Robert Steele (Professor, Florida Polytechnic University, USA)
Professor Robert Steele serves as a Full Professor of Data Analytics and Director of the Health Informatics Institute at Florida Polytechnic University, Lakeland, Florida, USA. Dr. Steele holds a PhD. in Computer Science, has authored over 130 peer-reviewed research publications and his work has also been patented and successfully commercialized. He has been awarded and led numerous external competitively funded research projects, along with numerous industry collaborations. His research interests include data analytics, distributed systems, health informatics and cyber-physical systems. He has also previously served as the Vice Chair of ACM SIGMOBILE the premier international community for mobile and pervasive computing research.
Keynote Title: Data Science-driven Design of Emerging Informatics Systems
Abstract: Predictive models can enable the prediction of target values for previously un-seen input sets. Historically the volume of available digitized data has been significantly lower and the processing power of machines comparatively less. In the past decades, this has contributed to limiting the domains that predictive models could be applied to and the impact and value of these models when applied. Similarly, the application of such models to improve the operation of real-world systems in various business and consumer domains, with the goal of having these systems improve or ‘learn’ over time, has faced concomitant limitations. The Internet-of-Things represents a transformative development in the role and domains of application of predictive models, with this current era of research providing the opportunity for great achievements and the development of new capabilities and methodologies to benefit society. The Internet-of-Things is not a single system nor a system emerging from a ‘big bang’ implementation, but rather is evolving via an incremental and increasing pervading of sensing, computation and actuation capabilities into the physical world and the entities within it. This represents a significant advancement in data acquisition, processing and predictive capabilities. The Internet-of-Things will support the acquisition of new types of datasets with greater ranges of attributes and domains of application, but to-date there is still often a mismatch between the sensor data collected and the needs of predictive models. This talk will cover current research drawing from the different knowledge domains of health informatics and other sectors, data science and the Internet of Things, to outline new possibilities for predictive and learning systems.