Truck Data Research Articles

Anomaly detection using manifold embedding and its applications in transportation corridors

The formation of secure transportation corridors, where cargoes and shipments from points of entry can be dispatched safely to highly sensitive and secure locations, is a high national priority. One of the key tasks of the program is the detection of anomalous cargo based on sensor readings in truck weigh stations. Due to the high variability, dimensionality, and/or noise content of sensor data in transportation corridors, appropriate feature representation is crucial to the success of anomaly detection methods in this domain. In this paper, we empirically investigate the usefulness of manifold embedding methods for feature representation in anomaly detection problems in the domain of transportation corridors. We focus on both linear methods, such as multi-dimensional scaling (MDS), as well as nonlinear methods, such as locally linear embedding (LLE) and isometric feature mapping (ISOMAP). Our study indicates that such embedding methods provide a natural mechanism for keeping anomalous points away from the dense/normal regions in the embedding of the data. We illustrate the efficacy of manifold embedding methods for anomaly detection through experiments on simulated data as well as real truck data from weigh stations.

Knowledge Extraction from Real-World Logged Truck Data

In recent years more data is logged from the electronic control units on-board in commercial vehicles. Typically, the data is transferred from the vehicle at the workshop to a centralized storage for future analysis. This vast amount of data is used for debugging, as a knowledgebase for the design engineer and as a tool for service planning.Manual analysis of this data is often time consuming, due to the rich amount of information contained. However, there is an opportunity to automatically assist in the process based on knowledge discovery techniques, even directly when the trucks data is first offloaded at the workshop. One typical example of how this technique could be helpful is when two groups of trucks behave differently, e.g. one well-functioning group and one faulty group, when the two groups have the same specification. The desired information is the specific difference in the logged data, e.g. what particular sensors or signals are different.An evaluation cycle is proposed and applied to extract knowledge from three different large real-world data-sets measured on Volvo long haulage trucks. Information in the logged data that describes the vehicle’s operating environment, allows the detection of trucks that are operated differently from their intended use. Experiments to find such vehicles were conducted and recommendations for an automated application are given.

Planning Product Configurations Based on Sales Data

Manufacturing companies are focusing on mass customization. Delivering products that meet the requirements of individual customers complicates the production process, and diminishes the benefits of the economy of scale. By exploring commonality among products, this complexity can be significantly reduced. To determine product configurations sought by the customers and to produce them in large quantities, a new approach is proposed. The proposed approach uses a modified k-means clustering algorithm to analyze past sales data for capturing prime product configurations. The most suitable configurations are selected by solving an integer-programming model or using a sorting-based algorithm. The proposed approach was tested with an industrial case study involving sales data of large trucks collected over a period of one year.

Using Dual-Loop Event Data to Enhance Truck Data Accuracy

The economic vitality of Washington State depends on continuing and even increasing strong foreign trade levels. Improving the mobility of freight traffic on Washington's streets and highways is an important factor in achieving this goal. The Washington State Department of Transportation (Washington State DOT) has devoted significant time and resources to investigating ways to improve freight mobility on its freeway networks. The primary type of sensor used by the department to collect truck volume and speed data on Washington State freeways is a dual-loop detection system. However, recent studies of the Washington DOT classification system found that the quality of dual-loop truck data being collected was questionable because of four main problems: (a) split of loop signals for multiunit trucks, (b) cross talk between adjacent loops, (c) constrained sensitivity adjustments of discrete levels at loop amplifiers, and (d) unsuitable thresholds of on-time differences between the two single loops of a dual-loop detector. This paper presents an algorithm for minimizing the effects of these four problems. The algorithm uses traffic information extracted from loop event data and the characteristics of vehicle length distribution to identify and correct erroneous loop event data for better truck data extraction. The proposed algorithm does not require hardware installations or adjustments to address the four problems affecting the quality of truck data obtained from dual-loop detectors. Therefore, it provides a cost-effective solution for obtaining much more accurate truck data from this commonly available detection system.

