臺灣博碩士論文加值系統

近年來，網際網路的使用人口呈現大幅度的成長的狀況。在網際網路快速普及化的情況下，伴隨而來的潛在負面影響也隨之增加。其中一個較受關注的議題亦即網路成癮。具有網路成癮的使用者會花費較多的時間在使用網際網路上，而且達到無法控制的狀態，甚至嚴重的影響原先正常的生活作息。為了減少網際網路所帶來的負面影響，及早發現不適當的網際網路使用行為，本研究使用資料探勘的方法分析使用者個人電腦中的網路暫存檔來辨識潛在的網路成癮使用者。研究當中所使用的資料集是真實世界的樣本，我們在全國性的討論區上發佈徵求受測者的訊息，共取得217筆樣本來評估本研究提出方法的辨識準確率。

在網路成癮的辨識方法上，使用支援向量機、決策樹、貝式網路分類器以及鄰近資料法所組成的結合分類器來進行第一階段的分類，當發生不一致的辨識結果時，再進入第二階段的案例式推理。經實驗結果顯示，提出的方法能獲得較佳的辨識準確率。同時，本研究亦提出一個以網路服務為基礎的安全網路成癮監視系統，使用網路服務開發的系統能夠達到跨平台與跨裝置的優勢。同時，系統也整合WS-Security來加強網路服務資料傳輸時的安全性。透過本系統協助，能夠隨時了解使用者網路成癮的程度，除了能夠矯正使用者不適當的網際網路使用行為之外，也減少使用者網路成癮程度加重的機會。

The use of the Internet has increased dramatically in recent years. This increasing use and availability has also resulted in an increase in the potential negative impact of the Internet. One recurring concern is Internet addiction, which involves individuals whose Internet usage has become excessive, gone out of control, and severely disrupts their lives. In order to reduce the negative impact of the Internet, it is necessary to detect inappropriate Internet usage behavior at an early stage. This study analyzes the temporary Internet files on a personal computer by using the data mining approach in order to identify potential Internet addiction in the user. The sample used in this study is a real-world dataset; we posted a message on a national forum to recruit participants. Finally, we obtained 217 effective samples to evaluate the proposed method for identifying Internet addiction.

In this method, we extract the feature of Internet usage behavior by using a self-organizing map and combine two classification methods to identify Internet addiction. The first stage is the ensemble classifier, which comprise a support vector machine, decision tree, Bayesian network classifier, and K-nearest neighbor. When the result of the base classifier was not consistent, the data was processed in the second stage, which involved case-based reasoning. The results of the experiment indicated that the ensemble classifier with case-based reasoning can improve the accuracy of identification. In this study, we also developed a secure web services-based Internet addiction monitoring system. The system using web services techniques was able to solve the problem of information integration among cross platforms and cross devices. Moreover, the proposed system uses WS-Security to enhance communication security in web services. With the help of this system, it is possible to identify the addiction level of Internet users, correct inappropriate Internet usage behaviors, and reduce the probability of the increase in Internet addiction levels. This study is expected to assist in Internet addiction diagnosis and contribute to solving the serious problem of Internet addiction.

1. Introduction..........................................................1
2. Related works.........................................................3
3. Methodology...........................................................6
3.1 Self organizing map...................................................7
3.2 Support vector machine................................................8
3.3 Bayesian Network Classifier...........................................8
3.4 Decision tree.........................................................9
3.5 K-nearest neighbor techniqe..........................................10
3.6 Case Based Reasoning.................................................11
4. System Overview......................................................13
4.1 Management Unit......................................................13
4.2 Guardian Unit........................................................14
4.3 User Unit............................................................14
4.4 Web services based system............................................15
4.5 Web Service Security Model...........................................17
4.5.1 Transport level security.............................................18
4.5.2 Message level security...............................................18
5. Experiment...........................................................22
5.1 Real world data set..................................................22
5.2 Feature extraction of Internet behaviors.............................23
5.3 Identification addiction by ensemble classifier and CBR..............25
5.3.1 Strategies for building base classifier..............................25
5.3.2 Ensemble classifier..................................................26
5.3.3 Combine ensemble classifier with CBR.................................28
6. Experimental results and Discussions.................................30
6.1 Performance of base classifiers......................................31
6.2 Performance of ensemble classifiers and CBR..........................32
7. Conclusion...........................................................34
References..................................................................36

