Home About us Contact
|
Home About us Contact | ||
|
|
||
Traffic Data (traffic + data)
Selected AbstractsEnhancing Neural Network Traffic Incident-Detection Algorithms Using WaveletsCOMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, Issue 4 2001A. Samant Researchers have presented freeway traffic incident-detection algorithms by combining the adaptive learning capability of neural networks with imprecision modeling capability of fuzzy logic. In this article it is shown that the performance of a fuzzy neural network algorithm can be improved through preprocessing of data using a wavelet-based feature-extraction model. In particular, the discrete wavelet transform (DWT) denoising and feature-extraction model proposed by Samant and Adeli (2000) is combined with the fuzzy neural network approach presented by Hsiao et al. (1994). It is shown that substantial improvement can be achieved using the data filtered by DWT. Use of the wavelet theory to denoise the traffic data increases the incident-detection rate, reduces the false-alarm rate and the incident-detection time, and improves the convergence of the neural network training algorithm substantially. [source] Feature Extraction for Traffic Incident Detection Using Wavelet Transform and Linear Discriminant AnalysisCOMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, Issue 4 2000A. Samant To eliminate false alarms, an effective traffic incident detection algorithm must be able to extract incident-related features from the traffic patterns. A robust feature-extraction algorithm also helps reduce the dimension of the input space for a neural network model without any significant loss of related traffic information, resulting in a substantial reduction in the network size, the effect of random traffic fluctuations, the number of required training samples, and the computational resources required to train the neural network. This article presents an effective traffic feature-extraction model using discrete wavelet transform (DWT) and linear discriminant analysis (LDA). The DWT is first applied to raw traffic data, and the finest resolution coefficients representing the random fluctuations of traffic are discarded. Next, LDA is employed to the filtered signal for further feature extraction and reducing the dimensionality of the problem. The results of LDA are used as input to a neural network model for traffic incident detection. [source] An Adaptive Conjugate Gradient Neural Network,Wavelet Model for Traffic Incident DetectionCOMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, Issue 4 2000H. Adeli Artificial neural networks are known to be effective in solving problems involving pattern recognition and classification. The traffic incident-detection problem can be viewed as recognizing incident patterns from incident-free patterns. A neural network classifier has to be trained first using incident and incident-free traffic data. The dimensionality of the training input data is high, and the embedded incident characteristics are not easily detectable. In this article we present a computational model for automatic traffic incident detection using discrete wavelet transform, linear discriminant analysis, and neural networks. Wavelet transform and linear discriminant analysis are used for feature extraction, denoising, and effective preprocessing of data before an adaptive neural network model is used to make the traffic incident detection. Simulated as well as actual traffic data are used to test the model. For incidents with a duration of more than 5 minutes, the incident-detection model yields a detection rate of nearly 100 percent and a false-alarm rate of about 1 percent for two- or three-lane freeways. [source] THE NARROWING GENDER GAP IN ARRESTS: ASSESSING COMPETING EXPLANATIONS USING SELF-REPORT, TRAFFIC FATALITY, AND OFFICIAL DATA ON DRUNK DRIVING, 1980,2004,CRIMINOLOGY, Issue 3 2008JENNIFER SCHWARTZ We evaluate two alternative explanations for the converging gender gap in arrest,changes in women's behavior versus changes in mechanisms of social control. Using the offense of drunk driving and three methodologically diverse data sets, we explore trends in the DUI gender gap. We probe for change across various age groups and across measures tapping DUI prevalence and chronicity. Augmented Dickey-Fuller time-series techniques are used to assess changes in the gender gap and levels of drunk driving from 1980 to 2004. Analyses show women of all ages making arrest gains on men,a converging gender gap. In contrast, self-report and traffic data indicate little or no systematic change in the DUI gender gap. Findings support the conclusion that mechanisms of social control