Pub Date : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449244
Ningyuan Wang, Chen Dong, Liang Liu, Wang Mian, Bingyuan Liang
With the rapid development of the LEO mega-constellations, the control technique of the tremendous constellation network become a mean challenge. The SDN-based centralized control scheme can solve the bottleneck of onboard computational resources in traditional distributed LEO mega-constellations. However, frequent network topology variation caused by constellation movement and communication link failure increases the difficulty of in-band control enormously. Therefore, we propose a novel Dual-Layer SDN (DLSDN) in-band control framework, which sets an Upper-layer control plane exclusively for providing reliable in-band control paths for control traffic generated/received by the Lower-layer control plane. In order to provide reliable control traffic transmission, a redundant path-planning algorithm is further proposed. Simulations show that the DLSDN framework possesses fewer inaccessible satellites when multiple link failures occur in a mega-constellation scenario.
{"title":"An SDN Based Highly Reliable in-Band Control Framework for LEO Mega-Constellations","authors":"Ningyuan Wang, Chen Dong, Liang Liu, Wang Mian, Bingyuan Liang","doi":"10.1109/ICCCS52626.2021.9449244","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449244","url":null,"abstract":"With the rapid development of the LEO mega-constellations, the control technique of the tremendous constellation network become a mean challenge. The SDN-based centralized control scheme can solve the bottleneck of onboard computational resources in traditional distributed LEO mega-constellations. However, frequent network topology variation caused by constellation movement and communication link failure increases the difficulty of in-band control enormously. Therefore, we propose a novel Dual-Layer SDN (DLSDN) in-band control framework, which sets an Upper-layer control plane exclusively for providing reliable in-band control paths for control traffic generated/received by the Lower-layer control plane. In order to provide reliable control traffic transmission, a redundant path-planning algorithm is further proposed. Simulations show that the DLSDN framework possesses fewer inaccessible satellites when multiple link failures occur in a mega-constellation scenario.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127221154","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449094
Annan Wang, Ziyang Gong
The low Signal Noise Ratio (SNR) and nonstationarity of electroencephalogram (EEG) signals affect the classification accuracy badly in motor imagery electroencephalogram (MI-EEG) classification. In this paper, a Distribution Based Learning (DBL) framework based on deep learning is proposed to improve the accuracy. Firstly, the framework uses modified multi band Common Spatial Pattern (CSP) algorithm to pre-process the raw EEG signals. Secondly, a Distribution Based Learning Network (DBLN) is utilized to divide the dataset into two parts. After that, a two-step distribution based learning and testing strategy are conducted on the two parts separately. Experimental results on BCI Competition IV Dataset 2b indicate that accuracy of DBL is 3.84 % higher than the state-of-the-art, which proves the effectiveness of the algorithm.
在运动图像脑电图分类中，脑电图信号的低信噪比和非平稳性严重影响了分类的准确性。本文提出了一种基于深度学习的分布式学习(DBL)框架，以提高识别精度。首先，该框架采用改进的多波段公共空间模式(CSP)算法对原始脑电信号进行预处理;其次，利用基于分布的学习网络(DBLN)将数据集分成两部分;然后，分别对这两个部分进行了基于分布的两步学习和测试策略。在BCI Competition IV Dataset 2b上的实验结果表明，DBL的准确率比现有算法提高了3.84%，证明了该算法的有效性。
{"title":"Distribution Based Learning Network for Motor Imagery Electroencephalogram Classification","authors":"Annan Wang, Ziyang Gong","doi":"10.1109/ICCCS52626.2021.9449094","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449094","url":null,"abstract":"The low Signal Noise Ratio (SNR) and nonstationarity of electroencephalogram (EEG) signals affect the classification accuracy badly in motor imagery electroencephalogram (MI-EEG) classification. In this paper, a Distribution Based Learning (DBL) framework based on deep learning is proposed to improve the accuracy. Firstly, the framework uses modified multi band Common Spatial Pattern (CSP) algorithm to pre-process the raw EEG signals. Secondly, a Distribution Based Learning Network (DBLN) is utilized to divide the dataset into two parts. After that, a two-step distribution based learning and testing strategy are conducted on the two parts separately. Experimental results on BCI Competition IV Dataset 2b indicate that accuracy of DBL is 3.84 % higher than the state-of-the-art, which proves the effectiveness of the algorithm.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126637411","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449298
E. Chen, Qinglong Zhang, Yubin Yang, Zhiying Cao, Shengkai Sun
In the vector network analyzer, the excitation source signal will produce nonlinear compression after being amplified for many times, resulting in the reduction of spurious rejection ratio. In power measurement, the spurious signal is detected as the main signal, while in narrowband reception, the spurious signal is filtered out and the amplitude decreases on the curve. This paper introduces a method to improve the spurious suppression of excitation signal. The spurious suppression is increased by 18dB.
