Pub Date : 2019-05-01DOI: 10.1109/WOCC.2019.8770689
Anqi Zhu, Songtao Guo, Mingfang Ma, Hao Feng, Bei Liu, Xin Su, Minghong Guo, Qiucen Jiang
Mobile edge computing (MEC) can significantly enhance device computing power by offloading service workflows from mobile device computing to mobile network edges. Thus how to implement an efficient computation offloading mechanism is a major challenge nowadays. For the purpose of addressing this problem, this paper aims to reduce application completion time and energy consumption of user device (UD) in offloading. The algorithm proposed formalizes the computation offloading problem into an energy and time optimization problem according to user experience, and obtains the optimal cost strategy on the basis of deep Q-learning (DQN). The simulation results show that comparing to the known local execution algorithm and random offloading algorithm, the computation offloading algorithm proposed in this paper can significantly reduce the energy consumption and shorten the completion time of service workflow execution.
{"title":"Computation Offloading for Workflow in Mobile Edge Computing Based on Deep Q-Learning","authors":"Anqi Zhu, Songtao Guo, Mingfang Ma, Hao Feng, Bei Liu, Xin Su, Minghong Guo, Qiucen Jiang","doi":"10.1109/WOCC.2019.8770689","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770689","url":null,"abstract":"Mobile edge computing (MEC) can significantly enhance device computing power by offloading service workflows from mobile device computing to mobile network edges. Thus how to implement an efficient computation offloading mechanism is a major challenge nowadays. For the purpose of addressing this problem, this paper aims to reduce application completion time and energy consumption of user device (UD) in offloading. The algorithm proposed formalizes the computation offloading problem into an energy and time optimization problem according to user experience, and obtains the optimal cost strategy on the basis of deep Q-learning (DQN). The simulation results show that comparing to the known local execution algorithm and random offloading algorithm, the computation offloading algorithm proposed in this paper can significantly reduce the energy consumption and shorten the completion time of service workflow execution.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122249830","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770544
Lincong Zhang, Ce Zhang, Kefeng Wei, Wenbo Zhang, Yongxin Feng
In recent years, the Wearable Wireless Sensor Network (WWSN) has become one of the most popular disaster relief networks. On-Body network is a key part of WWSN, which is responsible for the communication between wearable wireless sensor nodes and the coordinator in WWSN. The routing algorithm for On-body network is related to the energy consumption of wearable wireless sensor nodes and even the lifetime of the network. Therefore, this paper proposes a topology variable routing algorithm (TVRA) in On-Body networks. Firstly, the algorithm designs multi-hop routing to prolong the network lifetime on the premise of energy balance under the normal state of the network. When the network is abnormal, a single hop routing is adopted to ensure that the abnormal data can be sent with the lowest delay. The simulation results show that the proposed TVRA algorithm has better performance in terms of lifetime and time delay.
{"title":"Topology Variable Routing Algorithm for WWSN in Disaster Rescue","authors":"Lincong Zhang, Ce Zhang, Kefeng Wei, Wenbo Zhang, Yongxin Feng","doi":"10.1109/WOCC.2019.8770544","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770544","url":null,"abstract":"In recent years, the Wearable Wireless Sensor Network (WWSN) has become one of the most popular disaster relief networks. On-Body network is a key part of WWSN, which is responsible for the communication between wearable wireless sensor nodes and the coordinator in WWSN. The routing algorithm for On-body network is related to the energy consumption of wearable wireless sensor nodes and even the lifetime of the network. Therefore, this paper proposes a topology variable routing algorithm (TVRA) in On-Body networks. Firstly, the algorithm designs multi-hop routing to prolong the network lifetime on the premise of energy balance under the normal state of the network. When the network is abnormal, a single hop routing is adopted to ensure that the abnormal data can be sent with the lowest delay. The simulation results show that the proposed TVRA algorithm has better performance in terms of lifetime and time delay.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130198378","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770593
Ming Zhang, Chengjian Liao, Kui Xu, Wei Xie, Jianhui Xu, Lihua Chen
In this paper, we consider a hybrid air-terrestrial network secure transmission scenario, where a low-altitude air platform (AP) equipped with a two-dimensional (2D) rectangular antenna array serves a set of legitimate users (LUs). A single-antenna vehicle eavesdropper is within the courage of the AP, and the eavesdropper sends jamming signals in the uplink training and transmission phase and eavesdrops on LUs signals in the downlink transmission phase. During the training phase, a angle-domain (AD) channel estimation scheme is proposed. The active beam sets (ABS) of the interference channel and the LU channels can be separately extracted by comparing the beam gain vectors from different LUs. The pilot contamination can be eliminated and the channel state information (CSI) of LUs can be purified. By using spatial basis expansion model (BEM), full-dimension CSI of LUs and ED can be obtained, based on which the digital domain angle alignment method is designed to locate the ED. The superiority of the proposed scheme is evaluated by simulations.
