Mauro Dell'Orco

A Node-Based Modeling Approach for the Continuous Dynamic Network Loading Problem

In this paper, an analytical dynamic node-based model is proposed both to represent flows on a highway traffic network and to be utilized as an integral part of a dynamic network loading (DNL) process by solving a continuous DNL problem. The proposed model formulation has an integrate base structured with a mesoscopic link load-computing component that explicitly takes into account the acceleration behavior of discrete vehicle packets and an algorithm written with a set of nodal rules considering the constraints of link dynamics, flow conservation, flow propagation, and boundary conditions. The solution to the model formulation is obtained by simulation, where the coded algorithm of the proposed solution method is run after designing a discrete version of the problem. The performance of the proposed model, as a DNL model, is tested on a sample highway network following its validation study that is obtained on a sample highway node. It is seen that the proposed model provides consistent approximations to link flow dynamics. The new dynamic node model proposed in this paper is unique in that it encapsulates a mesoscopic approach in node-based flow dynamics modeling.

Modelling Parking Choice Behaviour using Possibility Theory

This article presents a discrete choice model for evaluating parking users’ behaviour. In order to explicitly take into account imprecision and uncertainty underlying a users choice process, the proposed model has been developed within the framework of Possibility Theory. This approach is an alternative way to represent imperfect knowledge (uncertainty) of users about both parking and transportation system status, as well as the approximate reasoning of the human decision maker (imprecision). The resulting model is a quantitative soft computing tool that could support traffic analysts in planning parking policies and Advanced Traveller Information Systems. In fact, effects of information on user choice can be incorporated into the model itself. Thus, we consider the parking user be a decision maker who assumes a certain choice set (set of perceived parking alternatives); the user has some information about the parking supply system and he/she associates each parking alternative with an approximate perceived cost/utility that is represented by a possibility distribution; and, finally, the user chooses the alternative which minimises/maximises his/her perceived parking cost/utility. The results show how the model is able to represent the effect of various parking policies on users’ behaviour and how the single component of parking policy affects the decision process.

A hybrid approach to combine fuzziness and randomness in travel choice prediction

Abstract Several approaches have been developed in order to deal with uncertainty, in the prediction of travellers’ choices. Uncertainty almost always affects travel alternatives in several different choice contexts. However, the way in which this uncertainty affects choice options may consistently vary. Two main types of uncertainty can be identified: randomness and fuzziness. This paper discusses the use of a hybrid approach for choice modelling of travellers’ behaviour in choice contexts that involve conditions of high variability and uncertainty. The aim of the work is to implement a hybrid methodology, based on the use of a two-term hybrid utility, which allows taking into account, at the same time, the effects of both random and fuzzy uncertainty on travellers’ choice behaviour. An application of the proposed methodology to a transit choice context is then presented.

A Dynamic Model for Acceleration Behaviour Description in Congested Traffic

In this paper, a mesoscopic dynamic model is utilized to depict the acceleration behaviour of congested traffic flow by overcoming the speed averaging drawback. The model is developed by both considering the oversaturation phenomenon and improving the computational efficiency on a previously proposed link model. Link exit function formulation, discretisation on time dimension, definition of capacity constraint rules for over-saturated states and uniformly accelerated speed assumption that allows a realistic representation of flow dynamics is made while setting out the model. Computation of link flows is performed regarding the acceleration of vehicles that validates the consistency of flow propagation with speed. In the presence of step-ups and step-downs on speed, adaptation of flow propagation is simultaneous, relative to the time lag defined to discretise time dimension. The iterative structure of the model enables convergence to any target performance criteria with the coded algorithm.

New Decision Support System for Optimization of Rail Track Maintenance Planning Based on Adaptive Neurofuzzy Inference System

It is well known that maintenance planning affects, in general, the life of the structures, material wear, and quality of service. In particular, the maintenance of rail tracks affects the traffic volume as well, and therefore it is an important issue for the management of a railway system. Accurate maintenance planning is necessary to optimize resources. The condition of railways is checked by special diagnostic trains. Because of the vast amount of data that these trains record, it is necessary to analyze these data through an appropriate decision support system (DSS). However, the most up-to-date DSSs, such as EcoTrack, are based on a binary logic with rigid thresholds and complicated algorithms with a large number of rules that restrict their flexibility in use. In addition, they adopt considerable simplifications in the rail track deterioration model. In this paper, a neurofuzzy inference engine has been implemented for a DSS to overcome these drawbacks. Based on fuzzy logic, it was able to handle thresholds expressed as a range, an approximate number, or even a verbal value. Moreover, through artificial neural networks, it was possible to obtain more precise rail track deterioration models. The results obtained with the proposed model have been clustered through a fuzzy procedure to optimize the maintenance schedule, thus grouping the interventions in space and in time.

