Program
09:00 - 09:10: Opening remarks
09:10 - 10:00: Invited Speech
Coordinating Distributed Speaking Objects
Prof. Franco Zambonelli
University of Modena and Reggio Emilia, Italy
Future smart sensors and actuators -- embedded in our everyday objects -- rather than simply producing streams of data, will be capable of understanding and reporting, via factual assertions and arguments, about what is happening (for sensors) and about what they can make possibly happen (for actuators). These ``speaking objects'' will dramatically change the approaches to implementing and coordinating the activities of distributed pervasive services. In fact, if distributed coordination will become associated with the capability of arguing about situations and about the current ``state of the affairs'', it will become possible to exploit distributed agreements to notably improve the quality of sensed situations and the quality and reliability of pervasive services. In this talk I will discuss, also with the help of case study examples, how such a novel vision can be built upon readily available technologies, and will highlight the research challenges that it poses.
10:00 - 10:30: Coffe break
10:30 - 11:50: Session 1 - Chair: Flora Salim
- Andrea Saracino; Fabio Martinelli; Paolo Mori; Christina Michailidou, "Managing QoS in Smart Buildings through Software Defined Network and Usage Control"
- Jose Talusan; Francis Tiausas; Sopicha Stirapongsasuti; Yugo Nakamura; Teruhiro Mizumoto; Keiichi Yasumoto, "Evaluating Performance of In-Situ Distributed Processing on IoT Devices by Developing a Workspace Context Recognition Service "
- Tim Rutermann; Aboubakr Benabbas; Daniela Nicklas, "Know Thy Quality: Assessment of Device Detection by WiFi Signals"
- Naufil Hassan; Ifrah Siddiqui; Suleman Mazhar; Hadia Hameed, "Road Anomaly Classification for Low-Cost Road Maintenance and Route Quality Maps"
12:00 - 13:30: Lunch
13:30 - 14:10: Invited Speech
Wildlife monitoring system for detecting poachers using activity monitoring
Prof. Paul Havinga
University of Twente, Netherlands
Wild animals, rhinos and elephants, in particular, are facing ever increasing poaching, which endangers not only those animals, yet in fact it harms a wide ecosystem. In this presentation, we will address some poaching detection technologies that aim to save endangered species from extinction.
We introduce dual radio based IoT network architecture for wildlife monitoring system (WMS). This solution will facilitate IoT devices to be deployed for sustainable wildlife monitoring applications. One important aspect is to detect the behavior of the animals. Animal behavior is a commonly-used and sensitive indicator of animal welfare. Moreover, the behavior of animals can provide rich information about their environment, and can be an indicator for poachers in the area.
Fundamental challenges faced by real-time animal activity recognition include variation in motion data due to changing sensor orientations, numerous features, and energy and processing constraints of animal tags. We aim at finding small optimal feature sets that are lightweight and robust to the sensor's orientation. We collected real-world data through multiple sensors around the neck of five animals. The results show that activities can be accurately recognized using only accelerometer data and a few lightweight features. Additionally, we show that the performance is robust to sensor orientation and position.
14:10 - 15:10: Session 2 - Chair: Daniela Nicklas
- Zilu Liang; Mario Alberto Chapa Martell, "Combining Numerical and Visual Approaches in Validating Sleep Data Quality of Consumer Wearable Wristbands"
- Pranita Dewan; Raghu Ganti; Mudhakar Srivatsa; Sebastian Stein, "NN-SAR: A Neural Network Approach for Spatial AutoRegression"
- Sunyanan Choochotkaew; Hirozumi Yamaguchi; Teruo Higashino, "Automatic Deadline-Oriented Sampling Method for Coarse-grained Stream Processing"
15:10 - 15:15: Closing remarks
