Pub Date : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449285
Qinyuan Zhao, Xiangyuan Bu, Zhenyi Song, Jinhui Fang, Shuai Wang
Wireless broadband high-speed data transmission technology is one of the key technologies used to realize mutual communication between various unmanned vehicles, unmanned ships and unmanned aerial vehicles in the future civil and military fields. Since data transfer rate is continuously increasing and the multipath effect of the near-earth channel brings frequency selective fading, the receiver usually uses an adaptive equalizer to eliminate inter-symbol interference (ISI). Instead of the time-domain-equalization methods commonly used in current engineering implementations, in this article, we use the frequency-domain MMSE equalization algorithm to give a realtime accurate estimation method for the “noise power” coefficient in the equalizer parameters during engineering implementation. In this article, we will explain the system design and demodulation methods required for real-time noise estimation based on frequency-domain MMSE equalization, and discuss the performance advantages over time domain equalization without increasing the complexity of the algorithm. It is demonstrated that it can be better applied to high-speed data communication under multipath fading channels. The algorithm is verified through computer simulation and field measurement.
{"title":"Real Time Noise Power Estimation for Single Carrier Frequency Domain Equalization","authors":"Qinyuan Zhao, Xiangyuan Bu, Zhenyi Song, Jinhui Fang, Shuai Wang","doi":"10.1109/ICCCS52626.2021.9449285","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449285","url":null,"abstract":"Wireless broadband high-speed data transmission technology is one of the key technologies used to realize mutual communication between various unmanned vehicles, unmanned ships and unmanned aerial vehicles in the future civil and military fields. Since data transfer rate is continuously increasing and the multipath effect of the near-earth channel brings frequency selective fading, the receiver usually uses an adaptive equalizer to eliminate inter-symbol interference (ISI). Instead of the time-domain-equalization methods commonly used in current engineering implementations, in this article, we use the frequency-domain MMSE equalization algorithm to give a realtime accurate estimation method for the “noise power” coefficient in the equalizer parameters during engineering implementation. In this article, we will explain the system design and demodulation methods required for real-time noise estimation based on frequency-domain MMSE equalization, and discuss the performance advantages over time domain equalization without increasing the complexity of the algorithm. It is demonstrated that it can be better applied to high-speed data communication under multipath fading channels. The algorithm is verified through computer simulation and field measurement.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"12 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":"114252317","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/ICCCS52626.2021.9449256
Xuan Liu, Meijing Zhao, Song Dai, Qiyue Yin, Wancheng Ni
Opponent modeling is a significant method in imperfect information games. And intention recognition is regarded as the important but difficult in opponent modeling. This paper focuses on the task of tactical intention recognition in computational wargame. We propose an approach to recognize opponents' intention which models the intention as long-term trajectories. The approach consists of situation encoding model and position prediction model. The first model uses attention mechanism to attach the statistic map data with dynamic feature and adopt CNN to learn the representation of battlefield situation. The position prediction model then predicts the long-term trajectories of opponents, based on well-represented situation vectors. Experiment indicates that our approach is proven to be effective on the task of tactical intention recognition in wargame. Meanwhile, a high-quality replay data set for analyzing the actions' characteristics is also provided in this paper.
{"title":"Tactical Intention Recognition in Wargame","authors":"Xuan Liu, Meijing Zhao, Song Dai, Qiyue Yin, Wancheng Ni","doi":"10.1109/ICCCS52626.2021.9449256","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449256","url":null,"abstract":"Opponent modeling is a significant method in imperfect information games. And intention recognition is regarded as the important but difficult in opponent modeling. This paper focuses on the task of tactical intention recognition in computational wargame. We propose an approach to recognize opponents' intention which models the intention as long-term trajectories. The approach consists of situation encoding model and position prediction model. The first model uses attention mechanism to attach the statistic map data with dynamic feature and adopt CNN to learn the representation of battlefield situation. The position prediction model then predicts the long-term trajectories of opponents, based on well-represented situation vectors. Experiment indicates that our approach is proven to be effective on the task of tactical intention recognition in wargame. Meanwhile, a high-quality replay data set for analyzing the actions' characteristics is also provided in this paper.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"34 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":"114810277","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/ICCCS52626.2021.9449297
Wen Qian, Yuesheng Zhu
The existing methods for domain-adaptive few-shot relation classification based on word embeddings or pretraining models trained on massive corpora, are not strong enough to cover the wide disparity of text and relation definitions to the specific target domain, leading to the inferior performance. To fill in this gap, here we propose an enhanced adversarial approach utilizing domain-adaptive pretraining model to obtain semantic features of relations, which continues unsupervised pretraining on corpus in target domain. We also construct a classification enhancer module to emphasize the class differentiation by making greater use of the supporting and query data, which not only helps to deal with few-shot problem, but also diminishes the negative effect of domain alignment caused by adversarial learning. Experimental results on FewRel2.0-DA dataset demonstrate that our proposed method achieves strong performance, which can improve the best reported result by up to 5.3 % on average accuracy for few-shot relation classification across domains.