[1]Internet World Stats [Online]. Available: http://www.internetworldstats.com/emarketing.htm.
[2]Internet World Stats [Online].Available: http://www.internetworldstats.com/stats.htm.
[3]Morahan-Martin, J., & Schumacher, P. (2000). Incidents and correlates of pathological internet use among college students. Computers in Human Behavior, Vol. 16, pp. 13-29.
[4] Egger, O., & Rauterberg, M. (1996). Internet behavior and addiction [On-line]. Available: http://www.ifap.bepr.ethz.ch/~egger/ibq/res.html.
[5]Griffiths, M.D. (2000). Does Internet and computer “addiction” exist? Some case study evidence. Cyber-Psychology and Behavior, Vol. 3, pp. 211-218.
[6]Jennifer, B. G. & Neal, D. G. (2006). The Web of Internet Dependency: Search Results for the Mental Health Professional. International journal of mental health and addiction, Vol. 4, pp. 307-318.
[7] Lin, S. S. J., & Tsai, C. C. (2002). Sensation seeking and internet dependence of Taiwanese high school adolescents. Computers in Human Behavior, Vol. 18, No. 4, pp. 411-426.
[8]Brenner, V. (1996). An initial report on the online assessment of Internet addiction: the first days of the Internet usage survey [Online]. Available: http://www.ccsnet.com/prep/pap/pap8b/638b/012p.txt.
[9] Brenner, V. (1997). Parameters of Internet use, abuse, and addiction: the first 90 days of the Internet usage survey. Psychological Reports, Vol. 80, pp. 879-882.
[10]Greenfield, D. N. (2000). Psychological characteristics of compulsive Internet use: a preliminary analysis. Cyber Psychology and Behavior, Vol. 5, No. 2, pp. 403-412.
[11]Kraut, R., Patterson, M., Lundmark, V., Kiesler, S., Mukopadhyay, T., & Scherlis, W. (1998). A social technology that reduces social involvement and psychological welling being? American Psychologist, Vol. 53, No. 9, pp. 1017-1031.
[12]Young, K. S. (1996). Internet addiction survey [Online]. Available: http://www.pitt.edu/_ksy/survey.htm.
[13]Young, K. S. (1997). Internet addiction: the emergence of a new disorder. Paper presented at the 105th annual convention of the American Psychological Association, Chicago.
[14] Fei, B.K.L., Eloff, J.H.P., Olivier, M.S. & Venter, H.S. (2006). The use of self-organising maps for anomalous behaviour detection in a digital investigation. Forensic Science International, Vol. 162, No. 1-3, pp. 33-37.
[15]Griffiths, M. D. (1998). Internet addiction: Does it really exist? In Gackenbach, J. (ed.), Psychology and the Internet, Academic Press.
[16]Kandell, J. J. (1998). Internet addiction on campus: The vulnerability of college students. Cyberpsychology and Behavior, Vol. 1, No. 1, pp. 11-17.
[17]Chou, C., & Hsiao, M. C. (2000). Internet addiction, usage, gratifications, and pleasure experience-The Taiwan college students’ case. Computer Education, Vol. 35, No. 1, pp. 65-80.
[18]Young, K. S. (1996). Internet addiction: The emergence of a new clinical disorder. The 104th American Psychological Association Annual Convention, Toronto, Canada.
[19]Goldberg, I. (1996). Internet Addiction Disorder [Online].Available: http://www.rider.edu/∼suler/psycyber/supportgp.html.
[20]Davis, R. A. (2001). A cognitive-behavioral model of pathological Internet use. Computers in Human Behavior, Vol. 77, pp. 187-195.
[21] Scherer, K. (1997). College life on-line: Healthy and unhealthy internet use. Journal of College Student Development, Vol. 38, pp. 655-665.
[22]Young, K. S. (1998). Internet addiction: The emergence of a new clinical disorder. Cyber Psychology and Behavior, Vol. 3, pp. 237-244.
[23] Young, K. (1998). Caught in the Net. New York: John Wiley & Sons.
[24]Chen, S. H., & Chou, C. (1999). Development of Chinese Internet addiction scale in Taiwan. The 107th American Psychology Annual convention, Boston, USA.
[25]Lin, S. S. J., & Tsai, C. C. (1999). Internet Addiction among High Schoolers in Taiwan. The 107th American Psychology Association (APA) Annual Convention, Boston, USA.
[26] Widyanto, L. & McMurran, M. (2004). The Psychometric Properties of the Internet Addiction Test. CyberPsychology and Behavior, Vol. 7, No. 4, pp. 443-450.
[27] Marcella, A. & Greenfield, R. (2002). Cyber Forensics: A Field Manual for Collecting, Examining and Preserving Evidence of Computer Crimes. Auerbach.
[28] Fei, B., Eloff, J., Venter, H. & Olivier, M. (2005). Exploring forensic data with self-organising maps. Advances in Digital Forensics, pp. 113-123.
[29] Kohonen, T. (1997). Self-Organizing Maps, 2nd Edition. Springer-Verlag.
[30] Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer-Verlag.
[31] Jensen, F.V. (1996). An Introduction to Bayesian Networks. UCL Press Limited, London.
[32] Cowell, R.G., Dawid, A.P., Lauritzen, S.L. & Spiegelhalter, D.J. (1999). Probabilistic Networks and Expert Systems. Springer, New York, USA.
