References of "Cantelmo, Guido 50001173"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailUsing Passive Data Collection Methods to Learn Complex Mobility Patterns: An Exploratory Analysis
Toader, Bogdan UL; Cantelmo, Guido UL; Popescu, Mioara et al

Scientific Conference (in press)

Detailed reference viewed: 54 (1 UL)
Full Text
Peer Reviewed
See detailCrowdsensed Data Learning-Driven Prediction of Local Businesses Attractiveness in Smart Cities
Capponi, Andrea UL; Vitello, Piergiorgio UL; Fiandrino, Claudio UL et al

in IEEE Symposium on Computers and Communications (ISCC), Barcelona, Spain, 2019 (2019, July)

Urban planning typically relies on experience-based solutions and traditional methodologies to face urbanization issues and investigate the complex dynamics of cities. Recently, novel data-driven ... [more ▼]

Urban planning typically relies on experience-based solutions and traditional methodologies to face urbanization issues and investigate the complex dynamics of cities. Recently, novel data-driven approaches in urban computing have emerged for researchers and companies. They aim to address historical urbanization issues by exploiting sensing data gathered by mobile devices under the so-called mobile crowdsensing (MCS) paradigm. This work shows how to exploit sensing data to improve traditionally experience-based approaches for urban decisions. In particular, we apply widely known Machine Learning (ML) techniques to achieve highly accurate results in predicting categories of local businesses (LBs) (e.g., bars, restaurants), and their attractiveness in terms of classes of temporal demands (e.g., nightlife, business hours). The performance evaluation is conducted in Luxembourg city and the city of Munich with publicly available crowdsensed datasets. The results highlight that our approach does not only achieve high accuracy, but it also unveils important hidden features of the interaction of citizens and LBs. [less ▲]

Detailed reference viewed: 73 (5 UL)
Full Text
Peer Reviewed
See detailA Big Data Demand Estimation Framework for Modelling of Urban Congested Networks
Cantelmo, Guido UL; Viti, Francesco UL

in CSUM 2018, AISC 879 proceedings (2019)

Detailed reference viewed: 70 (2 UL)
Full Text
Peer Reviewed
See detailIncorporating activity duration and scheduling utility into equilibrium-based Dynamic Traffic Assignment
Cantelmo, Guido UL; Viti, Francesco UL

in Transportation Research. Part B, Methodological (2018)

This paper deals with the problem of jointly modelling activity scheduling and duration within a Dynamic Traffic Assignment (DTA) problem framework. Although the last decades witnessed an intense effort ... [more ▼]

This paper deals with the problem of jointly modelling activity scheduling and duration within a Dynamic Traffic Assignment (DTA) problem framework. Although the last decades witnessed an intense effort in developing utility-based departure time choice models, relatively little has been done for understanding how the different assumptions on the utility model affect the model outputs. This problem is the main focus of this paper, which evaluates the effect of explicitly incorporating activity scheduling and duration within a generic user equilibrium DTA formulation. While using utility functions to model the positive component of the utility is a quite common procedure, the object of this paper is to show that a generic utility-based framework behaves as trip-based, activity-based, tour-based, or schedule-based if specific assumptions are specified. By establishing a set of properties, we quantify the amount of utility lost due to traffic congestion and how this affects activity (re-)scheduling and duration decisions. This allows predicting the effect of using a different assumption on the evolution of the transport system – and more specifically the departure time choice model. Conclusions support the idea that, under specific conditions, complex user behaviour can be approximated through a simplified model, and that the ratio between utility at origin and destination can be used to identify systematic biases within an existing DTA model – such as anticipating the rush hour. We also propose a novel utility function suited for modelling different activities, which can be used for modelling activities with a different duration. The mathematical model used to evaluate the effect of scheduling and duration into the equilibrium-based Dynamic Traffic Assignment is a simple bottleneck model. While this model has been recently re-formulated in order to capture the interaction between morning/evening commute, this paper further generalizes it in order to account for all type of activities. [less ▲]

Detailed reference viewed: 27 (3 UL)
Full Text
Peer Reviewed
See detailA utility-based dynamic demand estimation model that explicitly accounts for activity scheduling and duration
Cantelmo, Guido UL; Viti, Francesco UL; Nigro, Marialisa et al

in Transportation Research. Part A, Policy and Practice (2018)

This paper proposes a Dynamic Demand Estimation (DODE) framework that explicitly accounts for activity scheduling and duration. By assuming a Utility-Based departure time choice model, the time-dependent ... [more ▼]