{"title":"Design of Low Spurious Phase Locked Loop for Vector Network Analyzer","authors":"E. Chen, Qinglong Zhang, Yubin Yang, Zhiying Cao, Shengkai Sun","doi":"10.1109/ICCCS52626.2021.9449298","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449298","url":null,"abstract":"In the vector network analyzer, the excitation source signal will produce nonlinear compression after being amplified for many times, resulting in the reduction of spurious rejection ratio. In power measurement, the spurious signal is detected as the main signal, while in narrowband reception, the spurious signal is filtered out and the amplitude decreases on the curve. This paper introduces a method to improve the spurious suppression of excitation signal. The spurious suppression is increased by 18dB.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115802286","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449219
Kechang Qian, Ying Wan, Youchen Fan, Dapeng Xiong
The use of data fusion algorithms for fusion processing of the obtained multivariate measurement data is a common method to improve measurement accuracy. This paper designs a multivariate measurement data fusion method based on the principle of EMBET, which avoids the limitation of the conventional EMBET method for measuring equipment error models and effectively improves the accuracy of multivariate measurement data fusion. The effectiveness of this method is verified by measured data.
{"title":"A Method of Measuring Data Fusion Based on EMBET","authors":"Kechang Qian, Ying Wan, Youchen Fan, Dapeng Xiong","doi":"10.1109/ICCCS52626.2021.9449219","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449219","url":null,"abstract":"The use of data fusion algorithms for fusion processing of the obtained multivariate measurement data is a common method to improve measurement accuracy. This paper designs a multivariate measurement data fusion method based on the principle of EMBET, which avoids the limitation of the conventional EMBET method for measuring equipment error models and effectively improves the accuracy of multivariate measurement data fusion. The effectiveness of this method is verified by measured data.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"50 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113991259","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449255
Qimin Dong, Y. Jiraraksopakun, A. Bhatranand
Obstructive Sleep Apnea (OSA) identification aims to recognize the sounds from the obstructive sleep apneahypopnea syndrome (OSANHS) patients. Despite remarkable advances have been made, the performance heavily relies on the sound representation. Feature selection is needed to improve the performance. Generally, the normal snoring and the snoring of OSANHS patients have a greater difference in acoustic characteristics. Ordinary snoring of human breathing is a regular, fluctuating and cyclical state, while OSANHS pathological snoring is often accompanied by a long pause. Based on the acoustic characteristics, this paper proposes an OSA recognition algorithm based on a convolutional neural network. First, the Mel-scale frequency cepstral coefficient (MFCC) of the sound are extracted. Then, convolutional neural network is deployed to predict the possibility of OSA. To empirically investigate the effectiveness and robustness of the proposed approach, extensive experiments were performed on a benchmark dataset. The obtained results showed that our method significantly outperforms related baselines and is also competitive or superior to the recently reported systems.
