Seminar: I2MB – Validation of Activity Patterns in Buildings
Background
The I2MB simulator is a simulation engine that uses activities and behaviour descriptors to determine emergent behaviours of populations. I2MB is designed to provide insight into situations where we do not have the data to create evidence-based models. In particular, I2MB was designed to evaluate the effect of individual behaviours on the transmission of the COVID-19 virus. The simulator uses the current understanding of activity primitives, how routines and schedules determine a person’s possible actions, and how a person’s decision-making profile might influence compliance with current regulations. During I2MB development we have recognized that specific locations determine specific behaviours that might have consequences for virus transmission.
Aim
Working in a team, characterize the behaviour in buildings like stores, supermarkets, and schools, implement those behaviours into I2MB modules, and validate simulator performance using existing data.
Learning Objectives
- Gain an overview of epidemiological simulation strategies and agent-based strategies
- Explore and understand human behaviour in public places
- Apply different modelling strategies to behavioural data
- Develop team working and project management skills
- Create efficient behaviour models based on literature and collected data
Data
| Project type | Seminar |
| ECTS | 5 |
| Language | English |
| Period | Summer Semester 2022 |
| Presence time | Virtual seminar, working from remote |
| Useful knowledge | Python, data analytics |
| Work distribution | 20% data collection, 20% algorithm development, 30% data analysis and evaluation, 20% consultation, 10% reporting |
| Med. Eng. designation | Advanced Context Recognition (ACR) |
| StudOn link | Coming soon |
| First meeting | Coming soon |
| Registration | Via StudOn, obligatory after introduction. |
Literature
Up-to-date literature recommendations are provided during the lectures.
Examination
- Final project presentation, demonstrator and final report.
Contact
Dr. Luis I. Lopera G.
- Job title: Researcher
- Address: Henkestraße 91, Haus 7, 1. OG
91052 Erlangen
Germany - Phone number: +49 9131 85-23605
- Email: luis.i.lopera@fau.de