1,720,985 research outputs found
Advanced techniques for aircraft bearing diagnostics
Full text linkThe task is the creation of a method able to diagnose and monitor bearings healthy, mainly in case of varying external conditions. The ability of the technique is verified through data acquisition on a laboratory test rig, where various operating conditions could be checked (load, speed, temperature). Signal processing techniques and data mining techniques are applied to analyse the data
A study of tour-based mode choice based on a Support Vector Machine classifier
Full text linkA new approach in recognizing travel mode choice patterns is proposed, based on the Support Vector Machine classification technique. The tour-based travel demand dataset that is analysed is for New York State, derived from the 2009 U.S. National Household Travel Survey. The main features characterizing each tour are the means used, travel-related variables and socioeconomic aspects. Results obtained demonstrate the ability to predict to some extent, in real settings where car use dominates, which tours are likely to be made by public transport or non-motorized means. Moreover, the flexibility of the technique allows assessing the predictive power of each feature according to the combination of travel means used in different tours. Potential applications range from activity-based travel choice simulators to search engines supporting personalized travel planners – in general, whenever ‘best guesses’ on mode choice patterns have to be made quickly on large amounts of data prejudicing the possibility of setting up a statistical model
Integrating mobility data sources to define and quantify a vehicle-level congestion indicator: an application for the city of Turin
Full text linkPurpose: Traffic congestion is a large-scale problem in urban areas all over the world that can lead to substantial costs for travellers and business operations. This paper focus on how to measure the way in which congestion selectively affects different traffic streams, with special emphasis on light duty vehicles travelling around a city.
Methods: The idea is to integrate a dataset collecting Global Positioning System (GPS) vehicle traces with road side data sources related to traffic conditions in a road network, which on the other hand usually lack focus on specific traffic streams. The core of the data integration method is the creation of a specific indicator focusing on the time lost in congestion. This is a Key Performance Indicator (KPI) of an urban network that is of paramount importance as a decision support tool for policy makers, also because it has an impact on other key issues such as air pollution, noise emissions, energy efficiency and health problems. Then, a method is proposed to quantify the congestion KPI in a highly disaggregated fashion (each single vehicle travelling on each single link or street segment).
Results: This KPI can be used to inform a wide range of policy actions within the transport sector, both from the viewpoint of a city and from that of an individual actor of the transport system, such as the operator of a fleet of vehicles for urban freight deliveries. Some preliminary examples of how the aggregation of the KPI at different scales can provide insights into the transport system are presented
Classification of tours in the U.S. National Household Travel Survey through clustering techniques
Full text linkTours are increasingly being considered as an appropriate unit of observation of mobility behaviors and are one of the key ideas underpinning contemporary activity-based modeling approaches. Identifying typologies of tours would benefit both modelers and decision makers, striving to set up more tailored actions aimed at promoting environmentally benign travel choices. Different a priori classifications based on activity kinds have been proposed, none of which seems clearly preferable on empirical grounds. This paper takes a complementary approach and defines a data-driven segmentation through a cluster analysis of tours that were derived from the trip records from a United States national survey. The socioeconomic characterization of each cluster is finally carried out to link travelers' profiles with specific kinds of tours. Four main tour clusters have thus been identified: nonwork tours for compulsory activities done by young individuals, tours done by elder or retired persons, short and secondary tours within the travel day, and tours dominated by the working activity. Their relevance on a modeling and policy viewpoint is discusse
Stated interest, actual use or indifference towards car sharing: profiling students and staff of a university campus in Turin (Italy)
Full text linkA mobility survey was proposed to the staff and to the students of Politecnico di Torino (a technical university located in Turin, Italy) in autumn 2016 with a focus on the interest and on the current use of car sharing. Turin is in fact offering a relatively broad variety of such services, with several different operators and a fleet of about 700 vehicles. A data mining technique, named co-clustering, is then applied to the dataset of 1314 answers in order to characterise respondents’ profiles and assess to which extent specific combinations of variables describing personal, travel-related or satisfaction with travel aspects are associated with the actual use, the interest or the lack of interest in car sharing. Early adopters of car sharing are more frequently encountered among students than among staff and show more multimodal behaviours. The levels of use of different modes can be helpful in discriminating between mere positive attitudes towards car sharing and actual intention to use it, while travel related satisfaction ratings are rather indicating the interest or lack of interest in this service. Among university workers, younger females living in the outer part of the metropolitan city showed a good interest in car sharing, although the service is not available in the place where they live. Policy implications of such findings within a mobility management perspective are discussed
