Nuova ricerca


Ricercatore t.d. art. 24 c. 3 lett. A
Dipartimento di Scienze e Metodi dell'Ingegneria

Home | Curriculum(pdf) | Didattica |


2023 - Machine learning for activity pattern detection [Articolo su rivista]
Hadjidimitriou, N.; Cantelmo, G.; Antoniou, C.

2023 - Using mobile phone data to map evacuation and displacement: a case study of the central Italy earthquake [Articolo su rivista]
Giardini, F.; Hadjidimitriou, N. S.; Mamei, M.; Bastardi, G.; Codeluppi, N.; Pancotto, F.

Population displacement is one of the most common consequences of disasters, and it can profoundly affect communities and territories. However, gaining an accurate measure of the size of displacement in the days and weeks following a major disaster can be extremely difficult. This study uses aggregated Call Detail Records as an inexpensive and efficient technique to measure post-disaster displacement in four Italian regions affected by repeated earthquakes in 2016-2017. By comparing post-disaster mobile phone count with a forecast computed before the earthquake hit, we can compute an index of change in the presence of mobile phones (MPE). This measure, obtained thanks to advanced analytical techniques, provides a reliable indication of the effect of the earthquake in terms of immediate and medium-term displacement. We test this measure against census data and in combination with other datasets. Looking into available data on economic activities and requests for financial support to rebuild damaged buildings, we can explain MPE and identify significant factors affecting population displacement. It is possible to apply this innovative methodology to other disaster scenarios and use it by policymakers who want to understand the determinants of population displacement.

2022 - A hybrid approach for high precision prediction of gas flows [Articolo su rivista]
Petkovic, M.; Chen, Y.; Gamrath, I.; Gotzes, U.; Hadjidimitriou, N.; Zittel, J.; Xu, X.; Koch, T.

About 23% of the German energy demand is supplied by natural gas. Additionally, for about the same amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by transmissions system operators (TSOs). The number one priority of the TSOs is to ensure the security of supply. However, the TSOs have only very limited knowledge about the intentions and planned actions of the shippers (traders). Open Grid Europe (OGE), one of Germany’s largest TSO, operates a high-pressure transport network of about 12,000 km length. With the introduction of peak-load gas power stations, it is of great importance to predict in- and out-flow of the network to ensure the necessary flexibility and security of supply for the German Energy Transition (“Energiewende”). In this paper, we introduce a novel hybrid forecast method applied to gas flows at the boundary nodes of a transport network. This method employs an optimized feature selection and minimization. We use a combination of a FAR, LSTM and mathematical programming to achieve robust high-quality forecasts on real-world data for different types of network nodes.

2022 - Activity Imputation of Shared e-Bikes Travels in Urban Areas [Relazione in Atti di Convegno]
Hadjidimitriou, N. S.; Lippi, M.; Mamei, M.

In 2017, about 900 thousands motorbikes were registered in Europe. These types of vehicles are often selected as the only alternative when the congestion in urban areas is high, thus consistently contributing to environmental emissions. This work proposes a data-driven approach to analyse trip purposes of shared electric bikes users in urban areas. Knowing how e-bikes are used in terms of trip duration and purpose is important to integrate them in the current transportation system. The data set consists of GPS traces collected during one year and three months representing 6,705 trips performed by 91 users of the e-bike sharing service located in three South European cities (Malaga, Rome and Bari). The proposed methodology consists of computing a set of features related to the temporal (time of the day, day of the week), meteorological (e.g. weather, season) and topological (the percentage of km traveled on roads with cycleways, speed on different types of roads, proximity of arrival to the nearest Point of Interest) characteristics of the trip. Based on the identified features, logistic regression and random forest classifiers are trained to predict the purpose of the trip. The random forest performs better with an average accuracy, over the 10 random splits of the train and test set, of 82%. The overall accuracy decreases to 67% when training and test sets are split at the level of users and not at the level of trips. Finally, the travel activities are predicted for the entire data set and the features are analysed to provide a description of the behaviour of shared e-bike users.