{"title":"Convolutional Neural Network-Based Obstructive Sleep Apnea Identification","authors":"Qimin Dong, Y. Jiraraksopakun, A. Bhatranand","doi":"10.1109/ICCCS52626.2021.9449255","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449255","url":null,"abstract":"Obstructive Sleep Apnea (OSA) identification aims to recognize the sounds from the obstructive sleep apneahypopnea syndrome (OSANHS) patients. Despite remarkable advances have been made, the performance heavily relies on the sound representation. Feature selection is needed to improve the performance. Generally, the normal snoring and the snoring of OSANHS patients have a greater difference in acoustic characteristics. Ordinary snoring of human breathing is a regular, fluctuating and cyclical state, while OSANHS pathological snoring is often accompanied by a long pause. Based on the acoustic characteristics, this paper proposes an OSA recognition algorithm based on a convolutional neural network. First, the Mel-scale frequency cepstral coefficient (MFCC) of the sound are extracted. Then, convolutional neural network is deployed to predict the possibility of OSA. To empirically investigate the effectiveness and robustness of the proposed approach, extensive experiments were performed on a benchmark dataset. The obtained results showed that our method significantly outperforms related baselines and is also competitive or superior to the recently reported systems.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116839787","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449311
Qian Liang, Bin Chen, Huaning Wu, Meng Han
A novel modified sparrow search algorithm based on adaptive weight and improved boundary constraints is proposed to tackle disadvantages of sparrow search algorithm, which tends to fall into local optimum and has limited convergence speed. The convergence speed of algorithm is improved by adaptive weight, and the improved boundary handling strategy improves the convergence accuracy of algorithm to a certain extent. In order to verify the effectiveness of improved algorithm, a total of nine benchmark test functions of three types were calculated, and the ant lion optimizer, seagull optimization algorithm, tunicate swarm algorithm and standard sparrow search algorithm were compared and analyzed statistically. The simulation results indicate that the improved algorithm can overcome precocious convergence problem effectively, and is superior to the other four algorithms in terms of convergence speed and precision.
{"title":"A Novel Modified Sparrow Search Algorithm Based on Adaptive Weight and Improved Boundary Constraints","authors":"Qian Liang, Bin Chen, Huaning Wu, Meng Han","doi":"10.1109/ICCCS52626.2021.9449311","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449311","url":null,"abstract":"A novel modified sparrow search algorithm based on adaptive weight and improved boundary constraints is proposed to tackle disadvantages of sparrow search algorithm, which tends to fall into local optimum and has limited convergence speed. The convergence speed of algorithm is improved by adaptive weight, and the improved boundary handling strategy improves the convergence accuracy of algorithm to a certain extent. In order to verify the effectiveness of improved algorithm, a total of nine benchmark test functions of three types were calculated, and the ant lion optimizer, seagull optimization algorithm, tunicate swarm algorithm and standard sparrow search algorithm were compared and analyzed statistically. The simulation results indicate that the improved algorithm can overcome precocious convergence problem effectively, and is superior to the other four algorithms in terms of convergence speed and precision.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122813805","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449150
Zhao-Ming Huang
Low earth orbit (LEO) satellite has attracted worldwide attention due to its wide coverage, low transmission delay, and low transmission loss. Therefore, it has been given many uses including military communication. Direct sequence spread spectrum (DSSS) is widely used in military communication for its good ability of anti-jamming and anti-eavesdropping. However, the high-speed movement of LEO satellite relative to the terminal will cause serious carrier offset and pseudo-noise (PN) code offset of DSSS receiver signal, which seriously increases the complexity of the algorithm. In this paper, a pilot-aided method of Doppler offset estimation and compensation is proposed. The real-time Doppler carrier offset and PN code offset between satellite and terminal are estimated by terminal processing of the pilot signal, and real-time precompensation is carried out when sending uplink service signal or receiving downlink service signal. Through hardware verification, this method can significantly reduce the resource consumption of terminal and satellite.
