Pub Date : 2017-04-01DOI: 10.1109/ICNISC.2017.00035
Zi-Hui Pei, Qi Shen
Aiming at the problem that linear data reduction algorithm is difficult to deal with data with nonlinear structure, this paper proposes a new algorithm for facial expression feature extraction based on manifold decomposition algorithm. The algorithm utilizes the characteristic of local linearity of nonlinear manifolds. Through classical principal component analysis The local linear patches of nonlinear manifold structures are reduced in dimension. The local PCA representation can be obtained by local dimension reduction, and then the local coordinates are aligned by the coordinate arrangement technique, so that the low dimensional coordinates of the whole manifold can be obtained. The simulation results show that the local linear dimensionality reduction algorithm of nonlinear manifold decomposition is superior to other classical manifold learning algorithms in the recognition accuracy when applied to facial expression feature extraction.
{"title":"Local Linear Dimensionality Reduction Algorithm Based on Nonlinear Manifolds Decomposition","authors":"Zi-Hui Pei, Qi Shen","doi":"10.1109/ICNISC.2017.00035","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00035","url":null,"abstract":"Aiming at the problem that linear data reduction algorithm is difficult to deal with data with nonlinear structure, this paper proposes a new algorithm for facial expression feature extraction based on manifold decomposition algorithm. The algorithm utilizes the characteristic of local linearity of nonlinear manifolds. Through classical principal component analysis The local linear patches of nonlinear manifold structures are reduced in dimension. The local PCA representation can be obtained by local dimension reduction, and then the local coordinates are aligned by the coordinate arrangement technique, so that the low dimensional coordinates of the whole manifold can be obtained. The simulation results show that the local linear dimensionality reduction algorithm of nonlinear manifold decomposition is superior to other classical manifold learning algorithms in the recognition accuracy when applied to facial expression feature extraction.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127056787","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00016
X. Yuan, Fen Hu
Software-defined networking introduces the possibility of building self-tuning networks that constantly monitor network conditions and react rapidly to important events such as congestion. However, it is not an easy task to monitor network status without any overhead. Traditional monitoring mechanisms may introduce huge overheads when monitoring the network continuously. In this paper, we present OFMON - an adaptive flow measurement framework to reduce the overhead and improve the accuracy. It utilizes the Packet-In and Flow-Removed messages as a passive method and uses an adaptive polling algorithm based on fuzzy logic as an active method to obtain traffic metrics. The adaptive techniques are significantly more flexible in their ability of dynamically adjusting the interval of polling depending on the fluctuations of flow, which find a balance between accuracy and overhead. The experiments illustrate that OFMON provides a better method to monitor the link utilization with higher accuracy and lower overhead.
{"title":"OFMON: An Adaptive Flow Monitoring Framework for SDN","authors":"X. Yuan, Fen Hu","doi":"10.1109/ICNISC.2017.00016","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00016","url":null,"abstract":"Software-defined networking introduces the possibility of building self-tuning networks that constantly monitor network conditions and react rapidly to important events such as congestion. However, it is not an easy task to monitor network status without any overhead. Traditional monitoring mechanisms may introduce huge overheads when monitoring the network continuously. In this paper, we present OFMON - an adaptive flow measurement framework to reduce the overhead and improve the accuracy. It utilizes the Packet-In and Flow-Removed messages as a passive method and uses an adaptive polling algorithm based on fuzzy logic as an active method to obtain traffic metrics. The adaptive techniques are significantly more flexible in their ability of dynamically adjusting the interval of polling depending on the fluctuations of flow, which find a balance between accuracy and overhead. The experiments illustrate that OFMON provides a better method to monitor the link utilization with higher accuracy and lower overhead.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125461594","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00068
Tao Yu, Jian-hua Zou, Qin-Bao Song
This paper presents a framework on multi-user and multi-view human eyes' detection and tracking. First, it uses fives kinds of AdaBoost face detectors with four different sizes at each area of image to detect faces in turn. Then, to locate eyes' positions, four kinds of AdaBoost eye detectors are used and if the eye-detection above fails, the prior knowledge of human organs' positions in anatomy is applied as a spare method. Next, it uses the unscented filter to predict the targets' next possible positions. Finally, the detection method above is used to detect the third frame and amend the relative forecasting. And repeat above cycle until tracking over. This framework is robust to subject's eyes' blinking, closing, wearing glasses and partly sheltering in multi-face and multi-view to a certain extent for the optimized structure performance and reasonable selected features. And because of the nonlinear filtering, it can track targets in curves with changing speeds. It mainly fits most usual vertical head scenes in monitoring environment.
