Pub Date : 2018-11-01DOI: 10.1109/CIS2018.2018.00059
Weiguo Shen, Wei Wang
Aiming at the problem of node identification in wireless networks, a method of node identification based on deep learning is proposed, which starts with the tiny features of nodes in radiofrequency layer. Firstly, in order to cut down the computational complexity, Principal Component Analysis is used to reduce the dimension of node sample data. Secondly, a convolution neural network containing two hidden layers is designed to extract local features of the preprocessed data. Stochastic gradient descent method is used to optimize the parameters, and the Softmax Model is used to determine the output label. Finally, the effectiveness of the method is verified by experiments on practical wireless ad-hoc network.
{"title":"Node Identification in Wireless Network Based on Convolutional Neural Network","authors":"Weiguo Shen, Wei Wang","doi":"10.1109/CIS2018.2018.00059","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00059","url":null,"abstract":"Aiming at the problem of node identification in wireless networks, a method of node identification based on deep learning is proposed, which starts with the tiny features of nodes in radiofrequency layer. Firstly, in order to cut down the computational complexity, Principal Component Analysis is used to reduce the dimension of node sample data. Secondly, a convolution neural network containing two hidden layers is designed to extract local features of the preprocessed data. Stochastic gradient descent method is used to optimize the parameters, and the Softmax Model is used to determine the output label. Finally, the effectiveness of the method is verified by experiments on practical wireless ad-hoc network.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346204","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00078
Kangshun Li, Xiaoling Huang, Yueyi Li, Ying Feng
With the improvement of living standards, people pay more attention to the quality of life and have a higher pursuit of household goods. Lighting, which is a kind of indispensable furniture, has attracted more and more attention. The rapid development of the Internet and the popularity of smart phones provide technical support for the construction of two-dimensional code traceability system. Tracing the source of the light is helpful to strengthen the safety and quality of lamps and lanterns. This paper introduces the design and main functions of the two-dimensional code lighting traceability shopping guide system.
{"title":"Design and Implementation of Tracing Shopping Guide System Based on Two Dimensional Code Lighting","authors":"Kangshun Li, Xiaoling Huang, Yueyi Li, Ying Feng","doi":"10.1109/CIS2018.2018.00078","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00078","url":null,"abstract":"With the improvement of living standards, people pay more attention to the quality of life and have a higher pursuit of household goods. Lighting, which is a kind of indispensable furniture, has attracted more and more attention. The rapid development of the Internet and the popularity of smart phones provide technical support for the construction of two-dimensional code traceability system. Tracing the source of the light is helpful to strengthen the safety and quality of lamps and lanterns. This paper introduces the design and main functions of the two-dimensional code lighting traceability shopping guide system.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128977501","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00032
Si Chen, Dehui Qiu, Qirun Huo
In recent years, Discriminant Correlation Filters (DCF) based methods have performed well on online object tracking. And Fully-convolutional Siamese network becomes a dominant approach to real-time object tracking. In this work, we build a two-fold Siamese network, namely SiamDCF, to learn the convolutional features and perform the correlation tracking process with channel attention simultaneously. We train these two branches of SiamDCF separately, ensuring their heterogeneous features. We treat DCF as a correlation filter layer, and the layer outputs the response map of object location. This branch learns filters which extract semantic features and perform well in situations, such as deformation and motion blur, as a complement to the original SiamFC. In particular, we introduce the channel attention module to the network. The architecture and channel attention mechanism improve the tracking performance. The network is trained on the ILSVRC15 dataset for object detection in video. The proposed architecture is end-to-end and operates at frame-rates beyond real-time. We perform comprehensive experiments on OTB2013 benchmark, and the proposed tracker achieves high performance.
