{"title":"An Automatic Evaluation Method for Chinese Name Recognition","authors":"Yujian Li, Dedong Zhang, Zhen Yang","doi":"10.1109/CIS.2010.131","DOIUrl":"https://doi.org/10.1109/CIS.2010.131","url":null,"abstract":"In order to evaluate the methods of Chinese name recognition effectively, this paper presents an automatic evaluation method for measuring the performance of Chinese name recognition systems by using the idea of randomly selecting sentences and replacing names. The method can be mainly divided into three parts: the construction of evaluation corpus, the generation of evaluation files and the computation of evaluation scores. As evaluation files are generated automatically and randomly in the method, the method can overcome the disadvantages that traditional standard evaluation files usually have such as small-scale, fixed and un-reusable. Experiments show that the method is not only efficient, valid and objective, but also can be extended to evaluating other kinds of named entity recognition such as place names and organization names.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131355440","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 Real-Time Pineapple Matching System Based on Speeded-Up Robust Features","authors":"Bin Li, Maohua Wang, Li Li","doi":"10.1109/CIS.2010.59","DOIUrl":"https://doi.org/10.1109/CIS.2010.59","url":null,"abstract":"Real-time and accurate image matching is a key to stereo vision of agricultural harvesting robots. This research is part of a pineapple harvesting robot project. In this paper, pineapples were selected as research objects and low cost binocular vision platform was constructed, fruit area of left image was got by real-time image acquisition and rapid segmentation, rapid matching of fruit area in left image with the integral right image was done by employing SURF (Speeded-Up Robust Features) algorithm. The algorithm was programmed and tested in VC++ software and the results showed that, the segmentation cost 0.017s and the real-time matching performed well. Compared with other agricultural harvesting robots’ research, area matching and real-time matching were well-realized.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122707890","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 Multi-objective Genetic Algorithm Approach Based on the Uniform Design Metmod","authors":"Xiaoshu Ma, Jing Huo, Qun Wang","doi":"10.1109/CIS.2010.43","DOIUrl":"https://doi.org/10.1109/CIS.2010.43","url":null,"abstract":"Many optimization problems in the scientific research and engineering practice can be modeled as multi-objective optimization problems. Effective algorithms for them is of not only important in scientific research, but also valuable in applications. In this paper, a new genetic algorithm for multi-objective optimization problems based on uniform design called BUMOGA is proposed combined with uniform design. The algorithm can find the sparse areas of non-dominated frontier, and explore the sparse area which can make the non-dominated solutions more uniform. The introductions of uniform crossover operator and single point crossover complex operator make up the defects of weak search capabilities of simulated binary crossover operator. The global convergence of the algorithm is proved, and effectiveness of the algorithm is demonstrated by the simulations. The computer simulations for five difficult standard benchmark functions also verify this fact.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122317058","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 Wireless Sensor Network Security","authors":"Yan-Xiao Li, Lian Qin, Qian Liang","doi":"10.1109/CIS.2010.113","DOIUrl":"https://doi.org/10.1109/CIS.2010.113","url":null,"abstract":"Wireless sensor networks are a new type of networked systems, characterized by severely constrained computational and energy resources, and an ad hoc operational environment. When wireless sensor networks are deployed in a hostile terrain, security becomes extremely important, as they are prone to different types of malicious attacks. Due to the inherent resource limitations of sensor nodes, existing network security methods, including those developed for Mobile Ad-Hoc Networks, are not well suitable for wireless sensor networks. As a crucial issue security in wireless sensor networks has attracted a lot of attention in the recent year. This paper made a thorough analysis of the major security issue and presented the ongoing aspect of further development to designers in their struggle to implement the most cost effective and appropriate method of securing their network.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116476601","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":"Soft Information Improvement for PN Sequence Iterative Acquisition","authors":"Wei Wang, Nianke Zong, Jie Tang, S. Lambotharan","doi":"10.1109/CIS.2010.122","DOIUrl":"https://doi.org/10.1109/CIS.2010.122","url":null,"abstract":"Iterative message passing algorithms (iMPAs) which are generalized from the well-known turbo principle can reach a rapid pseudo-noise (PN) sequence acquisition at low computational complexity. However, its performance will degrade at low signal-to-noise ratio (SNR). In this paper, a soft information improvement using multiple samples in one chip is proposed. Meanwhile, to mitigate the timing error which will affect the information improvement, a Maximum-Likelihood (ML) estimation without significant increase on the complexity is introduced. Simulation results show that proposed method can realize rapid PN code acquisition at lower SNR than existing method.