This paper proposes a Dynamic Demand Estimation (DODE) framework that explicitly accounts for activity scheduling and duration. By assuming a Utility-Based departure time choice model, the time-dependent OD flow becomes a function, whose parameters are those of the utility function(s) within the departure time choice model. In this way, the DODE is solved using a parametric approach, which, on one hand, has less variables to calibrate with respect to the classical bi-level formulation while, on the other hand, it accounts for different trip purposes. Properties of the model are analytically and numerically discussed, showing that the model is more suited for estimating the systematic component of the demand with respect to the standard GLS formulation. Differently from similar approaches in literature, which rely on agent-based microsimulators and require expensive survey data, the proposed framework is applicable with all those DTA models, which are based on OD matrix, and do not necessarily need any data at user level. This has been proven by applying the proposed approach with a standard macroscopic realistic Dynamic Traffic Assignment (DTA) [less ▲]

Detailed reference viewed: 45 (1 UL)
Full Text
See detailDynamic Origin-Destination Matrix Estimation with Interacting Demand Patterns
Cantelmo, Guido UL

Doctoral thesis (2018)

It has become very fashionable to talk about Mobility as a Service, multimodal transport networks, electrified and green vehicles, and sustainable transportation in general. Nowadays, the transportation ... [more ▼]

It has become very fashionable to talk about Mobility as a Service, multimodal transport networks, electrified and green vehicles, and sustainable transportation in general. Nowadays, the transportation field is exploring new angles to solve mobility issues, applying concepts such as using machine learning techniques to profile user behaviour. While for many years “traffic pressure” and “congestion phenomena” were the most established keywords, there is now a widespread body of research pointing out how new technologies alone will solve most of these issues. One of the main reasons for this change of direction is that earlier approaches have been proven to be more “fair” than “effective” in tackling mobility issues. The main limitation was probably to rely on simple assumptions, such as in-elastic mobility travel demand (car users will stick to their choice), when modelling travel behaviour. However, while these assumptions were questionable twenty years ago, they simply do not hold in today's society. While it is still true that high-income people usually own a car, the concept of urban mobility evolved. First, new generations are likely to buy a car ten-twenty years later than their parents. Second, in many cases, users can choose options that are more effective by combining different transport modes. Wealthy people might decide to live next to their working place or to the city centre, rather than to buy a car. Thus, it becomes clear that to understand the evolution of the mobility demand we need to question some of these assumptions. While data can help in understanding this societal transformation, we argue in this dissertation that they cannot be considered as the sole source of information for the decision maker. Although data have been there for many years, congestion levels are increasing, meaning that data alone cannot solve the problem. Although successful in many case studies, data-driven approaches have the limitation of being capable of modelling only what they observed in the past. If there is no record of a specific event, then the model will simply provide a biased information. In this manuscript we point out that both elements – data and model – are equally relevant to represent the evolution of a transport system, and specifically how important is to consider the heterogeneity of the mobility demand within the modelling framework in order to fully exploit the available data. In this manuscript, we focus on the so-called Dynamic Demand Estimation Problem (DODE), which is the problem of estimating the mobility demand patterns that are more likely to best fit all the available traffic data. While this dissertation still focuses on car-users, we stress that the activity based structure of the demand needs to be explicitly represented in order to capture the evolution of a transport system. While data show a picture of the reality, such as how many people are travelling on a certain road segment or even along a certain path, this information represents a coarse aggregation of different individuals sharing a common resource (i.e. the infrastructure). However, the traffic flow is composed of different users with different trip purposes, meaning they react differently to a certain event. If we shut down a road from one day to another, commuting and not commuting demand will react in a different way. The same concept holds when dealing with different weather conditions, which also lead to a different demand pattern with respect to the typical one. This dissertation presents different frameworks to solve the DODE, which explicitly focus on the estimation of the mobility demand when dealing with typical and atypical user behaviour. Although the approach still focuses on a single mode of transport (car-users), the proposed formulation includes the generalized travel cost within the optimization framework. This key element allows accounting for the departure time choice and, in principle, it can be extended to the mode choice in future work. The methodologies presented in this thesis have been tested with a “state of the practice” dynamic traffic assignment model. Results suggest that the models can be used for real-life networks, but also that more efficient algorithm should be considered for practical implementations in order to unleash the full potential of this new approach. [less ▲]

Detailed reference viewed: 61 (14 UL)
See detailUtility-Based Kalman Filtering for real-time estimation of daily demand flows
Cantelmo, Guido UL; Qurashi, Moeid; Prakash, Arun et al

Scientific Conference (2018)

Time-dependent Origin-Destination (OD) demand flows are fundamental inputs for Dynamic Traffic Assignment (DTA) systems and real-time traffic management. This work introduces a novel state-space framework ... [more ▼]

Time-dependent Origin-Destination (OD) demand flows are fundamental inputs for Dynamic Traffic Assignment (DTA) systems and real-time traffic management. This work introduces a novel state-space framework to estimate these demand flows in an online context. Specifically, we propose to explicitly include trip-chaining behavior within the state-space formulation, which is solved using the well-established Kalman Filtering technique. While existing works already consider structural information and recursive behavior within the online demand estimation problem, this information has been always considered at the OD level. In this study, we introduce this structural information by explicitly representing trip-chaining within the estimation framework. The advantage is twofold. First, all trips belonging to the same tour can be jointly calibrated. Second, given the estimation during a certain time interval, a prediction of the structural deviation over the whole day can be obtained without the need to run additional simulations. The effectiveness of the proposed methodology is demonstrated first on a toy network and then on a large real-world network. Results show that the model improves the prediction performance with respect to a conventional Kalman Filtering approach. We also show that, on the basis of the estimation of the morning commute, the model can be used to predict the evening commute without need of running additional simulations. [less ▲]

Detailed reference viewed: 64 (1 UL)
See detailDemo: MAMBA: A Platform for Personalised Multimodal Trip Planning
Faye, Sébastien UL; Cantelmo, Guido UL; Tahirou, Ibrahim UL et al

Software (2017)

In recent years, multimodal transportation has become a challenging approach to route planning. Most existing planning systems usually rely on data sourced from different organisations, enabling the user ... [more ▼]

In recent years, multimodal transportation has become a challenging approach to route planning. Most existing planning systems usually rely on data sourced from different organisations, enabling the user to select a limited number of routing strategies. As part of the MAMBA project, developed in Luxembourg until 2017, we have been interested in the potential benefits of multimodal mobility systems. A key factor has been integrated into our studies: the need for a personalised experience at user level, whether when selecting the means of transport or describing user habits (e.g. route style, environment). In this context, we have developed a platform for planning personalised multimodal trips, broken down into the three main modules presented in this demonstration. More importantly, this platform has been developed to facilitate the daily mobility of people in Luxembourg, and considers datasets and characteristics that are specific to this region, which has an exceptionally high volume of daily commuting between Luxembourg and neighbouring countries. [less ▲]

Detailed reference viewed: 169 (33 UL)
Full Text
Peer Reviewed
See detailEffectiveness of the Two-Step Dynamic Demand Estimation model on large networks
Cantelmo, Guido UL; Viti, Francesco UL; Derrmann, Thierry UL

in Proceedings of 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS) (2017, June 28)

In this paper, the authors present a Two-Step approach that sequentially adjusts generation and distribution values of the (dynamic) OD matrix. While the proposed methodology already provided excellent ... [more ▼]

In this paper, the authors present a Two-Step approach that sequentially adjusts generation and distribution values of the (dynamic) OD matrix. While the proposed methodology already provided excellent results for updating demand flows on a motorway, the aim of this paper is to validate this conclusion on a real network: Luxembourg City. This network represents the typical middle-sized European city in terms of network dimension. Moreover, Luxembourg City has the typical structure of a metropolitan area, composed of a city centre, ring, and suburb areas. An innovative element of this paper is to use mobile network data to create a time-dependent profile of the generated demand inside and outside the ring. To support the claim that the model is ready for practical implementation, it is interfaced with PTV Visum, one of the most widely adopted software tools for traffic analysis. Results of these experiments provide a solid empirical ground in order to further develop this model and to understand if its assumptions hold for urban scenarios. [less ▲]

Detailed reference viewed: 95 (12 UL)
Full Text
Peer Reviewed
See detailGenerating purpose-dependent production factors through Monte Carlo sampling techniques.
Scheffer, Ariane; Cantelmo, Guido UL; Viti, Francesco UL

Scientific Conference (2017, May)

Detailed reference viewed: 43 (15 UL)
Full Text
Peer Reviewed
See detailA network-wide assessment of local signal control policies’ performance in practical implementations
Cantelmo, Guido UL; Viti, Francesco UL; Rinaldi, Marco UL

in Intelligent Transportation Systems (ITSC), 2016 IEEE 19th International Conference on (2016, November)

Detailed reference viewed: 62 (9 UL)
Full Text
Peer Reviewed
See detailSystematic analysis of global and local control policies
Cantelmo, Guido UL; Viti, Francesco UL; Rinaldi, Marco et al

in Periodica Polytechnica (2015)

Detailed reference viewed: 55 (6 UL)
Full Text
Peer Reviewed
See detailA Markov chain dynamic model for trip generation and distribution based on CDR
Viti, Francesco UL; Cantelmo, Guido UL

in Periodica Polytechnica (2015)

Detailed reference viewed: 83 (13 UL)
Full Text
Peer Reviewed
See detailThe Impact of Route Choice Modeling on Dynamic OD Estimation
Cipriani, Ernesto; Del Giudice, Andrea; Nigro, Marialisa et al

in Proceedings of IEEE-ITS Conference (2015, September)

Detailed reference viewed: 47 (4 UL)
Full Text
Peer Reviewed
See detailA two-steps dynamic demand estimation approach sequentially adjusting generations and distributions
Cantelmo, Guido UL; Viti, Francesco UL; Cipriani, Ernesto et al

in Proceedings of IEEE-ITS Conference (2015, September)

Detailed reference viewed: 63 (7 UL)