Pub Date : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345101
Junri Mi, Jin Xu
Traditional machine learning algorithms heavily depend on training data. In order to reduce the amount of training data, active learning is proposed to find out the critical data, which place more important roles against other data. The active learning algorithm is also used to learn real-time automaton(RTA). However, a huge number of membership queries and equivalence queries are generated in the learning process. In this paper, We design a new data structure to store the information obtained by membership queries. This data structure is a kind of tree structure, and improve the efficiency of the active learning for real-time RTA because this structure can process counter-examples effectively. Some experiments are conducted, and the results show that the algorithm can significantly reduce the number of membership queries without increasing the equivalence queries numbers. From the data point of view, our algorithm reduces the number of membership queries by 50% and the execution time by 80%.
{"title":"The Learning Algorithm of Real-Time Automata","authors":"Junri Mi, Jin Xu","doi":"10.1109/ICCC51575.2020.9345101","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345101","url":null,"abstract":"Traditional machine learning algorithms heavily depend on training data. In order to reduce the amount of training data, active learning is proposed to find out the critical data, which place more important roles against other data. The active learning algorithm is also used to learn real-time automaton(RTA). However, a huge number of membership queries and equivalence queries are generated in the learning process. In this paper, We design a new data structure to store the information obtained by membership queries. This data structure is a kind of tree structure, and improve the efficiency of the active learning for real-time RTA because this structure can process counter-examples effectively. Some experiments are conducted, and the results show that the algorithm can significantly reduce the number of membership queries without increasing the equivalence queries numbers. From the data point of view, our algorithm reduces the number of membership queries by 50% and the execution time by 80%.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115420462","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345166
Le Yang, Meng Li, Yanhua Zhang, Pengbo Si, Zhuwei Wang, Ruizhe Yang
Industrial Internet of Things (IIoT) has emerged with the developments of various communication technologies. In order to guarantee the security and privacy of massive IIoT data, blockchain is widely considered as a promising technology and applied into IIoT. However, there are still several issues in the existing blockchain-enabled IIoT: 1) unbearable energy consumption for computation tasks, 2) poor efficiency of consensus mechanism in blockchain, and 3) serious computation overhead of network systems. To handle the above issues and challenges, in this paper, we integrate mobile edge computing (MEC) into blockchain-enabled IIoT systems to promote the computation capability of IIoT devices and improve the efficiency of consensus process. Meanwhile, the weighted system cost including the energy consumption and the computation overhead are jointly considered. Moreover, we propose an optimization framework for blockchain-enabled IIoT systems to decrease consumption, and formulate the proposed problem as a Markov decision process (MDP). The master controller, offloading decision, block size and computing server can be dynamically selected and adjusted to optimize the devices energy allocation and reduce the weighted system cost. Accordingly, due to the high-dynamic and large-dimensional characteristics, deep reinforcement learning (DRL) is introduced to solve the formulated problem. Simulation results demonstrate that our proposed scheme can improve system performance significantly compared to other existing schemes.
