Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603396
Yuexiang Shi, Xiaoxue Ren, Saizhou Yang, Ping Gong
In this paper, an improved Kernel Fisher Discriminant (KFD) method is used in face recognition. A Generalized Kernel Fisher Discriminant Analysis (GKFD) is proposed to make the most of two kinds of discriminant information in “double discriminant subspaces”. It can also uniform the discriminant functions in two subspaces of DSDA. Experimental results on ORL face database show the feasibility of the suggested method.
{"title":"A generalized Kernel Fisher Discriminant framework used for feature extraction and face recognition","authors":"Yuexiang Shi, Xiaoxue Ren, Saizhou Yang, Ping Gong","doi":"10.1109/FSKD.2016.7603396","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603396","url":null,"abstract":"In this paper, an improved Kernel Fisher Discriminant (KFD) method is used in face recognition. A Generalized Kernel Fisher Discriminant Analysis (GKFD) is proposed to make the most of two kinds of discriminant information in “double discriminant subspaces”. It can also uniform the discriminant functions in two subspaces of DSDA. Experimental results on ORL face database show the feasibility of the suggested method.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128511159","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603398
J. Gao, Xiuhong Chen
Fisher discrimination dictionary sparse learning (FDDL) has led to interesting image recognition results where the Fisher discrimination criterion is subject to the coding coefficients. But Fisher discrimination criterion has the limitations of data distribution assumptions and does not consider the local manifold structure of the coding coefficients. In this paper, we will introduce a novel Fisher discrimination sparse learning based on graph embedding (GE-FDSL) scheme. First, we utilizes graph embedding framework to define intra-class compact matrix and inter-class separable matrix imposed on the coding coefficients of training samples to preserving the intra-class compactness and the inter-class separability for the training samples, which simultaneously consider the local manifold structure and label information of the coding coefficients. Then, a new Fisher discrimination criterion based on graph embedding is added to the object function of the sparse coding problem so that the coding coefficients have more discriminative power, where the dictionary atoms in the sparse coding model are associated with the class labels so that the reconstructed error is applied to classification. This method can learn a structured dictionary and sparse coefficients, and in the meantime, it will also keep the local manifold structure of the coding coefficients. So, they will be more discriminative. Experiments on many image databases show that the our algorithm has good classification and recognition performance.
{"title":"Fisher discrimination sparse learning based on graph embedding for image classification","authors":"J. Gao, Xiuhong Chen","doi":"10.1109/FSKD.2016.7603398","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603398","url":null,"abstract":"Fisher discrimination dictionary sparse learning (FDDL) has led to interesting image recognition results where the Fisher discrimination criterion is subject to the coding coefficients. But Fisher discrimination criterion has the limitations of data distribution assumptions and does not consider the local manifold structure of the coding coefficients. In this paper, we will introduce a novel Fisher discrimination sparse learning based on graph embedding (GE-FDSL) scheme. First, we utilizes graph embedding framework to define intra-class compact matrix and inter-class separable matrix imposed on the coding coefficients of training samples to preserving the intra-class compactness and the inter-class separability for the training samples, which simultaneously consider the local manifold structure and label information of the coding coefficients. Then, a new Fisher discrimination criterion based on graph embedding is added to the object function of the sparse coding problem so that the coding coefficients have more discriminative power, where the dictionary atoms in the sparse coding model are associated with the class labels so that the reconstructed error is applied to classification. This method can learn a structured dictionary and sparse coefficients, and in the meantime, it will also keep the local manifold structure of the coding coefficients. So, they will be more discriminative. Experiments on many image databases show that the our algorithm has good classification and recognition performance.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233145","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603373
Rafael Rodrigues Pereira, V. A. D. Silva, J. N. Brito, Joao Daniel Nolasco
The monitoring of induction motors through predictive techniques and artificial intelligence has grown considerably in recent years. These techniques allow the detection of a defect in its early stages, consequently allow maintenance personnel to schedule the intervention, working within the concept of planned corrective maintenance, avoiding catastrophic failures on the production line. Among these techniques, there is the Fuzzy Logic. The motor operational conditions are described by using fuzzy linguistic variables in an effective monitoring program that acquire, analyze and present the results. The knowledge base, comprising fuzzy rules and databases, was built to support the fuzzy inference process to analyze the data processing. The experimental results shown the efficiency of the vibration sensor developed and the strategies for detection diagnosis, and on-line monitoring tasks. The results were undoubtedly impressive and in a near future the system developed can be adapted and used in real predictive maintenance programs in industries.