{"title":"Adversarial Learning with Domain-Adaptive Pretraining for Few-Shot Relation Classification across Domains","authors":"Wen Qian, Yuesheng Zhu","doi":"10.1109/ICCCS52626.2021.9449297","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449297","url":null,"abstract":"The existing methods for domain-adaptive few-shot relation classification based on word embeddings or pretraining models trained on massive corpora, are not strong enough to cover the wide disparity of text and relation definitions to the specific target domain, leading to the inferior performance. To fill in this gap, here we propose an enhanced adversarial approach utilizing domain-adaptive pretraining model to obtain semantic features of relations, which continues unsupervised pretraining on corpus in target domain. We also construct a classification enhancer module to emphasize the class differentiation by making greater use of the supporting and query data, which not only helps to deal with few-shot problem, but also diminishes the negative effect of domain alignment caused by adversarial learning. Experimental results on FewRel2.0-DA dataset demonstrate that our proposed method achieves strong performance, which can improve the best reported result by up to 5.3 % on average accuracy for few-shot relation classification across domains.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"21 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":"126524732","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/ICCCS52626.2021.9449099
Yunfeng Tang, Enxiao Liu, Chen Tao, Jianjun Yang, Jianpo Liu, Lei Zhang, Wenji Zhang, Haiyong Wang
Ultraviolet (UV) wireless is very suitable for local area Non-line of sight(NLOS) dedicated covert communication. Overcoming the path loss and delay spread from NLOS channel is a critical mission for the UV NLOS transmitter. In the first part of this paper, the main recent short distance line of sight (LOS) and long distance NLOS UV communication transmitters are reviewed. Next, “UV NLOS acquisition tracking pointing (ATP)” is introduced. Then, “UV high speed modulation technology”, “high-power UV source” and etc. are analyzed and summarized. The prospect of “High repetition rate high power UV pulse modulation” and “High power sub-millisecond UV pulse OFDM modulation” is put forward in the end.
{"title":"Research Progress and Prospect of Ultraviolet Communication","authors":"Yunfeng Tang, Enxiao Liu, Chen Tao, Jianjun Yang, Jianpo Liu, Lei Zhang, Wenji Zhang, Haiyong Wang","doi":"10.1109/ICCCS52626.2021.9449099","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449099","url":null,"abstract":"Ultraviolet (UV) wireless is very suitable for local area Non-line of sight(NLOS) dedicated covert communication. Overcoming the path loss and delay spread from NLOS channel is a critical mission for the UV NLOS transmitter. In the first part of this paper, the main recent short distance line of sight (LOS) and long distance NLOS UV communication transmitters are reviewed. Next, “UV NLOS acquisition tracking pointing (ATP)” is introduced. Then, “UV high speed modulation technology”, “high-power UV source” and etc. are analyzed and summarized. The prospect of “High repetition rate high power UV pulse modulation” and “High power sub-millisecond UV pulse OFDM modulation” is put forward in the end.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"11 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":"121484516","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/ICCCS52626.2021.9449161
Shaofei Liu, Ying Lin, Chao Luo, Weiye Shi
The prediction of traffic flow in cities has always been one of the most important issues in the study of road traffic congestion in the world. However, it is difficult to accurately predict the traffic flow between cities, because the traffic flow prediction process involves a more complex nonlinear data model, especially during the daily peak hours, the traffic flow data presents a cycle Sexual (seasonal) trends. In recent years, support vector regression (SVR) has been widely used to solve nonlinear regression and time series problems. This paper uses a combination of chaos theory and simulated annealing algorithm to optimize the kernel parameters of the correlation vector machine. However, for the time being, there is no recognized SVR model to deal with cyclical (seasonal) trend time series. This paper proposes a traffic flow prediction model, which combines seasonal support vector regression model and chaotic simulated annealing algorithm (SSVRCSA) to predict the traffic flow between cities. Under previous research, support vector regression using chaotic sequence and simulated annealing algorithm has shown its advantages, which can effectively avoid falling into local optimal. Experimental results show that the proposed SSVRCSA model can produce more accurate prediction results than other alternative methods. This research finally proposed a prediction model that blends the seasonal support vector regression model and the chaotic cloud simulated annealing algorithm (SSVRCCSA) to obtain more accurate prediction performance. The experimental results show that the proposed SSVRCCSA model is more accurate than other methods.
