Approaches to Affective Computing and Learning towards Interactive Decision Making in Process Control Engineering
-
摘要: 当今大量的工业过程控制工程问题, 如控制性能评价等的多目标决策问题通过人机交互得到解决. 然而, 在使用传统的交互式进化计算方法求解多目标决策问题时, 表现为局部搜索能力不强和过度依赖决策人员的主观意图. 本文提出一种新的情感计算方法和人机交互学习机制的解决方案. 提出一类基于刺激响应的情感计算模型(STAM), 并给出了情感空间和人的主观偏好之间的定量关系. 此外, 基于遗传算法框架, 建立情感交互学习策略, 旨在决策过程中逐步掌握人员的主观偏好, 降低人的疲劳程度, 使决策更加客观和科学. 附录A和B分别展示了情感学习算法的复杂度和收敛性分析. 为验证所提方法的正确性, 以测试函数及单回路反馈控制的PID参数整定问题进行研究, 得到了满意的结果, 验证了所提方法的可靠性与有效性.Abstract: Numerous multi-objective decision-making problems related to industrial process control engineering such as control and operation performance evaluation are being resolved through human-computer interactions. With regard to the problems that traditional interactive evolutionary computing approaches suffer i.e., limited searching ability and human's strong subjectivity in multi-objective-attribute decision-making, a novel affective computing and learning solution adapted to human-computer interaction mechanism is explicitly proposed. Therein, a kind of stimulating response based affective computing model (STAM) is constructed, along with quantitative relations between affective space and human's subjective preferences. Thereafter, affective learning strategies based on genetic algorithms are introduced which are responsible for gradually grasping essentials in human's subjective judgments in decision-making, reducing human's subjective fatigue as well as making the decisions more objective and scientific. Affective learning algorithm's complexity and convergence analysis are shown in Appendices A and B. To exemplify applications of the proposed methods, ad-hoc test functions and PID parameter tuning are suggested as case studies, giving rise to satisfying results and showing validity of the contributions.
-
[1] Zitzler E, Thiele L, Laumanns M, Fonseca C M, da Fonseca V G. Performance assessment of multiobjective optimizers: an analysis and review. IEEE Transactions on Evolutionary Computation, 2003, 7(2): 117-132[2] Peng H, Ling X. Optimal design approach for the plate-fin heat exchangers using neural networks cooperated with genetic algorithms. Applied Thermal Engineering, 2008, 28(5-6): 642-650[3] Lai C C, Chang C Y. A hierarchical evolutionary algorithm for automatic medical image segmentation. Expert Systems with Applications, 2009, 36(1): 248-259[4] John V, Trucco E, Ivekotic S. Markerless human articulated tracking using hierarchical particle swarm optimization. Image and Vision Computing, 2010, 28(11): 1530-1547[5] Burgoon J K, Bonito J A, Bengtsson B, Cederberg C, Lundeberg M, Allspach L. Interactivity in human-computer interaction: a study of credibility, understanding, and influence. Computers in Human Behavior, 2000, 16(6): 553-574[6] Jaimes A, Sebe N. Multimodal human-computer interaction: A survey. Computer Vision and Image Understanding, 2007, 108(1-2): 116-134[7] Serenko A. Are interface agents scapegoats? Attributions of responsibility in human-agent interactive. Interacting with Computers, 2007, 19(2): 293-303[8] St Amant R, Freed A R, Ritter F E. Specifying ACT-R models of user interaction with a GOMS language. Cognitive Systems Research, 2005, 6(1): 71-88[9] Picard R W. Affective Computing. London, England: MIT Press, 1997[10] Onony A, Clore G L, Collons A. The Cognitive Structure of Emotions. Cambridge, UK: Cambridge University Press, 1988[11] Wang Z L, Zhao Y L, Hao C H, Nagai M, Cui G W. An expert system of commodity choose applied with artificial psychology. In: Proceedings of the 2001 IEEE International Conference on Systems, Man, and Cybernetics. Tucson, AZ: IEEE, 2001. 2326-2330[12] Van Kesteren A J, op den Akker R, Pole M, Nijholt A. Simulation of emotions of agents in virtual environments using neural networks. In: Proceedings of the 20th Workshops on Language Technology 18. Enschede, the Netherlands, 2000. 137-147[13] Ishihara H, Fukuda T. Traffic signal networks simulator with learning emotional algorithm. In: Proceedings of the 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems. Takamatsu, Japan: IEEE, 2000. 2274-2279[14] Rudolph G, Agapie A. Convergence properties of some multi-objective evolutionary algorithms. In: Proceedings of the 2000 Congress on Evolutionary Computation. La Jolla, CA: IEEE, 2000. 1010-1016[15] Ishibuchi H, Yamamoto T. Fuzzy rule selection by multi-objective genetic local search algorithms and rule evaluation measures in data mining. Fuzzy Sets and Systems, 2004, 141(1): 59-88[16] Gacto M J, Alcalá R, Herrera F. A multi-objective evolutionary algorithm for an effective tuning of fuzzy logic controllers in heating, ventilating and air conditioning systems. Applied Intelligence, 2012, 36(2): 330-347[17] Fazzolari M, Alcala R, Nojima Y, Ishibuchi H, Herrera F. A review of the application of multi-objective evolutionary fuzzy systems: current status and further directions. IEEE Transactions on Fuzzy Systems, 2013, 21(1): 45-65[18] Seah C W, Ong Y S, Tsang I W, Jiang S W. Pareto rank learning in multi-objective evolutionary algorithms. In: Proceedings of the 2012 IEEE Congress on Evolutionary Computation. Brisbane, QLD: IEEE, 2012. 1-8
点击查看大图
计量
- 文章访问数: 1685
- HTML全文浏览量: 77
- PDF下载量: 1328
- 被引次数: 0