Vehicular Traffic Flow Reconstruction Analysis to Mitigate Scenarios With Large City Changes

Bellini, Pierfrancesco; Bilotta, Stefano; Palesi, Luciano Alessandro Ipsaro; Nesi, Paolo; Pantaleo, Gianni

doi:10.1109/access.2022.3229183

Cited by 5 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different scenarios may imply and produce corresponding traffic conditions, pollutant emissions, parking status, public transportation loads, etc. Traffic scenarios can be identified on the basis of different mobility data in some hypothetical, typical or future contexts by using corresponding data, see Snap4City scenarios [ 9 ]. Such data results are at the basis of the what-if analysis approaches (orange blocks) to assess and set up different strategies for sustainable mobility, which can solve specific critical or hypothetical conditions in order to improve mobility and transport scenarios.…”

Section: Data Management and Exploitationmentioning

confidence: 99%

“…At the same time, dynamic data on traffic status [ 8 ] (such as congestion), car accidents, weather conditions, etc., are taken into account to compute optimal routing solutions according to the user’s need, specific assessment and also to plan how to recover from critical events, to plan strategies to improve viability in city areas, etc. [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data Sources and Models for Integrated Mobility and Transport Solutions

Bellini,

Bilotta,

Collini

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

The number of data sources and models in the mobility and transport domain strongly proliferated in the last decade. Most formats have been created to enable specific and innovative applications. On the other hand, the available data models present a certain degree of complexity in terms of their integration and management due to partial overlaps, and in most cases, they could be exploited alternatively to implement the same smart and latest innovative solutions. This paper offers an overview of data models, standards and their relationships. A second contribution highlights any possible exploitation of data models for implementing operational processes for city transportation management and for the feeding of simulation and optimization processes that produce other data results in other data models. The final goal in most cases is the monitoring and control of city transport conditions, as well as the tactic and strategic planning of city infrastructure. This work was developed in the context of the CN MOST, a national center of sustainable mobility in Italy, and it is based on exploiting the Snap4City platform.

show abstract

Section: Data Management and Exploitationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data Sources and Models for Integrated Mobility and Transport Solutions

Bellini,

Bilotta,

Collini

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed prediction model has been created in the context of a national center on sustainable mobility (MOST, in Italy) within the spoke on urban mobility and funded by the Ministry of Research, and by exploiting data and facilities of Snap4City, https://www.snapcity.org, infrastructure in the Florence / Tuscany area, Italy for Smart City [40], [41].…”

Section: B Paper's Aim and Organizationmentioning

confidence: 99%

Predicting Free Parking Slots via Deep Learning in Short-Mid Terms Explaining Temporal Impact of Features

Bilotta,

Ipsaro Palesi,

Nesi

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Looking for available parking slots has become a serious issue in urban mobility, since it influences traffic and emissions. This paper presents a set of metrics and techniques to predict the number of available parking slots in off-street parking facilities. This study deals with deep learning model solutions according with a mid-term prediction of 24 hours, every 15 minutes. Such a mid-term prediction can be useful for citizens who need to plan a car transfer well in advance and to reduce as much as possible any computational effort. Since most solutions in literature are focused on 1-hour ahead prediction, the proposed solution has been also tested in these conditions. The proposed solution is based on Convolutional Bidirectional LSTM models. Results have been compared in terms of precision metrics based both on occupancy and free slots. The paper also provides a framework to pass from an assessment model based on occupancy to models based on free slots and vice-versa. The obtained results have improved those already available in literature. A formal study has been conducted to perform feature relevance analysis by using explainable AI technique based on gradient and integrated gradient and proposing new heatmaps which highlighted the difference from LSTM and Bidirectional LSTM, feature relevance (base line, weather, traffic, etc.) and the impact of seasonality on predictions, namely the temporal relevance of features. The comparison has been performed on the basis of data collected in garages in the area of Florence, Tuscany, Italy by using Snap4city platform and infrastructure.INDEX TERMS smart city, available parking lots, prediction model, machine learning, deep learning, explainable AI.

show abstract