The emergence and wide application of the Internet have brought convenience to people's lives, but at the same time, it has also brought many security problems. How to protect network security and prevent intrusion detection is the focus of current research. This article adopts the method of review, first introduces the application examples of big data technology and machine learning technology in intrusion detection respectively, and then introduces intrusion detection system, machine learning algorithm and deep learning algorithm in detail. Finally, the model of spark applied to intrusion detection system is listed, and it is concluded that the combination of spark and machine learning technology for intrusion detection system can make it more efficient.
{"title":"A Survey on Machine Learning based Intrusion Detection Systems Using Apache Spark","authors":"Hao Lin","doi":"10.1145/3497737.3497740","DOIUrl":"https://doi.org/10.1145/3497737.3497740","url":null,"abstract":"The emergence and wide application of the Internet have brought convenience to people's lives, but at the same time, it has also brought many security problems. How to protect network security and prevent intrusion detection is the focus of current research. This article adopts the method of review, first introduces the application examples of big data technology and machine learning technology in intrusion detection respectively, and then introduces intrusion detection system, machine learning algorithm and deep learning algorithm in detail. Finally, the model of spark applied to intrusion detection system is listed, and it is concluded that the combination of spark and machine learning technology for intrusion detection system can make it more efficient.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114389255","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}
Rustam Tagiew, T. Buder, Kai Hofmann, Christian Klotz, Roman Tilly
The approval of Automatic Train Operation (ATO) from GoA3 on (GoA3+) requires a strong developers’ network to ensure the homogeneous landscape of expert opinions for regulators and courts. Certain technologies needed for GoA3+, especially Computer Vision (CV) powered by Deep Learning (DL), are fast developing and therefore do not exhibit a sufficient degree of professional experience for technical norms, although there is no scarcity at methodical candidates for such an approval process. What appears to be missing is a set of the relevant approval requirements as well as their implications for CV and DL, in order to serve as a common nucleation core for the development of a GoA3+ approval process. This paper aims at providing such a core. THIS CONTRIBUTION REPRESENTS SOLELY AUTHORS’ PROFESSIONAL OPINION, NOT THE ONE OF THEIR EMPLOYER.
{"title":"Towards Nucleation of GoA3+ Approval Process","authors":"Rustam Tagiew, T. Buder, Kai Hofmann, Christian Klotz, Roman Tilly","doi":"10.1145/3497737.3497742","DOIUrl":"https://doi.org/10.1145/3497737.3497742","url":null,"abstract":"The approval of Automatic Train Operation (ATO) from GoA3 on (GoA3+) requires a strong developers’ network to ensure the homogeneous landscape of expert opinions for regulators and courts. Certain technologies needed for GoA3+, especially Computer Vision (CV) powered by Deep Learning (DL), are fast developing and therefore do not exhibit a sufficient degree of professional experience for technical norms, although there is no scarcity at methodical candidates for such an approval process. What appears to be missing is a set of the relevant approval requirements as well as their implications for CV and DL, in order to serve as a common nucleation core for the development of a GoA3+ approval process. This paper aims at providing such a core. THIS CONTRIBUTION REPRESENTS SOLELY AUTHORS’ PROFESSIONAL OPINION, NOT THE ONE OF THEIR EMPLOYER.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130552585","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 studies a bionic gesture recognition system based on surface electromyography (sEMG). The system was designed and realized based on STM32F4. The sEMG signals of the operator's upper palmaris longus muscle, extensor digitorum muscle and flexor digitorum superficial muscle were collected by means of electrode patch. The machine learning method was used to improve the quality of signal acquisition, optimize motion recognition, improve motion recognition accuracy and control the manipulator to make corresponding actions. In this paper, a set of gesture recognition data set is constructed, which contains 90,000 data of 24 kinds of gesture actions. Through comparative analysis of BP, MPL, LeNet and DenseNet, it is shown that the system can obtain better recognition accuracy by using the MPL model and the LeNet model. In addition, a control experiment was conducted in this paper. The experimental results show that the recognition accuracy of the system can be significantly improved when the gesture data of the experimenter is added to the data set for training.
