University of Cambridge > > Computer Laboratory Systems Research Group Seminar > Computational Behavior Analysis through Wearables and Machine Learning -- Pushing the Boundaries towards usable Digital Health.

Computational Behavior Analysis through Wearables and Machine Learning -- Pushing the Boundaries towards usable Digital Health.

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Marco Caballero.

Abstract: We live in an era in which the number of smartphones is now greater than the number of humans living on Earth. As such, the field of mobile and ubiquitous computing is transforming many—if not all—areas of our lives. With the next wave of technological breakthroughs now wearables, such as smartwatches but also head-worn devices, are becoming mainstream. This overall transformation has great potential for many application areas. Most prominently, it is now possible to continuously and unobtrusively record rich behavior data that can inform objective health assessments thereby serving as basis for improved care and treatment, and thus wellbeing.

The basis for effective health assessments are robust and reliable methods for human activity recognition—more generally referred to as sensor-based Computational Behavior Analysis (CBA). From a technical perspective the analysis task translates into a time-series assessment problem, yet with a number of domain-specific constraints and requirements. In this talk I will explore these specific challenges and give an overview of work in our group that is pushing the boundaries of CBA with specific focus on usable Digital Health. In response to challenges such as noisy sensor data, ambiguous ground truth annotation, and typically limited size sample datasets we have developed and validated sensor data analysis and machine learning methods that focus on these domain specifics and thus enable effective operation. I will illustrate how the constraints and requirements of real-world application scenarios have allowed me and my team to push the boundaries of core sensor data analysis research.

Bio: Thomas Ploetz is a Computer Scientist with expertise and more than 15 years of experience in Pattern Recognition and Machine Learning research (PhD from Bielefeld University, Germany). His research agenda focuses on applied machine learning, that is developing systems and innovative sensor data analysis methods for real world applications. Primary application domain for his work is computational behaviour analysis where he develops methods for automated and objective behaviour assessments in naturalistic environments, thereby making opportunistic use of ubiquitous and wearable sensing methods. Main driving functions for his work are “in the wild” deployments and as such the development of systems and methods that have a real impact on people’s lives.

In 2017 Thomas joined the School of Interactive Computing at the Georgia Institute of Technology in Atlanta, USA where he works as an Associate Professor of Computing. Prior to this he was an academic at the School of Computing Science at Newcastle University in Newcastle upon Tyne, UK, where he was a Reader (Assoc. Prof.) for “Computational Behaviour Analysis” affiliated with Open Lab, Newcastle’s interdisciplinary research centre for cross-disciplinary research in digital technologies.

This talk is part of the Computer Laboratory Systems Research Group Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity