Content of Computer and Electronics in our journal

Published in last 1 year |  In last 2 years |  In last 3 years |  All Please wait a minute... For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails Select Solving TSP Issue Based on  Improved Harmony Algorithm WU Ying, OU Yun, YAO Xuanshi, DING Lei Journal of Jishou University(Natural Sciences Edition)    2021, 42 (1): 35-40.   DOI: 10.13438/j.cnki.jdzk.2021.01.006 Abstract （1595）      PDF（pc） （682KB）（699）       Knowledge map    Save To improve the convergence speed and accuracy of harmony search (HS) algorithm, a dynamic harmony search algorithm (DHSA) by dynamic adjustment probability mechanism is presented in this paper to settle traveling salesman problem (TSP). In simulation, three classic algorithms, which are genetic algorithm (GA), Harmony Search Algorithm (HSA), and DHSA are selected to verify the feasibility by implementing two TSP data-sets bayg29 and ch150, respectively. The results reveal that the DHSA could obtain the shortest path among these algorithms. Reference | Related Articles | Metrics | Comments（0） Select Research Review of Recurrent Neural Networks WANG Yuyan, LIAO Bolin, PENG Chen, LI Jun, YIN Yumin Journal of Jishou University(Natural Sciences Edition)    2021, 42 (1): 41-48.   DOI: 10.13438/j.cnki.jdzk.2021.01.007 Abstract （2156）      PDF（pc） （516KB）（663）       Knowledge map    Save Recurrent neural network (RNN) is a kind of neural network with feedback connection in each layer. Because of its storage characteristics, it can process the sequence data which is related before and after input, and can be widely used in the field of text audio, video and so on. But when the input gap is large, RNN has a short-term memory problem, which can not process long input sequences, while long short-term memory (LSTM) can deal with the long-term dependence problem well. Almost all the exciting results based on RNNs have been realized by LSTM since LSTM was proposed, so LSTM has become the focus of deep learning. This review firstly introduces the basic working principle and characteristics of RNN, and then it introduces the principle and characteristics of LSTM and its variants, as well as  the application of RNN and LSTM in various fields. Finally, the future research direction of RNN is proposed. Reference | Related Articles | Metrics | Comments（0） Select Performance Analysis of Fifth Order IIR Digital Low-Pass Filter ZHOU Xuan, WU Yunwen Journal of Jishou University(Natural Sciences Edition)    2021, 42 (1): 49-53.   DOI: 10.13438/j.cnki.jdzk.2021.01.008 Abstract （1822）      PDF（pc） （437KB）（436）       Knowledge map    Save MATLAB software platform is used to study the performance of the fifth order IIR digital low-pass filter designed by bilinear transformation method. The relationship between the order of digital filter and the maximum attenuation of passband, the minimum attenuation of stopband, the corner frequency of passband boundary and the corner frequency of stopband boundary is derived. At the same time, the transition band and stop band of the filter are further analyzed by combining the system function, z-domain analysis and simulation results. Analysis indicates that: the fifth order IIR digital low-pass filter is a stable system, the phase presents delay in the passband and stopband. When the frequency is 0.25π rad/s, the phase state has reverse mutation, and the transmitted signal envelope collapses and enters the transition band. At this time, the phase presents a leading state. When the amplitude response in the stopband decays to 0, the system signal still has phase change, and  there is still signal in this frequency band. Reference | Related Articles | Metrics | Comments（0）