Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 03/12/2020
Room #1

Welcome Message by the General Chair 15:10 - 15:15

Sérgio F. Lopes

Welcome Message by EAI 15:10 - 15:15

Elena Davydova

Welcome Message by EAI Community Manager 15:15 - 15:20

Michal Dudic

EAI S-CUBE 2020 Presentations 15:20 - 17:55

15:20 - 15:55
An Attack-resistant Weighted Least Squares Localization Algorithm Based on RSSI

As an important part of the Internet of things (IoT), wireless sensor networks (WSNs) have been applied in many fields. Most applications require accurate location information, hence node localization is one of the important issues in WSNs. It is very important to ensure the security of localization when WSNs are under attack. A new attack-resistant weighted least squares (ARWLS) algorithm based on RSSI was proposed in the paper. The algorithm is oriented to the problem solution for the situation that the attacker influences the system by tampering with the transmitting power in the localization mechanism. The proposed algorithm can be used in the attack scenarios. Simulations results show that, compared with other algorithms, the proposed algorithm has merits in localization accuracy and robustness to resisting the tampering activities of attackers.
Authors: Yitong Liu (Sun Yat-sen University), Jun Peng (Sun Yat-sen University), Xingcheng Liu (Sun Yat-sen University), Zhao Tang (Sun Yat-sen University), Yi Xie (Sun Yat-sen University),
Hide Authors & Abstract

Show Authors & Abstract
15:55 - 16:25
MOBIUS: Smart Mobility Tracking with Smartphone Sensors

In this paper we introduce MOBIUS, a smartphone-based system for remote tracking of citizens' movements. By collecting smartphone's sensor data such as accelerometer and gyroscope, along with self-report data, the MOBIUS system allows to classify the users' mode of transportation. With the MOBIUS app the users can also activate GPS tracking to visualise their journeys and travelling speed on a map. The MOBIUS app is an example of a tracing app which can provide more insights into how people move around in an urban area. In this paper, we introduce the motivation, the architectural design and development of the MOBIUS app. To further test its validity, we run a user study collecting data from multiple users. The collected data are used to train a deep convolutional neural network architecture which classifies the transportation modes using with a mean accuracy of 89%.
Authors: Daniele Di Mitri (Open University of The Netherlands), Khaleel Asyraaf Mat Sanusi (Open University of The Netherlands), Kevin Trebing (Maastricht University), Stefano Bromuri (Open University of The Netherlands),
Hide Authors & Abstract

Show Authors & Abstract
16:25 - 16:55
Are Neural Networks Really the Holy Grail? A Comparison of Multivariate Calibration for Low-cost Environmental Sensors

It is widely known that environmental interference and practical constraints can impinge on the data of low-cost sensors in terms of its size, completeness and integrity; and such data would not provide sufficient information without proper calibration. However, despite extensive study in sensor calibrations, little work has been done on reporting how different calibration methods would cope on the data that faces issues such as small dataset being available and data showing unexpected patterns. To better understand the calibration of low-cost senors and the limitation of different calibration methods, this paper presents a systematic comparison of two well-known calibration techniques (ANN-based method and regression-based method). Six-months worth of real hourly data from our deployment was used for this comparison, which preserves the real property of data obtained in a typical urban environment. The evaluation on our data shows that the ANN-based method is sensitive to the use of model parameters and the random variation in the model generation process, which could lead to a large variation in the calibrated result. By contrast, the regression based method provides a more predictable result and requires much less computational resources. The comparison also suggests that the ANN-based method would benefit from using an increased training dataset, whereas the regression based method would have a better performance over time.
Authors: xinwei fang (university of york), Iain Bate (University of York), David Griffin (university of york),
Hide Authors & Abstract

Show Authors & Abstract
16:55 - 17:25
A feature-fusion transfer learning method as a basis to support automated smartphone recycling in a circular smart city

In this paper, we present how Artificial Intelligence (AI) could support automated smartphone recycling, hence, act as an enabler for Circular Smart Cities (CSC), where the Smart City paradigm could be linked to the Circular Economy (CE), a leading concept of the sustainable economy. While business and society strive to gain benefits from automation, the ongoing rapid digitalization, in turn, accelerates the mass production of Waste Electric and Electronic Equipment (WEEE), often called E-Waste. Therefore, E-Waste is the fastest growing waste stream in the world and comes up with several negative environmental and social impacts. In our research, we show an AI technique that could become an enabler for the CSC and the CE in general and supporter of automated recycling, specifically. However, research on this topic is emerging only recently, and practical applications are lacking even more. For instance, object recognition has extensive research, whereas smartphone classification nevertheless has rare attention within this field of research. Our main contribution is to investigate, based on visual-feature extraction that uses the Transfer Learning (TL) approach can classify smartphones; as a result, it supports automated smartphone recycling without any knowledge of product design. We also test the main advantages of using TL, which are reducing the size of the training-set, computation time, and significant enhancements without designing a completely new network from scratch
Authors: Nermeen Abou Baker (Ruhr West University of Applied Sciences), Paul Szabo-Müller (Ruhr West University of Applied Sciences), Uwe Handmann (Ruhr West University of Applied Sciences),
Hide Authors & Abstract

Show Authors & Abstract
17:25 - 17:55
Assessment of Video Games Players and Teams Behaviour via Sensing and Heterogeneous Data Analysis: Deployment at an eSports Tournament

eSports is video gaming where individual players or teams oppose their physical, psychological and emotional conditions in the game context to achieve a specific goal by the end of the game. However, neither players nor teams have been studied in real scenarios. In this paper, we report on the deployment of sensing system for collecting a player biometric data (a computer mouse and keyboard), voice data, and heart rate in an eSports 'Team Fortress 2' tournament. Upon the data analysis we demonstrate that an increased heart rate has a negative impact on the player performance. At the same time, successful teams communicate more during the game. Moreover, team communication in positive tone has a positive contribution in the overall team performance.
Authors: Alexander Korotin (Skoltech), Anton Stepanov (Skoltech), Andrey Lange (Skoltech), Dmitry Nikolaev (Skoltech), Simon Abramov (Skoltech), Nikita Klyuchnikov (Skoltech), Evgeny Burnaev (Skoltech), Andrey Somov (Autonomous Non-Profit Organization for Higher Education “Skolkovo Institute of Science and Technology”),
Hide Authors & Abstract

Show Authors & Abstract

Closing Message by Sérgio F. Lopes 17:55 - 18:00

Best Paper Announcement