Time Sequences Classification using Classification Learner (MATLAB based)

Department of Engineering

Seminar Report

Title: Time Sequences Classification using Classification Learner (MATLAB based)

The seminar titled “Time Sequences Classification using Classification Learner (MATLAB based)” was conducted online via MS Teams on 1st May 2025, from 2:00 PM to 3:00 PM. The session was led by Dr. Pratapa Raju M., Ph.D., from the University of Technology and Applied Sciences (UTAS), Ibra. This insightful seminar provided a comprehensive introduction to the classification of time sequences using MATLAB’s Classification Learner app.

Dr. Raju, an expert in the application of artificial intelligence and machine learning in engineering, highlighted the growing significance of time sequences—data points collected over time—in solving problems in power systems, biomedical signal analysis, mechanical diagnostics, and environmental monitoring. He emphasized how AI and ML techniques can be effectively leveraged to classify and analyze time-dependent data in these diverse fields.

The seminar detailed the use of MATLAB’s Classification Learner app, a user-friendly tool designed to streamline the machine learning process without requiring advanced programming skills. Participants were introduced to the process of building and evaluating machine learning models for time series classification using this app.

A major highlight of the session was the live demonstration of the Classification Learner pipeline. Dr. Raju walked participants through the steps of loading sample data, training models, validating results, and evaluating performance metrics. He also presented real-world case studies from electrical, biomedical, and mechanical systems, showcasing the practical applications of time sequence classification.

Targeted at faculty members, researchers, postgraduate students, and industry professionals in fields related to AI, signal processing, and engineering, the seminar offered valuable, hands-on insights. The session’s visual, practical approach to machine learning made the content accessible even to those with limited coding experience.

By the end of the session, attendees had acquired the knowledge and confidence to use the Classification Learner app for their own time sequence data. The seminar successfully combined theoretical concepts with practical demonstrations, empowering participants to integrate machine learning techniques into their work.

In conclusion, the seminar was a well-rounded and informative experience. Dr. Pratapa Raju M.’s clear explanations, engaging presentation style, and live examples significantly enhanced the learning experience, making this session a valuable opportunity for anyone interested in the practical application of AI and ML in engineering contexts.