Juan Guo, Liang Chen, Haoran Sun, Aidong Xu, Zeguang Li, Yinwei Zhao, Yixin Jiang, Tengyue Zhang, Yunan Zhang
{"title":"A Defense Method Based on a Novel Replay Attack","authors":"Juan Guo, Liang Chen, Haoran Sun, Aidong Xu, Zeguang Li, Yinwei Zhao, Yixin Jiang, Tengyue Zhang, Yunan Zhang","doi":"10.1109/ICPECA51329.2021.9362528","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362528","url":null,"abstract":"Replay attack is a common attack model, and we propose a novel voice replay attack against intelligent voice assistants. This is a speaker array-based attack method that modulates the attack commands onto a high-frequency carrier and uses the nonlinear self-demodulation of the speaker array and air to produce speech commands audible to the human ear that which confirm can be executed by a voice smart assistance. In this paper, a novel voice replay attack against intelligent voice assistants is proposed by characterizing the speech attack and non-attack signals generated by the loudspeaker arrays and analyze their amplitude and frequency characteristics. We also propose and validate a software defense method based on machine learning and neural networks, and the results show that the method is effective.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115428442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on Passive Method of Doppler Coefficient of Underwater High Speed Moving Target","authors":"Nan Zou, Junyi He, Feng Liu, Chenmu Li, Yunbo Hao","doi":"10.1109/ICPECA51329.2021.9362626","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362626","url":null,"abstract":"Doppler estimation is an important issue for passive positioning of flank arrays. In practical applications, Doppler compensation is an effective method to correct positioning errors caused by Doppler. To obtain the Doppler coefficient difference, this paper proposes two estimation methods: a method based on frequency domain cross-correlation (Hereinafter referred to as FDC method) and a method based on feature extraction (Hereinafter referred to as FE method). FDC method obtains the cross-correlation peak position of each subband Fourier series module of the receiving signal. FE method matches the pole position of the frequency domain waveform between different array elements and calculates the frequency shift to obtain the curve of the relationship between frequency and frequency shift. This paper comparatively analyzes the estimation error and computation amount of ambiguity function method (Hereinafter referred to as AF method), FDC method and FE method. Compared with AF method, the FDC and FE methods can achieve Doppler estimation and effectively reduce the estimation computation cost.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115719576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FPGA-based scalable and highly concurrent convolutional neural network acceleration","authors":"Hao Xiao, Kunhua Li, Mingcheng Zhu","doi":"10.1109/ICPECA51329.2021.9362549","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362549","url":null,"abstract":"This article proposes an efficient, low-latency, scalable, and low-error neural network acceleration architecture. Considering the performance requirements of high efficiency and low latency, the methods of multi-channel parallel computing between layers and pipeline design are adopted to accelerate the neural network. Then, based on Xilinx zynq-7000 FPGA, the acceleration strategy is realized, and the effect of calculating 28*28 handwritten images at 25.95us at a clock frequency of 200M is investigated. Further, the flexibility and scalability of the network is improved by adding a line buffer for variable image width and designing a mechanism for selectable convolution kernel size. Since the convolutional neural networks are based on floating-point operations, if the floating-point is converted to fixed-point when implemented on FPGA, there will not only be a loss of precision, but also introduce a tedious conversion work. Thus, our neural network uses 32-bit Floating point operations. Moreover, the task of handwritten digit recognition is performed on the MNIST data set, to experimentally evaluate our solution. Experiment results show that the neural network acceleration architecture proposed in this paper achieves better performance. Compare with the literature [4],[6], the calculation speed is significantly improved, and the calculation speed is increased by 101.6 times compared with the literature [4] Compared with the literature [6], there is a speed increase of 11.88 times.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124826352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liu Chaonan, Wang Jinliang, Fan Hongzhen, Rong Xiao, Xu Jiaheng, Fan Youpeng
{"title":"A practical on-site analysis method of smart electricity meter wiring with the reversed secondary polarity of voltage transformer","authors":"Liu Chaonan, Wang Jinliang, Fan Hongzhen, Rong Xiao, Xu Jiaheng, Fan Youpeng","doi":"10.1109/ICPECA51329.2021.9362658","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362658","url":null,"abstract":"High-voltage three-phase three-wire energy meter is widely used in small current grounding system, whose neutral point ungrounded or grounded through arc suppression coil in 35kV and below voltage level. In particular, 10kV power customers mostly use this three-phase two-element electric energy meter to measure electric energy. Because the voltage transformer and current transformer are connected with the meter, the wiring is more complicated. After the meter have been installed, there may be some problems which will lead to incorrect measurement. Among these wrong wirings, the reverse polarity of the secondary side of the TV is difficult to distinguish. An initial judgment for TV secondary polarity reverse wiring can be obtained through conventional data measuring. Assuming that the uv (or wv) phase polarity is reversely connected, analyze the line voltages related to phase v, determine another line voltage vector in the vector diagram according to the angle between the two line voltage vectors on corresponding measuring elements, and identify current vector position through the phase angle from voltage vector. Then the accurate analysis and judgment of the three-phase and three-wire energy meter TV secondary polarity reverse wiring can be achieved.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125808957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Underwater target tracking method based on convolutional neural network","authors":"Jiaqi Wang, Ruxin Fan","doi":"10.1109/ICPECA51329.2021.9362582","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362582","url":null,"abstract":"In order to solve the problems of low accuracy of underwater target tracking, poor real-time performance and large amount of calculation required, an underwater target tracking method based on the improved SiamRPN++ algorithm is adopted. By selecting the inverted residual bottleneck block to construct a new backbone network SmallMobileNet, instead of the backbone network ResNet-50 of the SiamRPN++algorithm, the use of deep separable convolution to reduce the amount of calculation, while ensuring accuracy and real-time performance, adjust The number of channels, layers, parameters of the network and the complexity of each segment of the network are used to reduce the computational cost and hardware requirements, so that the algorithm can be transplanted to the underwater tracking platform. Through experiments, compared with the original algorithm, the accuracy of the SiamRPN++ algorithm with Small-MobileNet as the backbone network is improved, the amount of network parameters and calculations are reduced, and the tracking speed is improved, which verifies the effectiveness of the method.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125498539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xincheng Shen, Y. Qu, Shaoxiong Huang, Zhi Li, Kaifeng Zhang
