Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896542
Pengsong Duan, Shuhang Han, Yangjie Cao
For Wi-Fi signal perception, aiming at problems of insufficient acquisition of feature and low recognition accuracy in multi-person scene in gait recognition, we propose a new gait recognition model WiMGNet based on energy distribution map(EDM). Depending on the channel response information impact factor analysis, WiMGNet uses the mechanism EDM to reconstruct the raw data effectively, so that it can contain more gait features. Furthermore, WiMGNet introduces EDM into neural network model, which obtains a high accuracy in gait recognition in multi-person scene. Compared to current gait recognition models, WiMGNet significantly improves the ability of feature acquisition and recognition accuracy. The experimental results show that WiMGNet has a recognition accuracy of 98.8% in 30-person scene experiment in indoor environment, which has obvious advantages compared to other similar models.
{"title":"An improved model for contactless gait recognition","authors":"Pengsong Duan, Shuhang Han, Yangjie Cao","doi":"10.1109/ISNE.2019.8896542","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896542","url":null,"abstract":"For Wi-Fi signal perception, aiming at problems of insufficient acquisition of feature and low recognition accuracy in multi-person scene in gait recognition, we propose a new gait recognition model WiMGNet based on energy distribution map(EDM). Depending on the channel response information impact factor analysis, WiMGNet uses the mechanism EDM to reconstruct the raw data effectively, so that it can contain more gait features. Furthermore, WiMGNet introduces EDM into neural network model, which obtains a high accuracy in gait recognition in multi-person scene. Compared to current gait recognition models, WiMGNet significantly improves the ability of feature acquisition and recognition accuracy. The experimental results show that WiMGNet has a recognition accuracy of 98.8% in 30-person scene experiment in indoor environment, which has obvious advantages compared to other similar models.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130711432","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896551
Huajie Xu, Zhaohui Wu, Jie Ding, Bin Li, Lanbo Lin, Jiangfeng Zhu, Zhijie Hao
The AdaBoost-based real-time face detections have been widely used in current video surveillance. However, the AdaBoost-based face detection has poor performances in detecting multi-face with different scales, multiple poses, and occlusion in complex lighting environment. Recent research shows that the convolutional neural network (CNN) can improve its accuracy. In this work, a FPGA based real-time multi-face detection system for crowded area surveillance application using CNN is presented. A hardware friendly fully quantization strategy is proposed and the result is tested on WIDER FACE dataset. With acceptable loss of accuracy, the FPGA based system can achieve a frame rate of 37 FPS at $512 times 288$ resolution with only 65 ms processing delay.
{"title":"FPGA Based Real-Time Multi-Face Detection System With Convolution Neural Network","authors":"Huajie Xu, Zhaohui Wu, Jie Ding, Bin Li, Lanbo Lin, Jiangfeng Zhu, Zhijie Hao","doi":"10.1109/ISNE.2019.8896551","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896551","url":null,"abstract":"The AdaBoost-based real-time face detections have been widely used in current video surveillance. However, the AdaBoost-based face detection has poor performances in detecting multi-face with different scales, multiple poses, and occlusion in complex lighting environment. Recent research shows that the convolutional neural network (CNN) can improve its accuracy. In this work, a FPGA based real-time multi-face detection system for crowded area surveillance application using CNN is presented. A hardware friendly fully quantization strategy is proposed and the result is tested on WIDER FACE dataset. With acceptable loss of accuracy, the FPGA based system can achieve a frame rate of 37 FPS at $512 times 288$ resolution with only 65 ms processing delay.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128981018","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896514
Dong Liang, Qinrang Liu, Bo Zhao, Zhihua Zhu, Dongpei Liu
Intrusion detection system(IDS) plays an important role in the cyberspace security. With the rapid development of Internet today, the network traffics to be processed by IDS has many redundant and irrelevant characteristics. Meanwhile, the amount of the network traffics to be processed is very large, which will affect the identification effect of IDS. This paper presents a method which integrates clustering algorithm with support vector machine to improve the accuracy and recognition rate of IDS. Firstly, the preprocessed data is processed by clustering algorithm and divided into several subsets, and then machine learning algorithm is used to model each subset. We compared our method with other state-of-the-art algorithms, and the experimental results showed that our method greatly reduced the training time of the model, and effectively improved the performance of the model.
