{"title":"Web Usage Mining to Evaluate the Transfer of Learning in a Web-Based Learning Environment","authors":"F. Chanchary, Indrani Haque, M. Khalid","doi":"10.1109/WKDD.2008.139","DOIUrl":"https://doi.org/10.1109/WKDD.2008.139","url":null,"abstract":"Application of data mining for web log analysis has received significant attention in finding customers' behavioral pattern in e-commerce and learners' behavioral pattern in e- learning. While hit-counts indicate customers' interest in the product or purchasing behavior, a student's visits to a Learning Management System (LMS) do not necessarily involve transfer of learning. Addressing such complexity in e-learning, this study analyzed students' log of a Learning Management System (LMS) of two subjects at a university in Bangladesh, taught over six weeks duration. Data mining and statistical tools have been used to find relationships between students' LMS access behavior and overall performances. Results show that students having 'Low' access obtained poor grade, on campus access was higher than access from home. Background of students is very important for effective usage of web resources. Majority of the student considered LMS to be a quite helpful tool as teaching-learning method. Preparation and cleaning of the web-log files as well as application of data mining algorithms is important for learners' web usage analysis.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125848377","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":"An Improved Particle Swarm Optimization with New Select Mechanism","authors":"Yi Jiang, Qingling Yue","doi":"10.1109/WKDD.2008.71","DOIUrl":"https://doi.org/10.1109/WKDD.2008.71","url":null,"abstract":"The particle swarm optimization is a stochastic, population-based optimization technique. A modified PSO algorithm is proposed in this paper to avoid premature convergence with the new select mechanism. This mechanism is simulating the principle of molecular dynamics, which attempts to activate all particles as the most possible along with their population evolution. Two stopping criteria of the algorithm are derived from the principle of energy minimization and the law of entropy increasing. The performance of this algorithm is compared to the standard PSO algorithm and experiments indicate that it has better performance.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130195867","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":"Intrusion Detection System Based on Data Mining","authors":"Zhan Jiuhua","doi":"10.1109/WKDD.2008.12","DOIUrl":"https://doi.org/10.1109/WKDD.2008.12","url":null,"abstract":"Analyzed recent IDS models, the development of IDS (Intrusion Detection System), and the current and gives a brief introduction to DM (Data Mining) technology. Presented a framework of IDS based on data mining for resolving the current problems IDS is facing. The system that performs anomaly detection can detect intrusions known and unknown, reduce omissions and misstatements, improve accuracy and speed of intrusion detection and has good adaptive capacity and scalability.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132495588","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 Hybrid RBAC-PBAC Access Control Model for Network Isolation System","authors":"Haiyan Wu, Chengxiang Tan, Haihang Wang","doi":"10.1109/WKDD.2008.120","DOIUrl":"https://doi.org/10.1109/WKDD.2008.120","url":null,"abstract":"Network isolation system integrates various technologies to achieve its high-security performance and access control is an indispensable one among them. In order to control and manage accesses to all the services provided by network isolation system, we need to establish an efficient access control model and make a set of fine-grained rules for the model. In this paper, we analyze service access control requirements in network isolation system firstly. And, according to the special running environment, we propose a hybrid service access control model based on RBAC (Role- based Access Control) and PBAC (Police-based Access Control). Then, we research rules making and realization method of the proposed model. In the end, we realize the hybrid model and its configuration.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129899087","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 Parametric Algorithm for Long-Short Portfolio Optimization","authors":"Yanwu Liu, Zhongzhen Zhang, Feng Xiong, Liu Fang","doi":"10.1109/WKDD.2008.97","DOIUrl":"https://doi.org/10.1109/WKDD.2008.97","url":null,"abstract":"A parametric algorithm is proposed to calculate efficient frontier of long-short portfolio. The key to the algorithm is to introduce parametric technique into the pivoting algorithm. The numerical results show that the algorithm has high computing efficiency.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133241765","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 Anomaly Detection Algorithm Based on Real-Valued Negative Selection System","authors":"Zhengbing Hu, Zhou Ji, Ping Ma","doi":"10.1109/WKDD.2008.110","DOIUrl":"https://doi.org/10.1109/WKDD.2008.110","url":null,"abstract":"In this paper, a new method of detector generation and matching mechanism for negative selection algorithm(NSA )is introduced with variable properties, which are called the Nsa-Vs-Detector. The detectors can be variable in different ways using this concept, the paper describes an algorithm when the variable parameter is the size of the detectors in real-valued space. The algorithm is tested with a synthetic datasets, the new method improves the NSA 's efficiency and reliability without significant increase in complexity.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134530222","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":"The Spam Filtering Technology Based on SVM and D-S Theory","authors":"Miao Ye, Qiuxiang Jiang, F. Mai","doi":"10.1109/WKDD.2008.42","DOIUrl":"https://doi.org/10.1109/WKDD.2008.42","url":null,"abstract":"The development of spam techniques and rapid increase of spam amount poses a severe challenge to anti-spam technologies. Given the limitation of classification based on mail body textual content, this paper focuses on designing the spam discrimination model based on SVM and D-S theory, which uses SVM with probability to classify e-mail, according to the features of mail headers and mail body respectively, and uses D-S Theory to judge the combination result. Experimental result indicates that the proposed model can improve the accuracy of spam identification.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133616857","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 New Digital Image Hiding Approach Using Multi-Image Fusion","authors":"Daqi Zhang, Shiru Qu, Baosheng Kang","doi":"10.1109/WKDD.2008.81","DOIUrl":"https://doi.org/10.1109/WKDD.2008.81","url":null,"abstract":"Using the idea of digital image's information sharing, a new hiding approach for multi-image fusion based on NURBS curve is presented. The approach makes use of a k-order non-uniform rational B-spline curve with weights to hide information of one image into information of n images. These hiding schemes have more fusion parameters to act as the private keys, which can enhance the security and robustness of the hiding image more. Actually, in the whole image sequence, only p+1 public images do work, so the influence on the recovering result can be decreased, which is caused by the pollution of various noises during public images' transmission. Examples show that these schemes can be realized expediently and have some degree of robustness. These hiding approaches can also be used in the field of digital watermarking and other digital application.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117287705","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":"Influences of CAI English Teaching Pattern on the Autonomous Learning -Research on Divided Class Instruction of Independent College","authors":"X. Tian","doi":"10.1109/WKDD.2008.144","DOIUrl":"https://doi.org/10.1109/WKDD.2008.144","url":null,"abstract":"With the development of the technology of CAI, it is widely used in our english teaching. So many people focus their attentions on the influences of CAI in different aspects. Therefore, the author tries to investigate the influences of CAI english teaching pattern on the autonomous learning, in divided class instruction of independent college. As far as it is concerned, it is important for us to find out the essential influences of \"divided class instruction\" on students in independent college, thus to make the reform of our teaching pattern successfully.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130832403","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":"Personalized E-learning System by Using Intelligent Algorithm","authors":"Mingmin Gong","doi":"10.1109/WKDD.2008.152","DOIUrl":"https://doi.org/10.1109/WKDD.2008.152","url":null,"abstract":"Nowadays, network and multimedia are the trend of the development of the modern education technology. With the rapid development of the network technique and the prevalence of the Internet, e-learning has become the major trend of the development of international education since 1980's, and the important access for the internationalization and the information of education. To meet the personalized needs of learners in e-learning, a new intelligent algorithm is proposed in the paper by using personality, association rules mining and collaborative filtering technologies. The intelligent algorithm is composed of two phases: association rules algorithm and collaborative filtering.","PeriodicalId":101656,"journal":{"name":"First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131329341","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}