Pub Date : 2021-04-23DOI: 10.1109/ICCCS52626.2021.9449275
Haolin Ma, Weihang Cui, Meng Yue, Zhi-jun Wu
In order to analyze the performance of the integrated modular avionics (IMA) system, it is difficult to describe the dynamic process of the state change of complex systems by reliability block diagram (RBD) method, dynamic fault tree analysis (DFTA) method and GO method, etc. This paper first uses the DTFA to decompose the running status of the multi-partition software of the IMA system, and then uses the extended deterministic and stochastic Petri nets (EDSPN) model and analysis method to determine the Petri nets model of AND gate, OR gate, hot reserve gate, cold reserve gate and VOTE gate in the DFTA. Finally, taking the display function of the IMA system as an example, the DTFA is used to decompose the failure mode of the display function of the IMA system, and the reliability EDSPN model of the multi-partition software of the display function of the IMA system is established. Using TimeNET4.4 simulation software to perform transient analysis and steady-state analysis on the model, the failure rate of the display function of the IMA system is 7.8×10−5, and the influence of the fault propagation rate between the partition software on the display function of the IMA system is obtained. A good model foundation for reliability analysis of IMA system multi-partition software is provided.
{"title":"Modeling and Simulation on Dynamic Reliability of Multi-partition Software of IMA Based on TimeNET4.4","authors":"Haolin Ma, Weihang Cui, Meng Yue, Zhi-jun Wu","doi":"10.1109/ICCCS52626.2021.9449275","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449275","url":null,"abstract":"In order to analyze the performance of the integrated modular avionics (IMA) system, it is difficult to describe the dynamic process of the state change of complex systems by reliability block diagram (RBD) method, dynamic fault tree analysis (DFTA) method and GO method, etc. This paper first uses the DTFA to decompose the running status of the multi-partition software of the IMA system, and then uses the extended deterministic and stochastic Petri nets (EDSPN) model and analysis method to determine the Petri nets model of AND gate, OR gate, hot reserve gate, cold reserve gate and VOTE gate in the DFTA. Finally, taking the display function of the IMA system as an example, the DTFA is used to decompose the failure mode of the display function of the IMA system, and the reliability EDSPN model of the multi-partition software of the display function of the IMA system is established. Using TimeNET4.4 simulation software to perform transient analysis and steady-state analysis on the model, the failure rate of the display function of the IMA system is 7.8×10−5, and the influence of the fault propagation rate between the partition software on the display function of the IMA system is obtained. A good model foundation for reliability analysis of IMA system multi-partition software is provided.","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":"128584148","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/ICCCS52626.2021.9449140
Shuai Chen, C. Zheng, Liguo Sun
A new method using deep learning to retrieve the main parameters of ocean waves which include significant wave heights, peak wave periods, peak wave lengths and peak wave directions. At present, retrieve of significant wave height can use the model of Convolutional Long Short-Term Memory(ConvLSTM) with attention. However, the accuracy of this method needs to be improved, and it can only retrieve a single wave parameter. We propose a Transformer-based network structure, which improves the accuracy effectively and can simultaneously retrieve multiple wave parameters. Finally, we use Pearson's correlation coefficient as an evaluation index to compare with the baseline. Experimental results show that the performance of the network has been improved.
{"title":"A New Method of Wave Parameter Retrieve Based on Transformer","authors":"Shuai Chen, C. Zheng, Liguo Sun","doi":"10.1109/ICCCS52626.2021.9449140","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449140","url":null,"abstract":"A new method using deep learning to retrieve the main parameters of ocean waves which include significant wave heights, peak wave periods, peak wave lengths and peak wave directions. At present, retrieve of significant wave height can use the model of Convolutional Long Short-Term Memory(ConvLSTM) with attention. However, the accuracy of this method needs to be improved, and it can only retrieve a single wave parameter. We propose a Transformer-based network structure, which improves the accuracy effectively and can simultaneously retrieve multiple wave parameters. Finally, we use Pearson's correlation coefficient as an evaluation index to compare with the baseline. Experimental results show that the performance of the network has been improved.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"os-15 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":"127764710","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/ICCCS52626.2021.9449242
Xu Wang, Kaili Zhou, Zhiyong Hong
In view of the current majority of family farm planting, especially open field planting, the information technology level is lower. Based on the Internet of Things(IoT) technology, an open field smart planting system is designed. STM32 microprocessor is used as the main control chip to design terminal nodes. Each node has the ability to sense the air temperature and humidity, soil humidity, light intensity and other planting environment parameters, and has on-off control function for irrigation and plastic film device. The number of terminal nodes can be increased or decreased to meet the needs of open field smart planting. The terminal node connects the NB-IoT base station through NB-IoT module, and then transmits the sensing data to the cloud server. We can monitor the plants, the planting environment and the working states of the device by the 5G wireless cameral. The user terminal is a smartphone. User can log in to the open field smart planting system through mobile APP, and then interact with the terminal device, monitor the sensing data in real time, watch videos of plant growth status and planting environment, and control the irrigation and plastic film devices remotely. It can also be set to automatic control mode to control the devices automatically. The system has the advantages of simple architecture, convenient deployment and use. The rented cloud server is used for data storage and data processing. Data is transmitted through services provided by operators. It is safe and reliable with low operation and maintenance cost, and is suitable for open field planting of family farm.
