It is now widely accepted that human behaviour accounts for a large portion of total global emissions, and thus influences climate change to a large extent. Changing human behaviour when it comes to mode of transportation is one component which could make a difference in the long term. In order to achieve behavioural change, we investigate the use of a persuasive multiplayer game. Transportation mode recognition is used within the game to provide bonuses and penalties to users based on their daily choices regarding transportation. To easily identify modes of transportation, an approach to transport recognition based on accelerometer and gyroscope data is analysed and extended. Preliminary results from the machine learning tests show that the classification true-positive rate for recognizing 10 different classes can reach up to 95% when using a history set (66% without). Preliminary results from testers of the game indicate that using games may be successful in causing positive change in user behaviour. / <p>Del av Erasmus Mundus PERCCOM. Redovisning skedde på anordnad summer school av partner-universitet där hela konsortiet närvarade.</p>

A wide range of contemporary technologies leveraging ubiquitous mobile phones have addressed the challenge of transportation mode recognition, which involves identifying how users move about, such as walking, cycling, driving a car, or taking a bus. This problem has found applications in various areas, including smart city transportation, carbon footprint calculation, and context-aware mobile assistants. Previous research has primarily focused on recognizing mobility modes using GPS and motion sensor data from smartphones. However, these approaches often necessitate the installation of specialized mobile applications on users’ devices to collect sensor data, resulting in power inefficiency and privacy concerns. In this study, we tackle these issues by presenting a user-independent system capable of distinguishing four forms of locomotion—walking, bus, car, and train—solely based on mobile data (4G) from smartphones. Our system was developed using data collected in three diverse locations (Mekkah, Jeddah, KAUST) in the Kingdom of Saudi Arabia. The underlying concept is to correlate phone speed with features extracted from Channel State Information (CSI), which includes information about Physical Cell ID, received signal strength, and other relevant data. The feature extraction process involves utilizing sliding windows over both the time and frequency domains. By employing statistical classification and boosting techniques, we achieved remarkable F-scores of 85%, 95%, 88%, and 70% for the car, bus, walking, and train modes, respectively. Moreover, we conducted an analysis of the handover rate in a one-tier network and compared the analytical results with real data. This investigation provided novel insights into the influence of transportation modes on handover rate, revealing the correlation between different modes of mobility and network connectivity. This work sets the stage for the development of more efficient and privacy-friendly solutions in transportation mode recognition and network optimization.