Khaled Hamad

Near-Term Travel Speed Prediction Utilizing Hilbert-Huang Transform

: Accurate short-term prediction of travel speed as a proxy for time is central to many Intelligent Transportation Systems, especially for Advanced Traveler Information Systems and Advanced Traffic Management Systems. In this study, we propose an innovative methodology for such prediction. Because of the inherently direct derivation of travel time from speed data, the study was limited to the use of speed only as a single predictor. The proposed method is a hybrid one that combines the use of the empirical mode decomposition (EMD) and a multilayer feedforward neural network with backpropagation. The EMD is the key part of the Hilbert–Huang transform, which is a newly developed method at NASA for the analysis of nonstationary, nonlinear time series. The rationale for using the EMD is that because of the highly nonlinear and nonstationary nature of link speed series, by decomposing the time series into its basic components, more accurate forecasts would be obtained. We demonstrated the effectiveness of the proposed method by applying it to real-life loop detector data obtained from I-66 in Fairfax, Virginia. The prediction performance of the proposed method was found to be superior to previous forecasting techniques. Rigorous testing of the distribution of prediction errors revealed that the model produced unbiased predictions of speeds. The superiority of the proposed model was also verified during peak periods, midday, and night. In general, the method was accurate, computationally efficient, easy to implement in a field environment, and applicable to forecasting other traffic parameters.

DEVELOPING A MEASURE OF TRAFFIC CONGESTION: FUZZY INFERENCE APPROACH

Many measures have been proposed to represent the status of traffic conditions on arterial roadways in urban areas. The debate about what is the most appropriate measure continues. In a contribution to the debate, another approach was offered. Traditionally, two general approaches exist. One is based on the relationship between supply and demand. The other is a measure relative to the most acceptable status of service quality. The latter measure allows the public to relate to their travel experience. In either case, however, derivation of measures of congestion involves uncertainty because of imprecision of the measurement, the traveler’s perception of acceptability, variation in sample data, and the analyst’s uncertainty about causal relations. A measure is proposed that is a composite of two traditional measures, travel speed and delay. In recognition of the uncertainty, a fuzzy inference process was proposed. The inputs are travel speed, free-flow speed, and the proportion of very low speed in the total travel time. These values were processed through fuzzyrule-based inference. The outcome was a single congestion index value between 0 and 1, where 0 is the best condition and 1 is the worst condition. The process was demonstrated using real-world data. The results were compared with those of the Highway Capacity Manual. Although no conclusion can be drawn about the best measure of congestion, the proposed inference process allows the mechanism to combine different measures and also to incorporate the uncertainty in the individual measures so that the composite picture of congestion can be reproduced.

Application of GPS in Traffic Management Systems

Integrated Traffic Management Systems (ITMS) need reliable, accurate, and real-time data. Travel time, speed, and delay are three of the most important factors used in ITMS for monitoring, quantifying, and controlling congestion. GPS has recently become available for civil applications. Because it provides real-time spatial and time measurements, it has an increasing use in conducting different transportation studies. This article presents the application of GPS in collecting travel time, speed, and delay information of 64 major roads in the state of Delaware. A comparative statistical analysis was performed on data collected by GPS, with data collected simultaneously by the conventional method. The GPS data proved to be at least as accurate as the data collected by the conventional method, and it was 50% more efficient in terms of manpower. Moreover, the sample-size requirement was determined to maintain 95% confidence level throughout the controlled test. Benefiting from the Geographic Information Systems dynamic segmentation tool, our travel time, delay, and speed information were integrated with other relevant traffic data. This was presented graphically on the Internet for public use. Statistical trend analysis for the data collected in 1997, 1998, 1999, and 2000 are also presented and applications on the overall ITMS are discussed.

A Behavioral Component Analysis of Route Guidance Systems Using Neural Networks

Route guidance systems (RGS) are considered to be a low-cost alternative for reduction of traffic congestion by providing real-time information to drivers to redistribute traffic in space and time to enable use of highway networks more efficiently. This paper looks at the behavioral component, 1 of 3 components of a practical RGS developed within a 4-year project at the University of Delaware. Development of the behavioral model is based on the premise that drivers perceive and behave differently in response to the information provided. Backpropagation neural networks with their ability to map complex input-output relationships were used to structure the model, which was tested on 2 networks under both recurring and nonrecurring congestion. A comparative analysis of the measures of effectiveness revealed that the performance of the developed RGS is significantly better than the performance under existing non-RGS conditions.

Intelligent Transportation System Spatial Data Modeling

Transportation management centers (TMCs) generate and archive enormous amounts of multimodal transportation data. Archived intelligent transportation system (ITS) data applications today tend to focus on ITS data as a resource for transportation planning and research, mainly to generate aggregated system performance measures such as corridor travel times, speeds, and delays. As ITS data applications increase, interest is also growing in using archived ITS data to help optimize TMC operations. One area of considerable interest is incident management. This paper focuses on freeway ITS features and data. It describes a prototype geographically referenced framework for ITS data and summarizes spatial and temporal patterns in the distribution of incidents along instrumented freeways in San Antonio, Texas. The geodatabase uses architecture information and archived sensor and incident data from the San Antonio TMC (TransGuide). However, it is sufficiently generic for implementation at other TMCs with relatively minor variations. The paper focuses on data model and geodatabase development, although it includes a summary of application examples.