{"title":"On-line monitoring induction motors by fuzzy logic: A study for predictive maintenance operators","authors":"Rafael Rodrigues Pereira, V. A. D. Silva, J. N. Brito, Joao Daniel Nolasco","doi":"10.1109/FSKD.2016.7603373","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603373","url":null,"abstract":"The monitoring of induction motors through predictive techniques and artificial intelligence has grown considerably in recent years. These techniques allow the detection of a defect in its early stages, consequently allow maintenance personnel to schedule the intervention, working within the concept of planned corrective maintenance, avoiding catastrophic failures on the production line. Among these techniques, there is the Fuzzy Logic. The motor operational conditions are described by using fuzzy linguistic variables in an effective monitoring program that acquire, analyze and present the results. The knowledge base, comprising fuzzy rules and databases, was built to support the fuzzy inference process to analyze the data processing. The experimental results shown the efficiency of the vibration sensor developed and the strategies for detection diagnosis, and on-line monitoring tasks. The results were undoubtedly impressive and in a near future the system developed can be adapted and used in real predictive maintenance programs in industries.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122347427","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603416
Xianghua Tan, Tao Tang
In this paper, we propose a robust edge indicator employing two eigenvalues of nonlocal structure tensor matrix. In our method, a new nonlocal structure tensor is first constructed. This structure tensor is robust to noise, which inherits from nonlocal means algorithm. Furthermore, based on the constructed nonlocal structure tensor, a new and edge indicator is built, which can effectively differentiate a pixel at edge from a pixel in flat region with noise. Moreover, the proposed edge indicator can characteristic the strength of the edges. By experiments, the results of our method is superior to the gradient's results.
{"title":"A robust edge indicator employing nonlocal structure tensor","authors":"Xianghua Tan, Tao Tang","doi":"10.1109/FSKD.2016.7603416","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603416","url":null,"abstract":"In this paper, we propose a robust edge indicator employing two eigenvalues of nonlocal structure tensor matrix. In our method, a new nonlocal structure tensor is first constructed. This structure tensor is robust to noise, which inherits from nonlocal means algorithm. Furthermore, based on the constructed nonlocal structure tensor, a new and edge indicator is built, which can effectively differentiate a pixel at edge from a pixel in flat region with noise. Moreover, the proposed edge indicator can characteristic the strength of the edges. By experiments, the results of our method is superior to the gradient's results.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131088935","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603413
Guanzhong Yang, Rong Zhou
The traditional object model only focuses on single application system, cannot represent the relationship between objects of multiple sample systems in a domain correctly. Moreover, as the current domain feature modeling is doped with too many subjective factors of domain experts, there may be some error or missing feature constraint relationship. Combining with the macroscopic characteristics of domain object model, this paper improved the traditional object model, introduced new object relationship: use relationship, influence relationship, modification relationship, mutex relationship, represented feature by using object set. and complemented the definition of feature associated attribution. Some mapping rules are proposed for identifying the feature constraint relationship objectively and accurately, based on which the integrity and consistency of traditional feature dependency view is verified and the quality of feature model is improved.
{"title":"A feature dependency graph analysis method based on object","authors":"Guanzhong Yang, Rong Zhou","doi":"10.1109/FSKD.2016.7603413","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603413","url":null,"abstract":"The traditional object model only focuses on single application system, cannot represent the relationship between objects of multiple sample systems in a domain correctly. Moreover, as the current domain feature modeling is doped with too many subjective factors of domain experts, there may be some error or missing feature constraint relationship. Combining with the macroscopic characteristics of domain object model, this paper improved the traditional object model, introduced new object relationship: use relationship, influence relationship, modification relationship, mutex relationship, represented feature by using object set. and complemented the definition of feature associated attribution. Some mapping rules are proposed for identifying the feature constraint relationship objectively and accurately, based on which the integrity and consistency of traditional feature dependency view is verified and the quality of feature model is improved.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126948042","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603527
Hui Yu, Yuchao Tang, Chunxiang Zong
Solving sudoku is a very challenging problem. It is not only a logic problem, but also can be seen as a mathematic problem. In this paper, we develop a binary integer linear programming (BILP) model for solving Odd/Even sudoku puzzles. Consequently, we solve the BILP model by using the optimization toolbox of MATLAB software. The performance of the proposed model was tested under different difficulty levels of Odd/Even sudoku puzzles. Numerical results show that it can successfully solve the Odd/Even sudoku puzzles in a quick time.
