2026 ASEE Annual Conference & Exposition

With the rise in data availability and wearable technology, future engineers must be equipped to meet data processing demands as they enter the workforce. To help students fulfill this need, a new signal processing and machine learning course focused on biomedical applications was developed for senior electrical and computer engineering students. The course, designed using the backward design method, had as primarily objective to teach how to use signal processing and machine learning techniques to analyze physiological signals in a real time fashion.
In electrical and computer engineering curricula, courses such as “Signals and Systems” and “Digital Signal Processing” introduce students to the analysis and processing of signals, such as removing noise and understanding frequency content. Other courses, such as “Pattern Recognition” or machine learning and artificial intelligence classes, provide tools for extracting and recognizing patterns from data. However, these concepts are rarely presented from a comprehensive perspective, where signals in the physical word are collected by sensors connected to processing units that convert them from analog form to digital form, and further integrated with signal processing techniques combined with machine learning, especially in real-time scenarios. This paper will describe the approach that was taken to present students with a comprehensive perspective on the processing and analysis of physiological signals and to evaluate developed skills among students.
Overall, students participated in a well-rounded learning experience that blended theoretical concepts with practical applications. The course content was divided into two parts: the first focused on digital signal processing techniques and the second on machine learning techniques. For both sections, the implications of these algorithms for real-time processing were discussed. Specific physiological signals and their common processing analyses were also covered. Two exams assessed students' understanding of theoretical concepts and design implications, while a final project evaluated their ability to apply what they learned to process a physiological signal. Three in-class labs, which served as steppingstones for the final project, were also part of the course evaluation. Throughout the course, students practiced design, programming, research, and communication skills.
The body of this paper includes course learning objectives, a description of the course modules, major assessments (exams and final project description), minor assessments (minute papers, lab exercises in MATLAB, homeworks, and quizzes), description of grading rubrics, and students’ reflections and feedback. Students’ reflections, collected through minute papers at the end of every class and post-class surveys, demonstrate student engagement and understanding of the class material.