臺灣博碩士論文加值系統

本文從本國製造工業優勢得到自動化實驗平台的初步構想，而單純的自動化平台並不稀有，在國內有許多單位皆使用半自動化的實驗平台來進行科學研究。但是，半自動化平台仍需要研究人員長時間進行監控，平台本身也沒有中途檢測並發現錯誤的能力，本文設計以全自動化平台來釋放研究人員的時間。我們以執行生化實驗為第一目標，所以我們以簡易操作、高靈活度與應用性來設計平台，期望此平台能執行各種不同的實驗。我們共規劃三種可動平台與其它固定式裝置，分別是分析儀器更換升降台、液體處理器轉換平台、培養盤輸送器、儲放分析儀器的儲放架及實驗桌，上述皆是從零組件開始設計，並以CAD軟體繪製成CAD檔案後，匯入模擬軟體Webots中組建完成，對力學與運動軌跡加以規劃並模擬，軟體中可進行動力源與承載力的參數設定與測試，再考量各種實驗可能的問題點，在平台中架測感測裝置。藉由感測裝置與控制系統的雙向回饋系統希望平台擁有自主調整實驗參數與動作參數，並於控制系統中建置機器學習能力。本文設計的可動平台與其它裝置以成功在Webots軟體中組裝並進行測試，我們將對組裝完成平台進行最佳化調整與感測器系統初步建置，讓平台能得到最佳化的物理參數，以此參數在未來架設實體平台時能夠直接應用，減少實體平台建置時間及生化實驗的成本。

In this study, we take the advantage of precision manufacturing techniques combined with biotechnology to construct automated biochemistry platform. In this issue, it is popular in semi-automated platform in the world. In Taiwan, Many organizations have used semi-automated platforms for scientific researches. Amount of errors which were difficult to be corrected while the platform is working and the researchers still need to monitor the platform by themselves nowadays. In order to save the monitoring time of the researchers, we design a full automated biochemistry platform which contains three movable apparatus and two fixed ones, including Change lifts of apparatus, Conversion platform of liquid handling, Conveyer system of microtiter plate, Storage rack of apparatus and working bench. Firstly, we build the components of the platform by using CAD software, then, the models are imported to the simulation software, Webots. Secondly, we set the physical mechanics of the power and the carrier systems and then optimize the best motion of pathways and find out the best physical parameters in our structure. We put the sensors in both ends of the sport pathways and the feedback systems will auto-adjust the minor movement. And we will also build the machine learning in the controlling system. The results show that the designed automated biochemistry platform can achieve high performance with easy operation and high flexibility by simulation. This study provides optimized parameters and apply them to the construction of platform to speeding the building time. This will also lower the cost of biochemical experiments. We hope the automated biochemical platform can help scientists and researchers to decrease repetitive works, speed up their work and have more time to think their projects.

中文摘要 ............................................I
英文摘要 ...........................................II
致謝 ...........................................IV
目錄 ....................................i
表目錄 ...........................................iv
圖目錄 ............................................v
第一章 緒論 ....................................1
1-1 研究背景 ....................................2
1-1-1 藥物設計簡史 ............................2
1-1-2 機器人發展簡史 ............................7
1-1-3 自動化研究設備簡介 ............................9
1-2 研究動機 ...................................15
1-3 研究目的 ...................................16
1-4 研究方法 ...................................18
1-5 本文架構 ...................................19
第二章 文獻回顧 ...................................20
2-1 藥物設計概念 ...........................20
2-1-1 藥物研發過程 ...........................20
2-1-2 藥物目標解析 ...........................22
2-1-3 先導化合物（Lead Compounds） ...........24
2-1-4 虛擬篩選(virtual screening) ...........26
2-2 工業機器人 ...........................29
2-2-1 工業機器人系統機能 ...........................29
2-2-2 工業機器人手部運作原理 ...................39
2-2-3 機器學習歷史 ...........................51
2-2-4 機器學習原理 ...........................55
2-2-5 機器學習演算法 ...........................58
第三章 結構設計與模擬方法 ...........................70
3-1 Webots系統介面 ...........................70
3-2 使用方法 ...................................76
3-2-1 場景樹 ...................................76
3-2-2 控制程序編譯器 ...........................84
3-3 元件介紹 ...................................85
3-3-1 Shape ...................................85
3-3-2 Transform ...........................87
3-3-3 Solid ...................................88
3-3-4 Directional Light ...................90
3-3-5 Group ...................................91
3-3-6 DifferentialWheels ...................92
3-3-7 Robot ...................................94
3-3-8 Servo ...................................96
第四章 結果與討論 ...........................99
4-1 實驗桌與分析儀器儲放區塊 ..................100
4-2 分析儀器升降平台 ..........................103
4-3 液體處理器轉換平台 ..........................109
4-4 培養盤輸送器 ..........................112
第五章 結論 ..................................118
5-1 結論 ..................................118
5-2 未來展望 ..................................120
參考文獻 ..........................................125

[1]K. Chan, Progress in traditional Chinese medicine, Trends in Pharmacological Sciences, vol. 16, pp. 182-187, 6, 1995.
