Stephen Ritchie - Academia.edu (original) (raw)

Uploads

Papers by Stephen Ritchie

Research paper thumbnail of Vehicle Reidentification Using Multidetector Fusion

IEEE Transactions on Intelligent Transportation Systems, Sep 1, 2004

Research paper thumbnail of Real-Time Expert System Approach to Freeway Incident Management

Transportation Research Record, 1991

Research paper thumbnail of A knowledge-based decision support architecture for advanced traffic management

Transportation Research Part A: General, 1990

Research paper thumbnail of Neural Network Models For Automated Detection Of Non-recurring Congestion

RePEc: Research Papers in Economics, 1993

Research paper thumbnail of Section Related Measures of Traffic System Performance: Final Report

RePEc: Research Papers in Economics, Nov 1, 1998

Research paper thumbnail of Field Investigation of Advanced Vehicle Reidentification Techniques and Detector Technologies - Phase 1

RePEc: Research Papers in Economics, Mar 1, 2002

Research paper thumbnail of A Neuro-Genetic-Based Universally Transferable Freeway Incident Detection Framework

University of California Transportation Center, 1996

Research paper thumbnail of New Tool from UC Irvine Could Save the State Millions while Providing Better Data on Truck Activity in California

Research paper thumbnail of Understanding Commercial Vehicle Travel Through New High-Fidelity Inductive Sensors

Transportation Research Board 86th Annual MeetingTransportation Research Board, 2007

Despite their impacts on traffic performance, infrastructure, environment and safety, the travel ... more Despite their impacts on traffic performance, infrastructure, environment and safety, the travel behavior of commercial vehicles is not well understood. This is largely due to limited data available to distinguish between various types of commercial vehicles and their travel patterns. This ...

Research paper thumbnail of Routing and Scheduling Problem of Container Trucks with Selective Empty Container Pickup in a Shared Resource Environment

Transportation Research Board 97th Annual MeetingTransportation Research Board, 2018

Research paper thumbnail of Development of a real-time on-road emissions estimation and monitoring system

Transportation has been a significant contributor to total greenhouse gas and criteria air pollut... more Transportation has been a significant contributor to total greenhouse gas and criteria air pollutant emissions. Emission mitigation strategies are essential in reducing transportation's impacts on the environment. In order to effectively develop and evaluate on-road emissions reduction strategies, it is important to have an information support system which can estimate and monitor on-road emissions under real world traffic operations. Emission data provided by such a system can be used to identify emission hot spots and their causes, and to develop and evaluate reduction strategies. In this paper, a system is developed to estimate and monitor operational on-road emissions with high accuracy and resolution in real time. The two sets of critical information for emission estimation, vehicle mix and vehicle activity, are directly generated from traffic detection using inductive vehicle signature technology. An initial implementation on a section of the I-405 freeway at Irvine, California is demonstrated. With more widespread deployment, the system can be used to perform before-and-after evaluation of certain mitigation strategies, to develop time sensitive optimal traffic control strategies with the purpose to control emissions, and to provide high fidelity greenhouse gas and air quality information to policymakers, researchers, and the general public.

Research paper thumbnail of Goal Programming Approach to Allocate Freight Analysis Framework Mode Flow Data

Transportation Research Record, 2014

Research paper thumbnail of Sponsored research report: Assessment and development of commodity flow, logistics, and other relevant goods movement data sources to facilitate statewide freight modeling

Research paper thumbnail of Sponsored research report: Conceptual and methodological development of a California statewide freight demand model: Final report of scoping study

Research paper thumbnail of A Real-Time Expert System Approach To Freeway Incident Management - eScholarship