{"title":"A Novel Learning Method for Traffic Flow Forecasting by Seasonal SVR with Chaotic Simulated Annealing Algorithm","authors":"Shaofei Liu, Ying Lin, Chao Luo, Weiye Shi","doi":"10.1109/ICCCS52626.2021.9449161","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449161","url":null,"abstract":"The prediction of traffic flow in cities has always been one of the most important issues in the study of road traffic congestion in the world. However, it is difficult to accurately predict the traffic flow between cities, because the traffic flow prediction process involves a more complex nonlinear data model, especially during the daily peak hours, the traffic flow data presents a cycle Sexual (seasonal) trends. In recent years, support vector regression (SVR) has been widely used to solve nonlinear regression and time series problems. This paper uses a combination of chaos theory and simulated annealing algorithm to optimize the kernel parameters of the correlation vector machine. However, for the time being, there is no recognized SVR model to deal with cyclical (seasonal) trend time series. This paper proposes a traffic flow prediction model, which combines seasonal support vector regression model and chaotic simulated annealing algorithm (SSVRCSA) to predict the traffic flow between cities. Under previous research, support vector regression using chaotic sequence and simulated annealing algorithm has shown its advantages, which can effectively avoid falling into local optimal. Experimental results show that the proposed SSVRCSA model can produce more accurate prediction results than other alternative methods. This research finally proposed a prediction model that blends the seasonal support vector regression model and the chaotic cloud simulated annealing algorithm (SSVRCCSA) to obtain more accurate prediction performance. The experimental results show that the proposed SSVRCCSA model is more accurate than other methods.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"90 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":"125482368","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/ICCCS52626.2021.9449181
X. Xie, Jingyi Shen, Yifan Zhao, R. Yang
In the land development industry chain, there are a variety of data, such as land transaction data, building sales data, developer data, etc. These data are relatively scattered, difficult to aggregate and share, unable to play the hidden value of the data. This paper presents an improved algorithm for Chinese address segmentation, and based on this algorithm, the entity linking algorithm of building and land is proposed, which correlates a large number of discrete building data with land data, and finally, the entity link algorithm is applied to the big data association analysis system as the service of the association analysis subsystem, and the analysis results are visualized through the client and server. The results show that the system can correlate a large number of isolated building and land, effectively correlate and integrate discrete data, and has good data analysis ability, which provides a strong support for enterprises and users to make decisions.
{"title":"Research and Design of Big Data Relevance Analysis System for Land Development Industry Chain","authors":"X. Xie, Jingyi Shen, Yifan Zhao, R. Yang","doi":"10.1109/ICCCS52626.2021.9449181","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449181","url":null,"abstract":"In the land development industry chain, there are a variety of data, such as land transaction data, building sales data, developer data, etc. These data are relatively scattered, difficult to aggregate and share, unable to play the hidden value of the data. This paper presents an improved algorithm for Chinese address segmentation, and based on this algorithm, the entity linking algorithm of building and land is proposed, which correlates a large number of discrete building data with land data, and finally, the entity link algorithm is applied to the big data association analysis system as the service of the association analysis subsystem, and the analysis results are visualized through the client and server. The results show that the system can correlate a large number of isolated building and land, effectively correlate and integrate discrete data, and has good data analysis ability, which provides a strong support for enterprises and users to make decisions.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"7 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":"130404697","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/ICCCS52626.2021.9449272
Hongfang Yuan, Peng Lei, Xi Cao
Products of fluorine chemical industry have the advantages of high performance and added value, which are widely used in military, machinery and other fields. As the main power source of the fluorine chemical industry, rotating machinery equipment ages quickly and the failure rate is high. Due to the large size and high data transmission delay of traditional fault diagnosis equipment, its application in fluorine chemical industry is greatly restricted. Based on the design idea of edge computing, an intelligent sensor unit with high performance was designed and implemented by using the digital chip. Compared with the traditional data acquisition unit, the intelligent sensor adopts the form of the non-intrusive stack in structure. Combined with the data processing module, it can realize the real-time acquisition and online processing of the vibration data of mechanical equipment. In terms of real-time and convenience, it has incomparable advantages over the traditional monitoring platform.