{"title":"Siamese Networks with Discriminant Correlation Filters and Channel Attention","authors":"Si Chen, Dehui Qiu, Qirun Huo","doi":"10.1109/CIS2018.2018.00032","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00032","url":null,"abstract":"In recent years, Discriminant Correlation Filters (DCF) based methods have performed well on online object tracking. And Fully-convolutional Siamese network becomes a dominant approach to real-time object tracking. In this work, we build a two-fold Siamese network, namely SiamDCF, to learn the convolutional features and perform the correlation tracking process with channel attention simultaneously. We train these two branches of SiamDCF separately, ensuring their heterogeneous features. We treat DCF as a correlation filter layer, and the layer outputs the response map of object location. This branch learns filters which extract semantic features and perform well in situations, such as deformation and motion blur, as a complement to the original SiamFC. In particular, we introduce the channel attention module to the network. The architecture and channel attention mechanism improve the tracking performance. The network is trained on the ILSVRC15 dataset for object detection in video. The proposed architecture is end-to-end and operates at frame-rates beyond real-time. We perform comprehensive experiments on OTB2013 benchmark, and the proposed tracker achieves high performance.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129101428","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00019
Aihong Ren, Xingsi Xue
In this paper, we develop a novel solving method by combing the magnitude of fuzzy number with a simple ranking approach to handle bilevel linear programming involving triangular fuzzy coefficients. A simple ranking approach of two triangular fuzzy numbers is used to tackle the fuzzy inequality constraints in the upper and lower level programming problems, and the definition of the magnitude of triangular fuzzy number is applied to deal with the fuzzy objective functions at the upper and lower levels. Then the original problem is changed into a deterministic bilevel model. Finally, the proposed solution method is explained with the help of a numerical example.
{"title":"A New Solving Method for Fuzzy Bilevel Optimization with Triangular Fuzzy Coefficients","authors":"Aihong Ren, Xingsi Xue","doi":"10.1109/CIS2018.2018.00019","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00019","url":null,"abstract":"In this paper, we develop a novel solving method by combing the magnitude of fuzzy number with a simple ranking approach to handle bilevel linear programming involving triangular fuzzy coefficients. A simple ranking approach of two triangular fuzzy numbers is used to tackle the fuzzy inequality constraints in the upper and lower level programming problems, and the definition of the magnitude of triangular fuzzy number is applied to deal with the fuzzy objective functions at the upper and lower levels. Then the original problem is changed into a deterministic bilevel model. Finally, the proposed solution method is explained with the help of a numerical example.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132026818","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00016
Fanghan Liu, Xiaobing Tang, Zhaohui Yang
The transportation network of the city is dynamic and stochastic, The problem of dynamic stochastic shortest path is NP-hard. the optimal problem of path is widely used in the fields of transportation, communication and computer network. An improved self adaptive genetic algorithm is proposed by encoding the chromosomal mode.The paper investigates the shortest path problem based on the genetic algorithm principle, and improved genetic algorithm by adjusting the encoding parameters. Mny experiments indicate that the improved genetic algorithm could adapt to new transportation rapidly in global optimization than A* algorithm and Dijkstra algorithm and obtain the better solutions in the shortest path problem in the fields of transportation and computer network.
{"title":"An Encoding Algorithm Based on the Shortest Path Problem","authors":"Fanghan Liu, Xiaobing Tang, Zhaohui Yang","doi":"10.1109/CIS2018.2018.00016","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00016","url":null,"abstract":"The transportation network of the city is dynamic and stochastic, The problem of dynamic stochastic shortest path is NP-hard. the optimal problem of path is widely used in the fields of transportation, communication and computer network. An improved self adaptive genetic algorithm is proposed by encoding the chromosomal mode.The paper investigates the shortest path problem based on the genetic algorithm principle, and improved genetic algorithm by adjusting the encoding parameters. Mny experiments indicate that the improved genetic algorithm could adapt to new transportation rapidly in global optimization than A* algorithm and Dijkstra algorithm and obtain the better solutions in the shortest path problem in the fields of transportation and computer network.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130442322","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00030
Xiaoqiao Zhang, Xiuling Zhou, Ping Guo
Denoising is a necessary and fundamental step in the hyperspectral image (HSI) analysis process. Since the spectral channels of HSI are highly correlated, they are characterized by a low rank structure and can be well approximated by low rank representation. Therefore, based on low rank structure and the EPLL, a 4-step algorithm is proposed to denoise the hyperspectral images with Gaussian noise. PCA is used to explore the high correlation and capture the low rank structure in spectral domain of HSI. The EPLL is used to further denoise the HSI in spatial domain. Compared with four state-of-the-art denoising algorithms, the proposed algorithm performs well in HSI denoising, especially for moderate and high noise levels.