Infrastructure growth assessment of urban areas based on multi-temporal satellite images and linear features

ABSTRACT Urbanization is typically demonstrated by expansion of a city’s infrastructure, mainly development of its roads and buildings. In particular, transportation infrastructure is a key indicator of growth in the city since transportation is the backbone of economic development and prosperity. Recent advances in satellite imagery, in terms of improved spatial and temporal resolutions, enable efficient identification of change patterns and prediction of built-up areas. In this study, two approaches were adopted to quantify and assess the pattern of urbanization. The first approach relied on extracting linear features (buildings and roads) from multi-temporal satellite images, where image-to-image registration was utilized based on linear features with Modified Iterated Hough Transform as matching criteria. The second approach relied on extracting linear features from vector (digitized) data. The latter approach complemented the first one by distinguishing between roads and buildings. The proposed methodology was then applied to Sharjah City, United Arab Emirates, as a case study. Results show that the urbanized area of the city almost quadrupled during 1976–2016. Growth in buildings and roads was generally consistent until 2005, after that the spatial growth witnessed a steep increase due to vertical expansion. To assess the accuracy of the utilized edge images and change detection, error matrices were prepared for the case study. An overall accuracy of more than 84% was achieved. The proposed methodology was successful in quantifying urban growth in the study area.

Forecasting Model for Vehicular Demand: An Alternative Methodology in the Context of Developing Countries

Two most challenging problems facing transportation planners and policymakers in many developing countries are rapid urban traffic growth and lack of financial and technical resources to conduct major planning studies, especially for assessing the impacts of new sites and land-uses. The conventional urban transportation planning process, which is data and time intensive, has been of little value due to many transportation related obstacles (inadequate database, lack of funds, inadequate technical expertise, etc.). Advances in computer technology, especially in the areas of Geographic Information Systems (GIS), offer new ways of dealing with the aforementioned problems. This paper presents a new methodology for conducting transportation planning studies in developing countries. Integrating TransCAD, well-known GIS software for transportation applications, and Excel, spreadsheet software, the new model starts by estimating an Origin-Destination (O-D) table from traffic counts at the base year. Then, a modified O-D table is obtained from a simple procedure before determining the new traffic assignment, taking into consideration the new sites and land uses. The model was developed and applied for conducting regional transportation planning in the Gaza Strip, Palestine. A flexible, yet vigorous transportation planning mechanism was needed to assist planners in their efforts to plan for transportation in that highly populated area with a poor and old highway network. The results of the verification work conducted after each step during the development of the model have been acceptable. Moreover, transportation experts who live and work in the area have conducted complete validation of the results.

Risk-based GIS model for hazardous materials routing in Sharjah, United Arab Emirates as a case study

Hazardous materials (HAZMATs) routing is a daily activity for organisations involved in transporting HAZMAT shipments to destinations within their jurisdictions. HAZMAT shipments need to be transported safely without posing significant risk to human and environmental health. While traditional routing is based on travel cost, represented by travel time or distance, this paper presents a risk-based geographic information system (GIS) model for finding the least-risky routes for HAZMAT shipments. Using the analytical hierarchy process (AHP), the proposed model combines multiple risks using importance weights into a single, comprehensive travel risk factor. The risks considered in the model include: travel time, travel distance, risk to exposed population, and risks due to traffic air and noise emissions. To test the proposed model, a comprehensive GIS-database was built for the main roads in the City of Sharjah, United Arab Emirates. The developed model, combined with the GIS-database, allows finding the least-risky route between any two destinations based on weighed risks or constraints. The proposed methodology is general enough to be applied to any case study worldwide.

Geovisualization of Archived ITS Data-Case Studies

Although transportation data have a spatial component by nature, this component generally has not been fully utilized when it comes to intelligent transportation system (ITS) archived data. This paper demonstrates the use of geographic information system (GIS) to spatially visualize and analyze transportation management center (TMC)-related performance measures derived from archived ITS data from a traffic management center in Texas, namely, San Antonios TransGuide. The paper discusses three case studies. The first case study involved a performance evaluation of an automatic incident detection algorithm deployed by many traffic management centers after a few years of implementation in the field. The overall detection rate was found to be about 20%, and the overall false rate was about 0.005%. The second case study summarizes work completed to address quality control issues associated with a very large archived ITS data set composed of some 3.4 billion 20-s loop detector data records. There were some 1.6 billion (about 48%) speed, volume, and occupancy records that had a quality control flag. Approximately 1.5 billion flagged records were “valid” records, and the remaining 126 million (about 3.7%) flagged records were “abnormal” records. In the third case study, the researchers evaluated the data completeness both at the aggregate level (by server) and at a more detailed individual detector level. At the server level, the completeness rate varied from 95% to 100%. At the individual detector level, the analysis showed that, on average, the completeness rate for all detectors was about 80%. The researchers utilized GIS to prepare maps showing the spatial distribution of incident detection rate, false alarm rate, quality control flags, and data completeness rate. It is worth mentioning that all of the analysis was performed at a detailed segment-by-segment level, which is by itself a unique addition. The researchers recommend implementing the demonstrated spatial analysis of the archived ITS data. This will allow TMC officials to identify spots with any abnormal behavior, whether it is at the corridor level or even at the segment level.

Road traffic accidents trends in Sharjah, United Arab Emirates during 2001-2014

This paper quantitatively describes the extent of the road traffic accidents problem in the Emirate of Sharjah, the third largest emirate in UAE, for the period 2001-2014. Several interesting findings were revealed. While Sharjahs population almost doubled during this period, the number of injury/fatality causing accidents decreased by more than half during the same period. The annual number of road accidents and injuries increased until the 2008 when the numbers sharply declined then stabilised in recent years, which could be attributed to the introduction of the new traffic law of UAE. Though both accidents and injuries per 100,000 population considerably decreased annually, the fatalities per 100,000 population only marginally decreased, indicating that the severity of accident may have increased. Overall, Sharjah enjoyed a better rate of fatalities per 100,000 population than that for the whole UAE. This papers results should be useful to identify directions to undertake in future research, policies, and programs on highway safety in Sharjah, UAE.