{"title":"A Design of on-Line Intelligent Sensor Unit for Fluorine Chemical Rotary Equipment","authors":"Hongfang Yuan, Peng Lei, Xi Cao","doi":"10.1109/ICCCS52626.2021.9449272","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449272","url":null,"abstract":"Products of fluorine chemical industry have the advantages of high performance and added value, which are widely used in military, machinery and other fields. As the main power source of the fluorine chemical industry, rotating machinery equipment ages quickly and the failure rate is high. Due to the large size and high data transmission delay of traditional fault diagnosis equipment, its application in fluorine chemical industry is greatly restricted. Based on the design idea of edge computing, an intelligent sensor unit with high performance was designed and implemented by using the digital chip. Compared with the traditional data acquisition unit, the intelligent sensor adopts the form of the non-intrusive stack in structure. Combined with the data processing module, it can realize the real-time acquisition and online processing of the vibration data of mechanical equipment. In terms of real-time and convenience, it has incomparable advantages over the traditional monitoring platform.","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":"130355404","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/ICCCS52626.2021.9449262
Jianling Li, Wuhang Lin, Shasha Li, Jie Yu, Jun Ma
Summary models, whether extractive or abstractive, have achieved great success recently. For long academic papers, the abstractive model with the encoder-decoder architecture mainly only relies on the attentional context vector for generation, unlike humans who have already mastered the salient information of the source text to have full control over what to write. While the extracted sentences always contain the correct and salient information which can be used to control the abstraction process. Therefore, based on a hierarchical encoder-decoder architecture specifically for academic papers, we proposed a summary model with an Instructor, an encoder in essence by taking the guiding sentences as the input to further control the generating process. In the encoder part, the final hidden state from Instructor is directly added to the basic hierarchical hidden state from the encoder. Experimental results on arXiv/PubMed show that the only encoder-improved model can generate better abstract. In the decoder part, the context vector from Instructor is integrated with the original discourse-aware context vector for the generation. The results show that Instructor is effective for control and our model can generate a more accurate and fluent abstract with significantly higher ROUGE values.
{"title":"Hierarchical Encoder-Decoder Summary Model with an Instructor for Long Academic Papers","authors":"Jianling Li, Wuhang Lin, Shasha Li, Jie Yu, Jun Ma","doi":"10.1109/ICCCS52626.2021.9449262","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449262","url":null,"abstract":"Summary models, whether extractive or abstractive, have achieved great success recently. For long academic papers, the abstractive model with the encoder-decoder architecture mainly only relies on the attentional context vector for generation, unlike humans who have already mastered the salient information of the source text to have full control over what to write. While the extracted sentences always contain the correct and salient information which can be used to control the abstraction process. Therefore, based on a hierarchical encoder-decoder architecture specifically for academic papers, we proposed a summary model with an Instructor, an encoder in essence by taking the guiding sentences as the input to further control the generating process. In the encoder part, the final hidden state from Instructor is directly added to the basic hierarchical hidden state from the encoder. Experimental results on arXiv/PubMed show that the only encoder-improved model can generate better abstract. In the decoder part, the context vector from Instructor is integrated with the original discourse-aware context vector for the generation. The results show that Instructor is effective for control and our model can generate a more accurate and fluent abstract with significantly higher ROUGE values.","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":"124605232","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}
Malicious code can be embedded into Web applications in various ways, which will lead to frequent malicious Web attacks. In the deep learning-based Web malicious code detection methods, the effect and applicability of different RNN-based methods are unknown, which needs to be further study. Therefore, a comparative study of RNN-based methods for Web malicious code detection was conducted in this paper. Different from existing research, this paper not only analyzes and discusses the advantages and disadvantages of different RNN-based methods, including LSTM, GRU, SRU, but also utilizes Web malicious code detection as the application target to evaluate the actual performance of these methods. Experiment results show that the recall rates of GRU and SRU are 81.07% and 80.96%, respectively, which are higher than LSTM and minimalRNN. The performance of textCNN is relatively satisfactory, with scores of 90.6%, 85.54%, 87.95%, 94.4% in terms of precision, recall, F1 and AUC respectively. The comparative study displays that the performance of RNN-based Web malicious code detection methods is greatly affected by the preprocessing ways of source code.
