Application of dynamic synapse neural networks on gunshot recognition

Synaptic dynamics: Linear model and adaptation algorithm

We have developed a speaker identification system that performs well under two situations that current identification system encounter difficulties with: when the speaker's voice is combined with interfering noise, and when multiple speakers have similar voices. Our system consists of several serial processors. First, four Chebyshev type 1 filters separate the sound signal into four overlapping spectral ranges. Each of the four signals is passed through a wavelet filter that utilizes a 3 level, Daubechies 4th order discrete wavelet transformation, generating one approximation and three detailed coefficient arrays. The resulting 16 signals are input for two gender-specific dynamic synapse neural networks that have three outputs corresponding to each of the 3 male or 3 female speakers in our study. The energy in each of the pulse train outputs of the DSNN is compared, the output with the highest energy is identified, and the corresponding speaker is chosen. The choice of which DSNN to use is determined by a gender identifier that has been developed in our laboratory. The DSNNs were trained using a genetic algorithm training method.

At present, the research on BP neural network has achieved good results in many industries and fields, but there are few projects in the application research of mineral resources mining. Under the social background of the rapid development of electronic information technology, BP neural network and GIS technology are combined to carry out research and application, which will provide a new research path for slope deformation monitoring and disaster prevention in mining area. Therefore, in the paper, the key technology of open-pit mine slope deformation automatic monitoring based on BP neural network and GIS technology was put forward. Firstly, the advantages of BP neural network were analyzed and BP neural network was selected as the prediction model of slope deformation. The artificial fish swarm algorithm was used to improve the BP neural network to improve the performance of the model. Based on the analysis and construction of GIS technology, the combination application of BP neural network and GIS technology was discussed. Through practice, the application effect of the technology was verified, and it has good theoretical and practical value

In this work a novel approach called peak detection and boundary identification (PD-BI) for period detection of heart sound (HS) signals in noisy environment is proposed. The PD method is inspired by a natural phenomenon that a horizontal soft string hits peaks of uneven ground line when falling from a high position. The BI method is based on the quasi-cyclic feature of HS. The simulation results validate the effectiveness and accuracy of PD-BI.Keywordsheart soundperiod detectionpeak detectionboundary identification

Paper focuses on the optimization of the advertising and other additional costs for the small business ecommerce web sites. The aim of this paper was to propose a dynamic neural network based algorithm to predict number of clicks on a particular advertising link in three web pages of three different small companies working in the same business segment. The dynamic neural network based algorithm was proposed for forecasting the upcoming values of the advertisement clicks. The best results of 10% average forecasting uncertainty was received for two layer NARX network with three additional inputs: bounce rate, average session time and average page load time. The application of NAR neural network without external inputs increased the forecasting uncertainty to 25% which is similar to received 26% LPC uncertainty.

This paper is concerned with stability analysis for a class of dynamical neural networks with distributed delays. The M-matrix theory and new analysis technique are used to obtain new sufficient conditions for the existence, uniqueness and global stability of the equilibrium point of dynamical neural networks with distributed delays. The importance of the new stability criteria in the design and application of dynamical neural networks with distributed delays is due to the fact that they can handle the case when the non-delayed terms can not dominate the delayed terms. The effectiveness of the obtained theoretical results are illustrated by numerical examples.

An adaptive identification method of simple dynamic recurr ent neural network (SRNN) for nonlinear dynamic systems is presented in this paper. This method based on the theory that by using the inner-states feed-back of dynamic network to describe the nonlinear kinetic characteris tics of system can reflect the dynamic ch aracteristics more directly, deduces the recursive prediction error (RPE) learning algorithm of SRNNe and improves the algorithm by studying topological structure on recursion layer without the weight values. The simulation results indicate that this kind of neural network can be used in real-time control, due to its less weight values, simpler learning algorithm, higher identification speed, and higher precision of model. It solves the problems of intricate in training algorithm and slow rate in convergence caused by the complicate topologi cal structure in usual dynami c recurrent neural network. Keywords: non-linear system, system identification, dynamic recurrent neural network, RPE algorithm

Discrimination and identification of acoustic signals in the human and animal auditory system are performed by means of feature extraction and analysis (Chistovich et al., 1976; Bibikov, 1978). Our first observations showed that dolphins also use features for signal discrimination (Dubrovsky and Titov, 1978; Dubrovsky and Zorikov, 1983).