ECONOMICS AT THE GAO

The articles in this section are part of a set submitted simultaneously to Contemporary Economic Policy (CEP) to illustrate policy relevant economic work that occurs at U.S. Government Accountability Office (GAO, formerly General Accounting Office). The articles and GAO's reports in general are consistent with CEP's objectives of communicating high-quality economic analysis on policy issues, to focus research on current issues of widespread concern, and to increase awareness among economists. The four articles in this section investigate strategic industry behavior stemming from Environmental Protection Agency (EPA) air regulation affecting diesel engines, setting priorities for homeland security expenditures, potential for discriminatory decisions in appeals to Social Security disability program, and potential for market power in wholesale gasoline markets resulting from corporate mergers. These articles are briefly sketched and then context of economics work at GAO is presented. Lam and Bausell investigated a recent EPA regulation that imposed more stringent emission standards on diesel engines as of October 2004. Among many strategies truck operators could have taken to comply, article investigates whether truck operators pre-bought trucks with diesel engines ahead of date of compliance that in effect could offset some of planned impact of regulation. Using production data of trucks with diesel engines, Lam and Bausell found that production of trucks with older diesel engines went up about 20%-30% in 6 months leading to October 2004, despite accounting for factors such as strength of economy. In second contribution, Farrow investigated basic approaches to setting priorities for homeland security expenditures in response to increased calls for an allocation based on risk. Acknowledging challenges of quantifying risk in heterogeneous settings and against an intelligent adversary, several expected cost-minimization models are developed to define kinds of trade-offs that public or private managers might pursue. The relevance of marginal investment rules so derived is illustrated with examples from GAO reports related to port security and border control among other applications. The third contribution by Godtland et al. is a test for racial disparities in Social Security Administration's (SSA) decision to award disability benefits for nation's two largest disability cash assistance programs. Using newly available data, they developed a comprehensive econometric model of appeal level of SSA's disability decision-making process. Among other findings, they determined that attorney representation plays a role in explaining racial differences in benefit awards that are appealed. Finally, Karikari et al. examined impact of wave of mergers in U.S. petroleum industry in 1990s on wholesale prices of both conventional and boutique gasoline specifications. They used an innovative econometric technique that accounts for correlations across gasoline terminals over time and contemporaneously in a model where gasoline inventories and refining capacity utilization rates are regarded as endogenous to gasoline prices. Their model also accounts for supply disruptions in Midwest and West Coast regions of country, as well as crude oil prices, a major component of gasoline prices. The authors found that majority of mergers resulted in wholesale gasoline prices that were higher by a few cents per gallon. As little is published about context in which GAO economists work, remainder of this introduction is a brief survey of opportunities and limits for work of economists in GAO, the investigative arm of Congress. GAO employs more than 80 full-time Ph.D. economists who are primarily focused on what GAO calls performance audits. (1) Within 3,200 analysts and staff of GAO, economists represent a distinct skill set but must find ways to interact and to contribute on research teams where economist's view is often one of many views among analysts. …

Video-Based Vehicle Detection and Classification System for Real-Time Traffic Data Collection Using Uncalibrated Video Cameras

Length-based vehicle classification data are important inputs for traffic operation, pavement design, and transportation planning. However, such data are not directly measurable by single-loop detectors, the most widely deployed type of traffic sensor in the existing roadway infrastructure. In this study a video-based vehicle detection and classification (VVDC) system was developed for truck data collection using wide-ranging available surveillance cameras. Several computer vision-based algorithms were developed or applied to extract background image from a video sequence, detect presence of vehicles, identify and remove shadows, and calculate pixel-based vehicle lengths for classification. Care was taken to handle robustly negative effects resulting from vehicle occlusions in the horizontal direction and slight camera vibrations. The pixel-represented lengths were exploited to distinguish long vehicles from short vehicles; hence the need for complicated camera calibration can be eliminated. These algorithms were implemented in the prototype VVDC system using Microsoft Visual C#. As a plug-and-play system, the VVDC system is capable of processing both digitized image streams and live video signals in real time. The system was tested at three test locations under different traffic and environmental conditions. The accuracy for vehicle detection was above 97%, and the total truck count error was lower than 9% for all three tests. This indicates that the video image processing method developed for vehicle detection and classification in this study is indeed a viable alternative for truck data collection.