{"title":"Multi-User and Multi-View Human Eyes' Detection and Tracking","authors":"Tao Yu, Jian-hua Zou, Qin-Bao Song","doi":"10.1109/ICNISC.2017.00068","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00068","url":null,"abstract":"This paper presents a framework on multi-user and multi-view human eyes' detection and tracking. First, it uses fives kinds of AdaBoost face detectors with four different sizes at each area of image to detect faces in turn. Then, to locate eyes' positions, four kinds of AdaBoost eye detectors are used and if the eye-detection above fails, the prior knowledge of human organs' positions in anatomy is applied as a spare method. Next, it uses the unscented filter to predict the targets' next possible positions. Finally, the detection method above is used to detect the third frame and amend the relative forecasting. And repeat above cycle until tracking over. This framework is robust to subject's eyes' blinking, closing, wearing glasses and partly sheltering in multi-face and multi-view to a certain extent for the optimized structure performance and reasonable selected features. And because of the nonlinear filtering, it can track targets in curves with changing speeds. It mainly fits most usual vertical head scenes in monitoring environment.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126081353","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00062
Mingzhe Su, Yan Ma, Xiangfen Zhang, Shun-bao Li, Yuping Zhang
The traditional SIFT method is capable of extracting distinctive feature for image matching. However, it is extremely time consuming in the SIFT matching due to the use of Euclidean distance measure. Recently, several binary SIFT (BSIFT) methods have been developed to improve the matching efficiency, whereas merely image brightness information is involved in these algorithms. The matching performance will drop because of the lack of the color information of the image. This paper presents a binary SIFT matching method combined with the color and exposure information. First, three components, including luminance, color offset and exposure offset are combined together to express the image pixel. Then, 128-D SIFT descriptor is converted into 256-bit binarized SIFT descriptor. Finally, the improved Hamming distance is proposed in the matching procedure. Experimental results on UKBench dataset show that the proposed method not only ensures the matching speed, but also improves matching accuracy.
{"title":"A Binary SIFT Matching Method Combined with the Color and Exposure Information","authors":"Mingzhe Su, Yan Ma, Xiangfen Zhang, Shun-bao Li, Yuping Zhang","doi":"10.1109/ICNISC.2017.00062","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00062","url":null,"abstract":"The traditional SIFT method is capable of extracting distinctive feature for image matching. However, it is extremely time consuming in the SIFT matching due to the use of Euclidean distance measure. Recently, several binary SIFT (BSIFT) methods have been developed to improve the matching efficiency, whereas merely image brightness information is involved in these algorithms. The matching performance will drop because of the lack of the color information of the image. This paper presents a binary SIFT matching method combined with the color and exposure information. First, three components, including luminance, color offset and exposure offset are combined together to express the image pixel. Then, 128-D SIFT descriptor is converted into 256-bit binarized SIFT descriptor. Finally, the improved Hamming distance is proposed in the matching procedure. Experimental results on UKBench dataset show that the proposed method not only ensures the matching speed, but also improves matching accuracy.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121679341","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00044
Dan Cai, Xiaoyong Ji, Weiqi Jin
Designing the key space based on the initial value xi, system parameter ui and coupling coefficient εi (i=1, 2... m, m is the dimension of hyperchaotic system). By theoretical analysis and practical test, the sensitivity of initial value xi is 10-16, the sensitivity of coupling coefficient εi is 10-15, the sensitivity of system parameter ui is 10-13, so the initial value and coupling coefficient are used as the parameters of designing the key space and the total number of the key space in one-dimensional system is 1031. Each node has different initial values and coupling coefficients in m-dimensional CPRS hyperchaotic system, so the total number of key space in m-dimensional system is 10 31*m. The design consists of an "S_Box" algorithm and two different valuing algorithms. The "S_Box" algorithm adopts BKDRHash function due to the Hash function which has minor conflict and make the value distribution uniform in the "S_Box" and two different valuing algorithms obtain the initial value and coupling coefficient desired in the encryption system. The experimental results show that the three algorithms obtaining the values is well distributed and improve the performance of anti-cracking. The Passwords that users input map into different parameters through the key space by which CPRS hyperchaotic system transmitting terminal encrypts and the receiving terminal can be decrypted successfully using the same parameters.