[33] Heckerman, D. (1995). A tutorial on learning Bayesian networks. Technical Report MSR-TR-95-06, Microsoft Research.
[34] Pernkopf F. (2005). Bayesian network classifiers versus selective k-NN classifier. Pattern Recognition, Vol. 38, pp. 1-10.
[35] Friedman, N., Geiger, D. & Goldszmidt, M. (1997). Bayesian network classifiers. Machine Learning, Vol. 29, pp. 131-163.
[36] Quinlan, R. (2005). Data Mining Tools [Online].Available: http://www.rulequest.com/see5-info.html.
[37] Rastogi, R. & Shim, K. (1998). PUBLIC: a decision tree classifier that integrates building and pruning. Proceedings of the 24th International Conference on Very Large Databases, pp. 404-415.
[38]Quinlan, J.R. (1986). Induction of decision trees. Machine Learning, Vol. 1, pp. 81-106.
[39] Chi, M. & Bruzzone, L. (2006). An ensemble-driven k-NN approach to ill-posed classification problems. Pattern Recognition Letters, Vol. 27, pp. 301-307.
[40] Aamodt, A. & Plaza, E. (1994). Case-based reasoning: foundational issues methodological variations and systems approaches. AI Communications, Vol. 7, pp. 39-59.
[41] Pinho, D., Vivacqua, A., Palma, S. & Souza, J. M. (2006). SYMBAD-Similarity based agents for design. Expert Systems with Applications, Vol. 31, pp. 728-733.
[42] Kolodner, J. (1993). Case-based reasoning. San Mateo, CA: Morgan Kaufmann
[43] Choy, K. L., & Lee, W. B. (2001). Multi-agent based virtual enterprise supply chain network for order management. Journal of Industrial Engineering Research, Vol. 2, No. 2, pp. 126-141.
[44] Choy, K. L., Lee, W. B., & Lo, V. (2003). Design of an intelligent supplier relationship management system-a hybrid case-based neural network approach. International Journal of Expert Systems with Applications, Vol. 24, No. 3, pp. 225-237.
[45] Dietterich, T. G. (1997). Machine learning research: four current directions. , AI Magazine, Vol. 18, No. 4, pp. 97-136.
[46] Bray, T., Paoli, J., Sperberg-McQueen, C.M. & Maler, E. (2000). Extensible markup language (xml) 1.0, 2nd ed. w3c recommendation. [Online]. Available:http://www.w3.org/TR/REC-xml.
[47] Ferris, C. & Farrell, J. (2003). What are web services. Communications of the ACM, Vol. 46, No. 6, pp. 31.
[48] Rezgui, Y. (2007). Role-based service-oriented implementation of a virtual enterprise: A case study in the construction sector. Computers in Industry, Vol. 58, pp. 74-86.
[49] Kreger, H. (2001). Web services conceptual architecture (WSCA 1.0). Technical Report, IBM Corporation.
[50] Mateos, C., Zunino, A. & Campo, M. (2007).Extending movilog for supporting Web services. Computer Languages, Systems & Structures, Vol. 33, pp. 11-31.
[51] Nakamur, Y., Hada, S. & Neyama, R. (2002). Towards the Integration of Web services Security on Enterprise Environments. Proceedings of the 2002 Symposium on Applications and the Internet, pp. 166-175.
[52] Yin, H., Lin, C. & Lin, Y.S. (2006). A Mobile Police Information System Based on Web Service. Journal of Tsinghua Science and Technology, No. 1.
[53]IETF. The SSL Protocol. Version 3.0.
[54] Neuman, C. & Ts’o, T. (1994). Kerberos: an authentication service for computer networks. IEEE Commun., Vol. 32, No. 9, pp. 33-38.
[55] Efrim Boritz, J. & Won, G. N. (2005). Security in XML-based financial reporting services on the Internet. Journal of Accounting and Public Policy, Vol. 24, pp. 11-35.
[56] Access Data Corp. (2004). [Online].Available: http://www.accessdata.com
[57] Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A practical guide to support vector classification. [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[58] Hsu, W.H. (2004). Genetic Wrappers for feature selection in decision tree induction and variable ordering in Bayesian network structure learning. Information Science, Vol. 163, pp. 103-122.
[59] Cano, R., Sordo, C. & Gutie’rrez, J.M. (2004). Applications of Bayesian Networks in Meteorology. Advances in Bayesian Networks , Springer-Verlag, pp. 309-327.
[60] Gregory, F. C. & Herskovitz, E. (1992). A Bayesian method for the induction of probabilistic networks from data. Machine Learning, Vol. 9, pp. 309-347.
[61] Hruschka, Jr. E. R. & Ebecken, F.F. (2007). Towards efficient variables ordering for Bayesian networks classifier. Data & Knowledge Engineering, Vol. 63, pp. 258-269.
[62] Bauer, E. & Kohavi, R. (1999). An empirical comparison of voting classification algorithms: bagging, boosting, and variants. Machine Learning, Vol. 36, No. 1, pp. 105-139.
[63]Richards, G., Rayward-Smith, V.J., Sonksen, P.H., Carey, S. & Weng, C. (2001). Data mining for indicators of early mortality in a database of clinical records. Artificial Intelligence in Medicine, Vol. 22, pp. 215-31.