{"title":"Resource Management for Energy-Efficient and Blockchain-Enabled Industrial IoT: A DRL Approach","authors":"Le Yang, Meng Li, Yanhua Zhang, Pengbo Si, Zhuwei Wang, Ruizhe Yang","doi":"10.1109/ICCC51575.2020.9345166","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345166","url":null,"abstract":"Industrial Internet of Things (IIoT) has emerged with the developments of various communication technologies. In order to guarantee the security and privacy of massive IIoT data, blockchain is widely considered as a promising technology and applied into IIoT. However, there are still several issues in the existing blockchain-enabled IIoT: 1) unbearable energy consumption for computation tasks, 2) poor efficiency of consensus mechanism in blockchain, and 3) serious computation overhead of network systems. To handle the above issues and challenges, in this paper, we integrate mobile edge computing (MEC) into blockchain-enabled IIoT systems to promote the computation capability of IIoT devices and improve the efficiency of consensus process. Meanwhile, the weighted system cost including the energy consumption and the computation overhead are jointly considered. Moreover, we propose an optimization framework for blockchain-enabled IIoT systems to decrease consumption, and formulate the proposed problem as a Markov decision process (MDP). The master controller, offloading decision, block size and computing server can be dynamically selected and adjusted to optimize the devices energy allocation and reduce the weighted system cost. Accordingly, due to the high-dynamic and large-dimensional characteristics, deep reinforcement learning (DRL) is introduced to solve the formulated problem. Simulation results demonstrate that our proposed scheme can improve system performance significantly compared to other existing schemes.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116787284","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344984
H. Gull, Gomathi Krishna, May Aldossary, S. Z. Iqbal
A bstract-Coronavirus disease has been declared as an infectious pandemic affecting the life and health of millions across the globe. It has caused high number of mortalities giving birth to exceptional state of emergency worldwide. It has not affected the people but also has damaged infrastructure of different countries, especially causing an expectational situation in health care systems globally. Due to unavailability of vaccination and faster human to human transmission of virus, healthcare facilities are at high risk of exceeding their limit and capacity, especially in developing countries like Pakistan. Therefore, it is important to manage resources properly in these countries to control high mortality rate and damage it can cause. In this paper we have taken a case study of small city in Pakistan, where healthcare facilities are not enough to deal with pandemic. Most of the COVID-19 patients have to be refer to big cities based on their severity. We have taken data of COVID-19 positive patients from this small city, developed and applied machine learning classification model to predict the severity of patient, in order to deal with the shortage of resources. Among all seven taken and tested algorithms, we have chosen SVM to predict severity of patients. Model has shown 60% of accuracy and have divided patient's severity into mild, moderate and severe levels.
{"title":"Severity Prediction of COVID-19 Patients Using Machine Learning Classification Algorithms: A Case Study of Small City in Pakistan with Minimal Health Facility","authors":"H. Gull, Gomathi Krishna, May Aldossary, S. Z. Iqbal","doi":"10.1109/ICCC51575.2020.9344984","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344984","url":null,"abstract":"A bstract-Coronavirus disease has been declared as an infectious pandemic affecting the life and health of millions across the globe. It has caused high number of mortalities giving birth to exceptional state of emergency worldwide. It has not affected the people but also has damaged infrastructure of different countries, especially causing an expectational situation in health care systems globally. Due to unavailability of vaccination and faster human to human transmission of virus, healthcare facilities are at high risk of exceeding their limit and capacity, especially in developing countries like Pakistan. Therefore, it is important to manage resources properly in these countries to control high mortality rate and damage it can cause. In this paper we have taken a case study of small city in Pakistan, where healthcare facilities are not enough to deal with pandemic. Most of the COVID-19 patients have to be refer to big cities based on their severity. We have taken data of COVID-19 positive patients from this small city, developed and applied machine learning classification model to predict the severity of patient, in order to deal with the shortage of resources. Among all seven taken and tested algorithms, we have chosen SVM to predict severity of patients. Model has shown 60% of accuracy and have divided patient's severity into mild, moderate and severe levels.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120915525","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}
At present, Chinese traditional physiotherapy is more and more trusted and valued by people, among which moxibustion is a very effective treatment. In order to improve the efficiency of human-computer interaction and help physiotherapists to use robots to replace human power, this paper proposes a visual based robot arm trajectory teaching method. The physiotherapy staff only needs to use an optical marker to demonstrate the therapeutic trajectory on the patient's back, and the robotic arm can pick up the expected trajectory and repeat the same work. We use LK optical flow algorithm to obtain marker's motion trajectory, and then smoothen the trajectory through SG filter, which is more executable for robot arm. Finally, we design an experiment and simulate it on MATLAB to obtain the accuracy of the trajectory and the results is impressive.
