{"title":"A Co-Evolutionary Model for Inferring Online Social Network User Behaviors","authors":"Xiaoming Liu, Chao Shen, Yingyue Fan, Xiaozi Liu, Yadong Zhou, X. Guan","doi":"10.1109/SPAC46244.2018.8965440","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965440","url":null,"abstract":"Accurate online social network user behavior inference can improve the performance of the other applications significantly, such as friend commendation, hot topic prediction, and personal website assistant. Previous works mainly focus on the trend analysis of user behaviors or adopt the method to fit the supposed user-behavior distribution, but they ignore the dynamic mutual influence among the users and behaviors on social networks. This paper proposes a co-evolutionary model to formulate the interaction pattern among the users and behaviors, in which a systematic method is used for embedding the distinctiveness and permanence properties of the users and behaviors into latent features. This model could naturally capture the dynamic evolving process of the user behaviors with the time. What’s more, we also take into account the following relationship to depict the interaction information among users. Extensive experiments show that our algorithm achieves 0.024 of the MAE (hour) in the crime time inference, and 0.506 and 0.579 of the accuracy in the user and behavior inference, which surpass the state-of-arts more than 7.19×, 1.12× and 1.14×, respectively. Additional experiments on different training echoes of our model are provided to further explore its effectiveness and scalability.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114502835","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}
{"title":"Research on investor sentiment and stock market prediction based on Weibo text","authors":"Yongheng Deng, Qing Xie, Yong Wang","doi":"10.1109/SPAC46244.2018.8965607","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965607","url":null,"abstract":"Microblog can obtain investors' views of stock market accurately and timely, and grasping the fluctuation of investor sentiment is beneficial to predict the future trend of stock market. Based on behavioral finance theory, this paper uses text mining and natural language processing technology to obtain investor sentiment, and then combines price earnings ratio and turnover rate to build a stock market prediction model. The results show that the investor sentiment based on Weibo text has a certain predictive ability to the Shanghai stock index. The model has the best performance in the ascending period, and the effect of the shock period is the worst.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122567800","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}
{"title":"Classification based Integration of Quantifications for LC-MS Analysis","authors":"Tianjun Li, Long Chen, Huiqin Wei","doi":"10.1109/SPAC46244.2018.8965613","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965613","url":null,"abstract":"A classification based integration of quantification method for the Liquid Chromatography – Mass Spectrometry (LC-MS) analysis is described in this paper. Typically, one biological tissue may be sent to the LC-MS many times in practice to generate multiple LC-MS data. Due to the precise level or the profile of the search engine, these multiple individual quantitative results of the multiple LC-MS data may be partially identical. Here we proposed a method to integrate the quantitative results for the case where there are multiple individual measurements but the results are only partially identical. This proposed method applies a classifier to the peptides and treats the predicted probabilities of the classification as the weights to combine these multiple individual quantitative results into a better one. Experimental results show that in the task of quantitative LC-MS, the results generated by this integration method perform better than the ones produced by other individual measurements.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122610074","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}
{"title":"A File Encryption Algorithm Based on Dynamic Block Out of order Matrix Mapping","authors":"Tan Dong, Yanxia Wang, Liu Lei","doi":"10.1109/SPAC46244.2018.8965585","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965585","url":null,"abstract":"In order to solve the security of content transfer during file transfer and fast encryption of large files. This paper proposes a method to quickly encrypt large files and protect the contents of file information, also prevent files from being intercepted and decrypted before use. The algorithm of file encryption based on dynamic block out of order matrix mapping. First, dynamically block the files according to a certain ratio, extract the raw data and key information of each block, then store the out of order data into a two-dimensional table of matrix after calculation and processing. Second, use Base64 encoding on this matrix mapping table. Then the matrix mapping table is to be a unique decryption key of this file. After that, the data in the spare block of the file is filled with the MD5 data, the MD5 data is generated by UUID and block with the same size as the number of dynamic block. The new encrypted file whose length is equal to the original file. Because it is dynamic block and random extracted data, so it is fast and efficient. The experimental results and security analysis show that the algorithm has a good encryption structure and high security, which can effectively resist various attack behaviors. Most of the files that with different types can be used, and the speed to encrypt and decrypt large files is greatly improved compared with the traditional encryption and decryption methods, the speed and efficiency far exceed the traditional file encryption and decryption algorithms, such as AES, DES, 3DES and so on.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122693771","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}
{"title":"Modeling and Analysis for Spectrum Handoff in Cognitive Heterogeneous Wireless Network","authors":"Bin Ma, Qianqian Zhang, Xianzhong Xie","doi":"10.1109/SPAC46244.2018.8965614","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965614","url":null,"abstract":"In cognitive heterogeneous wireless network where the open wireless network and the cognitive radio network coexist, we use the queuing theory to model the spectrum handoff of secondary user(SU), solving the problem of large secondary user service delay. First, a cognitive heterogeneous wireless network environment is established based on the shared unlicensed spectrum as well as the opportunity utilization authorized spectrum in cognitive radio network. Then, a novel dynamic data adjustment scheme is proposed based on the channel historical state information. Combining with the user classification and the PRP/NPRP M/G/1 queue model, we analyze the secondary users’ extened data transmission delay in spectrum handoff, and propose an adaptive frequency handoff strategy to minimize the delay. Finally, the simulation results show that the proposed cognitive heterogeneous wireless network can realize the network coexistence and improve the spectrum utilization efficiency. Meanwhile, the proposed adaptive spectrum handoff strategy can effectively reduce the transmission delay of delay-sensitive secondary users, while improve the service performance of non-delay-sensitive ones.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122333372","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}
{"title":"Weak Ordering Space Search in Turn-based War Chess Gaming","authors":"Hai Nan, Wanping Liu, Chao Liu, Chengyun Song","doi":"10.1109/SPAC46244.2018.8965586","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965586","url":null,"abstract":"Turn-Based War Chess Game (TBW) is the most important part of turn-based strategy game, and the research on its AI is hard but has a great significant impact not only on video games but also on applied mathematics. This paper is aimed at eliminating order independent redundancy plans in Nan’s enumeration methods. First, we propose the Weak Order Correlation theory, whose necessary and sufficient condition are deduced theoretical. Then, using this theory and its conditions, we design the non-redundant enumeration algorithm in weak order space. Consequently, the completeness and efficiency (zero redundancy of the plans) of the new algorithm are guaranteed.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"223 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120871694","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}
{"title":"Adaptive Fuzzy Inverse Optimal Control for A Class of Two Order Nonlinear Systems","authors":"Tingting Yang, Fengxue Cao, Yong-ming Li, Shaocheng Tong","doi":"10.1109/SPAC46244.2018.8965558","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965558","url":null,"abstract":"This study develops an adaptive fuzzy inverse optimal control method for a class of two order nonlinear systems with unknown nonlinear dynamics. By using the knowledge of a control Lyapunov function and the universal approximation property of a fuzzy logic system, the inverse optimal control design and unknown nonlinear dynamics problems are solved, respectively. A new adaptive fuzzy optimal controller is constructed based on backstepping design principle, and the stability and optimality are proven by using rigorous mathematical reasoning.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134498338","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}
{"title":"Image Shadow Removal Based on Residual Neural Network","authors":"Wei Zheng, Xiuping Teng","doi":"10.1109/SPAC46244.2018.8965500","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965500","url":null,"abstract":"The removal of image shadows has always been a challenging task that requires us to detect shadows and understand the surrounding scenes. The existing method of shadow detection and removal first locates the shadow area by shadow detection,and then uses some reconstruction algorithms to remove the shadows of the umbra and penumbra. However, detecting shadows is already a very rare task. Based on the traditional physical methods can be applied to a high quality image, and a method based on statistical characteristics must manually tag shadow. In this paper,we use a convolutional residual neural network to train the model. Using the residual neural network, we can prevent degradation due to the excessive number of network layers. The trained model can detect the shadow area by inputting the global image and combining the semantics of the picture. In these two aspects, good shadow area detection and positioning can be obtained, and image shadow removal can be realized.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120573","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}
Shuangrong Liu, Lin Wang, Bo Yang, Shuo Kong, Huifen Dong, Xuehui Zhu
{"title":"Fuzzy Nearest Neighbor Partitioning Neural Network for Classification","authors":"Shuangrong Liu, Lin Wang, Bo Yang, Shuo Kong, Huifen Dong, Xuehui Zhu","doi":"10.1109/SPAC46244.2018.8965611","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965611","url":null,"abstract":"The fuzzy nearest neighbor partitioning neural network (FNNP) is proposed to promote the capability of the neural network classifier. The fixed centroids problem restrains the further improvement of the neural network classifier. The original nearest neighbor partitioning method (NNP) have been proposed to address this problem. In the NNP, the learning method is employed to train the neural network in according with the distribution information of samples. However, the distribution information underutilization problem affects the learning method to obtains the neural network with expected mapping performance. Therefore, we propose the FNNP to overcome this problem. In the FNNP, the fuzzy logic theory is adopted to assist the learning method to comprehensively collect neglected distribution information that increases the probability to find the optimal neural network with expected mapping performance. Experiment results demonstrate that the FNNP achieves remarkable classification performance on various indictors.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115056332","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}
{"title":"Characters Verification via Siamese Convolutional Neural Network","authors":"Shengke Wang, Xin Lv, Rui Li, Changyin Yu, Junyu Dong","doi":"10.1109/SPAC46244.2018.8965605","DOIUrl":"https://doi.org/10.1109/SPAC46244.2018.8965605","url":null,"abstract":"In the printing and carving industries, it is necessary to check whether printed outputs or carved wares are missing or etched through comparing the drawings. Traditional approaches and identification methods can’t be used for this application where the number of character categories are not determined, and where the character may be unique designed by manufacturer. Driven by the one-to-one matching pattern, we propose an end-to-end dual input network for automatic comparison, which uses convolutional neural network to extract features from the scanned images which collected from printed matters. Then, we convert the corresponding drawing to the vector of the same dimension to calculate distance and the match/mismatch result. Experiments show that our method can effectively solve the problem of character comparison with many types, and at the same time propose an automated comparing program for the industrial imprinting process.","PeriodicalId":360369,"journal":{"name":"2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115081802","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}