{"title":"A Pilot-Aided Method of Doppler Offset Estimation and Compensation","authors":"Zhao-Ming Huang","doi":"10.1109/ICCCS52626.2021.9449150","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449150","url":null,"abstract":"Low earth orbit (LEO) satellite has attracted worldwide attention due to its wide coverage, low transmission delay, and low transmission loss. Therefore, it has been given many uses including military communication. Direct sequence spread spectrum (DSSS) is widely used in military communication for its good ability of anti-jamming and anti-eavesdropping. However, the high-speed movement of LEO satellite relative to the terminal will cause serious carrier offset and pseudo-noise (PN) code offset of DSSS receiver signal, which seriously increases the complexity of the algorithm. In this paper, a pilot-aided method of Doppler offset estimation and compensation is proposed. The real-time Doppler carrier offset and PN code offset between satellite and terminal are estimated by terminal processing of the pilot signal, and real-time precompensation is carried out when sending uplink service signal or receiving downlink service signal. Through hardware verification, this method can significantly reduce the resource consumption of terminal and satellite.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129561448","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}
By extensively mining system data and integrating with artificial intelligence means, knowledge graph can be exploited in various tasks of power communication network, effectively prompting the efficiency and performance of maintenance. One of the pivotal step of the knowledge graph construction is the named entity recognition. Abundant semantic features extracted from corpus can directly improve the accuracy of resulting concepts in knowledge graph. However, existing entity recognition method is mainly based on conventional word embedding technique such as Word2Vec, which still focuses on information within single word. In this paper, we propose to construct knowledge graph with the most recently proposed BERT-BiLSTM-CRF. This model can fully consider contextual information over words and extract more semantic features for further procedures. Our experimental results on realistic maintenance data of power communication networks proved the efficacy of BERT-BiLSTM-CRF model in the construction of knowledge graph. With the assistance of knowledge graph, we build applications for two typical maintenance scenarios, process standardization and fault disposal instruction, respectively. The knowledge graph has shown promising prospect as a novel auxiliary mechanism to power communication networks.
{"title":"Construction of Power Communication Network Knowledge Graph with BERT-BiLSTM-CRF Model Based Entity Recognition","authors":"Haiyang Wu, Peng Chen, Wei Li, Yong Dai, Chunxia Jiang, Jixuan Li, Pengyu Zhu","doi":"10.1109/ICCCS52626.2021.9449229","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449229","url":null,"abstract":"By extensively mining system data and integrating with artificial intelligence means, knowledge graph can be exploited in various tasks of power communication network, effectively prompting the efficiency and performance of maintenance. One of the pivotal step of the knowledge graph construction is the named entity recognition. Abundant semantic features extracted from corpus can directly improve the accuracy of resulting concepts in knowledge graph. However, existing entity recognition method is mainly based on conventional word embedding technique such as Word2Vec, which still focuses on information within single word. In this paper, we propose to construct knowledge graph with the most recently proposed BERT-BiLSTM-CRF. This model can fully consider contextual information over words and extract more semantic features for further procedures. Our experimental results on realistic maintenance data of power communication networks proved the efficacy of BERT-BiLSTM-CRF model in the construction of knowledge graph. With the assistance of knowledge graph, we build applications for two typical maintenance scenarios, process standardization and fault disposal instruction, respectively. The knowledge graph has shown promising prospect as a novel auxiliary mechanism to power communication networks.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"os-10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127687860","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449197
Claude Nawej, P. Owolawi, Tom Walingo
Automobiles traffic has increased exponentially around the world, posing serious threats to road users almost everywhere. To mitigate these threats, and make life on the road more viable, Vehicular ad-hoc networks (VANET) technology is emerging as one of the ultimate solutions. However, it was observed that most VANETs work with relativity of the mobile user's movement instead of vehicles movement as required by VANET simulation. Moreover, it seems to be a great challenge to create or obtain real-life network scenario data for use in VANET simulation. Works done in previous researches showed a proximate data generation closer to ideal. In this paper, using combined tools such as Open Street Map, Simulation of Urban Mobility (SUMO), and Network Simulator-2 (NS-2), a middleware solution capable of putting together vehicle movements and VANETs realistic properties is implemented. The implemented solution offers an improved, real, and ideal solution compared to existing solutions.
