For the last 12 years Dr. Musavi has been involved in development and research in the areas of neural networks, computer vision and robotics. His specialties are in development of intelligent computer systems to automate industrial tasks for increased efficiency and cost-effectiveness. He has collaborated with many local industries including James W. Sewall Company, Digital Equipment Corporation, National Semiconductor, Shape Industries, The Jackson Laboratory, S.D. Warren Company, and Dexter Shoe Company. Most recently he has developed an automated system for converting hard copy maps into computer readable codes and has tested and evaluated a digital image processing workstation. Some of Dr. Musavi\'s current projects are: 1) classification of mouse chromosomes using artificial neural networks, 2) extraction of drainage networks from digital elevation data, 3) registration of satellite images by neural networks, 4) prediction of K in wood pulp digester process, and 5) development of intelligent system expertise in Maine. His current research and development efforts are funded by the Department of Energy and the Maine Science and Technology Foundation (DOE/MSTF), Rome Laboratory (RL), the Air Force Office of Scientific Research (AFOSR), and the Dexter Shoe Company. He has published over 50 technical papers and is a member of IEEE, Eta Kappa Nu, Tau Beta Pi and Sigma Xi.

Publications

• Hummels, D.M., W. Ahmed, and M.T. Musavi, "Adaptive Detection of Small Sinusoidal Signals in Non-Gaussian Noise Using RBF Neural Networks," IEEE Trans. on Neural Networks, Vol. 6, No. 1, Jan. 1995. Musavi, M.T., K.H. Chan, D.M. Hummels and K. Kalantri, "On the Generalization Ability of Neural Network Classifiers," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 6, June 1994. Sweeney Jr., W.P., M.T. Musavi, and J.N. Guidi, "Classification of Chromosomes Using a Probabilistic Neural Network," Cytometry, Vol. 15, Issue 5, May 1994.

[Edit my profile]