Optimised bit serial modular multiplier for implementation on fieldprogrammable gate arrays

A high-speed architecture for bit serial modular multiplication is presented. The design of this array is highly regular, allowing the specific logic and routing resources available in field programmable gate arrays (FPGAs) to be exploited. Furthermore, an optimised array is presented which exploits the reprogrammability of the FPGA, such that a longer bit length can be implemented on the same FPGA     

基于CPLD的BP神经网络模型的硬件实现

神经网络模型的硬件实现已成为人工智能的一个重要的研究方向,本文提出一种基于CPLD的硬件实现方式,来实现BP三层神经网络模型方法,并对该模型进行了MAX+Plus II仿真验证.     

Atrial activity enhancement by Wiener filtering using an artificial neural network

This paper describes a novel technique for the cancellation of the ventricular activity for applications such as P-wave or atrial fibrillation detection. The procedure was thoroughly tested and compared with a previously published method, using quantitative measures of performance. The novel approach estimates, by means of a dynamic time delay neural network (TDNN), a time-varying, nonlinear transfer function between two ECG leads. Best results were obtained using an Elman TDNN with nine input samples and 20 neurons, employing a sigmoidal tangencial activation in the hidden layer and one linear neuron in the output stage. The method does not require a previous stage of QRS detection. The technique was quantitatively evaluated using the MIT-BIH arrhythmia database and compared with an adaptive cancellation scheme proposed in the literature. Results show the advantages of the proposed approach, and its robustness during noisy episodes and QRS morphology variations.     

Multiple contour extraction from graylevel images using an artificial neural network.

For active contour modeling (ACM), we propose a novel self-organizing map (SOM)-based approach, called the batch-SOM (BSOM), that attempts to integrate the advantages of SOM- and snake-based ACMs in order to extract the desired contours from images. We employ feature points, in the form of an edge-map (as obtained from a standard edge-detection operation), to guide the contour (as in the case of SOM-based ACMs) along with the gradient and intensity variations in a local region to ensure that the contour does not "leak" into the object boundary in case of faulty feature points (weak or broken edges). In contrast with the snake-based ACMs, however, we do not use an explicit energy functional (based on gradient or intensity) for controlling the contour movement. We extend the BSOM to handle extraction of contours of multiple objects, by splitting a single contour into as many subcontours as the objects in the image. The BSOM and its extended version are tested on synthetic binary and gray-level images with both single and multiple objects. We also demonstrate the efficacy of the BSOM on images of objects having both convex and nonconvex boundaries. The results demonstrate the superiority of the BSOM over others. Finally, we analyze the limitations of the BSOM.     

Active MEMS-based flow control using artificial neural network

These last years several research works have studied the application of Micro-Electro-Mechanical Systems (MEMS) for aerodynamic active flow control. Controlling such MEMS-based systems remains a challenge. Among the several existing control approaches for time varying systems, many of them use a process model representing the dynamic behavior of the process to be controlled. The purpose of this paper is to study the suitability of an artificial neural network first to predict the flow evolution induced by MEMS, and next to optimize the flow w.r.t. a numerical criterion. To achieve this objective, we focus on a dynamic flow over a backward facing step where MEMS actuators velocities are adjusted to maximize the pressure over the step surface. The first effort has been to establish a baseline database provided by computational fluid dynamics simulations for training the neural network. Then we investigate the possibility to control the flow through MEMS configuration changes. Results are promising, despite slightly high computational times for real time application.     

Design and implementation of industrial neural network controller using backstepping

In this paper, a novel neural network (NN) backstepping controller is modified for application to an industrial motor drive system. A control system structure and NN tuning algorithms are presented that are shown to guarantee stability and performance of the closed-loop system. The NN backstepping controller is implemented on an actual motor drive system using a two-PC control system developed at The University of Texas at Arlington. The implementation results show that the NN backstepping controller is highly effective in controlling the industrial motor drive system. It is also shown that the NN controller gives better results on actual systems than a standard backstepping controller developed assuming full knowledge of the dynamics. Moreover, the NN controller does not require the linear-in-the-parameters assumption or the computation of regression matrices required by standard backstepping.     

