BME 313: Wearable Devices: From Sensing to Biomedical Inference



BME 207, 220**


Wearable sensors are transforming biomedicine. From cellphones to smartwatches to the cutting-edge devices being developed in Northwestern laboratories, wearables that can record physiological and biological data in real-world settings are changing personal habits and medical practice. While the potential of wearable devices is widely appreciated, harnessing that potential requires an ability to infer health-related information from the vast amounts of data that can now be collected. This course will review the challenges and opportunities associated with using wearable devices to infer biomedical information about individuals and populations. It will cover techniques from signal processing, machine learning, and artificial intelligence relevant to this objective. Content will be taught using a series of projects relevant to the quantification of human movement and rehabilitation medicine. Projects will incorporate data acquisition with wearable devices, signal processing, machine learning, and artificial intelligence.

Course Objectives

By the end of this course, students will be expected to

  • Gain an appreciation for the benefits, limitations, and challenges of using wearable devices for biomedical applications
  • Understand some common principles of signal transduction, data acquisition, and sensor characterization relevant to wearable devices
  • Apply signal processing to condition data collected from wearable devices
  • Use model-based inference to estimate physiological variables using data collected from wearable sensors
  • Understand how machine learning and artificial intelligence can be used to infer the biological state of individuals and populations from wearable sensor data

Who Takes It?

This course is intended for undergraduate or graduate students in BME or other McCormick departments. It should typically be taken in the junior year or later. 


  1. Background on current state of wearable technology
  2. Fundamentals of sensing and data acquisition
  3. Signal processing and conditioning for wearables
  4. Model-based inference for small-scale wearable data sets
  5. Artificial intelligence and machine learning for processing massive amounts of wearable data 

Textbook/Required Materials


**Pre-Reqs: Additional Info

BME 207 - BME Lab: Experimental Design or an equivalent course covering introductory principles of sensing and error propagation

BME 220 - Introduction to Biomedical Statistics or equivalent introductory statistics course covering point and interval estimations, and linear regression  Students should be proficient in Python programming, as taught in the above courses

**Contact instructors if you are unsure that your background is sufficient