-
Chapter and Conference Paper
Globally Attractive Periodic State of Discrete-Time Cellular Neural Networks with Time-Varying Delays
For the convenience of computer simulation, the discrete-time systems in practice are often considered. In this paper, Discrete-time cellular neural networks (DTCNNs) are formulated and studied in a regime whe...
-
Chapter and Conference Paper
Blind Extraction of Singularly Mixed Source Signals
In this paper, a neural network model and its associate learning rule are developed for sequential blind extraction in the case that the number of observable mixed signals is less than the one of sources. This...
-
Chapter and Conference Paper
Gait Recognition Using Independent Component Analysis
This paper presents a new method for automatic gait recognition using independent component analysis (ICA). Firstly, a simple background subtraction algorithm is introduced to segment the moving figures accura...
-
Chapter and Conference Paper
Application of Neural Network to Interactive Physical Programming
A neural network based interactive physical programming approach is proposed in this paper. The approximate model of Pareto surface at a given Pareto design is developed based on neural networks, and a map fro...
-
Chapter and Conference Paper
Associative Memories Based on Discrete-Time Cellular Neural Networks with One-Dimensional Space-Invariant Templates
In this paper, discrete-time cellular neural networks with one-dimensional space invariant are designed to associative memories. The obtained results enable both heteroassociative and autoassociative memories ...
-
Chapter and Conference Paper
Fault Data Compression of Power System with Wavelet Neural Network Based on Wavelet Entropy
Through the analysis of function approximation with wavelet transformation, an adaptive wavelet neural network is introduced in the paper, which is applied in data compression of fault data in power system. In...
-
Chapter and Conference Paper
Robust Control for a Class of Uncertain Neural Networks with Time-Delays on States and Inputs
A class of uncertain neural networks with time-delays on states and inputs is studied. The theoretical analysis herein guarantees that the neural networks are robust stable. In addition, a state feedback contr...
-
Chapter and Conference Paper
Applying Bayesian Approach to Decision Tree
Applying Bayesian approach to decision tree (DT) model, and then a Bayesian-inference-based decision tree (BDT) model is proposed. For BDT we assign prior to the model parameters. Together with observed sample...
-
Chapter and Conference Paper
Global Exponential Stability in Lagrange Sense of Continuous-Time Recurrent Neural Networks
In this paper, global exponential stability in Lagrange sense is further studied for continuous recurrent neural network with three different activation functions. According to the parameters of the system its...
-
Chapter and Conference Paper
Analysis of Global Convergence and Learning Parameters of the Back-Propagation Algorithm for Quadratic Functions
This paper analyzes global convergence and learning parameters of the back-propagation algorithm for quadratic functions. Some global convergence conditions of the steepest descent algorithm are obtained by di...
-
Chapter and Conference Paper
Implementation of Multi-valued Logic Based on Bi-threshold Neural Networks
The implementation of multi-valued logic with a three layers forward neural network is proposed. The hidden layer is constituted by bi-threshold neurons compared with traditional simple threshold neurons. Acco...
-
Chapter and Conference Paper
Quantum Error-Correction Codes Based on Multilevel Constructions of Hadamard Matrices
To achieve quantum error-correction codes with good parameters, the recursive constructions of Hadamard matrices with even length are proposed with special characters. The generators of the stabilizer of the d...
-
Chapter and Conference Paper
A Sliding Singular Spectrum Entropy Method and Its Application to Gear Fault Diagnosis
Entropy changes with the variation of the system status. It has been widely used as a standard for the determination of system status, quantity of system complexity and system classification. Based on the sing...
-
Chapter and Conference Paper
Global Exponential Stability of Recurrent Neural Networks with Time-Dependent Switching Dynamics
In this paper, the switching dynamics of recurrent neural networks are studied. Sufficient conditions on global exponential stability with an arbitrary switching law or a dwell time switching law and the estim...
-
Chapter and Conference Paper
Robust Stability of Fuzzy Cohen-Grossberg Neural Networks with Delays
In the paper, a new exponentially robust stability criterion for interval fuzzy Cohen-Grossberg type neural networks with time- varying delays is obtained by using Lyapunov-Krasovskii functional with the diffe...
-
Chapter and Conference Paper
A New Short-Term Load Forecasting Model of Power System Based on HHT and ANN
Aiming to the disadvantages of short-term load forecasting with HHT such as mode mixing and random component, a new short-term load forecasting model based on HHT and ANN is proposed. The first order differenc...
-
Chapter and Conference Paper
A Parallel Wavelet Algorithm Based on Multi-core System and Its Application in the Massive Data Compression
In this paper we discuss the issue relevant to the parallel implementation of wavelet and wavelet packet on the single PC with multi-core system. The massive data compression has to manage large size of data w...
-
Chapter and Conference Paper
Power System Load Forecasting Based on EEMD and ANN
In order to fully mine the characteristics of load data and improve the accuracy of power system load forecasting, a load forecasting model based on Ensemble Empirical Mode Decomposition (EEMD) and Artificial ...
-
Chapter and Conference Paper
Real Coded Feature Selection Integrated with Self-adaptive Differential Evolution Algorithm
The current optimization algorithms for feature selection are mostly based on binary coded swarm intelligence algorithms. A novel real coded optimization algorithm which using the weighted distance metric is p...
-
Chapter and Conference Paper
Adaptive Backstep** Neural Control for Switched Nonlinear Stochastic System with Time-Delay Based on Extreme Learning Machine
In this paper, for a class of switched stochastic nonlinear systems with time-varying delays, the output feedback stabilization problem is addressed based on single hidden layer feed-forward network (SLFN) and...