VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

252-0312-00L 6 Credits BSC , DR , MSC , WBZ , NDS D-BSSE , D-MAVT , D-INFK , D-PHYS , D-ERDW , D-MATH , D-ITET , D-HEST , D-GESS

Mobile Health and Activity Monitoring

Lecturers & Examiners: Prof. Dr. Christian Holz
VVZ CR 4.1

Last Updated: 2026-06-03 00:14:06

Abstract

Mobile and wearable devices (phones, watches, rings) increasingly support health and activity monitoring. Course topics include sensing user behavior and activity, actions, and basic physiology, plus the sensors, signals, and methods to collect, process, and model the data. This includes affect-related and camera-based sensing within a mobile health and behavioral focus.

Objective

By the end of the course, students will be able to: - Identify common sensing modalities used in mobile health and interactive systems, and the signals they produce (e.g., inertial, optical, electrophysiological, acoustic, camera-based). - Explain how user behavior and activity, basic cardiovascular and pulmonary physiology, and affective states relate to measurable sensor signals. - Implement a basic sensing pipeline, including sampling, filtering, feature extraction in time and frequency domains. - Analyze multimodal recordings to segment activities or events, quantify signal quality, and interpret physiological and affect-related indicators in context. - Compare and justify suitable sensing and modeling choices for a given mobile health problem, including trade-offs in accuracy, robustness, privacy, power, and feasibility. - Conceptually design a small end-to-end behavior modeling or health monitoring solution using wearable or phone sensing.

Content

Health and activity monitoring has become a key purpose of mobile and wearable devices, including phones, (smart) watches, (smart) rings, (smart) belts, and other trackers (e.g., shoe clips, pendants). In this course, we cover the fundamental aspects that these devices observe, i.e., user behavior and activity, actions, and physiological dynamics of the human body, as well as the sensors, signals, and methods to capture, process, and analyze them. We then cover methods for pattern extraction, behavior modeling, and classification on such data. The course touches on human activities, basic cardiovascular and pulmonary physiology, affective computing as it relates to mobile health (recognizing and interpreting emotion-related signals), corresponding lower-level sensing systems (e.g., inertial sensing, optical sensing, photoplethysmography, electrodermal activity, electrocardiograms), and camera-based sensing via computer vision (e.g., facial expressions, motion, gestures), along with processing methods for these data types. The course is accompanied by a group exercise project in which students apply the concepts and methods taught in class. Students receive a wearable wristband device that streams IMU data to a mobile phone (code is provided for receiving, storing, and visualizing on the phone). Throughout the course and exercises, we collect data for various human activities from the band, annotate them, analyze them, and build models for detection and classification. Students will develop and adapt processing methods based on collected data and existing datasets, and optionally combine wristband data with signals obtained from the mobile phone to more holistically capture and analyze behavior, activity, and health-related signals.

Resources

Lecture Notes

Copies of the slides will be made available. Related work and further reading will be provided.More information on the course site:https://siplab.org/courses/mobile_health_activity_monitoring/2026

Literature

Will be provided in the lecture

Learning Materials (Links)

General Information

Language
English
Levels
BSC , DR , MSC , WBZ , NDS
Frequency
Yearly recurring

Examination

Type
end-of-semester examination
Mode
written 90 minutes
Aids
One handwritten two-sided A4 sheet and a non-programmable calculator.
Digital
The exam takes place on devices provided by ETH Zurich.
The end-of-term exam will be a computer-based presence exam at ETH facilities. The exam platform will be Moodle.The exam will count 50% of the final grade. The practical exercise counts for the remaining 50% of the final grade. The exercise assignment is mandatory and will need to be submitted on time during the term.

Course Components

Type Title Time & Place Hours
lecture Mobile Health and Activity Monitoring
TA-Meeting: Mondays, 2 March - 13 April 2026, time tba, room tba
  • Mon 14:15-16:00 (CAB G 11)
2 h weekly
independent project Mobile Health and Activity Monitoring No time listed 3 h weekly

Offered In