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127054362","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 Novel Image Classification Method Based on Double Manifold Learning","authors":"Li-Hua Ye, R. Zhu, Jie Xu","doi":"10.1109/CIS.2010.64","DOIUrl":"https://doi.org/10.1109/CIS.2010.64","url":null,"abstract":"To solve the two-class classification problem existing in semantic-based image understanding, a novel classification method based on double manifold learning is proposed, which can transform the classification problem from a high-dimensional data space to a feature space with lower dimensionality. Two manifolds with different intrinsic dimensionalities will be first established separately, according to the significant differences between the positive samples and the negative ones, where globular neighborhood-based locally linear embedding (GNLLE) algorithm is adopted to implement dimensionality reduction and meantime unsupervised clustering. Then the aggregation center of each manifold is calculated, taking into account the grouping characteristics of similar samples. Furthermore, a new classifier is constructed for a double manifold learning model via distance companion. Finally experiments indicate that our method, which can be easily extended to multi-classification manifold learning, will not only reflect the topological structure of the whole data more precisely, but also achieve performance of classification more efficiently.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125270343","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":"Securing GPRS Tunnel Protocol in 3G Core Network","authors":"Xuena Peng, Yingyou Wen, Hong Zhao","doi":"10.1109/CIS.2010.108","DOIUrl":"https://doi.org/10.1109/CIS.2010.108","url":null,"abstract":"The security concerns in 3G network, especially the core network, is far from being satisfied. As the most important protocol in the 3G core network, GPRS Tunnel Protocol (GTP) is quite vulnerable to attacks in the flat, full IP environment. Solving such a problem properly is very urgent and important for the operation of 3G network. In this paper, we discus the security issues in GTP, and propose a defense solution for these security threats. The experiment result shows the potential of our solution.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124026038","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":"Privacy-Preserving Classification on Horizontally Partitioned Data","authors":"Tian Tian, Hua Duan, G. He","doi":"10.1109/CIS.2010.56","DOIUrl":"https://doi.org/10.1109/CIS.2010.56","url":null,"abstract":"With the appearance of large-scale database and people's increasing concern about individual privacy, privacy-preserving data mining becomes a hot study area, to which the support vector machine(SVM) belongs. In this paper, a novel privacy-preserving SVM for horizontally partitioned data is given. It has comparable accuracy to that of an ordinary SVM as we obtain the SVM by using the distinct property of the orthogonal matrices.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132538122","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":"Credit Card Customer Segmentation and Target Marketing Based on Data Mining","authors":"Wei Li, Xuemei Wu, Yayun Sun, Quan-ju Zhang","doi":"10.1109/CIS.2010.23","DOIUrl":"https://doi.org/10.1109/CIS.2010.23","url":null,"abstract":"Based on the real data of a Chinese commercial bank’s credit card, in this paper, we classify the credit card customers into four classifications by K-means. Then we built forecasting models separately based on four data mining methods such as C5.0, neural network, chi-squared automatic interaction detector, and classification and regression tree according to the background information of the credit cards holders. Conclusively, we obtain some useful information of decision tree regulation by the best model among the four. The information is not only helpful for the bank to understand related characteristics of different customers, but also marketing representatives to find potential customers and to implement target marketing.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128308837","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":"Synchronization Algorithm for Multi-hop in Wireless Sensor Networks","authors":"Hong Yao, Wuneng Zhou","doi":"10.1109/CIS.2010.13","DOIUrl":"https://doi.org/10.1109/CIS.2010.13","url":null,"abstract":"Time synchronization possesses wide range of applications. There are already a variety of time synchronization methods. In wireless sensor networks, its equipment, limitations of resources and the environment, require time synchronization with high efficiency, while saving resources. This article describes the time synchronization algorithm using the time stamp of the effectiveness of the inspection stage, to simply send a small packet that is able to achieve the synchronization functions. The simulation results show that our algorithm can makes the system has lower synchronization errors and better performance.","PeriodicalId":420515,"journal":{"name":"2010 International Conference on Computational Intelligence and Security","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133441989","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}