Introduction to AI-Enabled Wearable Technologies

About

This two-week summer school provides a comprehensive, hands-on introduction to wearable systems, from hardware and sensing fundamentals to data processing and basic artificial intelligence methods. You will be guided through the core building blocks of modern wearables, including physiological and motion sensors, embedded programming, and low-power wireless communication. Using an open-source wearable platform, the course emphasises practical understanding by allowing students to directly interact with raw sensor data and observe how signals are captured, transmitted, and logged in realistic scenarios.

You will learn essential signal processing techniques and gradually move toward simple machine learning and deep learning concepts commonly used in wearable applications such as activity recognition, health monitoring, and personalisation.

By understanding the technologies behind activity tracking, health monitoring, and adaptive user experiences, you will gain skills that are highly relevant to modern industry, research, and the future of digital health and smart devices.

This course is ideal for individuals from diverse backgrounds, including students, professionals, and enthusiasts looking to enhance their understanding of artificial intelligence and machine learning, particularly in the context of wearable technology

Course leader

Dariush Salami

Target group

Participants are encouraged to have an interest in programming, preferably in Python and C, but no prior coding experience is required.

A basic understanding of statistics and mathematics will be helpful, but is not essential. A willingness to learn and engage in hands-on activities, along with a curiosity about AI and wearable technologies, are the most essential prerequisites for this summer course.

The course is designed to be accessible to beginners, providing a supportive environment for all participants to explore the exciting applications of AI/ML in real-world scenarios of wearable technologies.

Participants must have completed a high school or vocational degree or equivalent by the time the course starts. However, they do not have to be a degree student at a university to participate in our courses.

Additionally, all summer school course students must be 18 years or older, as it is the legal age in Finland

Course aim

After completing the course, students will be able to:

Knowledge (Knowing)

Explain the fundamental concepts of wearable systems, including common sensing modalities (e.g., PPG, IMU, temperature), embedded hardware, and low-power wireless communication.

Describe the basic principles of bio signal characteristics, noise sources, and signal processing methods used in wearable applications.

Recognise the role of data-driven and AI-based methods in transforming raw wearable sensor data into meaningful health- and activity-related insights.

Skills (Acting)

Acquire, visualize, and log multimodal sensor data using an open-source wearable platform and basic embedded software tools.

Apply introductory signal processing techniques to wearable data in order to extract simple features in the time and frequency domains.

Implement and evaluate basic machine learning or neural network models to analyze wearable data for tasks such as activity classification or physiological estimation.

Work collaboratively in a small team to define a simple research or application question, design an analysis pipeline, and communicate results clearly through a project presentation.

Attitudes and Professional Identity (Being)

Demonstrate a problem-oriented and exploratory mindset when working with real-world wearable data, acknowledging limitations, noise, and variability.

Reflect on ethical, usability, and societal considerations related to wearable technologies and data-driven health applications.

Develop confidence in engaging with interdisciplinary topics that combine hardware, data analysis, and AI, supporting further studies in wearable systems, data science, or applied machine learning

Fee info