Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.最新文献

{"title":"Identification of rear-end crash patterns on instrumented freeways: a data mining approach","authors":"A. Pande, M. Abdel-Aty","doi":"10.1109/ITSC.2005.1520155","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520155","url":null,"abstract":"Data mining is the analysis of large \"observational\" datasets to find unsuspected relationships that might be useful to the data owner. It typically involves analysis where objectives of the mining exercise have no bearing on the data collection strategy. Freeway traffic surveillance data collected through underground loop detectors is one such \"observational\" database maintained for various ITS (intelligent transportation systems) applications such as travel time prediction etc. In this research data mining process is used to relate this surrogate measure of traffic conditions (data from freeway loop detectors) with occurrence of rear-end crashes on freeways. The results from this analysis are envisioned to be the first step in the development of a functional proactive traffic management system. The dataset under consideration includes information on crashes and corresponding traffic data collected from detectors neighboring the crash locations just prior to the time of the crash. The problem is setup as a classification problem for a crash being rear-end vs. not. Three types of classification tree involving different splitting criterion were attempted for variable selection. It was found that the classification tree with chi sq. test as the splitting criterion resulted in the most inclusive list of variables. The variable selection was followed by two neural network architectures, namely, the RBF (radial basis function) and MLP (multi-layer perceptron) to model the binary target variable. The two neural network models were then combined based on their output to achieve any possible improvement in the classification accuracy. It was found, however, that the classification tree model with chi sq. test as splitting criterion (with more than 65% classification accuracy) was better than any of the individual or combined neural network models (54-55% classification accuracy). Since the decision tree model also provides simple interpretable rules to classify the data in a real-time application it was recommended as the final classification model.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124176493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transfer journey identification and analyses from electronic fare collection data","authors":"M. Hofmann, M. O’Mahony","doi":"10.1109/ITSC.2005.1520156","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520156","url":null,"abstract":"Understanding the behaviour of public transport passengers is key to providing a system from which passengers will derive the maximum benefit. One method of analysing this behaviour is with the use of passenger boarding data, stored in a database. Such a database may be improved by enriching the already existing dataset by applying specific algorithms. This paper describes an iterative classification algorithm that classifies passenger boardings into two categories; transfer journeys and single journeys. The dataset used was from an urban public transport operator with a large fleet (over 1000 buses) and data of 48 million magnetic strip card boardings from 1998 and 1999. This paper details the process involved in the initial development of the iterative classification algorithm, the analysis of transfer node identification matrices, waiting time information charts and spatial first/second boarding matrices. When the algorithm is applied to the dataset it provides transport planners with valuable information with regard to passenger boardings, transfers and waiting times which can assist them in transport planning and policymaking. The purpose of this paper is to describe the automatic generation of a new data attribute that cannot be derived directly and therefore increases the future utilization of the dataset. The paper presents various analyses based on the extended and enriched database to illustrate this point.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125274385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New development of an overall train inspection system for increased operational safety","authors":"T. Maly, M. Rumpler, H. Schweinzer, A. Schoebel","doi":"10.1109/ITSC.2005.1520059","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520059","url":null,"abstract":"The free market forces infrastructure operators to increase their operational efficiency. To achieve this, among other things personnel costs have to be reduced. This implicates the reduction of the number of train station inspectors. Since they were also responsible for checking the passing trains for fault states, the higher distances of unobserved movement of trains result in higher risks of heavy accidents. On the other hand, there were numerous developments of new sensor-systems for checking the mentioned train fault states. Unfortunately, all of these systems focus only on singular or at least on several particular deviations from normal and are completely stand-alone solutions. At higher passing speeds the accuracy and the reliability of these systems varies in a wide range. This is an important reason why today's fault-checking sensor systems are only used for alarming manned train guidance stations. Taking these trends into account, the demand for an overall train inspection system is obvious and resulted in a research project called \"Checkpoint\", which is funded by the Austrian government. Our approach is based on the acquisition of all relevant train properties to get knowledge of the complete train condition for better failure estimation. Thus, a concept for efficient integration of commercially available sensor systems and for universal data treatment was developed. It enables easy configuration of the data analysis and definition of fail-states by a rule based mechanism. The main technical innovation of the system comes from the direct connection to the interlocking system via the control system, which offers the ability to intervene automatically in case of a detected failure (e.g. stopping the train). To determine the reliability of new sensor systems under realistic conditions a prototype of a Checkpoint was built up and the most relevant sensor systems (hot box detector, flat wheel detector, dynamic scale and loading gauge detector) were integrated. Extensive testing would be performed to prove the functionality of the system.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124989127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new incident detection scheme developed in the Netherlands","authors":"W. Knibbe, A. Oostveen, H. Bokma, D. Poot-Geers","doi":"10.1109/ITSC.2005.1520103","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520103","url":null,"abstract":"Incident management can significantly reduce incidental congestion and improve traffic safety. Quick and accurate detection of incidents is required to start incident management. Dutch traffic control centers operated by the national road manager Rijkswaterstaat have real-time traffic speed and flow data available. We describe in this paper a new scheme that employs these data for detecting incidents. We also present results of field tests of this scheme, performed over a period of several months. It appears that this algorithm provides generally useful and low cost detection, in case real-time traffic data are available.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126684945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single camera lane detection and tracking","authors":"D. Schreiber, B. Alefs, M. Clabian","doi":"10.1109/ITSC.2005.1520207","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520207","url":null,"abstract":"In this paper we present a method to detect and track straight lane boundaries, using a forward-looking single camera mounted on-board. The method proved to be robust, even under varying lighting conditions, and in the presence of heavy shadowing cast by vegetation, vehicles, bridges, etc. Moreover, false positive hardly occur. The lane markings are being continuously detected even when the vehicle is performing maneuvers such as excursion or lane change. The performance is achieved by a novel combination of methods, namely, by first finding vanishing point candidates for the lane boundaries, and later by the careful selection of line segments given a vanishing point, and finally by using a smart heuristics to select the whole set of four lane boundaries. Suppression of false positives is further achieved by tracking the vanishing point, and by constraining the lane width based on recent history.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120955723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of a vehicle-to-vehicle based traffic information system","authors":"Jiang Zhang, A. Ziliaskopoulos, Ning Wen, R. Berry","doi":"10.1109/ITSC.2005.1520094","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520094","url":null,"abstract":"This paper is concerned with a vehicle-to-vehicle based traveler information system. The system relies on information exchanged by the vehicles themselves in a peer-to-peer manner; it does not involve any public investment from government agencies to build, manages and maintains the necessary infrastructure. This paper discusses the prototype design that utilizes the IEEE 802.11 wireless standards for inter-vehicle communication. A location-based broadcasting protocol is presented as well as the simulation results on an actual traffic network.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127898189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A general framework for the management of transportation systems affected by recurrent adverse weather conditions","authors":"P. Fiorucci, F. Gaetani, R. Minciardi","doi":"10.1109/ITSC.2005.1520218","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520218","url":null,"abstract":"In the paper, an integrated approach is presented, able to support the decision makers in the planning phase and in preventive/real time phases relevant to transportation systems subject to recurrent severe weather conditions. In the planning phase regressive models are carried out in order to measure the impact of adverse weather conditions on the efficiency of the traffic network, aiming at identifying the links most heavily responsive to such conditions. Besides, a weather responsive traffic management system (WRTMS), based on dynamic models and optimisation, is presented and discussed. Such a system has the purpose of supporting traffic managers in all decisions concerning the preventive location/allocation of resources able to mitigate the effect of weather conditions on the traffic infrastructures, as well as the real-time traffic management.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127953488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of adverse weather conditions on urban bus performance measures","authors":"M. Hofmann, M. O’Mahony","doi":"10.1109/ITSC.2005.1520087","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520087","url":null,"abstract":"Increases in congestion levels caused by adverse weather conditions are difficult to predict and therefore urban bus operators cannot incorporate appropriate changes into their planning, scheduling, and management decisions. Adverse weather conditions have an impact on the level of service an operator provides. They also result in higher levels of congestion due to an increase of personal car usage. The aim of the research paper is to investigate the impact of adverse weather conditions on urban bus performance measures. The Irish city which is used for this study given its geographical location experiences a maritime climate, dominated by low pressure from the Atlantic bringing cold wet weather with the trade winds. The study includes various types of performance measures such as ridership, frequency, headway regularity and travel time, which are analysed both in the presence and absence of adverse weather conditions. The performance measures include changing variables such as stage and destination, peak and off-peak, inbound and outbound in order to provide a comprehensive analysis. The data used for this research originate from an electronic fare collection system. 46 million individual boarding records are stored in the database. The results of the research paper include the calculation and presentation of various analysed performance measures followed by an extensive interpretation of how this information can support decision-making. The quantitative analysis method aims to improve and adjust planning, scheduling, and management decisions of urban bus operators and thereby alter and improve operations and level of service provided.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129123912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimal signal controls and effects of flow uncertainty","authors":"C. Lan, Xiaojun Gu","doi":"10.1109/ITSC.2005.1520107","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520107","url":null,"abstract":"This study examines effectiveness of a manual procedure for signal timing optimization, consisting of a modified Webster cycle length formulation applicable in saturated conditions and the equalized degree-of-saturation principle for green time allocation. Effects of statistical uncertainty of flows on control actions and delay performance are also investigated. The results indicate that the proposed procedure produces near-optimal delay performance, and performs as well as the state-of-the-art solution algorithms such as SOAP and TRANSYT with much less computation time. To evaluate effects of flow uncertainty, both stochastic mean and variance of control actions are derived based on approximation. The results show that approximations are reasonably accurate. Magnitude of changes in control actions relative to their means is linearly related to magnitude of statistical uncertainty in arrival flows. The control actions, especially cycle lengths, are less sensitive to flow uncertainty in saturated conditions. Delay performance is subjected to both direct and indirect effects from flow uncertainty. The stochastic mean of delay is always greater than the deterministic mean, indicating that ignoring flow uncertainty will substantially underestimate delay if degree of uncertainty is significant. When control actions are composed based on the actual flows, the mean of stochastic delay will reduce significantly, confirming that the adaptive control is much effective than the deterministic control. The Monte-Carlo simulation study also shows that if control actions deviate more than 3% to 7% from the perfect state, delay performance will substantially deteriorate. Error in flow predictions will affect the effectiveness of control actions and, consequently, delay performance. This study shows that the adverse effect of error in flow prediction on delay is slightly less than the imperfect controls. The margin of error in flow predictions, ranging from 4% to 10%, increases as the flow uncertainty grows.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116849600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A global optimization algorithm for stereo calibration","authors":"A. Abellard, M. Bouchouicha, M. Khelifa","doi":"10.1109/ITSC.2005.1520140","DOIUrl":"https://doi.org/10.1109/ITSC.2005.1520140","url":null,"abstract":"The aim of this paper is to propose an efficient solution to the codesign of a stereo calibration operation based on a hybrid approach using genetic algorithms and a nonlinear local search process. This solution can then be easily described by data flow Petri nets, for an implementation through a hardware description language.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134249652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}