ITS Devices Used to Collect Truck Data for Performance Benchmarks

This paper documents the development of data collection methodologies that can be used to measure truck movements along specific roadway corridors in Washington State cost-effectively. The intent of this study was to design and test methodologies that could provide information to ascertain the performance of freight mobility roadway improvement projects. The benchmarks created would be used to report on speed and volume improvements that resulted from completed roadway projects. One technology tested consisted of Commercial Vehicle Information System and Networks electronic truck transponders, which were mounted on the windshields of approximately 30,000 trucks traveling in Washington. These transponders were used at weigh stations across the state to improve the efficiency of truck regulatory compliance checks. With transponder reads from sites anywhere in the state being linked through software, the transponder-equipped trucks can become a travel time probe fleet. The second technology tested involved G...

ITS Devices Used to Collect Truck Data for Performance Benchmarks

This paper documents the development of data collection methodologies that can be used to measure truck movements along specific roadway corridors in Washington State cost-effectively. The intent of this study was to design and test methodologies that could provide information to ascertain the performance of freight mobility roadway improvement projects. The benchmarks created would be used to report on speed and volume improvements that resulted from completed roadway projects. One technology tested consisted of Commercial Vehicle Information System and Networks electronic truck transponders, which were mounted on the windshields of approximately 30,000 trucks traveling in Washington. These transponders were used at weigh stations across the state to improve the efficiency of truck regulatory compliance checks. With transponder reads from sites anywhere in the state being linked through software, the transponder-equipped trucks can become a travel time probe fleet. The second technology tested involved Global Positioning Systems (GPS) placed in volunteer trucks to collect specific truck movement data at 5-s intervals. GPS data made it possible to locate when and where monitored trucks experienced congestion. With this information aggregated over time, it was possible to generate performance statistics related to the reliability of truck trips and even to examine changes in route choice for trips between high-volume origin–destination pairs. The study found that both data collection technologies could be useful; however, the key to either technology is whether enough instrumented vehicles pass over the roadways for which data are required.

Improved Dual-Loop Detection System for Collecting Real-Time Truck Data

The Washington State Department of Transportation (WSDOT) has a loop detection system on its Greater Seattle freeway network to provide real-time traffic data. The dual-loop detectors installed in the system are used to measure vehicle lengths and then classify each detected vehicle into one of four categories according to its length. The dual loop's capability of measuring vehicle length makes the loop detection system a potential real-time truck data source for freight movement studies because truck volume estimates by basic length category can be developed from the vehicle length measurements produced by the dual-loop detectors. However, a previous study found that the dual-loop detectors were consistently underreporting truck volumes, whereas the single-loop detectors were consistently overcounting vehicle volumes. As an extension of the previous study, the research project described here investigated possible causes of loop errors under nonforced-flow traffic conditions. A new dual-loop algorithm tha...

Improved Dual-Loop Detection System for Collecting Real-Time Truck Data

The Washington State Department of Transportation (WSDOT) has a loop detection system on its Greater Seattle freeway network to provide real-time traffic data. The dual-loop detectors installed in the system are used to measure vehicle lengths and then classify each detected vehicle into one of four categories according to its length. The dual loop's capability of measuring vehicle length makes the loop detection system a potential real-time truck data source for freight movement studies because truck volume estimates by basic length category can be developed from the vehicle length measurements produced by the dual-loop detectors. However, a previous study found that the dual-loop detectors were consistently underreporting truck volumes, whereas the single-loop detectors were consistently overcounting vehicle volumes. As an extension of the previous study, the research project described here investigated possible causes of loop errors under nonforced-flow traffic conditions. A new dual-loop algorithm that can address these error causes and therefore tolerate erroneous loop actuation signals was developed to improve the performance of the WSDOT loop detection system. A quick remedy method was also recommended to address the dual-loop undercount problem without replacing any part of the existing system hardware or software. In addition, a laptop-based detector event data collection system (DEDAC) that can collect loop detector event data without interrupting a loop detection system's normal operation was developed in this research. The DEDAC system enables various kinds of transportation research and applications that could not otherwise be possible.

