Recent Courses
- EECS 6/8980-Wireless Sensor Networks
- EECS 4/5740-Artificial Intelligence
- EECS 4/5750-Machine Learning
- EECS 6/8370-Artificial Neural Nets
- EECS 4000-Senior Design
- EECS 3100-Microsystem Design
- EECS 1100-Digital Logic Design
- EECS 2550-Operating Systems
Research Interests
Intelligent and adaptive wireless sensor networks, Design and development of "smart/intelligent algorithms, rule based systems, and agents" (knowledge based systems), Empirical model development through input/output data for blackbox systems or processes (machine learning), Classifier development through empirical means (learning from data) (pattern recognition, neural net and machine learning), Probabilistic knowledge base/inferencing model construction from data (Bayesian belief network), Hybrid intelligent systems for regression (linear and nonlinear) and classification: ensembles, Computation complexity analysis and management of algorithms (space and time cost of algorithms), Design and development of intelligent algorithms for real-time and/or distributed environments
Current Students
- PhD: J.Li
- MS: J. Sangtani, L. Liu and C. Dou
Biography
Dr. Serpen received a Ph. D. in Electrical Engineering (with specialization in computer engineering) from the Old Dominion University, Norfolk, Virginia in 1992. He worked as an application and senior software engineer for Integrated Systems, Inc. (acquired by WindRiver Systems, Inc in late 90s) of Santa Clara, California between 1992 and 1993. Since 1993, he has been serving as a faculty member with the Electrical Engineering and Computer Science Department at the University of Toledo.
Recent Publications
- D. Baumgartner and G. Serpen, “Comparative performance evaluation of global-local hybrid ensemble,” to appear in International Journal of Hybrid Intelligent Systems.
- D. Baumgartner and G. Serpen, “A design heuristic for hybrid ensembles,” to appear in Intelligent Data Analysis journal.
- G. Serpen and M. Riesen, “Knowledge discovery for query formulation for validation of a Bayesian belief network model of NCVS dataset,” Journal of Intelligent Learning Systems and Applications (JILSA), 2010.
- S. Pathical and G. Serpen, “Hybridization of base classifiers of random subsample ensembles for enhanced performance in high dimensional feature space,” International Conference on Machine Learning and Applications, Washington DC, 2010.
- J. Li, G. Serpen, S. Selman, M. Franchetti, M. Riesen, and C. Schneider, “Bayes net classifiers for prediction of renal graft status and survival period,” International Journal of Medicine and Medical Sciences, Vol. 1, No. 4, pp. 215-221, 2010.
- S. Pathical and G. Serpen, “Comparison of subsampling techniques for random subspace ensembles,” International Conference on Machine Learning and Cybernetics, Qingdao, Shandong, China, pp. 380-385, 2010.
- J. Sangtani and G. Serpen, “Automated composition of web service workflow: a novel QoS-enabled multi-criteria cost search algorithm,” International Conference on Evaluation of Novel Approaches to Software Engineering, pp. 62-67, Athens, Greece, 2010.
- D. Baumgartner and G. Serpen, “Fast preliminary evaluation of new machine learning algorithms for feasibility,” International Conference on Machine Learning and Computing, Bengalore, India, pp. 113-115, 2010.
- M. Riesen and G. Serpen, “Validation of a Bayesian belief network representation for posterior probability calculations on national crime victimization survey,” Artificial Intelligence and Law, Vol. 16, Issue 3, pp. 245-276, 2008.
- G. Serpen, D. K. Tekkedil, and M. Orra, “A knowledge based artificial neural network classifier for pulmonary embolism diagnosis,” Computers in Biology and Medicine, 2008 Feb; 38(2):204-220
