Abstract

This paper introduces a new softwareoriented collaborative project-based learning approach to biomedical signal processing (BSP) for graduate biomedical engineering (BE) students. The course simulates industry-like practices under an imposed work environment and acquaints the participants with biomedical signal evaluation and quality assurance procedures required for software standardization. Background: Most academic approaches to teaching BSP focus either on acquisition procedures of electrophysiological data, predefined menu-driven signal processing methods using virtual laboratories, or ordinary SP procedures applied to biomedical signals without reaching the nature of the data and reflecting the future workplace. Methodology: The BE students individually code BSP procedures from scratch under teacher supervision, verify the results against the references and prepare reflective reports from their investigations. Students are involved in a simulated industry-like collaborative electrocardiogram signal processing project led by a project manager (PM) and assisted by a software architect (SA) and project coordinator (PC), with imposed working environment and standardization procedures. Research Questions: 1) Does implementing the BSP algorithms from scratch enable one to understand their nature thoroughly? 2) Does the simulated industry-like BSP course improve software engineering and soft skills via the hidden poll methodology? 3) Does including the PM, SA, and PC in the pipeline-dependent collaborative project positively result in its completion? The paper hypothesises that learning the BSP through a proposed project-based simulated industry-like approach with imposed work conditions improves understanding of BSP principles, computer programming skills and social competencies in developing a collaborative project. Findings: The participants significantly enriched BSP-related knowledge after the course, improved computer programming skills (p < .0001; non-parametric Wilcoxon Signed-Rank test), and enhanced soft skills in collaborative work (p < .001) and public presentations (p < .001). The course participants valued the role of algorithm prototyping stages and QA procedures according to official standardization rules. The PM and SA enabled the smooth software development process, while the PC has proven helpful in resolving intrinsic conflicts.