{"title":"Wind Speed Data Repairing Method Based on Bidirectional Prediction","authors":"Xincheng Shen, Y. Qu, Shaoxiong Huang, Zhi Li, Kaifeng Zhang","doi":"10.1109/ICPECA51329.2021.9362540","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362540","url":null,"abstract":"In order to repair the lost data in distributed wind power system, this paper puts forward a wind speed data repairing model based on a new bidirectional prediction method. This model consists of two one-way prediction models. In each prediction model, the original wind speed data are decomposed into several intrinsic mode functions (IMFs) and a residue signal by ensemble empirical mode decomposition (EEMD) method. Then the Savitzky–Golay (SG) filter is used to reduce noise for high-frequency IMFs. Next the long short-term memory (LSTM) model and autoregressive integrated moving average (ARIMA) model are combined to predict low-frequency IMFs and the noise reduction results respectively. At the end, all those forecast results are added and form a one-way result. By weighted average of two one -way results, the repairing result is calculated. The experimental results from multiple prediction cases show that this method can get more accurate results.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122311919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Entity recognition model of power safety regulations knowledge graph based on BERT-BiLSTM-CRF","authors":"Jianyou Yu, Jian Sun, Yunchang Dong, Dezhi Zhao, Xiaoyu Chen, Xianghong Chen","doi":"10.1109/ICPECA51329.2021.9362652","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362652","url":null,"abstract":"In the process of constructing the knowledge graph of power safety regulations, the traditional named entity recognition method is difficult to effectively identify the key information of the entity because the boundary of the power safety entity is fuzzy and difficult to define. Therefore, this paper proposes a power safety named entity recognition model based on BERT-BiLSTM-CRF. First, the word vector expression layer based on Transformer’s bidirectional encoder (BERT) obtains word-level features; then the bidirectional long-short-term memory neural network (BiLSTM) layer is used to extract contextual features to form a feature matrix, thereby improving the accuracy of text feature extraction; The optimal tag sequence is generated by the conditional random field layer (CRF), and the output result is corrected. Through the analysis of experimental examples, the validity and superiority of the proposed model are verified.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122030412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of the Frequency Modulated Continuous Wave (FMCW) Waveforms, Simulation of the Real Road Scenario and Signal Processing for the Automotive Adaptive Cruise Control","authors":"Xinyue Wang","doi":"10.1109/ICPECA51329.2021.9362523","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362523","url":null,"abstract":"Adaptive Cruise Control (ACC) system has aroused much concern nowadays to increase the ability of road scenario indication and enhance the safety of self-driving application. FMCW radar-based technology is the main technique used in ACC system for target detection due to its high resolution and accuracy. The dominating purpose from radar point of view is to observe all the objects within detection range and estimate their range and relative velocity simultaneously and provide all the target information for automotive control system for further processing. A 77GHz FMCW radar system, implementing Fast Fourier Transform (FFT) technology for signal processing, is presented in this paper to detect specific targets in the designed road scenario for automotive application. Basic features of FMCW radar are introduced in detail, along with the process of radar system simulation and waveform generation discussed. The results in regard to targets such as Range-Doppler map are displayed in MATLAB.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116616184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Computer network security countermeasures based on big data","authors":"Ke Mei","doi":"10.1109/ICPECA51329.2021.9362621","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362621","url":null,"abstract":"With the rapid development of science and technology in China, high-tech information technology is constantly developing and exploring, and is widely used in human work and life. Among them, computer technology based on big data is more representative. Big data technology is a technology of searching and analyzing collected information, which can solve many problems. Nowadays, big data technology plays an important role in construction, finance, trade and other fields. The increasingly innovative social demand puts forward new challenges to the development and application of computers, as well as new requirements for computer users. Network security is the basis of good application of computer technology. At the same time, “the wind of big data” also leads to many security problems. In view of the problems existing in the computer network in the era of big data, this paper studies how to effectively solve these problems, and uses data encryption technology to prevent them. The experimental results show that the data encryption technology can be effectively applied in the field of computer network security protection, and the accuracy rate of data information is as high as 95.3%. Hope to provide some help to the staff and users in related fields.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117042995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Cao, Weike Yang, Fen Li, Jie Zhao, Lifang Jia, Xiaoming Ma
{"title":"Research on Intelligent Drawing Technology of Steel Frame Structure","authors":"D. Cao, Weike Yang, Fen Li, Jie Zhao, Lifang Jia, Xiaoming Ma","doi":"10.1109/ICPECA51329.2021.9362629","DOIUrl":"https://doi.org/10.1109/ICPECA51329.2021.9362629","url":null,"abstract":"In order to improve the efficiency of drawing in the process of steel structure frame design, the intelligent drawing technology is studied and the intelligent drawing module is developed, the technology and realization method of the intelligent drawing module with the functions of graphic customization, graphic filtering, intelligent selection, intelligent editing and intelligent puzzle are presented. The technical content of the intelligent drawing module is also discussed in this paper. Through the research of intelligent module technology and the development of software, the drawing efficiency of steel structure frame has been greatly improved and the design period has been effectively shortened.","PeriodicalId":119798,"journal":{"name":"2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA)","volume":"650 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117102230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}