{"title":"Solving odd even sudoku puzzles by binary integer linear programming","authors":"Hui Yu, Yuchao Tang, Chunxiang Zong","doi":"10.1109/FSKD.2016.7603527","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603527","url":null,"abstract":"Solving sudoku is a very challenging problem. It is not only a logic problem, but also can be seen as a mathematic problem. In this paper, we develop a binary integer linear programming (BILP) model for solving Odd/Even sudoku puzzles. Consequently, we solve the BILP model by using the optimization toolbox of MATLAB software. The performance of the proposed model was tested under different difficulty levels of Odd/Even sudoku puzzles. Numerical results show that it can successfully solve the Odd/Even sudoku puzzles in a quick time.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130587022","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603458
Huan Zhao, Shaofang He
In order to further improve the robustness and discrimination of perceptual hashing and retrieval speed in large-scale data, a novel retrieval algorithm over encrypted speech is proposed. Before encrypted speech is uploaded, perceptual hashing sequences must be embedded as a digital watermark. In the process of generating perceptual hashing, multifractal characteristic of speech that has good distinctiveness and robustness is introduced, and the technology of piecewise aggregate approximation is used for compressing data size. The retrieval process does not need decryption but requires the generation of perceptual hashing sequence of query speech segment. Each perceptual hashing set in system hash table should then be matched successively. Experimental results indicate that the perceptual hashing generated from multifractal characteristics shows better distinctiveness and robustness than those derived from time and frequency domain features in existing methods. Furthermore, because of employing the technology of piecewise aggregate approximation, the generated perceptual hashing has small amounts of data, which leads to the greatly improvement of retrieval speed. And finally, the proposed retrieval algorithm achieves high recall and precision ratios in terms of the variety of content holding operation.
{"title":"A retrieval algorithm for encrypted speech based on perceptual hashing","authors":"Huan Zhao, Shaofang He","doi":"10.1109/FSKD.2016.7603458","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603458","url":null,"abstract":"In order to further improve the robustness and discrimination of perceptual hashing and retrieval speed in large-scale data, a novel retrieval algorithm over encrypted speech is proposed. Before encrypted speech is uploaded, perceptual hashing sequences must be embedded as a digital watermark. In the process of generating perceptual hashing, multifractal characteristic of speech that has good distinctiveness and robustness is introduced, and the technology of piecewise aggregate approximation is used for compressing data size. The retrieval process does not need decryption but requires the generation of perceptual hashing sequence of query speech segment. Each perceptual hashing set in system hash table should then be matched successively. Experimental results indicate that the perceptual hashing generated from multifractal characteristics shows better distinctiveness and robustness than those derived from time and frequency domain features in existing methods. Furthermore, because of employing the technology of piecewise aggregate approximation, the generated perceptual hashing has small amounts of data, which leads to the greatly improvement of retrieval speed. And finally, the proposed retrieval algorithm achieves high recall and precision ratios in terms of the variety of content holding operation.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132853165","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603381
Hongpu Hu, T. Dai, Xing Gao, Quan Chen, Xingyun Lei
Based on information systems and government's emphasis on efficient medical service and health management, Canadian health decision support system stands in a leading position. This paper firstly researches the Canadian health decision overall development situation, clinical decision support system, public decision support system, application features etc. through the literature research method. And then summarize the experiences and characters of Canadian decision support system construction and application situation. Finally by the analysis of development of the HDSS in Canada, some enlightens may be obtained to improve HDSS of China: (1) The establishment of Infoway is an important factor in the development of the Canadian health decision support system; (2) The Canadian government's support is the main power in the development of the Canadian health decision support system; (3) Improving the management system is an important undertaking for the Canadian health decision support system; (4) Strong financial security is the key to the development of the Canadian health decision support system; (5) Overall planning and standardization are the foundations of Canada's health decision support system development.