A comparative assessment of synthetic indices to measure multimodality behaviours
Full text linkThe study of how people jointly use different travel means is one of the key issues in contemporary transport research. However, measuring multimodality behaviours presents some intricacies that deserve more attention in order to come up with an instrument that is effective both on a modelling and on a policy viewpoint. The present work considers some methods that have been proposed in different disciplinary ambits to measure diversity and assesses to what extent they are useful to measure multimodality. A broad set of indices is then analysed, ranging from welfare economics (Gini, Dalton and Atkinson indices) to information theory and ecology (entropy, Herfindahl index). Theoretical investigations and empirical experiments on the properties of such indices show that there is not a measure of multimodality that consistently outperforms all the others in any circumstance. On the other hand, it emerged that some methods are clearly preferable for specific problem instances, as discussed in the conclusion
Preliminary Investigation of Women Car Sharing Perceptions Through a Machine Learning Approach
Full text linkMobility studies have shown that travel patterns and means use vary a lot comparing women and men behavior. In recent years, new solutions have been introduced in the urban mobility offer and the interest raised in investigating how they can help in reducing the gender mobility gap. The current work analyzes 2934 responses collected through a car sharing survey proposed in Italy with the precise objective of considering women and men like different kinds of users to delineate characteristics that could influence car sharing modal choice. A hierarchical clustering technique is applied to the dataset collecting a selection of questions, mainly focusing on socioeconomics features, travel patterns and individual habits. The algorithm identifies 8 clusters in the male dataset and 9 clusters in the female one, defined according to characteristics aggregating the survey respondents. Thus, a selection of these groups of respondents is analyzed in more detail according to their percentage of car sharing users, also comparing the results among male and female datasets. Many common attributes are found in clusters irrespective of the gender, showing how the interest (and its lack) toward this service affects women and men similarly. At the same time, this analysis helps in identifying the features characterizing the users to investigate how this new mobility offer can help in reducing the gender mobility gap
Comparing Transport Quality Perception among Different Travellers in European Cities through Co-Cluster Analysis
Full text linkThe quality of the transport system offered at city level constitutes an important and challenging goal for society, for local authorities, and transport operators. Therefore, appropriate evaluation of travellers’ satisfaction is required to support service performance monitoring, benchmarking, and market analysis. This aspect implies the collection of satisfaction levels for different passengers’ groups, as it could provide interesting suggestions for identifying priority areas of action. To this end, an original study aimed at understanding the main aspects affecting the common view of satisfaction among different kinds of travellers at European level is presented in this paper. A specific survey investigating how travellers perceive the quality of their journey is proposed to people living in cities characterised by different sizes. Data are then analysed through a multi-view co-clustering algorithm, an innovative machine learning technique that highlights clusters of respondents grouped according to various categories of features. Such results could be used by local authorities and transport providers to understand the specific actions to be operated to improve the quality of transport service offered in a market segmentation dimension
External condition removal in bearing diagnostics through EMD and One-Class SVM
Full text linkThe removal of the running conditions influencing data acquisitions in rotating machinery is a very important task because it could avoid some misunderstandings when diagnostic techniques are applied. This paper introduces a new parameter that could be able to identify damage in a rotating element of a roller bearing removing the effect of speed and external load. The parameter proposed in this paper is evaluated through Empirical Mode Decomposition (EMD). Our algorithm proposes firstly the decomposition of the acceleration vibration signals into a finite number of Intrinsic Mode Functions (IMFs) and then the evaluation of the energy for each one of these. Data are acquired both for a healthy bearing and for one with a 450 μm large indentation on a rolling element. Three different speeds and three radial loads are monitored for both cases, so nine conditions can be evaluated for each type of bearing overall. The parameters obtained, namely energy evaluated for a certain number of IMFs, are then used to train a One-Class Support Vector Machine (OCSVM). Healthy data belonging to the nine different conditions are taken into account and OCSVM is trained while other acquisitions are given to the classifier as test object. Since the real class membership is known, we consider how many errors the labelling produces. We compare these results with those obtained by considering a wavelet decomposition. Energies are evaluated for each level of decomposition and the previous approach is then applied to these parameter
- …
