to decide on source switching. That module is responsible for electing and appropriately training the closest fitting NN or switching to a new NN if a source switch is apparent. For the purpose of this paper, VLF signals transmitted by a number of European VLF transmitters are monitored for over a year in Thessaloniki (40.69N 22.78E) and the data from December 2010 to December 2011 are used. The received signals are sampled and stored for off line processing. The receiver was developed by Elettronika Srl, and is part of the International Network for Frontier Research on Earthquake Precursors (INFREP). Signals received from the 20.27KHz ICV station in Tavolara, Italy (Lat 40.923,Lon. 9.731) were used. The received VLF signal was normalized and then processed using the Empirical Mode Decomposition Method (EMD). The resulting data are used to train the unsupervised ANN and the performance of the developed network is then evaluated. The efficacy of different layouts of the PREMONN is evaluated and the application of a self
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.
Takemura, Aya; Ofuji, Tomoyo; Miura, Kenichiro; Kawano, Kenji
2017-01-01
To adapt to variable environments, humans regulate their behavior by modulating gains in sensory-to-motor processing. In this study, we measured a simple eye movement, the ocular following response (OFR), in monkeys to study the neuronal basis of adaptive motor learning in the visuomotor processing stream. The medial superior temporal (MST) area of the cerebral cortex is a critical site for contextual gain modulation of the OFR. However, the role of MST neurons in adaptive gain modulation of the OFR remains unknown. We adopted a velocity step-down sequence paradigm that was designed to promote adaptive gain modulation of the OFR to investigate the role of the dorsal MST (MSTd) in adaptive motor learning. In the initial learning stage, we observed a reduction in the OFR but no significant change in the “open-loop” responses for the majority of the MSTd neurons. However, in the late learning stage, some MSTd neurons exhibited significantly enhanced “closed-loop” responses in association with increases in retinal error velocity. These results indicate that the MSTd area primarily encodes visual motion, suggesting that MSTd neurons function upstream of the motor learning site to provide sensory signals to the downstream structures involved in adaptive motor learning. PMID:28102342
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.
Hua, Changchun; Zhang, Liuliu; Guan, Xinping
2017-01-01
This paper studies the problem of distributed output tracking consensus control for a class of high-order stochastic nonlinear multiagent systems with unknown nonlinear dead-zone under a directed graph topology. The adaptive neural networks are used to approximate the unknown nonlinear functions and a new inequality is used to deal with the completely unknown dead-zone input. Then, we design the controllers based on backstepping method and the dynamic surface control technique. It is strictly proved that the resulting closed-loop system is stable in probability in the sense of semiglobally uniform ultimate boundedness and the tracking errors between the leader and the followers approach to a small residual set based on Lyapunov stability theory. Finally, two simulation examples are presented to show the effectiveness and the advantages of the proposed techniques.
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.
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.
Li, Wei; Guo, Yangyang; Fan, Jing; Ma, Chaolin; Ma, Xuan; Chen, Xi; He, Jiping
2016-06-14
Adaptive flexibility is of significance for the smooth and efficient movements in goal attainment. However, the underlying work mechanism of the cerebral cortex in adaptive motor control still remains unclear. How does the cerebral cortex organize and coordinate the activity of a large population of cells in the implementation of various motor strategies? To explore this issue, single-unit activities from the M1 region and kinematic data were recorded simultaneously in monkeys performing 3D reach-to-grasp tasks with different perturbations. Varying motor control strategies were employed and achieved in different perturbed tasks, via the dynamic allocation of cells to modulate specific movement parameters. An economic principle was proposed for the first time to describe a basic rule for cell allocation in the primary motor cortex. This principle, defined as the Dynamic Economic Cell Allocation Mechanism (DECAM), guarantees benefit maximization in cell allocation under limited neuronal resources, and avoids committing resources to uneconomic investments for unreliable factors with no or little revenue. That is to say, the cells recruited are always preferentially allocated to those factors with reliable return; otherwise, the cells are dispatched to respond to other factors about task. The findings of this study might partially reveal the working mechanisms underlying the role of the cerebral cortex in adaptive motor control, wherein is also of significance for the design of future intelligent brain-machine interfaces and rehabilitation device.
Lundahl, P Johan; Kitts, Catherine C; Nordén, Bengt
2011-08-21
This article presents a new design of flow-orientation device for the study of bio-macromolecules, including DNA and protein complexes, as well as aggregates such as amyloid fibrils and liposome membranes, using Linear Dichroism (LD) spectroscopy. The design provides a number of technical advantages that should make the device inexpensive to manufacture, easier to use and more reliable than existing techniques. The degree of orientation achieved is of the same order of magnitude as that of the commonly used concentric cylinders Couette flow cell, however, since the device exploits a set of flat strain-free quartz plates, a number of problems associated with refraction and birefringence of light are eliminated, increasing the sensitivity and accuracy of measurement. The device provides similar shear rates to those of the Couette cell but is superior in that the shear rate is constant across the gap. Other major advantages of the design is the possibility to change parts and vary sample volume and path length easily and at a low cost.
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