OMSCS Seminar: Machine Learning for Sensor-Based Human Activity Recognition

  • Overview
  • Course Content
  • Requirements & Materials
Overview

OMSCS Seminar: Machine Learning for Sensor-Based Human Activity Recognition

Course Description

Human activity recognition (HAR) is the task of collecting data using on-body wearable and/or ubiquitous ambient sensors and recognizing human activities of interest. In this seminar, we will study how machine learning can be applied to address challenges in HAR. This seminar will consist of three units:

1. The HAR pipeline (training machine learning models in time-series sensor data)

2. Recent advances in HAR (a case study of self-supervised learning for HAR)

3. Future research directions in HAR with multimodal foundation models

Course Content

The HAR chain:

  • Conventional ML and DL approaches for sensor-based HAR
  • Self-supervised learning for sensor-based HAR
  • HAR with multimodal foundation models.
Requirements & Materials

Prerequisites

RECOMMENDED:

  • PyTorch and Jupyter Notebook

REQUIRED:

  • Foundations in Python programming, machine learning, and deep learning

Materials

PROVIDED (Student will receive):

  • Lecture slides, research papers, and codebase

Session Details

Who Should Attend

This seminar is designed for OMSCS students and alumni who work as data scientists, machine learning engineers, and researchers. It is also ideal for advanced practitioners with a foundation in machine learning who are interested in exploring cutting-edge research in human sensing.

Computer science students coding on computers

What You Will Learn

The 5-step HAR pipeline:

  • An introduction to conventional machine learning (ML) and deep learning (DL) approaches for HAR
  • Basics of self-supervised learning
  • Self-supervised pretext tasks for representation learning on time-series sensor data
  • Application of foundation models, LLMs, and other multimodal pre-trained resources for HAR Implementation of a subset of approaches
  • Writing research proposals for new research ideas.
Female professional in computer science lab looking at tablet

How You Will Benefit

  • Develop a solid foundation in working with real-world sensor data.
  • Understand how to conduct research on the state-of-the-art techniques in the field.
  • Become familiar with tutorial workshops embedded in the course schedule.
  • Analyze guest lectures from leading experts in industry and academia.
  • Grow Your Professional Network icon
    Grow Your Professional Network
  • Taught by Experts in the Field icon
    Taught by Experts in the Field

TRAIN AT YOUR LOCATION

We enable employers to provide specialized, on-location training on their own timetables. Our world-renowned experts can create unique content that meets your employees' specific needs. We also have the ability to deliver courses via web conferencing or on-demand online videos. For 15 or more students, it is more cost-effective for us to come to you.

  • Save Money
  • Flexible Schedule
  • Group Training
  • Customize Content
  • On-Site Training
  • Earn a Certificate
Learn More

Want to learn more about this course?