2022 - Developing a meta-model for early-stage overheating risk assessment for new apartments in London [Articolo su rivista]
Botti, A.; Leach, M.; Lawson, M.; Hadjidimitriou, N.

The study presents a proposed approach towards developing the core engine for a simplified Rapid Overheating ASSessment Tool (ROASST), which is intended to help assist early-stage analysis of the risks of indoor overheating for apartments located in Greater London. Using a discrete number of plan forms selected from case studies, a virtual risk database was populated with the results of a large number of parametric dynamic thermal simulations based on the EnergyPlus calculation engine and including aspects such as location within Greater London, orientation, fenestration size and natural ventilation, which are associated with known overheating risk factors. Alternative statistical meta-models were developed with both explanatory and predictive purposes, correlating the simulation input with the overheating risk predictions expressed according to multiple metrics. Results from multiple linear regression analysis show that while all factors considered are relevant towards determining the propensity to overheating, window opening and natural ventilation capacity are by far the strongest predictors among those considered. The implementation of machine learning algorithms is shown to improve the accuracy of the meta-model, producing very high coefficients of determination (R2) and lower prediction errors (RMSE). The development of a meta-model demonstrates the ability of returning accurate predictions with limited input, albeit with significant limitations. Possibilities of further improvements to the tool are briefly outlined, including the coupling with a User Interface for applicability in a design environment for early-stage design advice.

2022 - Innovative Business Models in Ports' Logistics [Relazione in Atti di Convegno]
Musso, S.; Perboli, G.; Apruzzese, M.; Renzi, G.; Hadjidimitriou, N.

Since the global request for freight transportation is increasing as a consequence of the increasing requirements of the modern economy, logistics processes need to be optimized through the application of innovative technologies, to ensure a high level of quality, flexibility, and effectiveness in logistics operations. The adoption of innovative technologies allows the creation and development of new products and services, able to optimize the existing logistics processes and create value. In particular, one of the most promising technology for logistics applications is the 5G communication network that allows, together with companion technologies such as the Internet of Things, Artificial Intelligence, and the Cloud, the collection, integration, and sharing of a large amount of data from different sources. However, to ensure the market adoption of innovative products and services, the different actors and stakeholders of the logistics chain must be involved from the early stages of the development. This allows them to keep into account their actual needs in the development process of the business models and for the future exploitation of the solutions. This paper analyzes the process of development of collaborative business models in the context of 5G-LOGINNOV, a project aimed at the development of 5G-based solutions to optimize the logistics operations in ports and retro-ports.

2021 - A Data Driven Approach to Match Demand and Supply for Public Transport Planning [Articolo su rivista]
Hadjidimitriou, Natalia; Lippi, Marco; Mamei, Marco

2021 - Enhancing port’s competitiveness thanks to 5G enabled applications and services [Relazione in Atti di Convegno]
Porelli, Andrea; Hadjidimitriou, Natalia; Rosano, Mariangela; Musso, Stefano

This work aims to evaluate a set of Critical Success Factors (CSF) that are important for port operations optimization. Furthermore, a set of 5G enabled applications is evaluated based on their importance for two typologies of companies located in the port of Hamburg, Athens and Luka Koper. More specifically, the importance of CSFs and 5G enabled applications and services is assessed based on the point of views of respondents working for technological companies and companies involved in the port’s operations, using Multi Criteria Analysis. Finally, the relationship between the CSFs and 5G applications and services is considered based on the χ 2 test of hypothesis. Then, the possibility to promote 5G applications and services as CSF for port operations optimization which will in turn increase port competitiveness, is discussed.

2021 - Mathematical optimization for efficient and robust energy networks [Capitolo/Saggio]
Hadjidimitriou, N.; Frangioni, A.; Koch, T.; Lodi, A.