[2]B. Patwardhan, D. Warude, P. Pushpangadan, and N. Bhatt, Ayurveda and Traditional Chinese Medicine: A Comparative Overview, Evidence-Based Complementary and Alternative Medicine, vol. 2, pp. 465-473, Dec 2005.
[3]G. Gu and L. Yi, Shen Nong’s Herbal Classic, ed: University of Lanzhou Press, 2004.
[4]S. Li and X. Luo, Compendium of materia medica: bencao gangmu: Foreign Languages Press, 2003.
[5]C. Buff, J. Orantes, and P. L. Kirk, Paper electrophoretic identification of microquantities of some toxicologically significant alkaloids and comparison with chromatography, Microchemical Journal, vol. 3, pp. 13-18, 1959.
[6]G. Domagk, Chemotherapie der bakteriellen Infektionen, Angewandte Chemie, vol. 48, pp. 657-667, 1935.
[7]P. Ehrlich, Partial cell functions, Scandinavian Journal of Immunology, vol. 31, pp. 4-13, 1990.
[8]N. Møller and J. O. L. Jørgensen, Effects of growth hormone on glucose, lipid, and protein metabolism in human subjects, Endocrine reviews, vol. 30, pp. 152-177, 2009.
[9]T. Reimers, R. Cowan, J. McCann, and M. Ross, Validation of a rapid solid-phase radioimmunoassay for canine, bovine, and equine insulin, American journal of veterinary research, vol. 43, p. 1274, 1982.
[10]G. Walsh, Biopharmaceuticals: biochemistry and biotechnology: Wiley. com, 2006.
[11]P. Gramatica, Principles of QSAR models validation: internal and external, QSAR ＆ combinatorial science, vol. 26, pp. 694-701, 2007.
[12]M. Karelson, Molecular descriptors in QSAR/QSPR vol. 1: Wiley-Interscience New York, 2000.
[13]K. Čapek, RUR (Rossum's universal robots): Penguin. com, 2004.
[14]S. Schaut, Robots of Westinghouse: 1924-Today: Mansfield Memorial Museum, 2007.
[15]T. T. Leagues, Asimov’s Three Laws of Robotics, Advisory Editors, p. 20.
[16]J. G. Keramas, T. Schin, F. McAvey, and L. Produced By-Main, Robot technology fundamentals: Delmar Learning, 1998.
[17]R. D. King, K. E. Whelan, F. M. Jones, P. G. Reiser, C. H. Bryant, S. H. Muggleton, et al., Functional genomic hypothesis generation and experimentation by a robot scientist, Nature, vol. 427, pp. 247-252, 2004.
[18]L. N. Soldatova and R. D. King, An ontology of scientific experiments, Journal of the Royal Society Interface, vol. 3, pp. 795-803, 2006.
