Winter Term 2022 / 2023

In recent years, various software and hardware tools have entered the consumer market which enable users to log data about their lives on a continuous basis. Popular examples include self-tracking devices or apps such as Fitbit or Garmin that allow users to keep track of their physical activities or to monitor their biometrics. The process of gathering such multimodal data from multiple sources is also referred to as lifelogging.

Due to the constant stream of data being captured, lifelogging can result in the creation of large personal archives that are too large for manual organization. Consequently, automated approaches to handle such data are needed. However, due to privacy concerns, advances in the field have been limited by the lack of shared test collections.

Aiming to promote further research on novel approaches to multi-modal personal data analytics and retrieval, the NTCIR Lifelog campaign, a comparative benchmarking exercise, was organised as part of the evaluation conference NTCIR [1]. Between 2015 and 2022, several Lifelog datasets were released, and participants could work on various sub-tasks to tackle different challenges related to Lifelog retrieval.

In this research lab, you are going to employ data mining and machine learning techniques to analyse a Lifelog dataset released in the context of NTCIR-Lifelog.

How to apply for enrolment

This research lab is offered to students enrolled in any of the Master programmes of Fachbereich 4. Prior knowledge of topics taught in the modules Introduction to Data Science and Machine Learning and Data Mining is expected.

In order to apply for enrolment, students are expected to form a team of four people and outline a short proposal (up to two pages) in which they outline their preferred Lifelog analytics task. Students looking for teammates can use our dedicated team-finding channel on Mattermost. This proposal should be sent to the module coordinator with the subject line “Lifelog Research Lab registration request” no later than 15^th October. In addition, the individual team members are expected to send their transcript in a separate email. After screening the proposals and transcripts, a maximum of three teams will be admitted to the research lab.

Reference

[1] Cathal Gurrin, Hideo Joho, Frank Hopfgartner, Liting Zhou, Rami Albatal, and Duc-Tien Dang- Nguyen. Experiments in Lifelog Organisation and Retrieval at NTCIR. chapter 13, pages 187-203. NTCIR: A Legacy of Research Impact, Springer Verlag, 2020

Lecturers