2021 - Preface [Prefazione o Postfazione]
Hadjidimitriou, N.; Frangioni, A.; Koch, T.; Lodi, A.

2020 - Assessing the Impact of Shared L-Category Electric Vehicles in six European cities [Relazione in Atti di Convegno]
Dell'Amico, M.; Hadjidimitriou, N. S.; Renzi, G.

This paper proposes a methodology to assess the impact of shared light electric vehicles in urban areas. The proposed approach consists of the comparison between the emissions and costs of travels carried out by traditional cars fueled by gasoline and those performed by shared light electric vehicles in six European cities (Bari, Berlin, Genoa, Malaga, Rome and Trikala) located in four different European countries (Italy, Germany, Spain and Greece). Based on the number of kilometers traveled and a set of conversion factors, the environmental impact and the cost of fuel/electricity are assessed for the two transport modes. Furthermore, the paper proposes a methodology to create a geographical scaled up scenario that allows to evaluate emissions and costs in case of an increased use of shared electric vehicles. The data analyzed revealed that the travel time of L-category electric vehicles might be longer compared to cars. Furthermore, by replacing car trips with L-category electric vehicles, CO 2 emissions could decrease of more than 70% in one year, thus reducing about 6, 082 kg of CO 2 emissions.

2020 - Decentralized Service Platform for Interoperable Electro-Mobility Services Throughout Europe [Capitolo/Saggio]
Masuch, Nils; Eryilmaz, Elif; Küster, Tobias; Pletat, Udo; Fähndrich, Johannes; Theodoropoulos, Thodoris; Koukovini, Mariza; Hadjidimitriou, Natalia Selini; Dellas, Nikolaos

2020 - Machine Learning for Severity Classification of Accidents Involving Powered Two Wheelers [Articolo su rivista]
Hadjidimitriou, N. S.; Dell'Amico, M.; Lippi, M.; Skiera, A.

Road traffic safety is one of the major challenges for the future of smart cities and transportation networks. Despite several solutions exist to reduce the number of fatalities and severe accidents happening daily in our roads, this reduction is smaller than expected and new methods and intelligent systems are needed. The emergency Call is an initiative of the European Commission aimed at providing rapid assistance to motorists thanks to the implementation of a unique emergency number. In this work, we study the problem of classifying the severity of accidents involving Powered Two Wheelers, by exploiting machine learning systems based on features that could be reasonably collected at the moment of the accident. An extended study on the set of features allows to identify the most important factors that allow to distinguish accident severity. The system we develop achieves over 90% of precision and recall on a large, publicly available corpus, using only a set of twelve features.

2018 - Forecasting natural gas flows in large networks [Relazione in Atti di Convegno]
Dell'Amico, M.; Hadjidimitriou, N. S.; Koch, T.; Petkovic, M.

Natural gas is the cleanest fossil fuel since it emits the lowest amount of other remains after being burned. Over the years, natural gas usage has increased significantly. Accurate forecasting is crucial for maintaining gas supplies, transportation and network stability. This paper presents two methodologies to identify the optimal configuration o parameters of a Neural Network (NN) to forecast the next 24h of gas flow for each node of a large gas network. In particular the first one applies a Design Of Experiments (DOE) to obtain a quick initial solution. An orthogonal design, consisting of 18 experiments selected among a total of 4.374 combinations of seven parameters (training algorithm, transfer function, regularization, learning rate, lags, and epochs), is used. The best result is selected as initial solution of an extended experiment for which the Simulated Annealing is run to find the optimal design among 89.100 possible combinations of parameters. The second technique is based on the application of Genetic Algorithm for the selection of the optimal parameters of a recurrent neural network for time series forecast. GA was applied with binary representation of potential solutions, where subsets of bits in the bit string represent different values for several parameters of the recurrent neural network. We tested these methods on three municipal nodes, using one year and half of hourly gas flow to train the network and 60 days for testing. Our results clearly show that the presented methodologies bring promising results in terms of optimal configuration of parameters and forecast error.

