The Internet of Things (IoT) is not only about connecting billions of devices to the Internet, but also about connecting people, services, applications, businesses, infrastructures, among many others. What makes the IoT even more interesting is how data and technology can be blended together to build sustainable IoT Data Analytics (IoTDA) applications. With billions of devices embedded in environments, buildings, vehicles, or products continuously generating huge amounts of real-time data in many different formats, building sustainable IoTDA applications is becoming more challenging. One of the main hurdles is determining a suitable environment for processing IoT data. While it is envisioned that IoT applications would typically perform data processing on the cloud, a growing number of limitations in meeting applications’ demands is prompting researchers to investigate more efficient ways for processing data near IoT devices particularly for applications that require low-latency response.
With the growing number of IoT devices that have very limited computational abilities, the emergence micro-clouds (or fog nodes) near data sources to create sustainable IoTDA applications makes this very timely. This workshop will provide researchers and practitioners a venue to discuss possible new methods for building sustainable IoTDA applications and develop methods and techniques to investigate existing IoTDA limitations. In this context, the workshop’s ambition is to help in shaping a community of interest on the existing research opportunities and challenges resulting from performing data analytics for IoT applications. In addition, the workshop will help in bringing researchers and practitioners together to investigate innovative ideas or approaches to this new research challenge with main focus on developing sustainable IoTDA applications, foster collaborations and exchange points of view.
Tuesday – December 10, 2019 - Location: San Bernardino
11:00 am – 11:05 am Opening Remarks and Welcome
11:10 am – 11:30 am Ptolemaic Indexing for Managing and Querying Internet of Things (IoT) Data
Christian Beecks, Fabian Berns, and Kjeld Schmidt
11:30 am – 11:50 am Smart Home IoT Anomaly Detection based on Ensemble Model Learning From Heterogeneous Data
Sihai Tang, Zhaochen Gu, Song Fu, and Qing Yang
11:50 am – 12:10 pm Automatic Hyperparameter Tuning Method for Local Outlier Factor, with Applications to Anomaly Detection
Zekun Xu, Deovrat Kakde, and Arin Chaudhuri
12:10 pm – 1:30 pm Lunch
1:40 pm – 2:00 pm Kensor: Coordinated Intelligence from Co-Located Sensors
Olivera Kotevska, Kalyan Perumalla, and Juan Lopez Jr.
2:00 pm – 2:20 pm A New Approach for Efficient Structure Discovery in IoT
Fabian Berns, Kjeld Schmidt, Alexander Grass, and Christian Beecks
2:20 pm – 2:40 pm Cost-adaptive Neural Networks for Peak Volume Prediction with EMM Filtering
Bin Yu, Giovanna Graciani, Anderson Nascimento, and Juhua Hu
2:40 pm – 2:55 pm Coffee Break
3:00 pm – 3:20 pm Speech Emotion Detection using IoT based Deep Learning for Health Care
Zeenat Tariq, Sayed Khushal Shah, and Yugyung Lee
3:20 pm – 3:40 pm Effectively Testing System Configurations of Critical IoT Analytics Pipelines
Morgan Geldenhuys, Lauritz Thamsen, Kain Kordian Gontarska, Felix Lorenz, and Odej Kao
3:40 pm – 4:00 pm Detecting errors in short-term electricity demand forecast using people dynamics
Guillaume Habault, Yasutaka Nishimura, Kiyohito Yoshihara, and Chihiro Ono
4:00 pm – 4:20 pm Coffee Break
4:20 pm – 4:40 pm Towards an Interactive Visualization Framework for IoT Device Data Flow
Ebelechukwu Nwafor and Habeeb Olufowobi
4:40 pm – 5:00 pm Association Model between Visual Feature and AQI Rank Using Lifelog Data
Phuong-Binh Vo, Trong-Dat Phan, Minh-Son Dao, and Koji Zettsu
5:00 pm – 5:20 pm IoT based Urban Noise Monitoring in Deep Learning using Historical Reports
Sayed Khushal Shah, Zeenat Tariq, and Yugyung Lee
5:20 pm – 5:30 pm Closing Remarks
Chair:
Program Committee Members:
We welcome contributions describing original ideas, experiments and applications relevant to the workshop theme which have not been published earlier or are not currently pending submission at any other venue. All submitted papers must include the names and affiliations of all authors. Submitted papers will be peer-reviewed by members of the Workshop Program Committee. All accepted papers will be included in the main conference proceedings (see Proceedings section below).
Submission Categories:
Paper Submission Link:
Templates:
Camera Ready Instructions:
Proceedings: