Smart City Gnosys
Smart city article details
| Title | Vehicle Availability Profiling From Diverse Data Sources |
|---|---|
| ID_Doc | 60894 |
| Authors | Naylor S.; Pinchin J.; Gough R.; Gillott M. |
| Year | 2019 |
| Published | 2019 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2019 |
| DOI | http://dx.doi.org/10.1109/PERCOMW.2019.8730716 |
| Abstract | An understanding of the movement and utilisation rates of vehicles has many applications in the 'smart city'. The increasing availability of location and movement data from smartphones, in-vehicle loggers etc. allows for new applications of vehicle use analytics to be developed using a diverse range of data sources. However, for wide-scale application it may not be feasible to rely on consistent data from all possible sources - a need arises to process disparate data sources into a unified format. Raw user location data also presents significant issues around user privacy and the need to securely store and transmit any personally identifiable data. This paper covers the problem definition and development of a system to classify vehicle user driving patterns. A system was proposed to allow user driving patterns to be characterised in a way that does not explicitly store large volumes of location data while retaining key information needed for behavioural analysis. User driving data was converted to a personal profile based on statistical likelihood of vehicle use over a 24-hour period. Dynamic Time Warping was used to quantify the match between a new user's calculated profile and established driving archetypes. Additional profile features were tested in trained multi-class classification models including typical journey length, no. journeys etc. This was found to reduce the number of days of data needed to make a match for most users. This increases the feasibility of representing vehicle users in relation to driving archetypes rather than explicitly storing sensitive location data. © 2019 IEEE. |
| Author Keywords | activity profiles; location data; vehicle tracking |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
55733  | 0.869 | De Mattos E.P.; Domingues A.C.S.A.; Santos B.P.; Ramos H.S.; Loureiro A.A.F. | The Impact Of Mobility On Location Privacy: A Perspective On Smart Mobility | IEEE Systems Journal, 16, 4 (2022) |
| 4223 | 0.862 | Yuan Y.; Chow T.E.; Wang P.; Wang F. | A Review Of Third-Party Traffic Data For Public And Private Use: Opportunities And Challenges | Advances in Transportation Studies, 65 (2025) |
| 14531 | 0.862 | Bolaños-Martinez D.; Bermudez-Edo M.; Garrido J.L. | Clustering Pipeline For Vehicle Behavior In Smart Villages | Information Fusion, 104 (2024) |
| 46504 | 0.856 | Ghosh N.; Sarkar U.; Nagesh P. | Review On Application Of Call Details Records (Cdrs) Data To Understand Urban Mobility Scenarios For Future Smart Cities | Springer Geography (2023) |
| 21038 | 0.854 | Li T.; Alhilal A.; Zhang A.; Hoque M.A.; Chatzopoulos D.; Xiao Z.; Li Y.; Hui P. | Driving Big Data: A First Look At Driving Behavior Via A Large-Scale Private Car Dataset | Proceedings - 2019 IEEE 35th International Conference on Data Engineering Workshops, ICDEW 2019 (2019) |