{"title":"Design of Key Space Based on CPRS Algorithm","authors":"Dan Cai, Xiaoyong Ji, Weiqi Jin","doi":"10.1109/ICNISC.2017.00044","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00044","url":null,"abstract":"Designing the key space based on the initial value xi, system parameter ui and coupling coefficient εi (i=1, 2... m, m is the dimension of hyperchaotic system). By theoretical analysis and practical test, the sensitivity of initial value xi is 10-16, the sensitivity of coupling coefficient εi is 10-15, the sensitivity of system parameter ui is 10-13, so the initial value and coupling coefficient are used as the parameters of designing the key space and the total number of the key space in one-dimensional system is 1031. Each node has different initial values and coupling coefficients in m-dimensional CPRS hyperchaotic system, so the total number of key space in m-dimensional system is 10 31*m. The design consists of an \"S_Box\" algorithm and two different valuing algorithms. The \"S_Box\" algorithm adopts BKDRHash function due to the Hash function which has minor conflict and make the value distribution uniform in the \"S_Box\" and two different valuing algorithms obtain the initial value and coupling coefficient desired in the encryption system. The experimental results show that the three algorithms obtaining the values is well distributed and improve the performance of anti-cracking. The Passwords that users input map into different parameters through the key space by which CPRS hyperchaotic system transmitting terminal encrypts and the receiving terminal can be decrypted successfully using the same parameters.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127696514","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00027
Liquan Xie, Qiao Zhou, Jianyang Huang
Virtual network function supports the scalable control to the software-based network functions while leading to the challenge of flexible service chains migration for the load balance, processing performance or QoS. In this paper, we formulated the service chains migration (SCM) problem as an integer linear program that maximizes the utility of the network and subjects to the resource and performance constraints. We approximated the objective function of SCM with the Log-Sum-Exp function, and proposed a Markov chain-based distributed migration algorithm. Simulation results prove that the proposed algorithm can realize effective and cost-efficient service chain migration.
{"title":"Dynamic Service Chain Migration for Network Functions Virtualization","authors":"Liquan Xie, Qiao Zhou, Jianyang Huang","doi":"10.1109/ICNISC.2017.00027","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00027","url":null,"abstract":"Virtual network function supports the scalable control to the software-based network functions while leading to the challenge of flexible service chains migration for the load balance, processing performance or QoS. In this paper, we formulated the service chains migration (SCM) problem as an integer linear program that maximizes the utility of the network and subjects to the resource and performance constraints. We approximated the objective function of SCM with the Log-Sum-Exp function, and proposed a Markov chain-based distributed migration algorithm. Simulation results prove that the proposed algorithm can realize effective and cost-efficient service chain migration.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127744220","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00034
Xue-xiong Yan, Hengtai Ma
as for detecting taint-style vulnerabilities in PHP codes, this paper introduces function calling control vulnerability, which is a new kind of taint-style vulnerabilities in PHP codes without sensitive function, and enriches classical update rules for taint analysis with a new transfer function definition, which is used to deal with statements with a single function call. The new static vulnerabilities analysis algorithm is implemented in a tool named POSE, and the experiment results of the POSE show that the new algorithm is valid for detecting more type of taint-style vulnerabilities in PHP codes.
