Gianni Pantaleo

Dr. Gianni Pantaleo

Department of Information Engineering, University of Florence, Florence, Italy
orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 February 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PBPierfrancesco Bellini
Pierfrancesco Bellini
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
In recent years, smart cities have been significantly developed and have greatly expanded their potential. In fact, novel advancements to the Internet of things (IoT) have paved the way for new possibilities, representing a set of key enabling technologies for smart cities and allowing the production and automation of innovative services and advanced applications for the different city stakeholders. This paper presents a review of the research literature on IoT-enabled smart cities, with the aim of highlighting the main trends and open challenges of adopting IoT technologies for the development of sustainable and efficient smart cities. This work first provides a survey on the key technologies proposed in the literature for the implementation of IoT frameworks, and then a review of the main smart city approaches and frameworks, based on classification into eight domains, which extends the traditional six domain classification that is typically adopted in most of the related works.

10 March 2022 in IEEE Access
Verified
Journal Article
Open access
Enrico ColliniEnrico Collini
Enrico Collini
Luciano Alessandro Ipsaro PalesiLuciano Alessandro Ipsaro Palesi
Luciano Alessandro Ipsaro Palesi
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
NNNicola Nocentini
Nicola Nocentini
Ascanio RosiAscanio Rosi
Ascanio Rosi
Rainfall induced landslide is one of the main geological hazard in Italy and in the world. Each year it causes fatalities, casualties and economic and social losses on large populated areas. Accurate short-term predictions of landslides can be extremely important and useful, in order to both provide local authorities with efficient prediction/early warning and increase the resilience to manage emergencies. There is an extensive literature addressing the problem of computing landslide susceptibility maps (which is a classification problem exploiting a large range of static features) and only few on actual short terms predictions (spatial and temporal). The short-term prediction models are still empirical and obtain unsatisfactory results, also in the identification of the predictors. The new aspects addressed in this paper are: (i) a short-term prediction model (1 day in advance) of landslide based on machine learning, (ii) real time features as good predictors. The introduction of explainable artificial intelligence techniques allowed to understand global and local feature relevance. In order to find the best prediction model, some machine learning solutions have been implemented and assessed. The obtained models overcome the ones available in literature. The validation has been performed in the context of the Metropolitan City of Florence, data from 2013 to 2019. The method based on XGBoost achieved best results, demonstrating that it is the most reliable and robust against false alarms. Finally, we applied explainable artificial intelligence techniques locally and globally to derive a deep understanding of the predictive model’s outputs and features’ relevance, and relationships. The analysis allowed us to identify the best feature for short term predictions and their impact in local cases and global prediction model. Solutions have been implemented on Snap4City.org infrastructure.

29 May 2024 in IEEE Access
Verified
Journal Article
Open access
LALorenzo Adreani
Lorenzo Adreani
PBPierfrancesco Bellini
Pierfrancesco Bellini
Marco FanfaniMarco Fanfani
Marco Fanfani
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
Digital Twins are becoming fundamental tools to monitor the status of entities, predict their future evolution and simulate alternative scenarios to understand the impact of possible changes for planning and design. More recently, Digital Twin solutions have been applied in the context of Smart Cities. Thanks to the large deployment of sensors, together with the increasing amount of information available for municipalities and governmental organizations, it is possible to build wide virtual reproductions of urban environments including structural data and real-time information that can undoubtfully help decision makers to face future challenges in urban development and improve the citizens’ quality of life. In this paper, the Snap4City Smart City Digital Twin framework is presented, which can respond to the requirements identified in recent literature and by international forums. The proposed architecture provides an integrated solution for data gathering, indexing, computing, and information distribution, thus realizing a continuously updated digital twin of the urban environment at global and local scales for monitoring operation and planning. It addresses 3D building models, road networks, Internet of Things entities, points of interest, paths, as well as results from analytical processes for traffic density reconstruction, pollutant dispersion, predictions, and what-if analysis for assessing impact of changes, all integrated into a freely accessible interactive 3D web interface, enabling stakeholder and citizen participation to city decision processes. As case study, the digital twin of the city of Florence (Italy) is presented, including what-if analysis. The solution is released on top of the Snap4City platform as open-source and made available through our GitHub repository (https://github.com/disit) and as Docker compose.