{"title":"Development of the health decision support system (HDSS) in Canada and its implications in China","authors":"Hongpu Hu, T. Dai, Xing Gao, Quan Chen, Xingyun Lei","doi":"10.1109/FSKD.2016.7603381","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603381","url":null,"abstract":"Based on information systems and government's emphasis on efficient medical service and health management, Canadian health decision support system stands in a leading position. This paper firstly researches the Canadian health decision overall development situation, clinical decision support system, public decision support system, application features etc. through the literature research method. And then summarize the experiences and characters of Canadian decision support system construction and application situation. Finally by the analysis of development of the HDSS in Canada, some enlightens may be obtained to improve HDSS of China: (1) The establishment of Infoway is an important factor in the development of the Canadian health decision support system; (2) The Canadian government's support is the main power in the development of the Canadian health decision support system; (3) Improving the management system is an important undertaking for the Canadian health decision support system; (4) Strong financial security is the key to the development of the Canadian health decision support system; (5) Overall planning and standardization are the foundations of Canada's health decision support system development.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130278306","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603197
Yan Li, Peng Han, Jinkuan Wang, Xin Song
With the increasingly serious energy scarcity and environment pollution, the wide application of the renewable energy and the popularization of the electric vehicle are considered as two effective ways to improve the energy and environment situation. However, the negative effect on the system stability could not be ignored for their intermittent, fluctuant and random characteristics. Aiming to study the operation of micro-grid with access of the renewable energy and EVs, the synthetically modeling method that includes agent-based modeling and system dynamics modeling is applied to built the micro-grid-EV joint system model. Considering the time difference of renewable energy generation, EV charging and the residential load demands, the cascade charging strategy is proposed for scheduling the EV charging behavior to maintain the stable operation of the micro-grid-EV joint system and extremely improve the utilization of the renewable energy. Finally, the comparative simulations are carried out in the same conditions with the other two strategies include charging after travel and charging at night, and the optimal performance of the proposed cascade charging strategy is verified by index evaluation of the renewable energy utilization rate, the energy supplement ability and the peak-to-average ratio.
{"title":"Modeling and optimization oriented to the micro-grid-EV joint system","authors":"Yan Li, Peng Han, Jinkuan Wang, Xin Song","doi":"10.1109/FSKD.2016.7603197","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603197","url":null,"abstract":"With the increasingly serious energy scarcity and environment pollution, the wide application of the renewable energy and the popularization of the electric vehicle are considered as two effective ways to improve the energy and environment situation. However, the negative effect on the system stability could not be ignored for their intermittent, fluctuant and random characteristics. Aiming to study the operation of micro-grid with access of the renewable energy and EVs, the synthetically modeling method that includes agent-based modeling and system dynamics modeling is applied to built the micro-grid-EV joint system model. Considering the time difference of renewable energy generation, EV charging and the residential load demands, the cascade charging strategy is proposed for scheduling the EV charging behavior to maintain the stable operation of the micro-grid-EV joint system and extremely improve the utilization of the renewable energy. Finally, the comparative simulations are carried out in the same conditions with the other two strategies include charging after travel and charging at night, and the optimal performance of the proposed cascade charging strategy is verified by index evaluation of the renewable energy utilization rate, the energy supplement ability and the peak-to-average ratio.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126436524","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}
In order to enhance the ability of software defined network (SDN) proactive security protection, this paper puts forward a path hopping based SDN network defense (PH-SND) technology. PH-SND technology models the path hopping problem as a constraint solving problem, and utilizes satisfiability modulo theory solver to obtain multiple paths, which satisfy overlap and capacity constraints. According to the path hopping strategy and specific hopping slot, SDN controller installs corresponding flow entries into all OpenFlow switches along every path, and these switches can then use these flow entries to properly forward the corresponding protected flow, and randomly change the address and port information of this flow, which can not only realize random path hopping, and can also effectively hide original address and port information of both communication sides. Theoretical analysis and experimental results show that this proposed PH-SND technology can not only achieve transmission path hopping and address and port random hopping along every transmission path with a comparatively small communication delay and can also improve proactive security protection capability to resist network interception and analysis attack.
{"title":"Path hopping based SDN network defense technology","authors":"Liancheng Zhang, Qiang Wei, Kejun Gu, Huiqiang Yuwen","doi":"10.1109/FSKD.2016.7603498","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603498","url":null,"abstract":"In order to enhance the ability of software defined network (SDN) proactive security protection, this paper puts forward a path hopping based SDN network defense (PH-SND) technology. PH-SND technology models the path hopping problem as a constraint solving problem, and utilizes satisfiability modulo theory solver to obtain multiple paths, which satisfy overlap and capacity constraints. According to the path hopping strategy and specific hopping slot, SDN controller installs corresponding flow entries into all OpenFlow switches along every path, and these switches can then use these flow entries to properly forward the corresponding protected flow, and randomly change the address and port information of this flow, which can not only realize random path hopping, and can also effectively hide original address and port information of both communication sides. Theoretical analysis and experimental results show that this proposed PH-SND technology can not only achieve transmission path hopping and address and port random hopping along every transmission path with a comparatively small communication delay and can also improve proactive security protection capability to resist network interception and analysis attack.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123075070","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：