{"title":"A Clustering-SVM Ensemble Method for Intrusion Detection System","authors":"Dong Liang, Qinrang Liu, Bo Zhao, Zhihua Zhu, Dongpei Liu","doi":"10.1109/ISNE.2019.8896514","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896514","url":null,"abstract":"Intrusion detection system(IDS) plays an important role in the cyberspace security. With the rapid development of Internet today, the network traffics to be processed by IDS has many redundant and irrelevant characteristics. Meanwhile, the amount of the network traffics to be processed is very large, which will affect the identification effect of IDS. This paper presents a method which integrates clustering algorithm with support vector machine to improve the accuracy and recognition rate of IDS. Firstly, the preprocessed data is processed by clustering algorithm and divided into several subsets, and then machine learning algorithm is used to model each subset. We compared our method with other state-of-the-art algorithms, and the experimental results showed that our method greatly reduced the training time of the model, and effectively improved the performance of the model.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122996911","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}
In this paper, an optimized commutation method based on BP neural network is proposed to solve the problem of slow response, large overshoot and power dissipation caused by algorithm deviation in conventional commutation strategy based on back electromotive force method. Performance of different commutation methods is compared by simulation. Experiment results show that the proposed method can realize a good commutation performance, with a 0.8% power deviation and a 15.906 mean square error compared with ideal condition, which improves 275 times than conventional strategy, 42 times than conventional Neural Network based strategy and has a better stability. The proposed method has better compensation ability for fixed errors such as signal transmission delay, signal filtering delay and motor armature effect at the same time.
{"title":"An Optimized Commutation Method for Sensorless Brushless DC Motor Based on Back Electromotive Force Using Backpropogation Neural Network","authors":"Yuxiang Liu, Zhaohui Wu, Bin Li, Fang Yuan, Zhaolin Yao, Xu Zhang","doi":"10.1109/ISNE.2019.8896360","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896360","url":null,"abstract":"In this paper, an optimized commutation method based on BP neural network is proposed to solve the problem of slow response, large overshoot and power dissipation caused by algorithm deviation in conventional commutation strategy based on back electromotive force method. Performance of different commutation methods is compared by simulation. Experiment results show that the proposed method can realize a good commutation performance, with a 0.8% power deviation and a 15.906 mean square error compared with ideal condition, which improves 275 times than conventional strategy, 42 times than conventional Neural Network based strategy and has a better stability. The proposed method has better compensation ability for fixed errors such as signal transmission delay, signal filtering delay and motor armature effect at the same time.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128536924","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896550
Xingjin Zhang, Runchuan Li, Qingyan Hu, Bing Zhou, Zongmin Wang
Myocardial Infarction (MI) has the characteristics of rapid development and poor prognosis. Early intervention is of great significance in relieving pain and preventing death. For reducing the misdiagnosis rate of MI, a novel classification approach of MI based on a long short term memory (LSTM) is proposed in this paper. Firstly, the original electrocardiogram (ECG) signal is preprocessed, and then it is divided into a heartbeat sequence. Then the heartbeat sequence is input into the deep neural network model for training and learning. Finally, the validity of the method is verified on the Physikalisch-Technische Bundesanstalt (PTB) ECG database. The accuracy of the method is 99.91%. The experimental results show that the classification accuracy of the proposed method is superior to the other methods.
