David is an adaptive media researcher and entrepreneur. In his early career and doctoral work, he looked to computational intelligence, in particular genetic co-evolution, to create reflexive media systems that imitated and queried the nature of human creativity.He created the first European merger for Open Source startups and helped the National Health Service deploy the first mobile application to let users self-report in chronic illness.He has given papers and performances at the International Computer Music Conference, the European Conference on Artificial Life, IRCAM, the Darwin Symposium, and the Computer Arts Society in London, and more recently, has published on human emotion in play (affective modelling for games) in IEEE Computational Intelligence transactions and the International Conference on Creative Computing proceedings.His teaching focuses on software and hardware practices for digital media and core practices in Open Source and Open Innovation within startup culture.His industrial work, which has focused on creating mobile applications for self-reporting and behaviour change in mental health, is now focused on biobeats.com, a startup in San Francisco/London/Pisa that builds artificial intelligence solutions for large health platforms, including projects that address how decentralized digital currencies could offer derivative exchange value in health insurance for an individual's biometric data.
- Adaptive media algorithms as healthcare industry disruptors (SXSW'13 Accelerator)
- Better media discovery through biometric algorithms (won Echo Nest prize)
- Large-scale content-based retrieval for audiovisual archives (achieved 500K funding so far)
- Procedural audiovisual content generation for games engines (published IEEE journal papers)
- Cryptocurrency-based value exchange systems in healthcare data
uploaded to online repositories and made available under open licenses. Moreover, a constantly increasing amount
of multimedia content, originally released with traditional licenses, is becoming public domain as its license expires.
Nevertheless, the creative industries are not yet using much of all this content in their media productions. There is
still a lack of familiarity and understanding of the legal context of all this open content, but there are also problems
related with its accessibility. A big percentage of this content remains unreachable either because it is not published
online or because it is not well organised and annotated. In this paper we present the Audio Commons Initiative,
which is aimed at promoting the use of open audio content and at developing technologies with which to support
the ecosystem composed by content repositories, production tools and users. These technologies should enable the
reuse of this audio material, facilitating its integration in the production workflows used by the creative industries.
This is a position paper in which we describe the core ideas behind this initiative and outline the ways in which we
plan to address the challenges it poses.
Physiological-Monitoring Device, Healthcare Technology Letters 5 (2) pp. 59-64 Institution of Engineering and Technology
studies of their performance when measuring the physiology of ambulatory patients. In this paper, we investigate the reliability of the heartrate
sensor in an exemplar ?wearable" wrist-worn monitoring system (the Microsoft Band 2); our experiments quantify the propagation of
error from (i) the photoplethysmogram (PPG) acquired by pulse oximetry, to (ii) estimation of heart rate (HR), and (iii) subsequent calculation
of heart rate variability (HRV) features. Our experiments confirm that motion artefacts account for the majority of this error, and show that
the unreliable portions of heart rate data can be removed, using the accelerometer sensor from the wearable device. Our experiments further
show that acquired signals contain noise with substantial energy in the high-frequency band, and that this contributes to subsequent variability
in standard HRV features often used in clinical practice. We finally show that the conventional use of long-duration windows of data is not
needed to perform accurate estimation of time-domain HRV features.
learning using Extreme Learning Machine networks, relaying on limited
and subject-dependant information concerning pairwise relations between
data samples. We describe an application within the context of assessing
the effect of breathing exercises on heart-rate variability, using a dataset
of over 19K exercising sessions. Results highlight the importance of using
weight sharing architectures to learn smooth and generalizable complete
orders induced by the preference relation.