Surface roughness determination using spectral correlations ofscattered intensities and an artificial neural network technique

An artificial neural network (ANN) technique is applied to the determination of the RMS height and the correlation distance of one-dimensional rough surfaces. The surface is illuminated by a beam wave, and the intensity correlations of the scattered wave at two wavelengths in the specular and backward directions are used to determine the roughness parameters. Scattered intensity correlations calculated by Monte Carlo simulations are used to train the ANN, and two methods, the explicit inversion method and the iterative constrained inversion method, are used to perform the inversion. The inversion values are compared with the target values, and the iterative constrained method is shown to give smaller errors, but it requires longer computer CPU time     

Design and implementation of an adaptive recurrent neural networks (ARNN) controller of the pneumatic artificial muscle (PAM) manipulator

This paper presents the design, development and implementation of an adaptive recurrent neural networks (ARNN) controller suitable for real-time manipulator control applications. The unique feature of the ARNN controller is that it has dynamic self-organizing structure, fast learning speed, good generalization and flexibility in learning. The proposed adaptive algorithm focuses on fast and efficient optimization by weighting parameters of inverse recurrent neural models used in the ARNN controller. This approach is employed to implement the ARNN controller with a view to controlling the joint angle position of the highly nonlinear pneumatic artificial muscle (PAM) manipulator in real-time. The performance of this novel proposed controller was found to be superior compared with a conventional PID controller. These results can be applied to control other highly nonlinear systems as well.     

Parallel pixel processing using programmable gate arrays

A reconfigurable hardware design permits very fast feature extraction from high frame rate video images. By implementing parallel pixel processing paths in programmable gate arrays a wide range of image processing algorithms can be implemented in realtime     

Fuzzy-ChOA: an improved chimp optimization algorithm for marine mammal classification using artificial neural network

Analog Integrated Circuits and Signal Processing - Chimp optimization algorithm (ChOA) is a robust nature-inspired technique, which was recently proposed for addressing real-world challenging...     

利用改进的人工神经网络优选激光切割工艺参数

在激光切割中,工艺参数的优化搭配直接影响切割质量.为了更好的选择出最优化的工艺参数搭配,本文利用人工神经网络分析方法,建立一个用遗传算法改进的人工神经网络模型,并在实际的应用中选出大量实际实验数据对其加以训练和验证.实验证明,该模型将遗传算法和神经网络的优点相结合,既克服了以往正交实验中存在的选出工艺参数准确度的问题,同时也克服了传统神经网络中易出现的局部最优和收敛速度较慢的问题,从而有效地解决了激光切割中各参数优化搭配的问题.     

An implementation of a direction-finding antenna for mobilecommunications using a neural network

Direction-finding systems for radio signals are mostly used in mobile communications and avionics applications for antenna tracking or navigation purposes. In general, such systems require accurate calibration and may be sensitive to noise and external interference. In this paper, we investigate the performance of a neural network-based direction-finding system under such conditions. The proposed topology is a hybrid one, combining a simple RF signal beamformer with a neural network. The training of the neural network is accomplished experimentally with a three-element antenna array by varying the beam's direction and the carrier frequency. The error on the estimated direction of arrival caused by the environment and training limitations are investigated     

权重连接神经网络的光电实现

在Ｈｏｐｆｉｅｌｄ模型基础上，对具有权重连接的Ｈｏｐｆｉｅｌｄ模型引入连接权重矩阵，这样只要在Ｈｏｐｆｉｅｌｄ内容寻址记忆光电阵更前多加一个连接权重矩阵阵列，则得具有权重连接的神经网络模型的光电实现。     

Saliency-directed color image interpolation using artificial neural network and particle swarm optimization

In this study, a saliency-directed color image interpolation approach using artificial neural network (ANN) and particle swarm optimization (PSO) is proposed. First, a high-quality saliency map of a color image to be interpolated is generated by a modified block-based visual attention model in an effective manner. Then, based on the saliency map, bilinear interpolation and ANN-PSO interpolation are employed for non-saliency (non-ROI) and saliency (ROI) blocks, respectively, to obtain the final color interpolation results. In the proposed ANN-PSO interpolation scheme, ANN is used to determine the orientation of each 5 × 5 image pattern (block), whereas PSO is employed to determine the weights in 5 × 5 interpolation filtering masks. The proposed approach is applicable to image interpolation with arbitrary magnification factors (MFs). Based on the experimental results obtained in this study, the color interpolation results by the proposed approach are better than those by five comparison approaches.     

Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network

There are numerous neurological disorders such as dementia, headache, traumatic brain injuries, stroke, and epilepsy. Out of these epilepsy is the most prevalent neurological disorder in the human after stroke. Electroencephalogram (EEG) contains valuable information related to different physiological state of the brain. A scheme is presented for detecting epileptic seizures from EEG data recorded from normal subjects and epileptic patients. The scheme is based on discrete wavelet transform (DWT) analysis and approximate entropy (ApEn) of EEG signals. Seizure detection is performed in two stages. In the first stage, EEG signals are decomposed by DWT to calculate approximation and detail coefficients. In the second stage, ApEn values of the approximation and detail coefficients are calculated. Significant differences have been found between the ApEn values of the epileptic and the normal EEG allowing us to detect seizures with 100 % classification accuracy using artificial neural network. The analysis results depicted that during seizure activity, EEG had lower ApEn values compared to normal EEG. This gives that epileptic EEG is more predictable or less complex than the normal EEG. In this study, feed-forward back-propagation neural network has been used for classification and training algorithm for this network that updates the weight and bias values according to Levenberg–Marquardt optimization technique.     

Two analog counters for neural network implementation

Simple analog circuits which are useful for the implementation of the synchronous Boltzmann machine learning algorithms are presented. A simple charge-transfer-based analog counter is described. The authors give a functional model of its behavior and analyze the differences between this model and the counter implementation. They also present simulation results and the test of a prototype. Along the same lines, they study a switched-current-based counter, which achieves better results (dynamic range, linearity) through higher complexity     

Novel CMOS sampled-data VLSI implementation of artificial neural networks

A mixed-mode VLSI implementation of artificial neural networks offers a tradeoff solution for speed, area saving, and flexibility. A novel CMOS sampled-data programmable synapse and a simple CMOS analogue neuron have been developed. Using a 1.2 mu m CMOS technology, the synapse consumed 120*120 mu m/sup 2/ and the neuron consumed 120*260 mu m/sup 2/.<>     

A neural network approach-decision neural network (DNN) for preference assessment

A new neural-network-based approach to assess the preference of a decision-maker (DM) for the multiple objective decision making (MODM) problem is presented in this paper. A new neural network structure with a "twin-topology" is introduced in this approach. We call this neural network a decision neural network (DNN). The characteristics of the DNN are discussed, and the training algorithm for DNN is presented as well. The DNN enables the decision-maker to make pairwise comparisons between different alternatives, and these comparison results are used as learning samples to train the DNN. The DNN is applicable for both accurate and inaccurate comparisons (results are given in approximate values or interval scales). The performance of the DNN is evaluated with several typical forms of utility functions. Results show that DNN is an effective and efficient way for modeling the preference of a decision-maker.     

Holographic implementation of a fully connected neural network

A holographic implementation of a fully connected neural network is presented. This model has a simple structure and is relatively easy to implement, and its operating principles and characteristics can be extended to other types of networks, since any architecture can be considered as a fully connected network with some of its connections missing. The basic principles of the fully connected network are reviewed. The optical implementation of the network is presented. Experimental results which demonstrate its ability to recognize stored images are given, and its performance and analysis are discussed based on a proposed model for the system. Special attention is focused on the dynamics of the feedback loop and the tradeoff between distortion tolerance and image-recognition capability of the associative memory     

Pattern synthesis for uniform linear array using genetic algorithm and artificial neural network

Multidimensional Systems and Signal Processing - In this paper, we propose a new amplitude-only method for pattern synthesis of uniform linear array (ULA) based on genetic algorithm (GA) and...