have shifted to target female offending patterns disproportionately. Little support exists for the contention that increased strain and liberalized gender roles have altered the gender gap or female drunk-driving patterns. [source] Catchment-scale contribution of forest roads to stream exports of sediment, phosphorus and nitrogenHYDROLOGICAL PROCESSES, Issue 23 2007Gary J. Sheridan Abstract The relative contribution of forest roads to total catchment exports of suspended sediment, phosphorus, and nitrogen was estimated for a 13 451 ha forested catchment in southeastern Australia. Instrumentation was installed for 1 year to quantify total in-stream exports of suspended sediment, phosphorus, and nitrogen. In addition, a total of 101 road,stream crossings were mapped and characterized in detail within the catchment to identify the properties of the road section where the road network and the stream network intersect. Sediment and nutrient generation rates from different forest road types within the catchment were quantified using permanent instrumentation and rainfall simulation. Sediment and nutrient generation rates, mapped stream crossing information, traffic data and annual rainfall data were used to estimate annual loads of sediment, phosphorus, and nitrogen from each stream crossing in the catchment. The annual sum of these loads was compared with the measured total catchment exports to estimate the proportional contribution of loads from roads within the catchment. The results indicated that 3·15 ha of near-stream unsealed road surface with an average slope of 8·4% delivered an estimated 50 t of the 1142 t of total suspended sediment exported from the catchment, or about 4·4% of the total sediment load from the forest. Stream discharge over this period was 69 573 Ml. The unsealed road network delivered an estimated maximum of 22 kg of the 1244 kg of total phosphorus from the catchment, or less than 1·8% of the total load from the forest. The average sediment and phosphorous load per crossing was estimated at 0·5 t (standard deviation 1·0 t) and 0·22 kg (standard deviation 0·30 kg) respectively. The lower proportional contribution of total phosphorus resulted from a low ratio of total phosphorus to total suspended sediment for the road-derived sediment. The unsealed road network delivered approximately 33 kg of the 20 163 kg of total nitrogen, about 0·16% of the total load of nitrogen from the forest. The data indicate that, in this catchment, improvement of stream crossings would yield only small benefits in terms of net catchment exports of total suspended sediment and total phosphorus, and no benefit in terms of total nitrogen. These results are for a catchment with minimal road-related mass movement, and extrapolation of these findings to the broader forested estate requires further research. Copyright © 2007 John Wiley & Sons, Ltd. [source] A new traffic model for backbone networks and its application to performance analysisINTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, Issue 6 2008Ming Yu Abstract In this paper, we present a new traffic model constructed from a random number of shifting level processes (SLP) aggregated over time, in which the lengths of the active periods of the SLP are of Pareto or truncated Pareto distribution. For both cases, the model has been proved to be asymptotically second-order self-similar. However, based on extensive traffic data we collected from a backbone network, we find that the active periods of the constructing SLPs can be approximated better by a truncated Pareto distribution, instead of the Pareto distribution as assumed in existing traffic model constructions. The queueing problem of a single server fed with a traffic described by the model is equivalently converted to a problem with a traffic described by Norros' model. For the tail probability of the queue length distribution, an approximate expression and upper bound have been found in terms of large deviation estimates and are mathematically more tractable than existing results. The effectiveness of the traffic model and performance results are demonstrated by our simulations and experimental studies on a backbone network. Copyright © 2007 John Wiley & Sons, Ltd. [source] Observing freeway ramp merging phenomena in congested trafficJOURNAL OF ADVANCED TRANSPORTATION, Issue 2 2007Majid Sarvi This work conducts a comprehensive investigation of traffic behavior and characteristics during freeway ramp merging under congested traffic conditions. On the Tokyo Metropolitan Expressway, traffic congestion frequently occurs at merging bottleneck sections, especially during heavy traffic demand. The Tokyo Metropolitan