Program
| Thursday, June 16, 2016 | |
| 09:00 - 10:30 | Keynote III |
| 10:30 - 11:00 | Coffee/Tea Break |
| 11:00 - 11:10 | ECAAS Opening Session |
| 11:10 - 12:00 | ECAAS Keynote: New challenges and research trend in activity recognition, by Juan Ye, School of Computer Science, University of St Andrews, UK |
| 12:00 - 12:30 | Invited Talk: Scaling a real-time driving behaviour analysis system, by Bruno Cabral, Universidade de Coimbra / CISUC, Departamento de Engenharia Informática / Sentilant, Portugal |
| 12:30 - 14:00 | Lunch |
| 14:00 - 14:50 | ECAAS Keynote: APISENSE® (http://apisense.io) by Romain Rouvoy, University of Lille,France |
| 14:50 - 15:30 | Invited Talk: Emerging Applications of Context-Aware Systems in Healthcare, by Hugo Plácido da Silva, Chief Innovation Officer, PLUX - Wireless Biosignals, S.A., Portugal |
| 15:30 - 16:00 | Coffee/Tea Break |
| 16:00 - 16:25 | Divya Lohani and Debopam Acharya, SmartVent: A Context Aware IoT System to Measure Indoor Air Quality and Ventilation Rate, Shiv Nadar University, India |
| 16:25 - 16:50 | Nelson Mendes, Bruno Alves and Sara Paiva, Context-aware mobile recommender system based on activity patterns, Instituto Politecnico de Viana do Castelo, Portugal |
| 16:50 - 17:15 | Hugo Louro Cardoso and João Mendes Moreira, Human Activity Recognition by means of Online Semi-Supervised Learning, INESC TEC, University of Porto, Portugal |
| 17:15 - 17:30 | ECAAS Closing Session |
KEYNOTES
New challenges and research trend in activity recognition, by Juan Ye, School of Computer Science, University of St Andrews, UK
Recognising high-level human activities from low-level sensor data is a crucial driver for pervasive systems that wish to provide seamless and distraction-free support for users engaged in normal activities. Research in this area has grown alongside advances in sensing and communications, and experiments have yielded sensor traces coupled with ground truth annotations about the underlying environmental conditions and user actions. Traditional machine learning has had some success in recognising human activities. However, the potential of deploying pervasive systems in real-world environments has introduced a lot of new challenges, such as dealing with sensor failure, lacking of well-annotated ground truth, dealing with multiple users and recognising their interleaved activities, and detecting and learning unknown activities. This keynote will discuss each of these challenges and introduce our work towards addressing them.
Short bio: Juan Ye is a lecturer in School of Computer Science at the University of St Andrews, UK. Her research interests resides in designing and developing knowledge- and learning-hybrid techniques in human activity recognition, with speciality in ontologies, context modelling and reasoning, and uncertainty reasoning techniques. She received her Ph.D. degree from University College Dublin in 2009. She publishes in top venues in pervasive computing, including ACM transactions on Interactive Intelligent Systems, Pervasive and Mobile Computing, KER, IEEE Pervasive, Percom, IEEE SMC, IUI, Mobiquitous.
APISENSE® (http://apisense.io) by Romain Rouvoy, University of Lille,France
APISENSE® (http://apisense.io) is a crowd-sensing platform that leverages the gathering of field datasets at scale. In particular, APISENSE® is designed as a Software-as-a-Service (SaaS) solution that remotely orchestrates crowds of mobile devices to monitor physical events or human behaviours in the wild. Collecting data in the field tends to be a tedious tasks for most of researchers as it requires to spend time, energy and money to develop dedicated mobile apps. The role of APISENSE® is therefore to catalyse this process by delivering to the scientific community a comprehensive distributed infrastructure that guarantee both privacy and energy consumption of participants. The applications of APISENSE® encompasses case studies in the domains of telecom, smart cities, air quality, or human sciences.
