Search

This paper is concerned with a multi-resolution tool for analysis of a time series aiming to detect abnormalities in various frequency regions. The task is treated as a kernel based novelty detection applied to a multi-level time series representation obtained from the discrete wavelet transform. Having a priori knowledge that the abnormalities manifest themselves in several frequency regions, a committee of detectors utilizing data dependent aggregation weights is build by combining outputs of detectors operating in those regions. [ABSTRACT FROM AUTHOR]

An all-optical neural network based on coupled ring lasers is proposed in this paper. Each laser in the network has a different wavelength, representing one neuron. The network status is determined by the wavelength of the network's light output. Inputs to the network are in the optical power domain. The nonlinear threshold function required for neural-network operation is achieved optically by interaction between the lasers. A simple laser model developed in the paper has illuminated the behavior of the coupled lasers. An experimental system is implemented using single mode fiber optic components at wavelengths near 1550 nm. A number of functions are implemented to demonstrate the practicality of the new network. From the experiment, a conclusion can be obtained that the neural network is particularly robust against input wavelength variations. [ABSTRACT FROM AUTHOR]

This paper proposes a reconfigurable architecture for VLSI implementation of BP neural networks with on-chip learning. Basing on systolic arrays, this architecture can flexibly adapt to neural networks with different scales, transfer functions or learning algorithms by reconfiguration of basic processing components,. Three kinds of reconfigurable processing units (RPU) are proposed firstly basing on the analysis of neural network's reconfiguration. Secondly, the paper proposes a reconfigurable systolic architecture and the method of mapping BP networks into this architecture. The implementation of an instance on FPGA is introduced in the last. The results show that this flexible architecture can also achieve a high learning speed of 432M CUPS (Connection Updated Per Second) at 100MHz using 22 multipliers. [ABSTRACT FROM AUTHOR]

In this paper there is a natural language interface presented, which consists of the intelligent mechanisms of human identification, speech recognition, word and command recognition, command syntax and result analysis, command safety assessment, technological process supervision as well as human reaction assessment. In this paper there is also a review of the selected issues on recognition of speech commands in natural language given by the operator of the technological device. A view is offered of the complexity of the recognition process of the operator's words and commands using neural networks made of a few layers of neurons. The paper presents research results of speech recognition and automatic recognition of commands in natural language using artificial neural networks. [ABSTRACT FROM AUTHOR]

New applications of artificial neural networks are capable of recognition and verification of effects and safety of commands given by the operator of the technological device. In this paper there is a review of the selected issues on estimation of results and safety of the operator's commands as well as supervision of the technological process. A view is offered of the complexity of effect analysis and safety assessment of commands given by the operator using neural networks. The first part of the paper introduces a new concept of modern supervising systems of the technological process using a natural language human-machine interface and discusses the general topics and issues. The second part is devoted to a discussion of more specific topics of the automatic command verification that have led to interesting new approaches and techniques. [ABSTRACT FROM AUTHOR]

It is well known, the Job-Shop Scheduling Problem (JSSP) is the most complicated and typical problem of all kinds of production scheduling problems, the allocation of resources over time to perform a collection of tasks. The current method has several shortcomings in solving the JSSP. In this paper, we correct these deficiencies by introducing a dynamic model that is based on an analysis of the run-time behavior of CSANN algorithm. At the same time, this paper proposes several new heuristics in order to improve the performance of CSANN. The computational simulations have shown that the proposed hybrid approach has good performance with respect to the quality of solution and the speed of computation. [ABSTRACT FROM AUTHOR]

As more and more industries experience the globalization of business activities, measuring productivity performance has become an area of concern for companies and policy makers in Europe, the United States, Japan and so on. A novel way about nonlinear regression modeling of high-technology manufacturing (HTM) productivity with the support vector machines (SVM) is presented in this paper. Optimization of labor productivity (LP) is also presented in this paper, which is based on chaos and uses the SVM regression model as the objective function. [ABSTRACT FROM AUTHOR]

