Area of Study / Keywords
Signal and Image Processing Software Engineering and Intelligent Systems
Scott Dick received his B.Sc. degree in 1997, his M.Sc. degree in 1999, and his Ph.D. in 2002, all from the University of South Florida. His Ph.D. dissertation received the USF Outstanding Dissertation Prize in 2003. He was an Assistant Professor from 2002 - 2008, an Associate Professor from 2008 - 2018, and a Professor since 2018, all with the Department of Electrical and Computer Engineering at the University of Alberta in Edmonton, AB. He has also been the Program Director for Computer Engineering since 2017. Dr. Dick has published over 80 scientific articles in journals and conferences, and is a member of the ACM, IEEE, and ASEE.
Dr. Dick’s research interests are broadly in the areas of computational intelligence (fuzzy logic and neural networks), machine learning, and data mining, as well as the interdisciplinary application of these technologies. His main theoretical interests are in multivalued logics (particularly the new area of "complex fuzzy logic"), deep learning approaches based on them, and Explainable Artificial Intelligence (XAI). Some of his past applied research includes software reliability, proteomics, and livestock disease surveillance. Ongoing applied research projects include condition monitoring in pipelines and electric power distribution networks, Smart Grid applications, and railway operations optimization.
I teach courses for the Computer Engineering: Software Option degree stream. I presently teach the capstone design course for the Software Option (ECE 493). In the graduate program, I teach the Neural Networks specialty course (ECE 626).
We welcome project suggestions for both ECE 493 and ECE 626 from members of the University community, industry, government, and all other organizations. Students are free to choose a proposed project or another of their choosing, so bring your most interesting ideas - you are competing for mind share! Please contact Dr. Dick directly for further information.
Projects in ECE 493 should be a discrete software system. The project proponent and one student group will collaboratively write a Software Requirements Specification (IEEE Std. 830) defining the detailed scope of work.
Projects in ECE 626 should be a defined machine learning problem, with an anonymized non-confidential dataset (if a confidential data-sharing agreement is necessary, proponents MUST contact Dr. Dick well in advance of the start of term), as well as a data dictionary and detailed description of the machine learning task (the documentation for a Kaggle competition would be a good example). The dataset, and all ancillary materials, will be provided to volunteering ECE 626 students.
Design of software systems from concept to working prototype. Applying software engineering techniques. Working in small groups under constraints commonly experienced in industry. Exposing each team member to the design, implementation, documentation, and testing phases of the project. Managing software development projects. Provides a capstone experience in software development processes. Prerequisite: ECE 421 or CMPE 410. Credit may be obtained in only one of CMPE 440 or ECE 493.
Introductory and advanced topics in neural networks and connectionist systems. Fast backpropagation techniques including Levenberg-Marquardt and conjugate-gradient algorithms. Regularization theory. Information-theoretic learning, statistical learning, dynamic programming, neurodynamics, complex-valued neural networks.