{"title":"Motion Recognition of Bionic Manipulator Based on Surface Muscle Electrical Signals","authors":"Min Huang, Lei Mu","doi":"10.1145/3497737.3497743","DOIUrl":"https://doi.org/10.1145/3497737.3497743","url":null,"abstract":"This paper studies a bionic gesture recognition system based on surface electromyography (sEMG). The system was designed and realized based on STM32F4. The sEMG signals of the operator's upper palmaris longus muscle, extensor digitorum muscle and flexor digitorum superficial muscle were collected by means of electrode patch. The machine learning method was used to improve the quality of signal acquisition, optimize motion recognition, improve motion recognition accuracy and control the manipulator to make corresponding actions. In this paper, a set of gesture recognition data set is constructed, which contains 90,000 data of 24 kinds of gesture actions. Through comparative analysis of BP, MPL, LeNet and DenseNet, it is shown that the system can obtain better recognition accuracy by using the MPL model and the LeNet model. In addition, a control experiment was conducted in this paper. The experimental results show that the recognition accuracy of the system can be significantly improved when the gesture data of the experimenter is added to the data set for training.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130912891","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}
Quantum secure communication based on Quantum Key Distribution (QKD) has entered the practical stage, and will become one of the most reliable schemes to improve the network information security protection capability.Quantum key distribution (QKD), underpinned by the uncertainty, indivisibility and non-duplication nature of quantum, adopts coding techniques to ensure the security of keys with a series of protocols.
{"title":"The Design and Application in Secure Communication Based on Quantum Technology","authors":"J. Hu, Lejiang Guo, Lei Xiao, Fangxin Chen","doi":"10.1145/3497737.3497744","DOIUrl":"https://doi.org/10.1145/3497737.3497744","url":null,"abstract":"Quantum secure communication based on Quantum Key Distribution (QKD) has entered the practical stage, and will become one of the most reliable schemes to improve the network information security protection capability.Quantum key distribution (QKD), underpinned by the uncertainty, indivisibility and non-duplication nature of quantum, adopts coding techniques to ensure the security of keys with a series of protocols.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133205590","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}
Aiming at the difficult and expensive problem of dairy cow mastitis detection, an analysis method based on conductance method and weighted deep forest model is proposed, a new method of extracting conductance data features is added, and the deep random forest model is optimized by weighting. By comparing machine learning algorithms, using Accuracy, Recall, Precision, F1-Measure, and AUC (Area under Curve) as evaluation indicators, through case analysis, it is finally determined that the weighted deep forest performs well. AUC's somatic cell and somatic cell typing count reached 0.93 and 0.98, respectively.
针对奶牛乳腺炎检测难度大、成本高的问题，提出了一种基于电导法和加权深度森林模型的分析方法，增加了一种新的电导数据特征提取方法，并对深度随机森林模型进行了加权优化。通过对比机器学习算法，以Accuracy、Recall、Precision、F1-Measure和AUC (Area under Curve)作为评价指标，通过案例分析，最终确定加权深度森林表现较好。AUC的体细胞数和体细胞分型数分别达到0.93和0.98。
{"title":"Research on Dairy Cow Mastitis Based on Conductance Method and Weighted Deep Forest","authors":"Yabin Ma, Bin Liu, Jinsen Guan, Yang Zhang","doi":"10.1145/3497737.3497739","DOIUrl":"https://doi.org/10.1145/3497737.3497739","url":null,"abstract":"Aiming at the difficult and expensive problem of dairy cow mastitis detection, an analysis method based on conductance method and weighted deep forest model is proposed, a new method of extracting conductance data features is added, and the deep random forest model is optimized by weighting. By comparing machine learning algorithms, using Accuracy, Recall, Precision, F1-Measure, and AUC (Area under Curve) as evaluation indicators, through case analysis, it is finally determined that the weighted deep forest performs well. AUC's somatic cell and somatic cell typing count reached 0.93 and 0.98, respectively.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131709413","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}
Mogamat Yaaseen Martin, S. Winberg, M. Gaffar, D. MacLeod
The problem of space debris represents a major topic of concern in astronomy as the threat of space junk continues to grow, and the accuracy of its tracking is greatly restricted by the insufficiency and limitations of current surveillance sensors. This article presents the development of an open-source, high-performance, signal-level radar simulator to assist in modelling the detection and tracking of space debris from terrestrial radar stations, including multistatic installations where the transmitter and receiver may be separated by many kilometers. This tool is expected to aid astronomers and researchers in space situational awareness, supporting the modelling of radar interactions in this context and simulation-based exploration of radar designs for space surveillance. It makes use of an accelerated orbit propagation technique with measured two-line element datasets being used to define space debris objects. The software has been named the Space Object Astrodynamics and Radar Simulator – or SOARS – and both the transmitted and received signals generated by the application have been shown to agree with theoretical expectations. Additionally, SOARS is presently undergoing continued development, extension and optimization for heterogeneous computing platforms, enabling the use of the NVIDIA® Compute Unified Device Architecture (CUDA) interface. Results have demonstrated promising speed-ups in simulation runtimes when using the CUDA version of the application over the original sequential version, even on lower-end graphics processors. It is anticipated that the developed application will be used for the design and testing of radar sensors for space situational awareness applications, as well as for use in research, teaching and training environments.