26 October 2022 in IEEE Access
Verified
Journal Article
Open access
SBSTEFANO BILOTTA
STEFANO BILOTTA
Enrico ColliniEnrico Collini
Enrico Collini
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
Nowadays, traffic management and sustainable mobility are central topics for intelligent transportation systems (ITS). Thanks to new technologies, it is possible to collect real-time data to monitor the traffic situation and contextual information by sensors. An important challenge in ITS is the ability to predict road traffic flow data. The short-term predictions (10-60 minutes) of traffic flow data is a complex nonlinear task that has been the subject of many research efforts in past few decades. Accessing traffic flow data is mandatory for a large number of applications that have to guarantee a high level of services such as traffic flow analysis, traffic flow reconstruction, which in their turn are used to compute predictions needed to perform what-if analysis, forecast routing, conditioned routing, predictions of pollutant, etc. This paper proposes a solution for short-term prediction of traffic flow data by using a architecture capable to exploit Convolutional Bidirectional Deep Long Short Term Memory neural networks (CONV-BI-LSTM). The solution adopts a different architecture and features, so as to overcome the state-of-the-art solutions and provides precise predictions addressing traffic flow data in cities, which are tendentially very noisy with respect to the ones measured in high-speed roads, the latter being the validation context for the majority of state-of-the-art solutions. The proposed solution has been developed and validated in the city context and data via Sii-Mobility, a smart city mobility and transport national project and it is currently in use in other contexts such as in Snap4City PCP EC, TRAFAIR CEF, and REPLICATE H2020 SCC1, and it is operative in those areas.

20 March 2018 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
IPIrene Paoli
Irene Paoli
IZImad Zaza
Imad Zaza
The problem of assessing the mechanisms underlying the phenomenon of virality of social network posts is of great value for many activities, such as advertising and viral marketing, influencing and promoting, early monitoring and emergency response. Among the several social networks, Twitter.com is one of the most effective in propagating information in real time, and the propagation effectiveness of a post (i.e., tweet) is related to the number of times the tweet has been retweeted. Different models have been proposed in the literature to understand the retweet proneness of a tweet (tendency or inclination of a tweet to be retweeted). In this paper, a further step is presented, thus several features extracted from Twitter data have been analyzed to create predictive models, with the aim of predicting the degree of retweeting of tweets (i.e., the number of retweets a given tweet may get). The main goal is to obtain indications about the probable number of retweets a tweet may obtain from the social network. In the paper, the usage of the classification trees with recursive partitioning procedure for prediction has been proposed and the obtained results have been compared, in terms of accuracy and processing time, with respect to other methods. The Twitter data employed for the proposed study have been collected by using the Twitter Vigilance study and research platform of DISIT Lab in the last 18 months. The work has been developed in the context of smart city projects of the European Commission RESOLUTE H2020, in which the capacity of communicating information is fundamental for advertising, promoting alerts of civil protection, etc.

9 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
EBEmanuele Bellini
Emanuele Bellini
PBPierfrancesco Bellini
Pierfrancesco Bellini
Daniele CenniDaniele Cenni
Daniele Cenni
PNPaolo Nesi
Paolo Nesi
GPGianni Pantaleo
Gianni Pantaleo
MPmichela paolucci
michela paolucci
Today, the complexity of urban systems combined with existing and emerging threats constrains administrations to consider smart technologies and related huge amounts of data generated as a means to take timely and informed decisions. The smart city needs to be prepared for both expected and unexpected situations, and the possibility to mitigate the effect of the uncertainty behind the causes of disruptions through the analysis of all the possible data generated by the city open new possibility for resilience operationalization. This article aims at introducing a new conceptualization for resilience and presenting an innovative full stack solution to exploit Internet of Everything (IoE) and big multimedia data in smart cities to manage resilience of urban transport systems (UTS), which is one of the most critical infrastructures of the city. The approach is based on a novel data driven approach to resilience engineering and functional resonance analysis method (FRAM), to understand and model an UTS in the context of smart cities and to support evidence driven decision making. The paper proposes an architecture taking into account: (a) different kinds of available data generated in the smart city, (b) big data collection and semantic aggregation and enrichment; (c) data sense-making process composed by analytics of different data sources like social media, communication networks, IoT, user behavior; (d) tools for knowledge driven decisions able to combine different information generated by analytics, experience, and structural information of the city into a comprehensive and evidence driven decision model. The solution has been applied in Florence metropolitan city in the context of RESOLUTE H2020 research project of the European Commission.