Cell photoacoustic detection faces the problem where the strength of the sound wave signal is so weak that it easily gets interfered by other acoustic signals. A sonic triode model based on an artificial periodic structure is designed by COMSOL Multiphysics 5.3a software (Stockholm, Sweden), and software simulations are conducted. Experiments show that when a sound wave with a specific frequency is input by the sound wave triode, it can produce an energy amplification effect on the sound wave signals of the same frequency and a blocking effect on the sound wave signals of other frequencies. This contrast effect is more obvious after increasing the sound pressure intensity of the input sound wave signal. It can effectively filter out interference sound signals. The study of the acoustic triode model provides a new approach for the acquisition and identification of acoustic signals in cell photoacoustic detection, which can significantly improve the working efficiency and accuracy of cell photoacoustic detection.

In this paper the development and application of a dynamic neural network called the dynamic neural processor (DNP) are discussed. The DNP is developed based on the neuro-physiological evidence that neural activity of any complexity depends upon the interaction of assembly of cells called neural subpopulations. A single subpopulation of neurons is assumed to consist of a number of similar neurons that lie in close proximity. For simplicity, live neural subpopulations, namely excitatory and inhibitory, are assumed to exist in a neural population. The DNP consists of two dynamic neurons configured to function as excitatory and inhibitory neurons. A learning algorithm to adapt the weights of the subpopulation and the connecting weights between the subpopulations is developed. The efficacy of the DNP structure is demonstrated for the direct adaptive control of unknown nonlinear systems. >

With the development of computer technology, quantitative investment based on data and rules has gradually emerged in China. Quantitative model has become a powerful tool to predict the market and guide investment. However, due to the complexity of the stock market, the traditional time series prediction technology has many shortcomings. The introduction of nonlinear autoregressive neural network NARX provides a basis for quantitative analysis of investment in stocks. The quantitative stock technical index data is taken as the training parameter and input parameter of NARX dynamic regression neural network, and the analysis results are obtained. We have collected Shanghai composite index data, tested the accuracy of quantitative analysis method, analyzed the prediction results of the model, compared the difference between the prediction results and the actual data so as to analyze the accuracy of the model. KeywordsNeural networkNARXQuantitative investment

Retracted: Application of Neural Network and Virtual Reality Technology in Digital Video Effects

Application of Neural Networks in Computer Security

With the structure design and manufacture of CNC machine tool becoming more and more perfect, its geometry errors have been controlled, thermal error generated by thermal deformation of CNC machine tool is the main error, which has strongly influence on the CNC machine tool's process precision. Thermal error compensation is an important method for increasing the process precision of CNC machine tool, and the neural networks technology is the major tool in thermal error modeling and compensation. In this paper, some applications of neural networks in thermal error modeling and compensation are introduced, and they are demonstrated by examples, the results prove that researches on artificial neural networks and relative algorithms have good effects on CNC machine tool's thermal error modeling and compensation.

В статье рассмотрены теоретические основы концепции устойчивого развития и нейросетевых технологий, а также их компоненты. Исследуется применение нейронных сетей в разработке стратегии устойчивого развития компаний в отрасли информационных технологий. Рассматривается выделение ключевых показателей для разработки стратегии и план ее создания, включающий этапы анализа данных и определения целей. The article discusses the theoretical foundations of the concept of sustainable development and neural network technologies, as well as their components. The application of neural networks in the development of a strategy for the sustainable development of companies in the information technology industry is being investigated. The article considers the allocation of key indicators for the development of a strategy and a plan for its creation, including the stages of data analysis and goal definition.