{"title":"Open Field Smart Planting System of Family Farm","authors":"Xu Wang, Kaili Zhou, Zhiyong Hong","doi":"10.1109/ICCCS52626.2021.9449242","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449242","url":null,"abstract":"In view of the current majority of family farm planting, especially open field planting, the information technology level is lower. Based on the Internet of Things(IoT) technology, an open field smart planting system is designed. STM32 microprocessor is used as the main control chip to design terminal nodes. Each node has the ability to sense the air temperature and humidity, soil humidity, light intensity and other planting environment parameters, and has on-off control function for irrigation and plastic film device. The number of terminal nodes can be increased or decreased to meet the needs of open field smart planting. The terminal node connects the NB-IoT base station through NB-IoT module, and then transmits the sensing data to the cloud server. We can monitor the plants, the planting environment and the working states of the device by the 5G wireless cameral. The user terminal is a smartphone. User can log in to the open field smart planting system through mobile APP, and then interact with the terminal device, monitor the sensing data in real time, watch videos of plant growth status and planting environment, and control the irrigation and plastic film devices remotely. It can also be set to automatic control mode to control the devices automatically. The system has the advantages of simple architecture, convenient deployment and use. The rented cloud server is used for data storage and data processing. Data is transmitted through services provided by operators. It is safe and reliable with low operation and maintenance cost, and is suitable for open field planting of family farm.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"31 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":"132113399","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/ICCCS52626.2021.9449173
Yuqi Wang, Haiqiang Wang, Dan Liu, Xu Zhang, Xi Zhong, Xiaodong Han
For remote sensing mission planning problem, we establish the discretization of the mission planning model. We put forward disjoint set segmentation method of remote sensing satellite mission planning. We use disjoint set segmentation algorithm to segment large-scale problem of mission planning into several subproblems. At the same time, we improve the solving efficiency and guarantee the solving quality. The simulation results show that compared with the traditional mixed integer programming algorithm, the method based on disjoint set segmentation shows good practicability and optimization effect. The method can reduce the solving time of the model by about 50%.
{"title":"A Novel Mission Planning Method for Remote Sensing Satellite","authors":"Yuqi Wang, Haiqiang Wang, Dan Liu, Xu Zhang, Xi Zhong, Xiaodong Han","doi":"10.1109/ICCCS52626.2021.9449173","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449173","url":null,"abstract":"For remote sensing mission planning problem, we establish the discretization of the mission planning model. We put forward disjoint set segmentation method of remote sensing satellite mission planning. We use disjoint set segmentation algorithm to segment large-scale problem of mission planning into several subproblems. At the same time, we improve the solving efficiency and guarantee the solving quality. The simulation results show that compared with the traditional mixed integer programming algorithm, the method based on disjoint set segmentation shows good practicability and optimization effect. The method can reduce the solving time of the model by about 50%.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 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":"129986731","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/ICCCS52626.2021.9449274
Wei Wu, Qisheng Zhu, Fei Wang
In the field of HPC (High Performance Computing), tons of compiling optimizing technologies have been proposed. However, users are usually confused about which optimizing should be enabled to speed up their applications on the target processor. In this paper, an iterative compiling framework is proposed to probe the compiler options automatically to optimize programs. Tightly coupling with the system software of the SHENWEI family processors, this framework provides flexible iterative supports based on hot functions of many-core programs, which dramatically improve user-friendliness of the computer systems built on SHENWEI family processors. The evaluation shows that with the help of autotuning, the performance of the SPEC2000 cases and the SPEC2006 cases can be improved about 14% and 25% respectively on average compared with the -O3 optimizing level.