{"title":"Angle-Domain Channel and DOA Estimation in Airborne Massive MIMO System with Eavesdropper","authors":"Ming Zhang, Chengjian Liao, Kui Xu, Wei Xie, Jianhui Xu, Lihua Chen","doi":"10.1109/WOCC.2019.8770593","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770593","url":null,"abstract":"In this paper, we consider a hybrid air-terrestrial network secure transmission scenario, where a low-altitude air platform (AP) equipped with a two-dimensional (2D) rectangular antenna array serves a set of legitimate users (LUs). A single-antenna vehicle eavesdropper is within the courage of the AP, and the eavesdropper sends jamming signals in the uplink training and transmission phase and eavesdrops on LUs signals in the downlink transmission phase. During the training phase, a angle-domain (AD) channel estimation scheme is proposed. The active beam sets (ABS) of the interference channel and the LU channels can be separately extracted by comparing the beam gain vectors from different LUs. The pilot contamination can be eliminated and the channel state information (CSI) of LUs can be purified. By using spatial basis expansion model (BEM), full-dimension CSI of LUs and ED can be obtained, based on which the digital domain angle alignment method is designed to locate the ED. The superiority of the proposed scheme is evaluated by simulations.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130950920","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}
A network model for facial expression recognition is designed and named DI-FERNet in this paper. The network uses depth-wise separable convolution, dilated convolution and residual module to build the network structure. This paper uses MTCNN to perform face alignment processing on the pictures in the dataset. A large number of experiments are carried out on the selected expression datasets KDEF and RAF. The test accuracy on KDEF is 97.2% and on the RAF is 77.1%.
{"title":"Research on Facial Expression Recognition Algorithm Based on Convolutional Neural Network","authors":"Xiaobo Zhang, Yuliang Yang, Linhao Zhang, Wanchong Li, Shuai Dang, Peng Wang, Mengyu Zhu","doi":"10.1109/WOCC.2019.8770616","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770616","url":null,"abstract":"A network model for facial expression recognition is designed and named DI-FERNet in this paper. The network uses depth-wise separable convolution, dilated convolution and residual module to build the network structure. This paper uses MTCNN to perform face alignment processing on the pictures in the dataset. A large number of experiments are carried out on the selected expression datasets KDEF and RAF. The test accuracy on KDEF is 97.2% and on the RAF is 77.1%.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130968378","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770649
Huijuan Wang, Jiang Yong, Xingmin Ma
Bi-dimensional empirical mode decomposition can decompose the source image into several Bi-dimensional Intrinsic Mode Functions. In the process of image decomposition, interpolation is needed and the upper and lower envelopes will be drawn. However, these interpolations and the drawings of upper and lower envelopes require a lot of computation time and manual screening. This paper proposes a simple but effective method that can maintain the characteristics of the original BEMD method, and the Hermite interpolation reconstruction method is used to replace the surface interpolation, and the variable neighborhood window method is used to replace the fixed neighborhood window method. We call it fast bi-dimensional empirical mode decomposition of the variable neighborhood window method based on research characteristics, and we finally complete the image fusion. The empirical analysis shows that this method can overcome the shortcomings that the source image features and details information of BIMF component decomposed from the original BEMD method are not rich enough, and reduce the calculation time, and the fusion quality is better.
{"title":"Fast Bi-dimensional Empirical Mode based Multisource Image Fusion Decomposition","authors":"Huijuan Wang, Jiang Yong, Xingmin Ma","doi":"10.1109/WOCC.2019.8770649","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770649","url":null,"abstract":"Bi-dimensional empirical mode decomposition can decompose the source image into several Bi-dimensional Intrinsic Mode Functions. In the process of image decomposition, interpolation is needed and the upper and lower envelopes will be drawn. However, these interpolations and the drawings of upper and lower envelopes require a lot of computation time and manual screening. This paper proposes a simple but effective method that can maintain the characteristics of the original BEMD method, and the Hermite interpolation reconstruction method is used to replace the surface interpolation, and the variable neighborhood window method is used to replace the fixed neighborhood window method. We call it fast bi-dimensional empirical mode decomposition of the variable neighborhood window method based on research characteristics, and we finally complete the image fusion. The empirical analysis shows that this method can overcome the shortcomings that the source image features and details information of BIMF component decomposed from the original BEMD method are not rich enough, and reduce the calculation time, and the fusion quality is better.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114893780","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}
This paper addresses the joint time difference of arrival (TDOA) and frequency difference of arrival (FDOA) estimation problem in passive emitter localization, involving range migration during the long observation time. A noise-resistant estimation algorithm based on Keystone transform is proposed. This method can efficiently avoid the Doppler ambiguity problem of the conventional approach by constructing the phase compensation without any signal-to-noise ratio loss. Moreover, compared with the ideal maximum likelihood estimator via extensive numerical experiments, the proposed method can achieve comparable estimation performance and have gain a significant reduction to the computational cost. Extensive numerical experiments validate the effectiveness of the proposed algorithm.