Fundamental to the operation of most Intelligent Vehicle-Highway System (IVHS) projects are advan... more Fundamental to the operation of most Intelligent Vehicle-Highway System (IVHS) projects are advanced systems for surveillance, control and management of integrated freeway and arterial networks. A major concern in the development of such Smart Roads, and the focus of this paper, is the provision of decision support for traffic management center personnel, particularly for addressing non-recurring congestion in large or complex networks. Decision support for control room staff is necessary to effectively detect, verify and develop response strategies for traffic incidents. These are events that disrupt the orderly flow of traffic, and cause non-recurring congestion and motorist delay. Non-recurring congestion can be caused by accidents, spilled loads, stalled or broken down vehicles, maintenance and construction activities, signal and detector malfunctions, and special and unusual events. The ultimate objective of our research is to implement a novel artificial intelligence-based solution approach to the problem of providing operator decision support in integrated freeway and arterial traffic management systems, as part of a more general IVHS. In this paper, we present and discuss the development of FRED (Freeway Real-Time Expert System Demonstration), a component prototype real-time expert system for managing non-recurring congestion on urban freeways in Southern California. The application of FRED to a section of the Riverside Freeway (SR-91) in Orange County is presented as a case study, and illustrates the current capabilities of the system.

Research paper thumbnail of Real-Time Knowledge-Based Integration of Freeway Surveillance Data

Transportation Research Record, 1991

This paper describes an advanced processing capability that is based on the use of real-time know... more This paper describes an advanced processing capability that is based on the use of real-time knowledge-based expert system (KBES) technology integrate diverse types of traffic surveillance data for freeway monitoring and control purposes, particularly as part of future "Smart Roads" projects. One of the major functions of the prototype system developed is the acquisition and processing of input data drawn from sensors and processes in the real world. The real-time nature of these processes, and the associated need for decisionmaking information and recommendations, places particular importance on the efficient handling of data to avoid unnecessary overloading of the expert system. The relevant types of data include traffic occupancies and volumes from loop detectors in the pavement, information on traffic conditions from closed circuit television cameras, field reports from police officers and other official personnel, and cellular and emergency telephone calls from motorists. The paper emphasizes the way in which the data are acquired, processed and integrated within a prototype KBES framework in order to achieve the objectives of the incident management tasks, and specifically those of incident detection and verification. Examples are given of the implementation of these features.

Research paper thumbnail of Health Impacts of Moving Freight In and Out of the Ports of Long Beach and Los Angeles

University of California Transportation Center, Apr 1, 2010

Research paper thumbnail of A Deep Ensemble Neural Network Approach for FHWA Axle-based Vehicle Classification using Advanced Single Inductive Loops

The Federal Highway Administration (FHWA) vehicle classification scheme is designed to serve vari... more The Federal Highway Administration (FHWA) vehicle classification scheme is designed to serve various transportation needs such as pavement design, on-road emission estimation, and transportation planning. Many transportation agencies rely on Weigh-In-Motion and Automatic Vehicle Classification sites to collect these essential vehicle classification count data. However, the spatial coverage of these detection sites across the highway network are limited due to high installation and maintenance costs. One cost-effective approach investigated by researchers has been the use of single inductive loop sensors as an alternative to obtain FHWA vehicle classification data. However, most datasets used to develop such models are skewed since many classes belonging to larger truck configurations are rarely observed in the roadway network. This increases the challenge to accurately classify under-represented classes, even though many of these minority classes may pose disproportionately adverse impacts on pavement infrastructure and the environment. As a consequence, previous models have been unable to adequately classify under-represented classes, and the overall performance of the models are often masked by excellent classification accuracy of majority classes, such as passenger vehicles and five-axle tractor trailers. To resolve the challenge of imbalanced datasets in the FHWA vehicle classification problem, this paper describes a study that developed a bootstrap aggregating (bagging) deep neural network (DNN) model on a truck-focused dataset using single inductive loop signatures. The proposed method significantly improved the model performance on several truck classes, especially minority classes such as Classes 7 and 11 which were overlooked in previous research studies.