2017 - Classification of Livebus arrivals user behavior [Articolo su rivista]
Hadjidimitriou, N.; Mamei, M.; Dell'Amico, M.; Kaparias, I.

With the increasing use of Intelligent Transport Systems, large amounts of data are created. Innovative information services are introduced and new forms of data are available, which could be used to understand the behavior of travelers and the dynamics of people flows. This work analyzes the requests for real-time arrivals of bus routes at stops in London made by travelers using Transport for London's LiveBus Arrivals system. The available dataset consists of about one million requests for real-time arrivals for each of the 28 days under observation. These data are analyzed for different purposes. LiveBus Arrivals users are classified based on a set of features and using K-Means, Expectation Maximization, Logistic regression, One-level decision tree, Decision Tree, Random Forest, and Support Vector Machine (SVM) by Sequential Minimal Optimization (SMO). The results of the study indicate that the LiveBus Arrivals requests can be classified into six main behaviors. It was found that the classification-based approaches produce better results than the clustering-based ones. The most accurate results were obtained with the SVM-SMO methodology (Precision of 97%). Furthermore, the behavior within the six classes of users is analyzed to better understand how users take advantage of the LiveBus Arrivals service. It was found that the 37% of users can be classified as interchange users. This classification could form the basis of a more personalized LiveBus Arrivals application in future, which could support management and planning by revealing how public transport and related services are actually used or update information on commuters.

2016 - An analysis of drivers route choice behaviour using GPS data and optimal alternatives [Articolo su rivista]
Ciscal Terry, Wilner; Dell'Amico, Mauro; Hadjidimitriou, Natalia Selini; Iori, Manuel

This work aims to study drivers' route choices using a dataset of low frequency GPS coordinates to identify travels' trajectories. The sample consists of 89 drivers who performed 42 thousand paths in the province of Reggio Emilia, in Italy, during the seventeen considered months. Four attributes that may be important for the driver are identified and four optimal alternative paths are created based on the selected objectives to evaluate route choice behaviour. The comparison between the characteristics of the paths allows to conclude that drivers select routes that are overall longer than their optimal alternatives but that allow for higher speeds. Furthermore the statistical analysis of drivers' route choices in macroareas evidences that drivers have different behaviours depending on the geography of the territory. Specifically, there is higher heterogeneity of route choices in the plain areas compared to the mountains. In the second part of this work, clusters of repetitive travels are identified and a Geographical Route Directness Index is proposed to identify the areas of the province where the deviation from the shortest alternative path is higher. The analysis shows that, among groups of repetitive travels, the value of the index is higher along the ring road of the city of Reggio Emilia and there is a strong negative correlation between the frequency the driver selects the longer alternative that allow for higher speed, and the number of additional kilometres the same driver has to travel.

2015 - A Framework for Appraising European Member States' Readiness Level for eCall Deployment [Relazione in Atti di Convegno]
Hadjidimitriou, N.; Oorni, R.

This work provides a general overview of the main findings of two European projects, HeERO and HeERO2 aimed at facilitating the implementation of the eCall in-vehicle emergency call service in Europe. The representatives of 15 European Member States (MS) participated in the project's activities with the objective to demonstrate the functioning of the eCall. The projects identified several layers that form the eCall value chain. Based on these layers, a questionnaire was prepared and presented to MS representatives to identify the main barriers and enablers at country level. The results of the survey were used in the project to create the guidelines and recommendations for eCall deployment. The main contribution of the paper consists of the evaluation of the HeERO MS readiness level to implement eCall. To this aim, a set of evaluation criteria are measured based on the answers provided by the MS representatives. Furthermore, two multicriteria approaches are selected and implemented: the PROMETHEE and the PAPRIKA methods that consist in performing pairwise comparisons of alternatives. The outcome of the analysis is a ranking of HeERO countries based on their readiness level to implement eCall by October 2017, which is the mandatory deadline that has been set up by the European Commission.

