Duration: from 5 hours(incl. lunch break.)

Contents: methods from the field of AI (machine learning), metrics, acceleration
Previous knowledge: Euclidean distance (3D), vectors, magnitude of a vector
Participants: Mathematics courses from grade 11
Created by: Katja Hoeffer, Sarah Schönbrodt
Registration: Dates can be arranged individually using this form.

Mobile devices, such as smartphones, have become constant companions in our everyday lives. Around 3.6 billion people worldwide use a smartphone. In addition, interest in evaluating people's habits and daily routines has increased in recent years. This includes, among other things, the analysis of the activities performed. With the tremendous advancement of sensors in smartphones, they can be used to detect human activities. But how does activity recognition work and what does it have to do with math?

In this workshop, students:will work with real activity data and develop their own mathematical model for activity recognition. In doing so, they use current methods from the field of artificial intelligence.

Image source: https://br.atsit.in/de/wp-content/uploads/2021/05/so-sehen-sie-in-der-fitness-app-fur-das-iphone.jpg

The following mathematical contents are required as prior knowledge for the processing of the learning material:

• Euclidean distance between two points (3D)
• vectors
• magnitude of a vector

All other mathematical contents are introduced in the learning material in a problem-oriented way.

Page in progress

The interactive learning material can be accessed via the online platform workshops.cammp.online. How to create an account on the platform and use the
material is explained in this video. In addition, accompanying material is provided for teachers on the online platform, which can be accessed via a password that can be requested by e-mail.

• Hoeffer, K.: Aktivitätserkennung auf dem Smartphone - Entwicklung von Unterrichtsmaterial für computergestützte mathematische Modellierungsprojekte, Master's thesis, KIT.