In this paper posture control of a human arm in the sagittal plane is investigated by means of model simulations. The arm is modeled by a nonlinear neuromusculoskeletal model with two degrees of freedom and six muscles. A multilayer perceptron network is used in this paper, and effectively adapted by Levenberg-Marquardt training algorithm. The duration of next movement is regulated according as current feedback states. Simulation Results indicate that this method can maintain two joints at different location in allowable bound. The control scheme provides novel insight into neural prosthesis control and robotic control. [ABSTRACT FROM AUTHOR]

In this paper, we aim to address the cell phase identification problem, and two important aspects, the feature extraction methods and the classifier design, are discussed. In our study, we first propose extracting high frequency information of different orientations using Steerable filters. Next, we employ a multi-layer neural network using the back-propagation algorithm to replace K-Nearest Neighbor (KNN) classifier which has been implemented in the Cellular Image Quantitator (CELLIQ) system [3]. Experimental results provide a comparison between the proposed steerable filter features and existing regular features which have been used in published papers [3, 5]. From the comparison, it can be concluded that Steerable filter features can effectively represent the cells in different phases and improve the classification accuracy. Neural network also has a better performance than KNN currently deployed in CELLIQ system [3]. [ABSTRACT FROM AUTHOR]

Many interaction data still exist only in the biomedical literature and they require much effort to construct well-structured data. Discovering useful knowledge from large collections of papers is becoming more important for efficient biological and biomedical researches as genomic research advances. In this paper, we present a relation kernel-based interaction extraction method to extract knowledge efficiently. We extract protein interactions of from text documents with relation kernel and Yeast was used as an example target organism. Kernel for relation extraction is constructed with predefined interaction corpus and set of interaction patterns. The proposed method only exploits shallow parsed documents. Experimental results show that the proposed kernel method achieves a recall rate of 79.0% and precision rate of 80.8% for protein interaction extraction from biomedical document without full parsing efforts. [ABSTRACT FROM AUTHOR]

In self and non-self discrimination (SNSD) model, it is very important to generate a desirable detector set since it decides the performance and scale of the SNSD model based task. By using the famous principle of negative selection in natural immune system, a novel generating algorithm of detector, multiple-point bit mutation method, is proposed in this paper. It utilizes random multiple-point mutation to look for non-self detectors in a large range in the whole space of detectors, such that we can obtain a required detector set in a reasonable computation time. This paper describes the work procedure of the proposed detector generating algorithm. We tested the algorithm by using many datasets and compared it with the Exhaustive Detector Generating Algorithm in details. The experimental results show that the proposed algorithm outperforms the Exhaustive Detector Generating Algorithm both in computational complexities and detection performance. [ABSTRACT FROM AUTHOR]

This paper addresses the important issues of error control for video transmission over 3G, considering the fact that wireless video delivery faces the huge challenge of the high error rate and time variability in wireless channel. This paper proposes a real world statistics based event-trigger bit error rate (BER) model, which can describe and handle the time-varying wireless channel error characteristics better. Moreover, a recurrent neural network is employed to decide the state transfer as a mechanism. Simulation results and comparisons demonstrate effectiveness and efficiency of the proposed method in term of visual performance and transmission efficiency over a variety of wireless channel conditions. [ABSTRACT FROM AUTHOR]

The recommendation G.728 depends on the Levinson-Durbin (L-D) algorithm to update its gain filter coefficients. In this paper, it is contrasted with BP neural network method. Because quantizer has not existed at optimizing gain filter, the quantization SNR can not be used to evaluate its performance. This paper proposes a scheme to estimate SNR so that gain predictor can be separately optimized with quantizer. Using BP neural network filter, the calculation quantity is only 6.7 percent of L-D method's and its average segment SNR is about 0.156dB higher than G.728. It is also used to evaluate the case that excitation vector is 16 or 20 samples, respectively, the BP neural network algorithm has similarly good result. [ABSTRACT FROM AUTHOR]