[19]M. Kanehisa and S. Goto, KEGG: kyoto encyclopedia of genes and genomes, Nucleic acids research, vol. 28, pp. 27-30, 2000.
[20]S. F. Altshul, T. L. Madden, A. Shaffer, J. Zhang, Z. Zhang, W. Miller, et al., Gapped BLAST and PSI-BLAST: a new search generation of protein database programs, Nucleic Acids Res, vol. 25, pp. 3389-3402, 1997.
[21]W. R. Pearson, Searching protein sequence libraries: comparison of the sensitivity and selectivity of the Smith-Waterman and FASTA algorithms, Genomics, vol. 11, pp. 635-650, 1991.
[22]R. D. King, S. Muggleton, R. A. Lewis, and M. Sternberg, Drug design by machine learning: The use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase, Proceedings of the national academy of sciences, vol. 89, pp. 11322-11326, 1992.
[23]A. Sparkes, W. Aubrey, E. Byrne, A. Clare, M. N. Khan, M. Liakata, et al., Review Towards Robot Scientists for autonomous scientific discovery, Autom Exp, vol. 2, 2010.
[24]R. D. King, S. H. Muggleton, A. Srinivasan, and M. Sternberg, Structure-activity relationships derived by machine learning: The use of atoms and their bond connectivities to predict mutagenicity by inductive logic programming, Proceedings of the National Academy of Sciences, vol. 93, pp. 438-442, 1996.
[25]C. Hansch, Quantitative structure-activity relationships in drug design, Drug design, vol. 1, pp. 271-342, 1971.
[26]T. Kindt, S. Morse, E. Gotschlich, and K. Lyons, Structure-based strategies for drug design and discovery, Nature, vol. 352, p. 581, 1991.
[27]T. P. Kenakin, T. P. Kenakin, and Kenakin, Pharmacologic analysis of drug-receptor interaction: Lippincott-Raven Philadelphia, 1997.
[28]C. McInnes, Virtual screening strategies in drug discovery, Current opinion in chemical biology, vol. 11, pp. 494-502, 2007.
[29]W. P. Walters, M. T. Stahl, and M. A. Murcko, Virtual screening--an overview, Drug Discovery Today, vol. 3, pp. 160-178, 1998.
[30]A. D. Andricopulo, R. V. Guido, and G. Oliva, Virtual screening and its integration with modern drug design technologies, Current medicinal chemistry, vol. 15, pp. 37-46, 2008.
[31]Y. Koren and Y. Koren, Robotics for engineers vol. 168: McGraw-Hill New York et al, 1985.
[32]N. Sharkey and A. Sharkey, Electro-mechanical robots before the computer, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 223, pp. 235-241, 2009.
[33]L. J. Everett and H. Tsing-Wong, The theory of kinematic parameter identification for industrial robots, Journal of dynamic systems, measurement, and control, vol. 110, pp. 96-100, 1988.
[34]G. Lundström, Industrial robot grippers, Industrial Robot: An International Journal, vol. 1, pp. 72-82, 1974.
[35]J. G. Carbonell, R. S. Michalski, and T. M. Mitchell, An overview of machine learning, in Machine learning, ed: Springer, 1983, pp. 3-23.
[36]J. R. Anderson, R. S. Michalski, R. S. Michalski, and T. M. Mitchell, Machine learning: An artificial intelligence approach vol. 2: Morgan Kaufmann, 1986.
[37]J. R. Quinlan, Learning efficient classification procedures and their application to chess end games, in Machine learning, ed: Springer, 1983, pp. 463-482.
[38]E. Feigenbaum and B. Buchanan, DENDRAL and META-DENDRAL: Roots of knowledge systems and expert system applications, Artificial Intelligence. v59 i1, vol. 2, pp. 233-240, 1994.
[39]R. E. Stepp and R. S. Michalski, Conceptual clustering of structured objects: A goal-oriented approach, Artificial Intelligence, vol. 28, pp. 43-69, 1986.
[40]R. S. Michalski and Y. Kodratoff, Research in machine learning, Machine learning: An artificial intelligence approach, vol. 3, pp. 3-30, 1990.
