本研究目的主要在於建立人員行為觀察的技術，及早發現員工可能發生的異常或緊急情況，包括受傷、突發病症等情形，以預防因員工異常行為而危及核子保安系統之安全。同時從人因工程的觀點進行實驗，藉由比較傳統監視系統模式與本研究發展之異常行為偵測支援系統為基礎之監視系統模式，進行系統的績效的量度以及人員心智負荷的評估，驗證本研究發展之技術是否適合核電廠之監視作業。

首先探討核電廠之情境以及可能發生之異常狀況，接著根據歸納出之異常行為分類拍攝模擬監視影像，使用數位影像處理演算法擷取出人員影像資料，將資料編碼為姿態、移動速動、移動軌跡等三個量化變數，輸入決策樹軟體中進行資料分類，並根據生長完成決策樹之預測規則建立異常行為偵測支援系統 (UBDSS)。設計一模擬實驗，藉由比較傳統監視模式與UBDSS監視模式之受試者反應時間、作業績效、作業負荷，衡量人員績效提昇以及負荷降低之程度。

研究結果顯示，UBDSS具有良好之異常行為預測能力 (平均預測率為83.4%)；此外，實驗結果顯示，使用UBDSS的監視系統可以顯著提昇人員之績效，平均反應時間下降42.9%，平均錯誤率下降62.1%。對於智慧型監視系統之發展，實驗研究可應用勞力密集產業之廠房中自殺或異常行為之即時預防，以及其他安全層級較高設施，如高級政府機關之安全維護。

This study is to develop a technique of behavior observation to detect insider□s abnormal behavior and workers’ emergent situation such as heart attack or fall down in NPP in order to prevent safety hazard due to workers’ unusual behavior. Moreover, experiment has been carried out in the viewpoint of human factors engineering for the purpose of comparing conventional surveillance system and the surveillance system with Unusual Behavior Detection support system (UBDSS) to measure system effectiveness and workload reduction
First of all, the scenario and possible abnormal behavior in NPP were discussed. Next, the simulated video data was shot and, with image process algorithm, captured and transferred into three numerical variables that interpreting human action including gesture, moving speed and moving angle. The three variables were then analyzed with decision tree method to construct a model for finding relation among the three variables and the behavior observed. The rules of decision tree classification were used to predict new video data, which formed UBDSS. Afterward, an experiment was conducted to verify system effectiveness and reduction of workload by computing response time, error rate and NASA TLX task load index.
The results of this study indicated that unusual behavior prediction rate of UBDSS is acceptably high (average classification rate = 83.01), and auto-alarm system with UBDSS is able to improve system performance as results of experiment indicated that the response time decreased about 42.9% and the error rate decreased about 62.1%. The result of this study can be applied on other relevant industries such as suicide preventions of labor-intensive industry and secure protection in safety-concerned facilities such as government office.