{"title":"A New Static Vulnerabilities Analysis Algorithm for PHP Codes","authors":"Xue-xiong Yan, Hengtai Ma","doi":"10.1109/ICNISC.2017.00034","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00034","url":null,"abstract":"as for detecting taint-style vulnerabilities in PHP codes, this paper introduces function calling control vulnerability, which is a new kind of taint-style vulnerabilities in PHP codes without sensitive function, and enriches classical update rules for taint analysis with a new transfer function definition, which is used to deal with statements with a single function call. The new static vulnerabilities analysis algorithm is implemented in a tool named POSE, and the experiment results of the POSE show that the new algorithm is valid for detecting more type of taint-style vulnerabilities in PHP codes.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133511232","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00049
Huafang Geng, Jianmei Dai
Software is the core of Software-Intensive Systems which belong to information equipment. This paper analyses the elements of software support that depend on three-dimensional structure through setting up the static model. The test of software which acquires careful planning must run through the process of Software-Intensive Systems maintenance.
{"title":"Software Support and Test of Software-Intensive Systems","authors":"Huafang Geng, Jianmei Dai","doi":"10.1109/ICNISC.2017.00049","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00049","url":null,"abstract":"Software is the core of Software-Intensive Systems which belong to information equipment. This paper analyses the elements of software support that depend on three-dimensional structure through setting up the static model. The test of software which acquires careful planning must run through the process of Software-Intensive Systems maintenance.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131825400","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00063
Hanmin Ye, Shi Yan, Xue Bai
Aiming at the problem that traditional 2D Otsu algorithm is poor in image segmentation with serious noise pollution, a new image segmentation method based on the combination of median filter and 2-D Otsu is proposed. By using the switching median filter to the noise image anti-noise, and then use the two-dimensional Otsu to image segmentation to improve the segmentation effect. The experimental results show that the new method has a good segmentation effect on the gray image with high noise, and the advantage of this algorithm is more obvious when the noise is stronger.
{"title":"Application of Switching Median Filter in Two-Dimensional Otsu Image Segmentation","authors":"Hanmin Ye, Shi Yan, Xue Bai","doi":"10.1109/ICNISC.2017.00063","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00063","url":null,"abstract":"Aiming at the problem that traditional 2D Otsu algorithm is poor in image segmentation with serious noise pollution, a new image segmentation method based on the combination of median filter and 2-D Otsu is proposed. By using the switching median filter to the noise image anti-noise, and then use the two-dimensional Otsu to image segmentation to improve the segmentation effect. The experimental results show that the new method has a good segmentation effect on the gray image with high noise, and the advantage of this algorithm is more obvious when the noise is stronger.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129977523","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00030
Zuoxue Liu, Rui Jin
To solve some shortcomings existing in several typical master-slave synchronization protocols, this paper presented a new synchronization method for Ad hoc networks using the life cycle of network nodes. We used the life cycle of Ad hoc node as the criterion of the synchronization, used the slot alignment for coarse synchronization, and exchanged the synchronization information between nodes for fine synchronization. In order to reduce the number of synchronization and maintain the clock drift between the nodes will not be too much error, we proposed the monitoring algorithm in synchronization process. The simulation results show that the improved synchronization process which have monitoring algorithm can reduce the number of synchronizations when the clock drift error does not reach the threshold value, and the synchronization error between the master node and the 6 hops node is only 0.37ms.
{"title":"A New Time Synchronization Method of Ad Hoc Networks Based on Life Cycle","authors":"Zuoxue Liu, Rui Jin","doi":"10.1109/ICNISC.2017.00030","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00030","url":null,"abstract":"To solve some shortcomings existing in several typical master-slave synchronization protocols, this paper presented a new synchronization method for Ad hoc networks using the life cycle of network nodes. We used the life cycle of Ad hoc node as the criterion of the synchronization, used the slot alignment for coarse synchronization, and exchanged the synchronization information between nodes for fine synchronization. In order to reduce the number of synchronization and maintain the clock drift between the nodes will not be too much error, we proposed the monitoring algorithm in synchronization process. The simulation results show that the improved synchronization process which have monitoring algorithm can reduce the number of synchronizations when the clock drift error does not reach the threshold value, and the synchronization error between the master node and the 6 hops node is only 0.37ms.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131522232","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：