Technologies for Truck Classification and Methodologies for Estimating Truck Vehicle Miles Traveled

Results are presented of a national survey of all state departments of transportation (DOTs), including Puerto Rico, about technologies used for truck classification and methodologies used for estimating truck vehicle miles traveled (VMT). More than two-thirds of state DOTs returned the survey. Procedures were found to classify trucks, to adjust truck data from short-term counts, and to calculate truck VMT. To classify trucks, most state DOTs followed FHWA’s 13 categories. The products from two manufacturers, Peek Traffic and Diamond Traffic Products, with a variety of sensors, dominated the classification devices used by state DOTs. The sensor used most for short-term classification counts was the pneumatic tube. Duration and number of truck-classification counts (machine or manual) varied by state DOT. With machine classifiers, state DOTs collected short-term and continuous truck data for a variety of state highway coverage. Truck data were collected by using machine classifiers unless certain conditions, such as congested highways, demanded manual collection. To adjust truck data from short-term classification counts, most state DOTs developed their adjustment factors from continuous volume counts (not truck counts) and used them to adjust truck volumes. Some state DOTs used different adjustment factors for trucks and cars. For all state DOTs, the general practice of truck VMT estimation was based on traffic counts. When truck data were available, state DOTs directly calculated truck VMT by multiplying truck average daily traffic and the length of a roadway section; when the data were not available, truck VMT was indirectly calculated as a fraction (percentage) of total VMT. For the state highway systems, state DOTs generally relied on the first (direct) method, since the resources were normally available and the standards for conducting traffic counts were also available. However, some states lacked the necessary resources to adequately sample average daily traffic on the local road systems. As a result, many state DOTs used the indirect method to calculate truck VMT.

Fuel Consumption of Heavy-Duty Trucks: Potential Effect of Future Technologies for Improving Energy Efficiency and Emissions

The results of an analysis of heavy-duty truck (Classes 2b through 8) technologies conducted to support the Energy Information Administration’s long-term projections for energy use are summarized. Several technology options that have the potential to improve the fuel economy and emissions characteristics of heavy-duty trucks are included in the analysis. The technologies are grouped as those that enhance fuel economy and those that improve emissions. Each technology’s potential impact on the fuel economy of heavy-duty trucks is estimated. A rough cost projection is also presented. The extent of technology penetration is estimated on the basis of truck data analyses and technical judgment.

Computer Aided Design Tool For The Study OfElectric Traction Fixed Installations And TrainOperation

The complexity in design and dimensioning of electric traction fixed installations necessitates the development of a methodology for dimensioning based on numerical simulation models. This solution gives faster and more reliable results than those obtained by the empirical and inaccurate methods previously used. A computer aided design tool implementing this methodology is presented in this paper. Various elements such as truck data, catenary, traction substations, rolling stock, train composition, railway network and schedule conditions are considered. The analysis of the resulting simulated output allows optimisation and selection of the best solution for the power supply system of a railway network, as far as traction substations and overhead line systems are concerned. Therefore, the final choice of the electrical energy supply system that fulfils the technical requirements and ensures the programmed traffic, should be submitted to the analysis of a minimum cost criterion, regarding available feeding points of the energy supplier network.

SITE-SPECIFIC TRUCK LOADS ON BRIDGES AND ROADS.