Ackroyd, S. and Thompson, P., “Organizational Misbehaviour,” London: Sage, 1999.
Brown, G., “Sabotage: A Study of Industrial Conflict,” Spokesman Books, Nottingham, 1977.
Buma, M., Smit, J. and Noldus, L. P. J. J., “Automation of behavioral tests using digital imaging,” Neurobiology, pp.4-277,1997.
Buresova, O., Bolhuis, J. J. and Bures, J., “Differential effects of cholinergic blockade on performance of rats in the water tank navigation task and in a radial water maze,” Behavioral Neuroscience, Volume 100, pp. 476-482, 1986.
Carmona, E. J., Rincon, M., Bachiller, M., Martınez-Cantos, J., Martınez-Tomas, R. and Mira, J., “On the effect of feedback in multilevel representation spaces for visual surveillance tasks,” Neurocomputing, Volume 72, pp. 916–927, 2009.
Chatizwa, I., “Gender and ergonomics in agricultural engineering,” Proceedings from AGROTEC/FAO Workshop Gender and Agricultural Engineering, 1996.
Cheng, Y. Y., “Intelligent posture recognition,” Research of Control Program of National Science Council, 2008.
Dee, H. M. and Velastin, S. A., “How close are we to solving the problem of automated visual surveillance? A review of real-world surveillance, scientific progress and evaluative mechanism,” Machine Vision and Applications, Volume 19, Issue 5-6, pp.329-343, 2008.
Duque, D., Santos, H. and Cortez, P., “Prediction of Abnormal Behaviors for Intelligent Video Surveillance Systems,” Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Data Mining, 2007.
Fasela, B., and Luettin, J., “Automatic facial expression analysis: a survey”, Pattern Recognition, Volume 36, pp. 259 – 275, 2003.
Fujiyosh, H. and Lipton, A. J., “Real-time human motion analysis by image skeletonization,” Fourth IEEE Workshop on Applications of Computer Vision, pp. 15-21, 1998.
Giacalone, R. A., and Greenberg, J., “Antisocial behavior in organizations,” Thousand Oaks, CA: Sage, 1997.
Griffin, R. W., O’Leary-Kelly, A. and Collins, J. M. (Eds.), “Dysfunctional behavior in organizations: Violent and deviant behavior,” Non-Violent Dysfunctional Behavior in Organizations, 1998.
Haritaoglu, I., Harwood, D. and Davis, L. S., “ : Real-Time Surveillance of People and Their Activities,” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Volume 22, No.8, 2000.
Kaplan, H. B., “Self-attitudes and deviant behavior,” Pacific Palisades, CA:Goodyear, 1975.
Karhu, O., Kansi, P. and Kuorinka, I., “Correcting working postures in industry: A practical method for analysis,” Applied Ergonomics, Volume 8, pp. 199-201, 1977.
Lee, Z. H., “Human Behavior Analysis with Shadow Cancellation and occlusion Detection Techniques,” Master Thesis, National Hsing Hua University, 2006.
Liao, Y. T., “Slip and Fall Detection using Spatiotemporal Characteristics of Human Object for video Surveillance System,” Master Thesis, National Tsing Hua University, 2009.
Lin, C. Y., “Real-time Video Surveillance Using Fuzzy Self-Organizing Neural Network,” Master Thesis, National Central University, 2006.
Lin, L., Seo, Y. S., Gen, M. and Cheng, R., “Unusual human behavior recognition using evolutionary technique,” Computers & Industrial Engineering, Volume 56, pp. 1137–1153, 2009.
Lin, R. C., “Preservation and use of modern technology,” speech slides.
Lucas, B.D. and Kanade, T., “An iterative image registration technique with an application to stereo vision,” Proceedings of International Joint Conference on Artificial Intelligence, pp. 674–679, 1981.
Maltz, M. and Shinar, D., “Imperfect in-vehicle collision avoidance warning systems can aid distracted drivers,” Transportation Research, Part F, Volume 10, pp. 345–357, 2007
Martınez-Tomas, R., Rincon, M., Bachiller, M. and Mira, J., “On the correspondence between objects and events for the diagnosis of situations in visual surveillance tasks,” Pattern Recognition Letters, Volume 29, pp. 1117–1135, 2008.
Murray, S. A., “Human performance studies for control of multiple remote systems,” Technical Report 1658, 1994.
Parasuraman, R., “Handbook of Human Perception and Performance,” Cognitive Processes and Performance, Volume 2, pp. 41–1 - 41-49, New York, Wiley, 1986.
Parasuraman, R., and Riley, V., “Humans and automation: use, misuse, disuse, and abuse,” Human Factors, Volume 39, pp. 230–253, 1997.
Quinlan, J.R., “C4.5: Program for Machine Learning,” Morgan Kaufmann Publishers, San Mateo, CA, USA, 1993.
Scanlan, L. A., “Target acquisition in realistic terrain,” Proceedings of 21st annual meeting of the Human Factors Society, Santa Monica: Human Factors Society, 1977.
Scott, G.B. and Lambe, N. R., “Working practices in a perchery system, using the OWAS Working posture Analyzing System (OWAS),” Applied Ergonomics, Volume 27, Issue 4, pp. 281-284, 1996.
Shi, J., and Tomasi, C., “Good features to track,” Proceedings of CVPR94, pp. 593–600, 1994.
Spink, A. J., Tegelenbosch, R. A. J., Buma, M. O. S. and Noldus, L. P. J. J., “The EthoVision video tracking system—A tool for behavioral phenotyping of transgenic mice”, Physiology & Behavior, Volume 73, Issue 5, pp. 731-744, 2001.
Spruijt, B., Pitsikas, N., Algeri, S. and Gispen, W. H., “Org2766 improves performance of rats with unilateral lesions in the fimbria fornix in a spatial learning task”, Brain Research, Volume 527, Issue 2, pp. 192-197, 1990.
Spruijta, B. and Gispen, W. H., “Prolonged animal observation by use of digitized videodisplays,” Pharmacology Biochemistry and Behavior, volume 19, Issue 5, pp. 765-769, 1983.
Taylor, I., Walton, P. and Young, .J, “The New Criminology for a Social Theory of Deviance,” Routledge, UK, 1973.
Tonga Y., Wang, Y., Zhuc, Z. and Jia, Q., “Robust facial feature tracking under varying face pose and facial expression,” Pattern Recognition, Volume 40, pp. 3195 – 3208, 2007.
Wang, L.H., “Report of the Eighteenth International Training Course,” Physical Protection of Nuclear Material and Nuclear Facilities, Atomy Energy Council, New Mexico, 2005.
Wei, C. P., “Data mining,” slides of course, National Tsing Hua University, 2009.
Witten, I. H. and Frank, E., “Data mining: practical machine learning tools and techniques,” Morgan Kaufman publisher, MA, 2005.
“The Physical Protection of Nuclear Material and Nuclear Facilities INFCIRC/225/Rev.4,” Physical Protection of Nuclear Material: Conference to Amend Convention (CPPNM), 1999.