{"title":"The Design and Development of a GPU-accelerated Radar Simulator for Space Debris Monitoring","authors":"Mogamat Yaaseen Martin, S. Winberg, M. Gaffar, D. MacLeod","doi":"10.1145/3497737.3497741","DOIUrl":"https://doi.org/10.1145/3497737.3497741","url":null,"abstract":"The problem of space debris represents a major topic of concern in astronomy as the threat of space junk continues to grow, and the accuracy of its tracking is greatly restricted by the insufficiency and limitations of current surveillance sensors. This article presents the development of an open-source, high-performance, signal-level radar simulator to assist in modelling the detection and tracking of space debris from terrestrial radar stations, including multistatic installations where the transmitter and receiver may be separated by many kilometers. This tool is expected to aid astronomers and researchers in space situational awareness, supporting the modelling of radar interactions in this context and simulation-based exploration of radar designs for space surveillance. It makes use of an accelerated orbit propagation technique with measured two-line element datasets being used to define space debris objects. The software has been named the Space Object Astrodynamics and Radar Simulator – or SOARS – and both the transmitted and received signals generated by the application have been shown to agree with theoretical expectations. Additionally, SOARS is presently undergoing continued development, extension and optimization for heterogeneous computing platforms, enabling the use of the NVIDIA® Compute Unified Device Architecture (CUDA) interface. Results have demonstrated promising speed-ups in simulation runtimes when using the CUDA version of the application over the original sequential version, even on lower-end graphics processors. It is anticipated that the developed application will be used for the design and testing of radar sensors for space situational awareness applications, as well as for use in research, teaching and training environments.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125395700","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 deep understanding of the job characteristics and their impacts on the high performance computing system is one of the most critical steps for efficiently planning its design, development and optimization. However, frequent and regular characterization studies are insufficient in many HPC systems, which might make the study done by the system researchers inconsistent with the actual system features and application characteristics, and ultimately lead to the failure of the proposed strategy. Our study in this paper tries to bridge the gap by performing long-term analysis for job characteristics on a petascale ARM supercomputer, in this way, we get many meaningful findings and insights, which we believe can benefit the co-design of hardware and applications, and improve performance and experience of the job submitters in the HPC system.
{"title":"Long-Term Analysis for Job Characteristics on the Supercomputer","authors":"Wenxiang Yang, Jie Yu, Guolong Xing","doi":"10.1145/3497737.3497738","DOIUrl":"https://doi.org/10.1145/3497737.3497738","url":null,"abstract":"A deep understanding of the job characteristics and their impacts on the high performance computing system is one of the most critical steps for efficiently planning its design, development and optimization. However, frequent and regular characterization studies are insufficient in many HPC systems, which might make the study done by the system researchers inconsistent with the actual system features and application characteristics, and ultimately lead to the failure of the proposed strategy. Our study in this paper tries to bridge the gap by performing long-term analysis for job characteristics on a petascale ARM supercomputer, in this way, we get many meaningful findings and insights, which we believe can benefit the co-design of hardware and applications, and improve performance and experience of the job submitters in the HPC system.","PeriodicalId":250873,"journal":{"name":"Proceedings of the 2021 5th High Performance Computing and Cluster Technologies Conference","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131534321","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：