My current research is looking the integration of emerging, or novel, sensors in to personal informatics systems.
This research seeks to address questions such as:
- What are the expectations of users of novel sensors within the context of a PI tool?
- How do users of personal informatics systems, both experienced and new, integrate the data from novel sensor?
- What design opportunities are there, in terms of both UI and data visualisations? Can the data be presented in such a way as to afford users with actionable insights?
- Can machine learning/data science help to achieve this?
Machine Learning/Data Science
I am keen to explore the opportunities enabled by advances in machine learning and the abundance of data that can be exploited.
For my undergraduate final project I integrated a BCI and remote controlled car as well as some basic machine learning to determine it’s ability to improve the ability to detect users movement. More details are provided here.
For my Masters degree in Advanced Computer Science my thesis sought to determine if it was possible to use Kohonen Networks (Self-Organising Maps) to detect whether the content of documents flowed “well”.
I have a firm belief that brain-computer interfacing is the next movement likely to move forward in human-computer interaction. As the humble mouse ushered in greater and easier interaction between man and machine, followed by touchscreen, BCI is a form of human-computer interaction that will allow greater access to technology for more people, but also provides a novel form of interaction for able-bodied users too.
Extended Abstracts / Workshop Papers
Cillian Dudley and Simon L. Jones. 2018. Fitbit for the Mind?: An Exploratory Study of ‘Cognitive Personal Informatics’. In Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems (CHI EA ’18). ACM, New York, NY, USA, Paper LBW542, 6 pages. DOI: https://doi.org/10.1145/3170427.3188530