{"title":"Noise-Resistant Estimation Algorithm for TDOA and FDOA in Passive Emitter Localization","authors":"Zhixin Liu, D. Hu, Yonziun Zhao, Yongsheng Zhao, Rui Wang, Hongzhi Jiang","doi":"10.1109/WOCC.2019.8770683","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770683","url":null,"abstract":"This paper addresses the joint time difference of arrival (TDOA) and frequency difference of arrival (FDOA) estimation problem in passive emitter localization, involving range migration during the long observation time. A noise-resistant estimation algorithm based on Keystone transform is proposed. This method can efficiently avoid the Doppler ambiguity problem of the conventional approach by constructing the phase compensation without any signal-to-noise ratio loss. Moreover, compared with the ideal maximum likelihood estimator via extensive numerical experiments, the proposed method can achieve comparable estimation performance and have gain a significant reduction to the computational cost. Extensive numerical experiments validate the effectiveness of the proposed algorithm.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117070356","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770622
Cheng Li, D. Guo, K. Guo, Yuan Qin, Rui Xu
This paper investigates the impact of partial relay selection scheme (PRSS) on cooperative underlay cognitive radio (CR) non-orthogonal multiple access (NOMA) networks. Decode-and-forward (DF) protocol is used at the selected relay to assist simultaneous transmission from the source node to destination users. Based on the above assumptions, we obtain the closed-form expressions of the outage probability (OP) for the secondary users. Moreover, the analytical results of this paper verify the impacts of relay node's number and power allocation (PA) on the system performance. Monte Carlo (MC) simulations validate the theoretical results.
{"title":"Outage Performance of Partial Relay Selection in Underlay CR-NOMA Networks","authors":"Cheng Li, D. Guo, K. Guo, Yuan Qin, Rui Xu","doi":"10.1109/WOCC.2019.8770622","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770622","url":null,"abstract":"This paper investigates the impact of partial relay selection scheme (PRSS) on cooperative underlay cognitive radio (CR) non-orthogonal multiple access (NOMA) networks. Decode-and-forward (DF) protocol is used at the selected relay to assist simultaneous transmission from the source node to destination users. Based on the above assumptions, we obtain the closed-form expressions of the outage probability (OP) for the secondary users. Moreover, the analytical results of this paper verify the impacts of relay node's number and power allocation (PA) on the system performance. Monte Carlo (MC) simulations validate the theoretical results.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123689146","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770610
Ceyi Ma, Y. Wen, Dan Zhang, Jianjun Xiao, Wangqun Sheng
The position and morphology of cables may affect the calculation of distribution parameters between muti-conductors, and then impact crosstalk prediction of cables. Therefore, a novel method based on Cosserat elastic rod theory for predicting crosstalk of cables is proposed in this paper. Consider the physical characteristics of cable, which can be closer to reality, a central line function is applied into cables modeling. The crosstalk of the cable physical model are analyzed by Method of Moment. The results illustrate that crosstalk prediction will be affected due to various degree of cable deformation, and the Cosserat model is of great significance for crosstalk prediction of cables.