Web community of agents for the integrated logistics of industrial districts

Industrial districts are characterized by the agglomeration of medium and small-sized industries, localized within a certain geographic area with precise social and cultural connotations. A crucial element of industrial districts is the existence of a wide immaterial flow of knowledge and information. In this sense, industrial districts seem to have a network shape, rather than a hierarchical one. The paper aims to rationalize transportation flow within industrial districts. In particular, it focuses on districts in the first stage of the evolution process; that is, when a lot of companies exist, with low specialized level and absent inter-firm cooperation. Therefore, the considered industrial districts are characterized by nonlinear mechanisms of interaction among a variety of entrepreneurs, each of them trying to reach their target by conflicting with others, increasing the complexity of the system under examination and making more difficult the strategies for material flow rationalization. In this situation, a system able to facilitate both the contacts among agents and the negotiation processes, that creates a community of agents in a district with rare or absent relationships among different companies represents the most adequate solution. The paper deals with the definition of a community of agents in a real situation, using communityware tools - Web electronic media that facilitate contact with collaborators who have similar interests and preferences, but do not know each other. To define the similarity concept, a fuzzy algorithm is proposed.

User-Oriented Model to Support Funding Decisions in Pavement Management

A new choice model for corrective road maintenance work based on an economic evaluation of users’ expectations and perceptions about road quality is proposed. Because uncertainty affects human subjective perception processes, the model uses fuzzy sets to deal with this kind of uncertainty. Accordingly, the international roughness index was first fuzzified by combining users’ perceptions about pavement conditions with ranges of speeds for four different categories of rural roads. These fuzzy values were then used to calculate vehicle operating costs and freeflow speed. The latter can be considered a function of the international roughness index and the law enforcement factor. To calculate this factor, a fuzzy inference system was set up. Vehicle operating costs and free-flow speed, as well as the value of time, were then used to calculate the travel cost perceived by users. The model finds, through fuzzy maximization of the difference between perceived travel costs before and after interventions, the best allocation of the available budget for a rural road network. In other words, the results suggest the extent of interventions on specific road sections. An application to a real network shows how the proposed model may be used.

General Regression Neural Network Method for Delay Modeling in Dynamic Network Loading

In vehicular traffic modeling, the effect of link capacity on travel times is generally specified through a delay function. In this paper the Generalized Regression Neural Network (GRNN) method that supports a dynamic network loading (DNL) model is utilized to model delays on an unsignalized highway node. The presented DNL model is constructed with a linear travel time function for link performances and an algorithm written with a set of rules considering the constraints of link dynamics, flow conservation, flow propagation, and boundary conditions. The GRNN method is utilized in the integrated model structure in order to provide a closer functional approximation to pre-defined flow-rate delay function, a conical delay function (CDF). Delays forming as a result of capacity constraint and flow conflicting at an unsignalised node are calculated with selected GRNN configuration after calibrating the neural network component with the CDF formulation. The output of the model structure, run solely with the CDF, is then compared to evaluate the performance of the model supported with GRNN relatively.

A multivariate logic decision support system for optimization of the maritime routes

In recent years, maritime freight transportation and the consequent handling of containers are among the most dynamic and growing sectors. The aim of this research is to propose a Decision Support System (DSS) addressed mainly to shipping companies, allowing the choice, even en-route, of the hub port of destination for the successive multi-modal operations. The companies make choices in relation both to the ship location and to a dynamic accessibility indicator. The accessibility indicator is generally accepted as the parameter that better represents the interactions between a port and its hinterland. Different factors can influence the accessibility in maritime transport; some of them are characterized by low variability, while others show a high within-day dynamics. For example, the technical characteristics of ports (number of berths and their depths, number of cranes, storage area, etc.) belong to the first group; instead, the number of free berths, the delay time in freight loading and unloading operations, and weather conditions can change during the day. Their variability can be evaluated by a real-time monitoring, while the ship location can be easily obtained by GPS and radar signals. In the proposed DSS, we have considered data about the technical characteristics of ports and, depending on the request coming from ships, acquires the dynamic characteristics of each port, the ship location and the destination area. After the completion of the process, the DSS provides as output the port “closer” to the requests expressed by the users. Since some current values of both the dynamic characteristics of ports and information provided by shipping companies are subject to uncertainty, we proposed a DSS based on a multivariate accessibility indicator.

Delay Modelling at Unsignalized Highway Nodes with Radial Basis Function Neural Networks

In vehicular traffic modelling, the effect of link capacity on travel times is generally specified through a delay function. In this paper, the Radial Basis Function Neural Network (RBFNN) method, integrated into a dynamic network loading process, is utilized to model delays at a highway node. The results of the model structure have then been compared to evaluate the relative performance of the integrated neural network method.