Short bio: Romain Rouvoy is an associate professor from the University of Lille (France) and is a member of the Spirals research group (supported by CRIStAL and Inria - http://team.inria.fr/spirals). His domains of interest covers both software and system engineering challenges faced in the design of scalable and dependable systems-of-systems.
INVITED TALKS
Scaling a real-time driving behaviour analysis system, by Bruno Cabral, Universidade de Coimbra / CISUC, Departamento de Engenharia Informática / Sentilant, Portugal
Drivian is a system that helps drivers save fuel and drive safer. The Drivian system gathers data from smartphone sensors, analysis it, and provides real-time feedback to the user on his driving style, in terms of security and economy. Also, Drivian alerts the driver for harsh acceleration, braking and cornering events. Moreover, the collected data is forwarded to a central location and used for tracking the driver evolution over time, record trips, extract statistical information, validate trips and develop new insights. Considering that each device produces a new tuple of sensor data every 60ms, with several thousand (or more) equipments online, the amount data to process and store in real-time presents a serious challenge. In this talk, we will portray and discuss the major design decisions for coping with the architectural drivers for the Drivian system.
Short bio: Bruno Cabral is an Assistant Professor at the University of Coimbra (UC), Portugal. He obtained his PhD from the University of Coimbra in 2009. His main research interests are Concurrent/Distributed Programming and Programming Languages, Exception Handling Models and Code instrumentation. Bruno is the author of several publications in top-tier peer reviewed conferences and journals. He has participated and acted as PI in many research and software projects in cooperation with institutions such as the European Space Agency, Carnegie Mellon University, and the Portuguese Government. Bruno is also the founder and CTO of Sentilant, a spinoff company of the UC.
Emerging Applications of Context-Aware Systems in Healthcare, by Hugo Plácido da Silva, Chief Innovation Officer, PLUX - Wireless Biosignals, S.A., Portugal
Biomedical hardware and software is becoming increasingly more pervasive, mostly due to the fast growth and widespread adoption of smart wearable devices, capable of recording physiological data virtually in an always-on / always connected approach. When combined with context-aware information, the information collected using such devices is augmented in a way that has the potential to transform healthcare practices in several medical sub-domains. In this talk we will present multiple emerging use cases that can benefit from the interface between context-aware and wearable biomedical systems, highlighting aspects of topical interest for researchers and practitioners in the field of context-aware applications and services.
Short bio: Hugo Plácido da Silva has a PhD in Electrical and Computers Engineering from the Instituto Superior Técnico (IST) – University of Lisbon, Hugo is a researcher at the IT - Instituto de Telecomunicações (https://www.it.pt/Members/Index/1293) since 2004. In 2012 he was a visiting researcher at the Computational and NeuroEngineering Laboratory (CNEL) form the University of Florida. He is co-founder of PLUX – Wireless Biosignals (http://www.plux.info), established in 2007 as an innovative technology-based company operating in the field of medical devices for healthcare and quality of life, where he is currently a Board Member and Innovation Advisor. More recently, Hugo has been actively working towards making the world a bit more physiological, through BITalino (http://www.bitalino.com), an open source software and low-cost hardware toolkit, that allows anyone from students to professional app developers, to create cool projects and applications with physiological sensors. His main interest interests include biosignal research, system engineering, signal processing, and pattern recognition, and his work has been distinguished with several academic and technical awards such as the 1st place at the Ordem dos Engenheiros Young Engineer Innovation Award in 2015 with the project “BIT: Biosignal Igniter Toolkit”, the 1st place at the Venture Day Lisbon in 2013 with the project “Vitalidi: Your Heart (h)as a Key!”, the selection as a semi-finalist to the Engadget Expand NY Inset Coin competition in 2013, the Life Sciences Award in 2010 at a yearly venture competition co-promoted by the MIT, and the "Caixa Geral de Depósitos Award'' from 2003 to 2005 for recognized academic merit.