{"title":"Crosstalk Prediction of Cables Based on Cosserat Elastic Rod Theory","authors":"Ceyi Ma, Y. Wen, Dan Zhang, Jianjun Xiao, Wangqun Sheng","doi":"10.1109/WOCC.2019.8770610","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770610","url":null,"abstract":"The position and morphology of cables may affect the calculation of distribution parameters between muti-conductors, and then impact crosstalk prediction of cables. Therefore, a novel method based on Cosserat elastic rod theory for predicting crosstalk of cables is proposed in this paper. Consider the physical characteristics of cable, which can be closer to reality, a central line function is applied into cables modeling. The crosstalk of the cable physical model are analyzed by Method of Moment. The results illustrate that crosstalk prediction will be affected due to various degree of cable deformation, and the Cosserat model is of great significance for crosstalk prediction of cables.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"113 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129398018","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770559
Yansong Lv, Hang Yin, Jianping Li, Weizhang Xu, Ying Fang
Compared with the conventional successive cancellation (SC) decoding algorithm, the list decoder effectively improves the block error rate (BLER) performance, but also greatly increases the space complexity. Thus, some scholars have proposed a successive cancellation flip (SCF) decoder that can maintain the similar spatial complexity of the SC decoder while improving the BLER performance of SC decoder. However, the computational complexity of the SCF decoder at low SNR is greater than that of the SC decoder. To overcome the problem and further decrease the complexity, we propose a new decoder called modified successive cancellation flip (MSCF) decoder, which reasonably avoids the unnecessary flip operation of conventional SCF decoder by utilizing a threshold based on Gaussian approximation. Simulation results have shown that the new decoder can significantly reduce the complexity of SCF algorithm with not obvious BLER performance decrease.
{"title":"Modified Successive Cancellation Flip Decoder for Polar Codes Based on Gaussian Approximation","authors":"Yansong Lv, Hang Yin, Jianping Li, Weizhang Xu, Ying Fang","doi":"10.1109/WOCC.2019.8770559","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770559","url":null,"abstract":"Compared with the conventional successive cancellation (SC) decoding algorithm, the list decoder effectively improves the block error rate (BLER) performance, but also greatly increases the space complexity. Thus, some scholars have proposed a successive cancellation flip (SCF) decoder that can maintain the similar spatial complexity of the SC decoder while improving the BLER performance of SC decoder. However, the computational complexity of the SCF decoder at low SNR is greater than that of the SC decoder. To overcome the problem and further decrease the complexity, we propose a new decoder called modified successive cancellation flip (MSCF) decoder, which reasonably avoids the unnecessary flip operation of conventional SCF decoder by utilizing a threshold based on Gaussian approximation. Simulation results have shown that the new decoder can significantly reduce the complexity of SCF algorithm with not obvious BLER performance decrease.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130633002","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 : 2019-05-01DOI: 10.1109/WOCC.2019.8770614
K. Nkabiti, Yueyun Chen, Kashif Sultan, Bika Armand
Human identification is extremely crucial in the field of human-computer interaction. A number of studies on human identification have been done which includes using face and human gaits. Human beings have unique body structures and gaits patterns, so they induce different signal propagation paths which results in producing unique CSI signatures. These unique CSI signatures could be mapped with each individual person portraying them and by thus uniquely identifying a person. Since there are limited empirical research conducted on human identification using Wi-Fi and deep learning models, we propose a Deep bidirectional LSTM recurrent Neural networks (DBD-LSTM-RNN) for Identifying humans indoors using channel state information. A deep bidirectional LSTM-RNN model that segments the signals to determine the start and the end of human gait and map them with the appropriate body structure is deployed. Furthermore, we employed the Chebyshev filter to reduce noise on the collected CSI data. Lastly, the model is tested and evaluated using the data we have collected. The results indicated that the model achieved a high human identification accuracy with minimal computational effort and by thus making it a great option for systems that analyze human behavior.
{"title":"A Deep Bidirectional LSTM Recurrent Neural Networks For Identifying Humans Indoors Using Channel State Information","authors":"K. Nkabiti, Yueyun Chen, Kashif Sultan, Bika Armand","doi":"10.1109/WOCC.2019.8770614","DOIUrl":"https://doi.org/10.1109/WOCC.2019.8770614","url":null,"abstract":"Human identification is extremely crucial in the field of human-computer interaction. A number of studies on human identification have been done which includes using face and human gaits. Human beings have unique body structures and gaits patterns, so they induce different signal propagation paths which results in producing unique CSI signatures. These unique CSI signatures could be mapped with each individual person portraying them and by thus uniquely identifying a person. Since there are limited empirical research conducted on human identification using Wi-Fi and deep learning models, we propose a Deep bidirectional LSTM recurrent Neural networks (DBD-LSTM-RNN) for Identifying humans indoors using channel state information. A deep bidirectional LSTM-RNN model that segments the signals to determine the start and the end of human gait and map them with the appropriate body structure is deployed. Furthermore, we employed the Chebyshev filter to reduce noise on the collected CSI data. Lastly, the model is tested and evaluated using the data we have collected. The results indicated that the model achieved a high human identification accuracy with minimal computational effort and by thus making it a great option for systems that analyze human behavior.","PeriodicalId":285172,"journal":{"name":"2019 28th Wireless and Optical Communications Conference (WOCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130269536","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：