{"title":"A New Automatic Approach to Distinguish Myocardial Infarction Based on LSTM","authors":"Xingjin Zhang, Runchuan Li, Qingyan Hu, Bing Zhou, Zongmin Wang","doi":"10.1109/ISNE.2019.8896550","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896550","url":null,"abstract":"Myocardial Infarction (MI) has the characteristics of rapid development and poor prognosis. Early intervention is of great significance in relieving pain and preventing death. For reducing the misdiagnosis rate of MI, a novel classification approach of MI based on a long short term memory (LSTM) is proposed in this paper. Firstly, the original electrocardiogram (ECG) signal is preprocessed, and then it is divided into a heartbeat sequence. Then the heartbeat sequence is input into the deep neural network model for training and learning. Finally, the validity of the method is verified on the Physikalisch-Technische Bundesanstalt (PTB) ECG database. The accuracy of the method is 99.91%. The experimental results show that the classification accuracy of the proposed method is superior to the other methods.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116786318","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896605
Y. Hu, Zhiping Wang
In this paper, the state of charge (SOC) is estimated by charging the battery at constant current and voltage, collecting the current, voltage, temperature and internal resistance during the experiment. The influence of internal resistance on SOC prediction of lithium batteries is mainly considered. In this paper, the Improved BP neural network is used to carry out simulation experiments. The experimental results show that the prediction accuracy is higher and the simulation effect is better than that without considering the internal resistance.
{"title":"Study on SOC Estimation of Lithium Battery Based on Improved BP Neural Network","authors":"Y. Hu, Zhiping Wang","doi":"10.1109/ISNE.2019.8896605","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896605","url":null,"abstract":"In this paper, the state of charge (SOC) is estimated by charging the battery at constant current and voltage, collecting the current, voltage, temperature and internal resistance during the experiment. The influence of internal resistance on SOC prediction of lithium batteries is mainly considered. In this paper, the Improved BP neural network is used to carry out simulation experiments. The experimental results show that the prediction accuracy is higher and the simulation effect is better than that without considering the internal resistance.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115453132","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896447
Bei Li, Zhaohui Wu, J. Deng, D. Dai, Bin Li, Qiang Su, Yangyang Peng
In order to make the RF front-end more compact and efficient, a chip integrating surface acoustic wave (SAW) filters and a reconfigurable multi-frequency multi-mode power amplifier (MMPA) was designed. Taped out and the test results showed that: the EUTRAACLR1 of the integrated chip is decreased by 0.54dBc compared to the discrete connections, the UTRAACLR1 is decreased by 1.33dBc, the ICC is decreased by 43.5mA, the PAE is increased by 0.55% and the Gain is increased by 0.32dB. Reliability Electrostatic test and aging test meet the production requirements.
{"title":"Integrated Design of Power Amplifier and Saw Filters for Reconfigurable RF Front-end","authors":"Bei Li, Zhaohui Wu, J. Deng, D. Dai, Bin Li, Qiang Su, Yangyang Peng","doi":"10.1109/ISNE.2019.8896447","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896447","url":null,"abstract":"In order to make the RF front-end more compact and efficient, a chip integrating surface acoustic wave (SAW) filters and a reconfigurable multi-frequency multi-mode power amplifier (MMPA) was designed. Taped out and the test results showed that: the EUTRAACLR1 of the integrated chip is decreased by 0.54dBc compared to the discrete connections, the UTRAACLR1 is decreased by 1.33dBc, the ICC is decreased by 43.5mA, the PAE is increased by 0.55% and the Gain is increased by 0.32dB. Reliability Electrostatic test and aging test meet the production requirements.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115746087","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896417
H. Hua, Zhen Zhang
With the increasing demand for logistics in China, the shortcomings of the current short-range logistics field are inefficient, and the occupation of labor is becoming more and more obvious. The proportion of the personnel engaged in production and the transportation personnel who ensure the flow of materials continues to increase, and the production efficiency of the total social labor force continues to decline. In this paper, combined with artificial intelligence related technology, a special drone design scheme is proposed instead of short-distance logistics distributors, aiming at adjusting short-range logistics links, improving logistics efficiency, and optimizing related logistics processes to reduce the need of number of workers to ensure the normal transportation of logistics.