Contact maps are considered one of the most useful strategic steps in protein folding recognition. And there are a variety of measures of residues contact used in the literature. In this paper, we address our question on using a transiently chaotic neural network to predict the contact maps and whether it is reasonable. Our results show that it is more successful that we predict proteins contact maps based on modified transiently chaotic neural network. [ABSTRACT FROM AUTHOR]

The prediction of protein interactions is an important problem in post-genomic biology. In this paper, we present an association rule mining method for protein interaction prediction. A neural network is used to cluster protein interaction data and a feature selection is used to reduce the dimension of protein features. For model training, the preliminary network model was constructed with existing protein interaction data in terms of their functional categories and interactions. A set of association rules for protein interaction prediction are derived by decoding a set of learned weights of trained neural network after this model training. The protein interaction data of Yeast from public databases are used. The prediction performance was compared with simple association rule-based approach. According to the experimental results, proposed method achieved about 95.5% accuracy. [ABSTRACT FROM AUTHOR]

Neural Networks are usually implemented in software on sequential machines but when implemented in hardware, they are extremely fast due to the massive parallelism inherent in the hardware devices. Implementation of Neural Networks in Programmable Logic Devices such as FPGAs (Field Programmable Gate Arrays) gives us more flexibility since these devices are reconfigurable and their design can be altered whenever needed. The design proposed in this paper shows the implementation of perceptron neural network in FPGAs for the character recognition problem. The characters here are the English language alphabets which are input to the network and after training; they are tested for recognition. Each alphabet is tested for three different fonts. After implementation, the simulations are done and performance issues of the design are analyzed.The post-layout simulation gives excellent results even if some noise is introduced to the input patterns. [ABSTRACT FROM AUTHOR]

In this paper, hybrid neural network processor (HANNP) is designed in VLSI. The HANNP has RISC based architecture leading to an effective general digital signal processing and artificial neural networks computation. The architecture of a HANNP including the general digital processing units such as 64-bit floating-point arithmetic unit (FPU), a control unit (CU) and neural network processing units such as artificial neural computing unit (NNPU), specialized neural data bus and interface unit, etc. The HANNP is modeled in Veilog HDL and implemented with FPGA. Character recognition problems and Kohonen self-organization problems are applied to the proposed HANNP to justify its applicability to real engineering problems. [ABSTRACT FROM AUTHOR]

In this paper we present the results of neural network hardware in-the-loop training for an analogue Local Cluster Neural Network (LCNN) chip. We use a Probabilistic Random Weight Change (PRWC) algorithm that is a combination of the random weight change and simulated annealing algorithms. We applied the PRWC algorithm to in-the-loop training for multi-dimensional function approximations and for predictions. We discuss the training strategy and the experiment results. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient hardware architecture for a function generator suitable for an artificial neural network (ANN). A spline-based approximation function is designed that provides a good trade-off between accuracy and silicon area, whilst also being inherently scalable and adaptable for numerous activation functions. This has been achieved by using a minimax polynomial and through optimal placement of the approximating polynomials based on the results of a genetic algorithm. The approximation error of the proposed method compares favourably to all related research in this field. Efficient hardware multiplication circuitry is used in the implementation, which reduces the area overhead and increases the throughput. [ABSTRACT FROM AUTHOR]

A filtering method aided by neural network to improve the maneuvering target tracking performance is proposed in this paper. Based on unscented Kalman filter, the unscented particle filter (UPF) has more accurate proposal distribution and better approximation to non-linear tracking problem than other Sequential Monte-Carlo methods. The neural network is constructed and trained by the maneuvering features, and the outputs of NN are used as acceleration control parameters to correct model parameters. Simulation results show the performance of UPF aided by NN is much improved than extensive Kalman filter. [ABSTRACT FROM AUTHOR]