{"title":"A Comparative Study of RNN-based Methods for Web Malicious Code Detection","authors":"Zhibin Guan, Jiajie Wang, Xiaomeng Wang, Wei Xin, Jing Cui, Xiangping Jing","doi":"10.1109/ICCCS52626.2021.9449245","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449245","url":null,"abstract":"Malicious code can be embedded into Web applications in various ways, which will lead to frequent malicious Web attacks. In the deep learning-based Web malicious code detection methods, the effect and applicability of different RNN-based methods are unknown, which needs to be further study. Therefore, a comparative study of RNN-based methods for Web malicious code detection was conducted in this paper. Different from existing research, this paper not only analyzes and discusses the advantages and disadvantages of different RNN-based methods, including LSTM, GRU, SRU, but also utilizes Web malicious code detection as the application target to evaluate the actual performance of these methods. Experiment results show that the recall rates of GRU and SRU are 81.07% and 80.96%, respectively, which are higher than LSTM and minimalRNN. The performance of textCNN is relatively satisfactory, with scores of 90.6%, 85.54%, 87.95%, 94.4% in terms of precision, recall, F1 and AUC respectively. The comparative study displays that the performance of RNN-based Web malicious code detection methods is greatly affected by the preprocessing ways of source code.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"39 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":"116490416","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/ICCCS52626.2021.9449309
Bengang Li, Faguo Wu
Blockchain is a very important technology and financial innovation since the birth of the Internet. It is an innovative and integrated application of many technologies, with the characteristics of open and transparent data, not easy to tamper with, easy to trace and so on. Its cryptographic security relies on asymmetric cryptography, such as ECC, RSA. However, with the surprising development of quantum technology, asymmetric cryptography schemes mentioned above would become vulnerable. Recently, some lattice-based blockchain systems have been proposed to be secure against attacks in the quantum era. Although these schemes have theoretical significance, it is unpractical in actual situation due to handling capacity. In this paper, aiming at tackling the critical issue of throughput, we proposed post quantum blockchain with segregation witness which can effectively the proportion of signatures in block size. Based on the hardness assumption of Short Integer Solution (SIS), we demonstrate that the proposed post quantum blockchain with segregation witness existential unforgeability against adaptive chosen-message attacks in the random oracle. As compared to the existing scheme, our scheme has better performance in handling capacity. As the underlying lattice problem is intractable even for quantum computers, our scheme would work well in the quantum age.
{"title":"Post Quantum Blockchain with Segregation Witness","authors":"Bengang Li, Faguo Wu","doi":"10.1109/ICCCS52626.2021.9449309","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449309","url":null,"abstract":"Blockchain is a very important technology and financial innovation since the birth of the Internet. It is an innovative and integrated application of many technologies, with the characteristics of open and transparent data, not easy to tamper with, easy to trace and so on. Its cryptographic security relies on asymmetric cryptography, such as ECC, RSA. However, with the surprising development of quantum technology, asymmetric cryptography schemes mentioned above would become vulnerable. Recently, some lattice-based blockchain systems have been proposed to be secure against attacks in the quantum era. Although these schemes have theoretical significance, it is unpractical in actual situation due to handling capacity. In this paper, aiming at tackling the critical issue of throughput, we proposed post quantum blockchain with segregation witness which can effectively the proportion of signatures in block size. Based on the hardness assumption of Short Integer Solution (SIS), we demonstrate that the proposed post quantum blockchain with segregation witness existential unforgeability against adaptive chosen-message attacks in the random oracle. As compared to the existing scheme, our scheme has better performance in handling capacity. As the underlying lattice problem is intractable even for quantum computers, our scheme would work well in the quantum age.","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":"133213483","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：