{"title":"Compiler Autotuning Based on Hot Function for SHENWEI Processor","authors":"Wei Wu, Qisheng Zhu, Fei Wang","doi":"10.1109/ICCCS52626.2021.9449274","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449274","url":null,"abstract":"In the field of HPC (High Performance Computing), tons of compiling optimizing technologies have been proposed. However, users are usually confused about which optimizing should be enabled to speed up their applications on the target processor. In this paper, an iterative compiling framework is proposed to probe the compiler options automatically to optimize programs. Tightly coupling with the system software of the SHENWEI family processors, this framework provides flexible iterative supports based on hot functions of many-core programs, which dramatically improve user-friendliness of the computer systems built on SHENWEI family processors. The evaluation shows that with the help of autotuning, the performance of the SPEC2000 cases and the SPEC2006 cases can be improved about 14% and 25% respectively on average compared with the -O3 optimizing level.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"83 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":"134226210","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/ICCCS52626.2021.9449218
Ao Li, Qingshan Jiang, Wei Luo
5G data channel is latency-sensitive and demands high throughput. The Min-Sum (MS) algorithm, known as one of the LDPC Soft-Decision decoding algorithms, is widely used with guaranteed performance. However, the MS algorithm's latency and resource consumption are non-negligible drawbacks, especially for 5G system. In this paper, different strategies for FEC (Forward Error Correction) of LDPC codes are discussed. An improved Weighted Hard-Decision algorithm is proposed targeting to reduce resource occupation and latency. The decoding process is given in detail and performance is validated via simulations. Comparing with the MS algorithm and IHD (Improved Hard-Decision) algorithm, our proposed algorithm shows its potentiality to be applied in 5G data channel. Furthermore, a test bench is launched in Cisco server using X86 chipset to identify the advantage of this proposal.
{"title":"Low latency Improved Weighted Hard-Decision LDPC Algorithm for 5G NR","authors":"Ao Li, Qingshan Jiang, Wei Luo","doi":"10.1109/ICCCS52626.2021.9449218","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449218","url":null,"abstract":"5G data channel is latency-sensitive and demands high throughput. The Min-Sum (MS) algorithm, known as one of the LDPC Soft-Decision decoding algorithms, is widely used with guaranteed performance. However, the MS algorithm's latency and resource consumption are non-negligible drawbacks, especially for 5G system. In this paper, different strategies for FEC (Forward Error Correction) of LDPC codes are discussed. An improved Weighted Hard-Decision algorithm is proposed targeting to reduce resource occupation and latency. The decoding process is given in detail and performance is validated via simulations. Comparing with the MS algorithm and IHD (Improved Hard-Decision) algorithm, our proposed algorithm shows its potentiality to be applied in 5G data channel. Furthermore, a test bench is launched in Cisco server using X86 chipset to identify the advantage of this proposal.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"71 9-10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131495326","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/ICCCS52626.2021.9449182
Xi Qian, Wenyuan Wu
Lattice-based Attribute-based encryption is a well-known cryptographic mechanism that can resist quantum attacks and has the ability of fine-grained access control, and it has a wide range of application scenarios in current Internet of Thing (IoT) era. However, lack of efficiency and existing the problem of large ciphertext expansion rate are the main disadvantages impede the applications of this mechanism. Thus, we propose an efficient and practical ciphertext policy attribute-based encryption (CP-ABE) scheme from lattices in the paper. In this scheme, to make the secret key reusable, we adjust access tree and propose a basic access tree structure, which can be converted from disjunctive normal form, and combine it with a light post-quantum scheme of Kyber. In addition, the compression method and plaintext expansion method are introduced to optimize the scheme. Our CP-ABE scheme is secure against chosen plaintext attack under the hardness of module learning with errors problem. We implement our scheme and compare it with three recent related schemes in terms of security, function and communication cost. Experiments and comparisons show that our CP-ABE scheme has advantages in high encryption efficiency, small matrix dimension, small key sizes, and low ciphertext expansion rate, which has some merit in practice.