{"title":"Hyperspectral Image Denoising Based on Low Rank and Expected Patch Log Likelihood","authors":"Xiaoqiao Zhang, Xiuling Zhou, Ping Guo","doi":"10.1109/CIS2018.2018.00030","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00030","url":null,"abstract":"Denoising is a necessary and fundamental step in the hyperspectral image (HSI) analysis process. Since the spectral channels of HSI are highly correlated, they are characterized by a low rank structure and can be well approximated by low rank representation. Therefore, based on low rank structure and the EPLL, a 4-step algorithm is proposed to denoise the hyperspectral images with Gaussian noise. PCA is used to explore the high correlation and capture the low rank structure in spectral domain of HSI. The EPLL is used to further denoise the HSI in spatial domain. Compared with four state-of-the-art denoising algorithms, the proposed algorithm performs well in HSI denoising, especially for moderate and high noise levels.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125264688","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00026
Ying Zheng, H. Bao, Xinkai Xu, Nan Ma, Jialei Zhao, Dawei Luo
Target detection has a wide range of applications in many areas of life, and it is also a research hotspot in the field of unmanned driving. Urban roads are complex and changeable, especially at intersections, which have always been a difficult and key part in the research of pilotless technology. Traffic policemen detection at intersections is a key link, but there are few existing algorithms, and the detection speed is generally slow. Aiming at this problem, this paper proposes a real-time detection method of traffic police based on YOLOv3 network.The YOLO network is robust and capable of quickly completing target detection tasks. According to the information investigated, there are currently few data sets on traffic police detection. In response to this problem, this paper adopts the transfer learning method, adopts the imageNet set to training model, learns the basic characteristics of people, and then selects 1000 pictures containing traffic police to conduct experiments. The average accuracy of traffic police detection is 77%, and the detection speed reaches 50FPS, which basically meets the requirements of real-time performance, indicating that the method is reasonable and feasible.
{"title":"A Method of Detect Traffic Police in Complex Scenes","authors":"Ying Zheng, H. Bao, Xinkai Xu, Nan Ma, Jialei Zhao, Dawei Luo","doi":"10.1109/CIS2018.2018.00026","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00026","url":null,"abstract":"Target detection has a wide range of applications in many areas of life, and it is also a research hotspot in the field of unmanned driving. Urban roads are complex and changeable, especially at intersections, which have always been a difficult and key part in the research of pilotless technology. Traffic policemen detection at intersections is a key link, but there are few existing algorithms, and the detection speed is generally slow. Aiming at this problem, this paper proposes a real-time detection method of traffic police based on YOLOv3 network.The YOLO network is robust and capable of quickly completing target detection tasks. According to the information investigated, there are currently few data sets on traffic police detection. In response to this problem, this paper adopts the transfer learning method, adopts the imageNet set to training model, learns the basic characteristics of people, and then selects 1000 pictures containing traffic police to conduct experiments. The average accuracy of traffic police detection is 77%, and the detection speed reaches 50FPS, which basically meets the requirements of real-time performance, indicating that the method is reasonable and feasible.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122468213","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 : 2018-11-01DOI: 10.1109/cis2018.2018.00084
Qiang Wang, Tingting Lan
In the field of wireless communications, it is of great significance to structure LDPC codes (Low-density Parity-check codes) with large girth. We propose a method to construct high girth LDPC codes based on algebra permutation group of intelligent. Girth larger parity check matrix can be found in Gallager parity check matrix set using genetic algorithm based on permutation group in a relatively short period of time. Simulation results show that the algorithm is efficient, versatile, and consistent with the theoretical analysis.