{"title":"A Visual Based Robot Trajectory Teaching Method for Traditional Chinese Medical Moxibustion Therapy","authors":"Jiaxun Liu, Qujiang Lei, Yukai Qiao, Guangchao Gui, Xiuhao Li, Jintao Jin, Weijun Wang","doi":"10.1109/ICCC51575.2020.9345310","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345310","url":null,"abstract":"At present, Chinese traditional physiotherapy is more and more trusted and valued by people, among which moxibustion is a very effective treatment. In order to improve the efficiency of human-computer interaction and help physiotherapists to use robots to replace human power, this paper proposes a visual based robot arm trajectory teaching method. The physiotherapy staff only needs to use an optical marker to demonstrate the therapeutic trajectory on the patient's back, and the robotic arm can pick up the expected trajectory and repeat the same work. We use LK optical flow algorithm to obtain marker's motion trajectory, and then smoothen the trajectory through SG filter, which is more executable for robot arm. Finally, we design an experiment and simulate it on MATLAB to obtain the accuracy of the trajectory and the results is impressive.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120943323","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345280
Chen Jiayao, Zhang Dalong, Han Gangtao, Li Zhiyuan
In Inertial Navigation System (INS) and Global Positioning System (GPS) integrated system, lever arm effect is an important error source, which makes the integrated system highly nonlinear. In addition to nonlinear problem, the lever arm is difficult to measure in practical applications. To solve the problems, the direct filtering method considering the lever arm effect of Unscented Kalman Filter (UKF) is proposed in this paper. The proposed method adds lever arm to system model of direct Kalman filter and compensates the estimated lever arm, and thus the lever arm is constantly estimated and modified as the filter estimations are updated. Specifically, the system state model and measurement model are established based on the direct filtering method. The navigation parameters of INS and lever arm are taken as system state variable, the velocity and position of GPS are taken as measurement variable. Then the UKF is used for INS/GPS integrated system information fusion. Simulation results show that the proposed direct UKF considering lever arm of integrated navigation system can estimate the lever arm correctly. Furthermore, the accuracy of the proposed method is significantly higher than that of standard indirect KF and standard direct UKF.
{"title":"A Method for Lever Arm Estimation in INS/GPS Integration Using Direct Unscented Kalman Filter","authors":"Chen Jiayao, Zhang Dalong, Han Gangtao, Li Zhiyuan","doi":"10.1109/ICCC51575.2020.9345280","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345280","url":null,"abstract":"In Inertial Navigation System (INS) and Global Positioning System (GPS) integrated system, lever arm effect is an important error source, which makes the integrated system highly nonlinear. In addition to nonlinear problem, the lever arm is difficult to measure in practical applications. To solve the problems, the direct filtering method considering the lever arm effect of Unscented Kalman Filter (UKF) is proposed in this paper. The proposed method adds lever arm to system model of direct Kalman filter and compensates the estimated lever arm, and thus the lever arm is constantly estimated and modified as the filter estimations are updated. Specifically, the system state model and measurement model are established based on the direct filtering method. The navigation parameters of INS and lever arm are taken as system state variable, the velocity and position of GPS are taken as measurement variable. Then the UKF is used for INS/GPS integrated system information fusion. Simulation results show that the proposed direct UKF considering lever arm of integrated navigation system can estimate the lever arm correctly. Furthermore, the accuracy of the proposed method is significantly higher than that of standard indirect KF and standard direct UKF.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127160346","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345258
Yajun Liu, Xiaoqun Liu, Jianfang Zhang, Yingying Cao, Xiaodong Liu
The spectrum grid of the traditional wavelength division multiplexing (WDM) network is fixed, so it has the shortcomings of low spectrum utilization and poor flexibility. Based on this, elastic optical network (EON) came into being. Compared with the traditional WDM network, the EON has a flexible spectrum grid with high network flexibility and can provide different spectrums for different services. But the EON still has the problem of load balancing. In order to further optimize the EON, this article uses the Least Connections algorithm to solve the EON load balancing problem, taking into account the different server load capacity to improve it. In addition, to further improve the performance of EON, this paper combines genetic algorithm, improved least connections algorithm and ant colony algorithm to propose a new algorithm LC-GAACO. The simulation results show that the LC-GAACO algorithm will consume more optical transceivers while taking into account load balancing, but the network load balancing effect, network spectrum utilization, and blocking rate are better than traditional algorithms.