Expressway public corporation, generally applies different empirical strategies to increase the flow rate and decrease the accident rate at the merging sections. However, these strategies do not rely either on any behavioral characteristics of the merging traffic or on the geometric design of the merging segments. There have been only a few research publications concerned with traffic behavior and characteristics in these situations. Therefore, a three-year study is undertaken to investigate traffic behavior and characteristics during the merging process under congested situations. Extensive traffic data capturing a wide range of traffic and geometric information were collected using detectors, videotaping, and surveys at eight interchanges in Tokyo Metropolitan Expressway. Maximum discharged flow rate from the head of the queue at merging sections in conjunction with traffic and geometric characteristics were analyzed. In addition, lane changing maneuver with respect to the freeway and ramp traffic behaviors were examined. It is believed that this study provides a thorough understanding of the freeway ramp merging dynamics. In addition, it forms a comprehensive database for the development and implementation of congestion management techniques at merging sections utilizing Intelligent Transportation System. [source] Neural Network Modeling of Constrained Spatial Interaction Flows: Design, Estimation, and Performance IssuesJOURNAL OF REGIONAL SCIENCE, Issue 1 2003Manfred M Fischer In this paper a novel modular product unit neural network architecture is presented to model singly constrained spatial interaction flows. The efficacy of the model approach is demonstrated for the origin constrained case of spatial interaction using Austrian interregional telecommunication traffic data. The model requires a global search procedure for parameter estimation, such as the Alopex procedure. A benchmark comparison against the standard origin constrained gravity model and the two,stage neural network approach, suggested by Openshaw (1998), illustrates the superiority of the proposed model in terms of the generalization performance measured by ARV and SRMSE. [source] Zur Querkraftgefährdung bestehender SpannbetonbrückenBETON- UND STAHLBETONBAU, Issue 6 2010Teil II: Empfehlungen zur Vorgehensweise bei Sichtung und Überprüfung Brückenbau; Spannbeton; Normen; Berechnungs- und Bemessungsverfahren Abstract Zur Formulierung einer Handlungsanweisung wurden in Teil I die geänderten Lastannahmen für Brücken nach DIN Fachbericht 101 mit den Belastungsklassen nach alten Normen verglichen und gezeigt, wie anhand aktueller Verkehrszahlen die Lastansätze modifiziert werden können. Der aktuelle Brückenbestand in Hessen wurde mit der Straßeninformationsbank (Teilprojekt Bauwerksdaten) ausgewertet, um Klassifizierungs- und Bewertungskriterien zu erarbeiten. Zur Beurteilung des Querkraftwiderstandes wurden die Grundlagen der Querkraftbemessung nach DIN 1045, DIN 4227, DIN Fachbericht 102 und aus der Literatur gegenübergestellt. In Teil II werden Verfahren zur nachträglichen Verstärkung von Querschnitten und Tragsystemen mit zu geringer Querkrafttragfähigkeit zusammengestellt. Des Weiteren werden verschiedene Varianten der Modellierung verglichen, die bei der linearelastischen Schnittgrößenermittlung nach der Finite-Elemente- Methode verwendet werden. Auf Grundlage der gewonnenen Erkenntnisse werden schließlich Empfehlungen für eine Handlungsanweisung zur Beurteilung querkraftgefährdeter Brückenbauwerke formuliert. Shear-Vulnerability of Existing Pre-Stressed Concrete Bridges In Part I, to formulate an operation directive the revised load assumptions for bridges of DIN Technical Report 101 are compared with the loading classes according to old standards and it is demonstrated, how the loading models can be modified based on actual traffic data. The current bridge asset in the Federal State of Hesse is evaluated using the "Road Information Database (Sub-Project: Structural Data)" in order to work out classification and evaluation criteria. Regarding the assessment of the shear load-bearing capacity the fundamentals of the shear load design models of DIN 1045, DIN 4227, DIN TR 102 and from the literature are compared. In Part II, the procedures for the subsequent strengthening of cross-sections and structural systems with a low shear load-bearing capacity are compiled. In addition, different types of finite element modelling are compared used for the calculation of the linear-elastic internal forces. Finally, based on the findings recommendations are formulated for an operation directive in regard to the assessment of shear-vulnerable bridges. [source] | ||||||||||