Homepage Mannes Poel
I am a senior reseacher at the Human Media Interaction group of the department of Computer Science of the University of Twente. I have a background in pure mathematics and theoretical computer science. After working several years on verification of concurrent processes my interest shifted towards Neural Networks, Machine Learning and Artificial Intelligence. At the moment my research focuses on Machine Learning in the context of Human Behavior Computing, including Brain Computer Interfaces (BCI). Currently I supervise several PhD students in these area's. I have co-authored several papers on Machine Learning in Human Media Interaction and Brain Computer Interaction, some of them also focusing on affective dialogue management.
My publications can be found on the Publication page of the HMI website
Currently my research focuses on the application of Machine Learning in
Human Behaviour Computing and Brain Computer Interfaces (BCI).
Related projects, in which HMI participates, are:
Future BNCI is a project devoted to helping BCI research and the BCI research community. We are also exploring future directions with BCIs and a newly emerging class of systems called BNCIs
The Dutch National Project BrainGain .
Brain-Computer and Computer-Brain Interfaces: devices for detecting and modifying brain activity.
Detecting and modifying brain activity is currently one of the fastest developing areas of research. It promises to bring applications that have long been thought to be only science fiction, ranging from mind-controlled computer games to so-called mental prostheses and treatment for conditions previously thought untreatable.
BrainGain is a Dutch research consortium consisting of researchers, industry and potential users of Brain-Computer and Computer-Brain interfaces. The program started in September 2007 and is funded by SmartMix, a Dutch initiative to support applied research. BrainGain is researching possibilities of applications for both ill and healthy users, and aims to eventually manufacture off-the-shelf products making use of their research results.
SSPNet is a European Network of Excellence fostering and supporting research activities in Social Signal Processing, the new, emerging domain aimed at bringing Social Intelligence in computers.
The project SERA (Social Engagement with Robots and Agents) aims to advance science in the field of social acceptability of verbally interactive robots and agents, with a view to their applications especially in assistive technologies (companions, virtual butlers). To this aim, the project will undertake a field study in three iterations to collect data of real-life, long-term and open-ended relationships of subjects with robotic devices. The three iterations test different conditions (functionalities) of the equipment, which will consist of a room equipped with sensors at the subjects’ home, a computer and a simple robotic device (the Nabaztag) as the front-end for interaction. The project partners will analyse the collected audio and video data in parallel, using different, mainly qualitative, methods. Data analysis will be prepared and accompanied by theoretical and methodological research in order to a) take into account the state of the art and b) ensure quality of the field study. The project will use findings from the field study to specify, build and implement a reference architecture for social engagement, and use it for developing a showcase system of combined speech based service applications with relevance to the target field and audience.
The AMIDA project is concerned with new multimodal technologies to support human interaction, in the context of smart meeting rooms and remote meeting assistants. The project aims to enhance the value of multimodal meeting recordings and to make human interaction more effective in real time. These goals are being achieved by developing new tools for computer supported cooperative work and by designing new ways to search and browse meetings as part of an integrated multimodal group communication, captured from a wide range of devices.
Agenda Mannes Poel
(in Dutch and only accessible from the UT domain!)