2015 - Assessing the consistency between observed and modelled route choices through GPS data [Relazione in Atti di Convegno]
Hadjidimitriou, Natalia; Dell'Amico, Mauro; Cantelmo, Guido; Viti, Francesco

In traffic engineering, different assumptions on user behaviour are adopted in order to model the traffic flow propagation on the transport network. This paper deals with the classical hypothesis that drivers use the shortest possible path for their trip, pointing out the error related to using such approximation in practice, in particular in the context of dynamic origin-destination (OD) matrix estimation. If this problem is already well known in the literature, only few works are available, which provide quantitative and empirical analysis of the discrepancy between observed and modelled route sets and choices. This is mainly related to the complexity of collecting suitable data: to analyse route choice in a systematic way, it is necessary to have observations for a large period of time, since observing trajectories for the single user on a specific day could not be enough. Information is required for several days in order to analyse the repetitiveness and understand which elements influence this choice. In this work the use of the real shortest path for a congested network is evaluated, showing the differences between what we model and what users do. Results show that there is a systematic difference between the best possible choice and the actual choice, and that users clearly consider route travel time reliability in their choice process.

2012 - Innovative Logistics Model and Containers Solution for Efficient Last Mile Delivery [Relazione in Atti di Convegno]
Dell’Amico, Mauro; Hadjidimitriou, Selini

Urban goods distribution is important for the economy. However urban transport causes traffic, noise and pollution. The European Research project CityLog (part of Framework Programme 7) aims at increasing efficiency in urban distribution by proposing a logistics model based on two types of vehicles and containers solution in the context of parcel delivery. The urban delivery scheme currently consists of a number of vehicles that leave the hub and drive towards the city. The innovative logistics model for urban deliveries introduces a concept which make use of two types of vehicles: a Freight bus which is loaded at the depot with several load units that can carry generic parcels, and a Delivery van which is a light vehicle with high eco-compatible characteristics that make it very suitable to be used in the inner city Each load unit, when transferred from the Freight bus to the Delivery van, replaces the body of the van. These interoperable vehicles and containers form an improved logistics chain, reducing the number of vehicles entering the city, chilometers driven and pollutant emissions. Another source of unnecessary driven chilometers is unsuccessful deliveries when the receiver is not home during the delivery. The Modular BentoBox is the second concept introduced by the project. It allows to obtain a balance between optimisation of logistics and customers' interests by delivering goods to the bentobox, instead that to the customer location.. There parcels are stored in the bentobox until the customer picks them up. The Modular BentoBox System introduces the concept of removable modules that is trolleys with various size drawers. These trolleys and their drawers are filled in with parcels at the depot. The carrier transports the trolleys downtown and inserts them into the bentobox. As soon as the customer is notified, the parcel is ready at the bentobox. To access the parcel, the customer enters his special code on a user interface. The Modular BentoBox System can also be provided with a weighting and payment system and used for shipping parcels. The trolleys with shipments are taken back to the depot by the carrier. These CityLog concepts will be implemented and tested in 2012 in three European cities: Berlin, Lyon and Turin. (C) 2012 Published by Elsevier Ltd. Selection and/or peer review under responsibility of the Programme Committee of the Transport Research Arena 2012

2011 - CityLog - Sustainability and efficiency of city logistics: The M-BBX (Modular BentoBox System) [Relazione in Atti di Convegno]
Dell'Amico, M.; Deloof, W.; Hadjidimitriou, N.; Vernet, G.; Schoenewolf, W.

This paper presents some of the results of CityLog, a European Union project approved in the context of the 7th Framework Programme that is still ongoing and will terminate at the end of 2012. The project is intended to increase the sustainability and the efficiency of urban delivery of goods through an adaptive and integrated mission management and innovative vehicle solutions. Three partners of the CityLog consortium were in charge of the design and realization of a new container concept which had to be adapted to the associated innovative vehicles solutions for load units' handling operation. © 2011 IEEE.