{"title":"Research on Load Balancing Algorithm of Multicast Services Based on EON","authors":"Yajun Liu, Xiaoqun Liu, Jianfang Zhang, Yingying Cao, Xiaodong Liu","doi":"10.1109/ICCC51575.2020.9345258","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345258","url":null,"abstract":"The spectrum grid of the traditional wavelength division multiplexing (WDM) network is fixed, so it has the shortcomings of low spectrum utilization and poor flexibility. Based on this, elastic optical network (EON) came into being. Compared with the traditional WDM network, the EON has a flexible spectrum grid with high network flexibility and can provide different spectrums for different services. But the EON still has the problem of load balancing. In order to further optimize the EON, this article uses the Least Connections algorithm to solve the EON load balancing problem, taking into account the different server load capacity to improve it. In addition, to further improve the performance of EON, this paper combines genetic algorithm, improved least connections algorithm and ant colony algorithm to propose a new algorithm LC-GAACO. The simulation results show that the LC-GAACO algorithm will consume more optical transceivers while taking into account load balancing, but the network load balancing effect, network spectrum utilization, and blocking rate are better than traditional algorithms.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"09 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127182131","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344964
Yang Xu, W. Muqing, Yao Guohao
In order to solve the problem of low throughput and poor performance in data center network, this paper proposes a traffic scheduling algorithm exploiting fuzzy logic inference based on Software Defined Networking (SDN). The algorithm uses the characteristics of separation of control and forwarding in SDN architecture to choose paths for data flows by the centralized control of controller. It calculates the candidate path set of accessible paths between the source host and the destination host, then comprehensively considers path hops and bandwidth utilization, evaluates the candidate path using fuzzy logic model, and selects the optimal path. The experimental results show that compared with ECMP, Hedera and FSEM, the proposed algorithm improves the network throughput and load balancing, thus improving the overall network performance of the data center.
{"title":"An Effective Routing Mechanism Based on Fuzzy Logic for Software-Defined Data Center Networks","authors":"Yang Xu, W. Muqing, Yao Guohao","doi":"10.1109/ICCC51575.2020.9344964","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344964","url":null,"abstract":"In order to solve the problem of low throughput and poor performance in data center network, this paper proposes a traffic scheduling algorithm exploiting fuzzy logic inference based on Software Defined Networking (SDN). The algorithm uses the characteristics of separation of control and forwarding in SDN architecture to choose paths for data flows by the centralized control of controller. It calculates the candidate path set of accessible paths between the source host and the destination host, then comprehensively considers path hops and bandwidth utilization, evaluates the candidate path using fuzzy logic model, and selects the optimal path. The experimental results show that compared with ECMP, Hedera and FSEM, the proposed algorithm improves the network throughput and load balancing, thus improving the overall network performance of the data center.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125059203","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}
With the development of large-scale construction of smart grid, the edge terminal equipment of power grid will produce a large number of time series power data with great redundancy, which brings great challenges to the storage of edge side of the equipment. In order to reduce the storage cost of edge side, data mining and weight removal are needed. The traditional data mining technology generally adopts the data mining method based on dynamic time regularity, but the disadvantage is that the mining efficiency is low and the adjacent data with low similarity can not be weighed. Aiming at these problems, this paper proposes an algorithm based on weighted integration dynamic time-regulation and Euclidean distance optimization, which can eliminate data redundancy, achieve data mining and weight removal by calculating the similarity between data. Finally, based on the real sampling data of smart grid, the effect of the proposed data mining technology in edge computing security protection system is analyzed and verified.