{"title":"Smart Construct High Girth LDPC Codes Based on Permutation Groups","authors":"Qiang Wang, Tingting Lan","doi":"10.1109/cis2018.2018.00084","DOIUrl":"https://doi.org/10.1109/cis2018.2018.00084","url":null,"abstract":"In the field of wireless communications, it is of great significance to structure LDPC codes (Low-density Parity-check codes) with large girth. We propose a method to construct high girth LDPC codes based on algebra permutation group of intelligent. Girth larger parity check matrix can be found in Gallager parity check matrix set using genetic algorithm based on permutation group in a relatively short period of time. Simulation results show that the algorithm is efficient, versatile, and consistent with the theoretical analysis.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127018756","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00111
Ge Wen, Hai Liu, Jun Yan, Zhenqiang Wu
With the widespread popularity of social network platforms, privacy leakage has become a focus when users share personal information. As a result, there are so many different privacy preserving methods. However, one of the methods is to add noise to get a published graph, which cannot achieve the privacy preserving of social network completely. In this paper, we proposed a Bayesian privacy analysis model to identify nodes in a published graph. Firstly, we built a general privacy analysis model to explain the main idea of privacy analysis. Secondly, under this model, a privacy analysis method based on Bayes Rule is designed. Finally, experimental evaluation results showed that our method could identify one node of published graphs with some probability. Therefore, our model also provides guidance for designing better privacy preserving methods of social network.
{"title":"A Privacy Analysis Method to Anonymous Graph Based on Bayes Rule in Social Networks","authors":"Ge Wen, Hai Liu, Jun Yan, Zhenqiang Wu","doi":"10.1109/CIS2018.2018.00111","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00111","url":null,"abstract":"With the widespread popularity of social network platforms, privacy leakage has become a focus when users share personal information. As a result, there are so many different privacy preserving methods. However, one of the methods is to add noise to get a published graph, which cannot achieve the privacy preserving of social network completely. In this paper, we proposed a Bayesian privacy analysis model to identify nodes in a published graph. Firstly, we built a general privacy analysis model to explain the main idea of privacy analysis. Secondly, under this model, a privacy analysis method based on Bayes Rule is designed. Finally, experimental evaluation results showed that our method could identify one node of published graphs with some probability. Therefore, our model also provides guidance for designing better privacy preserving methods of social network.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132652552","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00072
Hao Jin, Yanru Yao, Liping Yang
Based on the CUSUM test, this paper considers testing a heavy index break of heavy-tailed observations with infinite variance. Given for the appropriate conditions, the asymptotic distribution of the test statistic is obtained under the null hypothesis and its consistency is proved under the alternative hypothesis. The critical value can be obtained by Monte Carlo simulation and its respond curve is obtained by fitting. Finally, a Monte Carlo study shows that our test has reasonably good size and power properties in finite samples.
{"title":"A CUSUM Tests for Stable Index Changes under Heavy-Tailed Sequences","authors":"Hao Jin, Yanru Yao, Liping Yang","doi":"10.1109/CIS2018.2018.00072","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00072","url":null,"abstract":"Based on the CUSUM test, this paper considers testing a heavy index break of heavy-tailed observations with infinite variance. Given for the appropriate conditions, the asymptotic distribution of the test statistic is obtained under the null hypothesis and its consistency is proved under the alternative hypothesis. The critical value can be obtained by Monte Carlo simulation and its respond curve is obtained by fitting. Finally, a Monte Carlo study shows that our test has reasonably good size and power properties in finite samples.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"339 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233888","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：