Classification of users’ transportation modalities from mobiles in real operating conditions

Abstract

The modern mobile phones and the complete digitalization of the public and private transport networks have allowed to access useful information to understand the user’s mean of transportation. This enables a plethora of old and new applications in the fields of sustainable mobility, smart transportation, assistance, and e-health. The precise understanding of the travel means is at the basis of the development of a large range of applications. In this paper, a number of metrics has been identified to understand whether an individual on the move is stationary, walking, on a motorized private or public transport, with the aim of delivering to city users personalized assistance messages for: sustainable mobility, health, and/or for a better and enjoyable life, etc. Differently from the state-of-the-art solutions, the proposed approach has been designed to provide results, and thus collect metrics, in real operating conditions (imposed on the mobile phones as: a range of different mobile phone kinds, operating system constraints managing Applications, active battery consumption manager, etc.). The paper reports the whole experimentations and results. The solution has been developed in the context of Sii-Mobility Km4City Research Project infrastructure and tools, performed with the collaboration of public transport operators, and GDPR compliant. The same solution has been used in Snap4City mobile Apps with experiments performed in Antwerp and Helsinki.

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors

“…To distinguish between 38 users' modes of travel, including being stationary, walking, motorized private transport (car or motorcycle), or public transportation (tram, bus, or train), Ref. [20] obtained over 30,000 observations from 30 different brands of mobile phones. Using GPS sensor, accelerometers, and GIS user contextual data, the authors achieved a mean accuracy of 96%.…”

Automating IoT Data Ingestion Enabling Visual Representation

“…A new generation of smart city solutions is built on the fact that data can be provided by city users (e.g., citizens, commuters, and tourists). They are, at the same time, data providers and data consumers [42,43]. The discussed related works, however, do not consider (except [22], which supports CSV files (comma-separated values)) the possibility of ingesting Despite the above considerations, in most smart cities and IoT solutions data access is focused on accessing a single data element and time series without addressing the possibility of sectioning the hypercubes.…”

Special issue on Sentient Multimedia Systems

“…The set of papers on Intelligent Multimedia Systems include two papers on Action Recognition [3,6], and four papers on Machine Learning Architectures and Models for Multimedia Applications [1,2,8,9].…”

“…The category of Machine Learning Architectures and Models for Multimedia Applications includes a paper on the automatic diagnosis of cervical cancer [9], one on a machine learning framework to increase safety at work [2], one on the classification of user transportation modalities [1], and finally, one on the prediction of Cyber-Attacks [8]. The paper by Elakkiya R et al proposes a hybrid deep learning algorithm for cervical localization and precancerous/cancerous lesion detection, in order to provide an end-to-end application for the early diagnosis and prognosis of cervical cancer, which represents one of the curable cancers when it is diagnosed in the early stages [9].…”

“…Moreover, the authors illustrate the specialization of the proposed framework on a typical scenario of safety at work, i.e., fall detection, by showing its effectiveness in monitoring the work environment, activating alarms in case of falls, and sending appropriate advice to help workers involved in falls. The paper by Badii et al tackles the sustainable mobility problem in smart cities [1], providing a solution for delivering useful personalized assistance messages to the user. In particular, they defined a classification system using data originating from sensors embedded in mobile phones, and GIS data (user contextual information), to identify the transportation mean of users.…”