{"title":"An Efficient Ciphertext Policy Attribute-Based Encryption Scheme from Lattices and Its Implementation","authors":"Xi Qian, Wenyuan Wu","doi":"10.1109/ICCCS52626.2021.9449182","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449182","url":null,"abstract":"Lattice-based Attribute-based encryption is a well-known cryptographic mechanism that can resist quantum attacks and has the ability of fine-grained access control, and it has a wide range of application scenarios in current Internet of Thing (IoT) era. However, lack of efficiency and existing the problem of large ciphertext expansion rate are the main disadvantages impede the applications of this mechanism. Thus, we propose an efficient and practical ciphertext policy attribute-based encryption (CP-ABE) scheme from lattices in the paper. In this scheme, to make the secret key reusable, we adjust access tree and propose a basic access tree structure, which can be converted from disjunctive normal form, and combine it with a light post-quantum scheme of Kyber. In addition, the compression method and plaintext expansion method are introduced to optimize the scheme. Our CP-ABE scheme is secure against chosen plaintext attack under the hardness of module learning with errors problem. We implement our scheme and compare it with three recent related schemes in terms of security, function and communication cost. Experiments and comparisons show that our CP-ABE scheme has advantages in high encryption efficiency, small matrix dimension, small key sizes, and low ciphertext expansion rate, which has some merit in practice.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"20 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":"131041205","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/ICCCS52626.2021.9449149
Yongwei Fu, Yong Liu, Xiaolong Lan, Qingchun Chen
In this paper, we focused on the achievable rate of multi-hop buffer-aided relay networks, where one source node is supposed to deliver message with the assistance of multi-hop buffer-aided relays to one destination node in a decode-and-forward manner. Unlike previous research efforts, not only buffer-aided transmission scheduling, but also adaptive power allocation at source node and all intermediate relays are taken into considerations to derive the theoretically achievable end-to-end rate. Analysis results showed that, both buffer-aided transmission strategy and optimal power allocations can significantly improve the end-to-end achievable rate.
{"title":"On the Achievable Rate of Multi-Hop Buffer-Aided Relay Networks","authors":"Yongwei Fu, Yong Liu, Xiaolong Lan, Qingchun Chen","doi":"10.1109/ICCCS52626.2021.9449149","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449149","url":null,"abstract":"In this paper, we focused on the achievable rate of multi-hop buffer-aided relay networks, where one source node is supposed to deliver message with the assistance of multi-hop buffer-aided relays to one destination node in a decode-and-forward manner. Unlike previous research efforts, not only buffer-aided transmission scheduling, but also adaptive power allocation at source node and all intermediate relays are taken into considerations to derive the theoretically achievable end-to-end rate. Analysis results showed that, both buffer-aided transmission strategy and optimal power allocations can significantly improve the end-to-end achievable rate.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"86 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":"132258493","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/ICCCS52626.2021.9449237
Jun Cai, Zeting Yu, Zenan Li, Han Han, Bo Zhang, Xiaodong Yi
In recent years, mobile ad hoc networks are becoming more and more widely used because they do not rely on infrastructure, can be networked at any time and any place, and are low in cost. This paper proposes an effective broadcast protocol to transfer data in mobile ad hoc networks. The proposed protocol is a network topology awareness based probabilistic broadcast (NTAPB) protocol. It requires each node in the network to be configured with a unique ID. Every time a data packet broadcast from the source node is rebroadcast by another node, the ID of the rebroadcast node is recorded in the rebroadcast record table of the packet header. One packet is only allowed to be rebroadcast by the same node once. The network topology knowledge is dynamically awared by each node according to the information of source node and rebroadcast record table carried in the header of the received data packets. The protocol adopts different rebroadcast probability calculation strategies according to different network topologies. It distinguishes network topologies into two categories, fully connected and non-fully connected. For fully connected topologies, it uses a novel mathematical model to solve the optimal rebroadcast probability. For non-fully connected topologies, it distinguishes egress nodes and non-egress nodes to calculate rebroadcast probability separately. Different from related literature that only carried out simulation experiment evaluations, the paper has carried out a large number of physical experiment evaluations. The experimental results show that the protocol can obtain satisfactory packet delivery ratio and end-to-end delay under different network topologies.