{"title":"Design and Simulation of VANETs Testbed Using OpenStreetMap, SUMO, and NS-2","authors":"Claude Nawej, P. Owolawi, Tom Walingo","doi":"10.1109/ICCCS52626.2021.9449197","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449197","url":null,"abstract":"Automobiles traffic has increased exponentially around the world, posing serious threats to road users almost everywhere. To mitigate these threats, and make life on the road more viable, Vehicular ad-hoc networks (VANET) technology is emerging as one of the ultimate solutions. However, it was observed that most VANETs work with relativity of the mobile user's movement instead of vehicles movement as required by VANET simulation. Moreover, it seems to be a great challenge to create or obtain real-life network scenario data for use in VANET simulation. Works done in previous researches showed a proximate data generation closer to ideal. In this paper, using combined tools such as Open Street Map, Simulation of Urban Mobility (SUMO), and Network Simulator-2 (NS-2), a middleware solution capable of putting together vehicle movements and VANETs realistic properties is implemented. The implemented solution offers an improved, real, and ideal solution compared to existing solutions.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127940950","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 : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449286
Lulu Yang, Chen Li, Ruibang You, Bibo Tu
Demand for remote work has surged as the COVID-19 epidemic has spread around the world. As one of the main implementations of desktop virtualization, Virtual Desktop Infrastructure (VDI) is popular and widely used in corporate remote work. A VDI user can connect to and use a virtual machine in a remote data center by logging in with a username and password using any device anywhere with Internet access. VDI has mobile convenience but is at risk of password leakage and insider threat. Traditional authentication methods, such as password and PIN, cannot withstand these threats. This work presents a keystroke-based continuous user authentication based on the Bidirectional Long Short-Term Memory (Bi-LSTM) network and embedding mechanism in deep learning to defend against such risks. It verifies the current user's identity based on the user's typing behavior continuously and non-invasively. We implement it on SPICE VDI and evaluate its performance and deployment feasibility on a public keystroke dataset - the Clarkson II dataset, which collected in uncontrolled and natural settings. The results show that it achieves state-of-art performance. It detects intruders with 8.28% of EER when only using 30 keystrokes and 0.85% of EER when using 990 keystrokes.
{"title":"A Keystroke-based Continuous User Authentication in Virtual Desktop Infrastructure","authors":"Lulu Yang, Chen Li, Ruibang You, Bibo Tu","doi":"10.1109/ICCCS52626.2021.9449286","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449286","url":null,"abstract":"Demand for remote work has surged as the COVID-19 epidemic has spread around the world. As one of the main implementations of desktop virtualization, Virtual Desktop Infrastructure (VDI) is popular and widely used in corporate remote work. A VDI user can connect to and use a virtual machine in a remote data center by logging in with a username and password using any device anywhere with Internet access. VDI has mobile convenience but is at risk of password leakage and insider threat. Traditional authentication methods, such as password and PIN, cannot withstand these threats. This work presents a keystroke-based continuous user authentication based on the Bidirectional Long Short-Term Memory (Bi-LSTM) network and embedding mechanism in deep learning to defend against such risks. It verifies the current user's identity based on the user's typing behavior continuously and non-invasively. We implement it on SPICE VDI and evaluate its performance and deployment feasibility on a public keystroke dataset - the Clarkson II dataset, which collected in uncontrolled and natural settings. The results show that it achieves state-of-art performance. It detects intruders with 8.28% of EER when only using 30 keystrokes and 0.85% of EER when using 990 keystrokes.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117031532","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：