{"title":"Application of Artificial Intelligence Technology in Short-range Logistics Drones","authors":"H. Hua, Zhen Zhang","doi":"10.1109/ISNE.2019.8896417","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896417","url":null,"abstract":"With the increasing demand for logistics in China, the shortcomings of the current short-range logistics field are inefficient, and the occupation of labor is becoming more and more obvious. The proportion of the personnel engaged in production and the transportation personnel who ensure the flow of materials continues to increase, and the production efficiency of the total social labor force continues to decline. In this paper, combined with artificial intelligence related technology, a special drone design scheme is proposed instead of short-distance logistics distributors, aiming at adjusting short-range logistics links, improving logistics efficiency, and optimizing related logistics processes to reduce the need of number of workers to ensure the normal transportation of logistics.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115290135","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896611
Chandrasekhar Mandalapu, I. Abdel-Motaleb, Sangki Hong, R. Patti
3D integrated circuit (3D-IC) technology gained acceptance due to the ability to achieve extremely high level of integration, where hundreds of ICs are stacked vertically. Such level of integration can result in local power dissipation of more than 50 kW/cm2. This will lead to instant evaporation of the IC, unless an effective cooling technique is employed. Liquid cooling may be one of the most effective techniques for this task. To investigate the effectiveness of this technique, we designed, built and tested a testing platform. The platform includes a testing chip and a cooling module. The test chip contains heaters to provide the power and sensors to measure the local temperature. The study shows that the proposed cooling modules can reduce the temperature for a 420W/inch square circuits to a normal operating range of ICs of 39-50 ˚C, using 2 phase R22 liquid coolant.
{"title":"Design, Fabrication, and Testing of a Liquid Cooling Platform for High Power 3D-ICs","authors":"Chandrasekhar Mandalapu, I. Abdel-Motaleb, Sangki Hong, R. Patti","doi":"10.1109/ISNE.2019.8896611","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896611","url":null,"abstract":"3D integrated circuit (3D-IC) technology gained acceptance due to the ability to achieve extremely high level of integration, where hundreds of ICs are stacked vertically. Such level of integration can result in local power dissipation of more than 50 kW/cm2. This will lead to instant evaporation of the IC, unless an effective cooling technique is employed. Liquid cooling may be one of the most effective techniques for this task. To investigate the effectiveness of this technique, we designed, built and tested a testing platform. The platform includes a testing chip and a cooling module. The test chip contains heaters to provide the power and sensors to measure the local temperature. The study shows that the proposed cooling modules can reduce the temperature for a 420W/inch square circuits to a normal operating range of ICs of 39-50 ˚C, using 2 phase R22 liquid coolant.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128140640","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}
Pub Date : 2019-10-01DOI: 10.1109/ISNE.2019.8896382
Feibo Du, Zhiwei Liu, J. Liou
In this paper, the influence of inner p-type guard ring (PGR) on the triggering characteristics of diode-triggered silicon-controlled rectifier (DTSCR) is studied. The ESD characteristics of conventional DTSCR with and without inner PGR are measured with the transmission line pulsing (TLP) tester. The results indicate that lower trigger voltage of DTSCR can be obtained by floating the internal PGR, which enhances the current conduction ability of the parasitic SCR in DTSCR essentially. A stronger parasitic SCR can provide a current discharge path with lower resistance before the main SCR is turned on, thus reducing the trigger voltage of the device. Furthermore, two improved structures of DTSCR are also considered, which further confirms the auxiliary triggering effect of parasitic SCR or parasitic PNPNPN structure in these devices.
{"title":"Effect of P-type Guard ring on the Turn-on Characteristics of Diode-triggered SCR","authors":"Feibo Du, Zhiwei Liu, J. Liou","doi":"10.1109/ISNE.2019.8896382","DOIUrl":"https://doi.org/10.1109/ISNE.2019.8896382","url":null,"abstract":"In this paper, the influence of inner p-type guard ring (PGR) on the triggering characteristics of diode-triggered silicon-controlled rectifier (DTSCR) is studied. The ESD characteristics of conventional DTSCR with and without inner PGR are measured with the transmission line pulsing (TLP) tester. The results indicate that lower trigger voltage of DTSCR can be obtained by floating the internal PGR, which enhances the current conduction ability of the parasitic SCR in DTSCR essentially. A stronger parasitic SCR can provide a current discharge path with lower resistance before the main SCR is turned on, thus reducing the trigger voltage of the device. Furthermore, two improved structures of DTSCR are also considered, which further confirms the auxiliary triggering effect of parasitic SCR or parasitic PNPNPN structure in these devices.","PeriodicalId":405565,"journal":{"name":"2019 8th International Symposium on Next Generation Electronics (ISNE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124481579","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：