{"title":"A Network Topology Awareness Based Probabilistic Broadcast Protocol for Data Transmission in Mobile Ad Hoc Networks","authors":"Jun Cai, Zeting Yu, Zenan Li, Han Han, Bo Zhang, Xiaodong Yi","doi":"10.1109/ICCCS52626.2021.9449237","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449237","url":null,"abstract":"In recent years, mobile ad hoc networks are becoming more and more widely used because they do not rely on infrastructure, can be networked at any time and any place, and are low in cost. This paper proposes an effective broadcast protocol to transfer data in mobile ad hoc networks. The proposed protocol is a network topology awareness based probabilistic broadcast (NTAPB) protocol. It requires each node in the network to be configured with a unique ID. Every time a data packet broadcast from the source node is rebroadcast by another node, the ID of the rebroadcast node is recorded in the rebroadcast record table of the packet header. One packet is only allowed to be rebroadcast by the same node once. The network topology knowledge is dynamically awared by each node according to the information of source node and rebroadcast record table carried in the header of the received data packets. The protocol adopts different rebroadcast probability calculation strategies according to different network topologies. It distinguishes network topologies into two categories, fully connected and non-fully connected. For fully connected topologies, it uses a novel mathematical model to solve the optimal rebroadcast probability. For non-fully connected topologies, it distinguishes egress nodes and non-egress nodes to calculate rebroadcast probability separately. Different from related literature that only carried out simulation experiment evaluations, the paper has carried out a large number of physical experiment evaluations. The experimental results show that the protocol can obtain satisfactory packet delivery ratio and end-to-end delay under different network topologies.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"5 3 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":"114389314","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/ICCCS52626.2021.9449280
Maonan Wang, K. Zheng, Xinyi Ning, Yanqing Yang, Xiujuan Wang
With the rapid development of the network, encrypted traffic classification plays a vital role in guaranteeing the quality of network services and ensuring the security of the network. Recent studies show that machine learning approaches based on statistical features and raw traffic sessions are effective for this task. However, the performance of the statistical-based approaches largely depends on the quality of the features. Experts need to design different features for different encrypted traffic classification tasks, which is time-consuming. Meanwhile, the raw traffic-based approach needs to uniformize the traffic size; this will cause the loss of information about the overall structure of the network traffic; for example, we do not know the time from the first packet to the last packet in a session. This paper proposes the CENTIME, which can extract comprehensive information based on ResNet and AutoEncoder to identify encrypted traffic. ResNet is used to extract information from uniformized traffic, and AutoEncoder is used to encode statistical features. The statistical features are used to compensate for the information loss caused by traffic uniformization. They only need to be designed once rather than be designed separately for different tasks. Moreover, the pooling layers are removed, and 1D convolution layers are used to help CENTIME make more effective use of raw traffic information. We evaluate the CENTIME on the public dataset “ISCX VPN-nonVPN”, and the results demonstrate the CENTIME outperforms the state-of-the-art encrypted traffic classification methods. More importantly, comprehensive traffic features generated in the CENTIME can represent different classes of traffic well.
{"title":"CENTIME: A Direct Comprehensive Traffic Features Extraction for Encrypted Traffic Classification","authors":"Maonan Wang, K. Zheng, Xinyi Ning, Yanqing Yang, Xiujuan Wang","doi":"10.1109/ICCCS52626.2021.9449280","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449280","url":null,"abstract":"With the rapid development of the network, encrypted traffic classification plays a vital role in guaranteeing the quality of network services and ensuring the security of the network. Recent studies show that machine learning approaches based on statistical features and raw traffic sessions are effective for this task. However, the performance of the statistical-based approaches largely depends on the quality of the features. Experts need to design different features for different encrypted traffic classification tasks, which is time-consuming. Meanwhile, the raw traffic-based approach needs to uniformize the traffic size; this will cause the loss of information about the overall structure of the network traffic; for example, we do not know the time from the first packet to the last packet in a session. This paper proposes the CENTIME, which can extract comprehensive information based on ResNet and AutoEncoder to identify encrypted traffic. ResNet is used to extract information from uniformized traffic, and AutoEncoder is used to encode statistical features. The statistical features are used to compensate for the information loss caused by traffic uniformization. They only need to be designed once rather than be designed separately for different tasks. Moreover, the pooling layers are removed, and 1D convolution layers are used to help CENTIME make more effective use of raw traffic information. We evaluate the CENTIME on the public dataset “ISCX VPN-nonVPN”, and the results demonstrate the CENTIME outperforms the state-of-the-art encrypted traffic classification methods. More importantly, comprehensive traffic features generated in the CENTIME can represent different classes of traffic well.","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":"127114718","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：