Prof.Dr.Halit Hami ÖZ
İstanbul Gedik University
Title: Medical Internet of Things (mIoT) Sensing and Cloud Based Remote Health Monitoring
Bio:
Prof. Dr. Halit Hami Öz, after graduating from Pertevniyal High School in Istanbul, graduated from Istanbul University, has a Master of Science (M.Sc.) degree from the University of Illinois at Urbana-Champaign, IL, USA, PhD from the University of Minnesota at St. Paul-Minneapolis, MN, USA and worked as Assistant Professor at Louisiana State University, Baton Rouge, Louisiana, USA for two years. Upon returning home, he worked at Marmara University, Akdeniz University, European University of Lefke, Istanbul Aydin University ( Head of Dept. of Software Engineering for 6 years), Kafkas University, and currently working at İstanbul Gedik University, Faculty of Engineering, Head, Dept. of Computer Engineering, Head, Artificial Intelligence Engineering Program, since 19th August 2019.
Abstract:
As the global population ages, mIoT will become increasingly important. Devices that constantly monitor health indicators, devices that auto-administer therapies, or devices that track real-time health data when a patient self-administers a therapy can reduce overall costs for the prevention or management of chronic illnesses. Today patients having access to high-speed Internet and smartphones have started using mobile applications (apps) to manage various health needs. These devices and mobile apps are now increasingly used and integrated with telemedicine and telehealth via the medical Internet of Things (mIoT). Networked sensors, either worn on the body or embedded in our living environments, make possible the gathering of rich information indicative of our physical and mental health. mIoT is a critical piece of the digital transformation of healthcare. It can: (a) facilitate an evolution in the practice of medicine, from the current post facto diagnose-and-treat reactive paradigm, to a proactive framework for prognosis of diseases at an incipient stage, coupled with prevention, cure, and overall management of health instead of disease, (b) enable personalization of treatment and management options targeted particularly to the specific circumstances and needs of the individual, and (c) help reduce the cost of health care while simultaneously improving outcomes. In this presentation, we highlight the opportunities and challenges for IoT in realizing this vision of the future of health care.
Prof. Dr Fethi Rabhi
University of New South Wales
Title: Software Engineering Techniques for Machine Learning Applications
Bio:
Professor Dr Fethi Rabhi is a Professor in the School of Computer Science and Engineering at the University of New South Wales (UNSW) in Australia. His main research areas are in service-oriented software engineering with a strong focus on business and financial applications. He completed a PhD in Computer Science at the University of Sheffield in 1990 and held several academic appointments in the USA and the UK before joining UNSW in 2000. He is currently actively involved in several research projects in the area of large-scale news and financial market data analysis.
https://www.unsw.edu.au/engineering/our-people/fethi-rabhi
Abstract:
Fuelled by the availability of massive amounts of data from social networks as well as public agencies, many businesses started investigating the use of AI and in particular machine learning (ML) techniques for improving their business operations or creating new revenue streams, possibly leveraging their own private enterprise data. However the application of ML techniques is still fraught with technical difficulties. Despite the availability of a huge panoply of ML techniques, many challenges remain such as working out which techniques apply to which problem, how to feed data the way different ML software modules expect it and how to fine tune parameters properly. In addition, several modules need to be programmatically chained together as “ML pipelines” for ingesting large volumes of data, applying complex transformations and repeating these processes for different combinations of parameters. Often, the performance of such ML pipelines is very sensitive to a number of design decisions, which constitutes a high entry barrier for new users. The talk will discuss a number of software engineering techniques that are currently being used to facilitate the development, deployment and maintenance of ML applications.