[41]H. Chen, Machine learning for information retrieval: neural networks, symbolic learning, and genetic algorithms, Journal of the American Society for Information Science, vol. 46, pp. 194-216, 1995.
[42]J. S. Albus, A new approach to manipulator control: The cerebellar model articulation controller, in (CMAC), Trans. Asme, Series G. Journal Of Dynamic Systems, Measurement And Control, 1975.
[43]H. B. Barlow, Unsupervised learning, Neural computation, vol. 1, pp. 295-311, 1989.
[44]D. E. Rumelhart, G. E. Hintont, and R. J. Williams, Learning representations by back-propagating errors, Nature, vol. 323, pp. 533-536, 1986.
[45]B. Widrow and M. A. Lehr, 30 years of adaptive neural networks: perceptron, madaline, and backpropagation, Proceedings of the IEEE, vol. 78, pp. 1415-1442, 1990.
[46]B. E. Boser, I. M. Guyon, and V. N. Vapnik, A training algorithm for optimal margin classifiers, in Proceedings of the fifth annual workshop on Computational learning theory, 1992, pp. 144-152.
[47]K. P. Murphy, Naive Bayes classifiers, ed: Technical Report, 2006.
[48]D. Wettschereck, D. W. Aha, and T. Mohri, A review and empirical evaluation of feature weighting methods for a class of lazy learning algorithms, Artificial Intelligence Review, vol. 11, pp. 273-314, 1997.
[49]H. Almuallim and T. G. Dietterich, Learning with Many Irrelevant Features, in AAAI, 1991, pp. 547-552.
[50]M. Dash and H. Liu, Feature selection for classification, Intelligent data analysis, vol. 1, pp. 131-156, 1997.
[51]L. C. Molina, L. Belanche, and À. Nebot, Feature selection algorithms: A survey and experimental evaluation, in Data Mining, 2002. ICDM 2003. Proceedings. 2002 IEEE International Conference on, 2002, pp. 306-313.
[52]T. K. Ho, The random subspace method for constructing decision forests, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 20, pp. 832-844, 1998.
[53]D. W. Opitz, Feature selection for ensembles, in AAAI/IAAI, 1999, pp. 379-384.
[54]P. Langley and H. A. Simon, Applications of machine learning and rule induction, Communications of the ACM, vol. 38, pp. 54-64, 1995.
[55]D. Michie, D. J. Spiegelhalter, and C. C. Taylor, Machine learning, neural and statistical classification, 1994.
[56]L. G. Heins and D. R. Tauritz, Adaptive resonance theory (ART): an introduction, published in, 1995.
[57]L.-J. Lin, Self-improving reactive agents based on reinforcement learning, planning and teaching, Machine learning, vol. 8, pp. 293-321, 1992.
[58]Z. Zhihua, C. Zhaoqin, S. Dong, and C. Shifu, THE DESIGN AND APPLICATION OF FAST ADAPTIVE CLASSIFIER FTART2, 1999.
[59]L. K. Hansen and P. Salamon, Neural network ensembles, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, pp. 993-1001, 1990.
[60]D. E. Goldberg and J. H. Holland, Genetic algorithms and machine learning, Machine learning, vol. 3, pp. 95-99, 1988.
[61]S. Chengyi, S. Yan, and X. Keming, Mind-evolution-based machine learning and applications, in Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on, 2000, pp. 112-117.
[62]C. M. Bishop and N. M. Nasrabadi, Pattern recognition and machine learning vol. 1: springer New York, 2006.
[63]M. E. Tipping, Sparse Bayesian learning and the relevance vector machine, The Journal of Machine Learning Research, vol. 1, pp. 211-244, 2001.
[64]A. Kandel, Fuzzy techniques in pattern recognition: Cambridge Univ Press, 1982.
[65]O. Michel, Webots-User Guide, Cyberbotics (http://www. cyberbotics. com), 1998.
[66]O. Michel, Webots, Reference manual, Users guide, ed.