Condition assessment of bridge structures, prediction of remaining life and evaluation of pavement performance and behaviour require knowledge of load and resistance statistical parameters. The present study addresses the need for the determination of live load on bridges and roads, and in particular the site-specific variation of the live load statistics. Truck loads were measured under normal traffic conditions at selected bridges located on interstate highways, state highways, US highways and surface streets using a bridge weigh-inmotion (WIM) system. Truck data is also available from highway weigh station logs and citation files. Stationary weigh station data is biased and may not accurately reflect the distribution of truck axle weights, axle spacing, and gross vehicle weight. Citation data is helpful in understanding the nature and extent of overloaded trucks; however, it will not be representative of the normal traffic distribution. WIM measurements of trucks can be taken discretely during normal traffic conditions, resulting in unbiased data for a statistically accurate sample of truck traffic travelling a particular highway. Results of the present study show that truck loads are strongly site specific. In addition, there is a negative correlation between law enforcement effort and the occurrence of overloaded trucks. Overloaded trucks are observed on roads not controlled by truck weigh stations. A comparison of the weigh station data, truck citation data and WIM measurements obtained in this study confirms this observation.

The effectiveness of automobile safety regulation: evidence from the FARS data.

In a paper published in the August 1981 issue of this Journal, Leon Robertson attempts to measure the effects of the vehicle safety and occupant protection standards implemented in the 1960s. Data from the Fatal Accident Reporting System are used. Additional statistical analysis with these data reveals a multicollinearity problem that makes the prediction of the effects of regulation uncertain. There is also bias in regression results due to the inappropriate inclusion of truck data in the regressions. Regressions on the car data reveal a lifesaving effect of regulation that, at best, is one-fourth the value reported by Robertson.

露天掘鉱山における大型運搬機械の更新時期について

Based on the maintenance data of open pit haulage machines, dump trucks and tire shovels, an optimumoperation planning for these machines was discussed.Considering the total investment of machine consists of the machine value purchased, overhaul cost andmaintenance cost, Total investment=machine value purchased+overhaul cost+maintenance cost was formulated as the fundamental equation.Then, the analysis of these costs were performed and simulations were carried out by introducing aninflation effect and D. C. F. concept. And conclusively, optimum replacement time of machine to new machine was decided and abenefit of employment of larger size machines was discussed.

Heavy Duty Diesel Particulate Emission Factors

For the past several years, EPA has been measuring particulate emissions from a variety of heavy-duty diesel engines through contracts with Southwest Research Institute. Particulate emissions samples have been collected using an exhaust splitter to divert a fraction of the engine exhaust into a standard dilution tunnel. A small fraction of the diluted exhaust from the tunnel is pulled through a filter from which particulate mass and, in some cases, organic content of the particulate is determined. This paper discusses the sampling system and gives particulate emission factors that have been computed from truck and bus fuel consumption data as well as average truck and bus speed data from New York and Los Angeles (freeway and nonfreeway usage). Average particulate emission test results (steady state tests) for 2-stroke engines were 4.74 g/kg fuel and for 4-stroke engines were 2.64 g/kg fuel. Using average particulate emissions results, a particulate emission factor range of 0.8 to 1.3 g/km was computed. Na...

Weigh-in-Motion System Using Instrumented Bridges

Acquisition of truck axle and gross weight information is necessary for structural and maintenance requirements of bridges and pavements. A system is described combining traffic sensors and strain gages on highway bridge girders to obtain axle and gross weights. A weight prediction algorithm is derived herein that filters out the dynamic components of bridge response and obtains the equivalent static axle weights by a least-square error minimization. It utilizes self-balancing signal conditioners, magnetic tape switches, analog-digital converters, and a minicomputer to record field data on magnetic tape. Output is subsequently obtained on a digital computer. The system showed predictions of gross truck weight and tandem axles consistent with calibration trucks and random traffic. The paper also describes modifications of the system that would allow its routine use in obtaining weigh-in-motion truck data and would also permit weight processing in the field.