{"title":"A Novel Weighted Integration Dynamic Time Regularization and Euclidean Distance Optimization Algorithm for Power Data Mining","authors":"Wenda Lu, Xiaolong Zhao, Chen Sun, Rongjun Chen, Guang Duan","doi":"10.1109/ICCC51575.2020.9345154","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345154","url":null,"abstract":"With the development of large-scale construction of smart grid, the edge terminal equipment of power grid will produce a large number of time series power data with great redundancy, which brings great challenges to the storage of edge side of the equipment. In order to reduce the storage cost of edge side, data mining and weight removal are needed. The traditional data mining technology generally adopts the data mining method based on dynamic time regularity, but the disadvantage is that the mining efficiency is low and the adjacent data with low similarity can not be weighed. Aiming at these problems, this paper proposes an algorithm based on weighted integration dynamic time-regulation and Euclidean distance optimization, which can eliminate data redundancy, achieve data mining and weight removal by calculating the similarity between data. Finally, based on the real sampling data of smart grid, the effect of the proposed data mining technology in edge computing security protection system is analyzed and verified.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125892919","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345086
Abdul Noor, Youxi Wu, Salabat Khan
Vehicular Social Networks (VSNs) are expected to become a reality soon, where commuters having common interests in the virtual community of vehicles, drivers, passengers can share information, both about road conditions and their surroundings. This will improve transportation efficiency and public safety. However, social networking exposes vehicles to different kinds of cyber-attacks. This concern can be addressed through an efficient and secure key management framework. This study presents a Secure and Transparent Public-key Management (ST-PKMS) based on blockchain and notary system, but it addresses security and privacy challenges specific to VSNs. ST-PKMS significantly enhances the efficiency and trustworthiness of mutual authentication. In ST-PKMS, each vehicle has multiple short-lived anonymous public-keys, which are recorded on the blockchain platform. However, public-keys get activated only when a notary system notarizes it, and clients accept only notarized public-keys during mutual authentication. Compromised vehicles can be effectively removed from the VSNs by blocking notarization of their public-keys; thus, the need to distribute Certificate Revocation List (CRL) is eliminated in the proposed scheme. ST-PKMS ensures transparency, security, privacy, and availability, even in the face of an active adversary. The simulation and evaluation results show that the ST-PKMS meets real-time performance requirements, and it is cost-effective in terms of scalability, delay, and communication overhead.
{"title":"Secure and Transparent Public-key Management System for Vehicular Social Networks","authors":"Abdul Noor, Youxi Wu, Salabat Khan","doi":"10.1109/ICCC51575.2020.9345086","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345086","url":null,"abstract":"Vehicular Social Networks (VSNs) are expected to become a reality soon, where commuters having common interests in the virtual community of vehicles, drivers, passengers can share information, both about road conditions and their surroundings. This will improve transportation efficiency and public safety. However, social networking exposes vehicles to different kinds of cyber-attacks. This concern can be addressed through an efficient and secure key management framework. This study presents a Secure and Transparent Public-key Management (ST-PKMS) based on blockchain and notary system, but it addresses security and privacy challenges specific to VSNs. ST-PKMS significantly enhances the efficiency and trustworthiness of mutual authentication. In ST-PKMS, each vehicle has multiple short-lived anonymous public-keys, which are recorded on the blockchain platform. However, public-keys get activated only when a notary system notarizes it, and clients accept only notarized public-keys during mutual authentication. Compromised vehicles can be effectively removed from the VSNs by blocking notarization of their public-keys; thus, the need to distribute Certificate Revocation List (CRL) is eliminated in the proposed scheme. ST-PKMS ensures transparency, security, privacy, and availability, even in the face of an active adversary. The simulation and evaluation results show that the ST-PKMS meets real-time performance requirements, and it is cost-effective in terms of scalability, delay, and communication overhead.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125917955","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345123
Zhao Ru-tao, Wang Jing, Chen Gao-jian, Li Qian-wen, Yuan Yun-jing
Data analysis requires a high level of expertise for domain workers, and AutoML aims to make these decisions in an automated way. But it is still a difficult problem to automatically generate machine learning pipelines with high performance in acceptable time. This paper presents a DFSR (Data Feature and Service Association) approach to automatically generating machine learning pipelines utilizing data features and service associations. The experimental results showed that the performance of the generated pipelines reached the satisfactory level of current AutoML tools, and the time consumption is reduced to the minute level.
{"title":"A Machine Learning Pipeline Generation Approach for Data Analysis","authors":"Zhao Ru-tao, Wang Jing, Chen Gao-jian, Li Qian-wen, Yuan Yun-jing","doi":"10.1109/ICCC51575.2020.9345123","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345123","url":null,"abstract":"Data analysis requires a high level of expertise for domain workers, and AutoML aims to make these decisions in an automated way. But it is still a difficult problem to automatically generate machine learning pipelines with high performance in acceptable time. This paper presents a DFSR (Data Feature and Service Association) approach to automatically generating machine learning pipelines utilizing data features and service associations. The experimental results showed that the performance of the generated pipelines reached the satisfactory level of current AutoML tools, and the time consumption is reduced to the minute level.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123247647","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}