Research paper thumbnail of New Methods for Monitoring Spatial Truck Travel Patterns in California Using Existing Detector Infrastructure

This study developed a methodology to accurately estimate network-wide truck flows by leveraging ... more This study developed a methodology to accurately estimate network-wide truck flows by leveraging existing point detection infrastructure, namely inductive loop detectors. The tracking model identifies individual trucks at detector locations using advanced inductive signatures and matches vehicle pairs at detector locations, using an extended form of the Bayesian classification model to estimate matching and non-matching probabilities of the vehicle pairs Several vehicle feature selection and weighting methods including Self Organizing Map and K-means clustering were applied to better identify individual vehicles from signature data. It was shown that the proposed extensive feature processing enhanced vehicle identification performance even among vehicle pools sharing similar physical configurations. The developed model was tested along an approximately 5.5-mile freeway segment on I-5 and CA-78 in San Diego, California where only 67 percent of the total trucks were observed at both up-and downstream detector sites. Results showed balanced performances in exactness and completeness of matching with 91 percent of correct outcomes for multi-unit trucks.

Research paper thumbnail of Driving California’s Transportation Emissions to Zero

The purpose of this report is to provide a research-driven analysis of options that can put Calif... more The purpose of this report is to provide a research-driven analysis of options that can put California on a pathway to achieve carbon-neutral transportation by 2045. The report comprises thirteen sections. Section 1 provides an overview of the major components of transportation systems and how those components interact. Section 2 discusses the impacts the COVID-19 pandemic has had on transportation. Section 3 discusses California’s current transportation-policy landscape. These three sections were previously published as a synthesis report. Section 4 analyzes the different carbon scenarios, focusing on “business as usual” (BAU) and Low Carbon (LC1). Section 5 provides an overview of key policy mechanisms to utilize in decarbonizing transportation. Section 6 is an analysis of the light-duty vehicle sector, section 7 is the medium- and heavy-duty vehicle sectors, section 8 is reducing and electrifying vehicle miles traveled, and section 9 is an analysis of transportation fuels and the...

Research paper thumbnail of Vehicle Reidentification Using Multidetector Fusion

IEEE Transactions on Intelligent Transportation Systems, Sep 1, 2004

Research paper thumbnail of Real-Time Expert System Approach to Freeway Incident Management

Transportation Research Record, 1991

Research paper thumbnail of A knowledge-based decision support architecture for advanced traffic management

Transportation Research Part A: General, 1990

Research paper thumbnail of Neural Network Models For Automated Detection Of Non-recurring Congestion

RePEc: Research Papers in Economics, 1993

Research paper thumbnail of Section Related Measures of Traffic System Performance: Final Report

RePEc: Research Papers in Economics, Nov 1, 1998

Research paper thumbnail of Field Investigation of Advanced Vehicle Reidentification Techniques and Detector Technologies - Phase 1

RePEc: Research Papers in Economics, Mar 1, 2002

Research paper thumbnail of A Neuro-Genetic-Based Universally Transferable Freeway Incident Detection Framework

University of California Transportation Center, 1996

Research paper thumbnail of New Tool from UC Irvine Could Save the State Millions while Providing Better Data on Truck Activity in California

Research paper thumbnail of Understanding Commercial Vehicle Travel Through New High-Fidelity Inductive Sensors

Transportation Research Board 86th Annual MeetingTransportation Research Board, 2007

Despite their impacts on traffic performance, infrastructure, environment and safety, the travel ... more Despite their impacts on traffic performance, infrastructure, environment and safety, the travel behavior of commercial vehicles is not well understood. This is largely due to limited data available to distinguish between various types of commercial vehicles and their travel patterns. This ...

Research paper thumbnail of Routing and Scheduling Problem of Container Trucks with Selective Empty Container Pickup in a Shared Resource Environment

Transportation Research Board 97th Annual MeetingTransportation Research Board, 2018

Research paper thumbnail of Development of a real-time on-road emissions estimation and monitoring system

Transportation has been a significant contributor to total greenhouse gas and criteria air pollut... more Transportation has been a significant contributor to total greenhouse gas and criteria air pollutant emissions. Emission mitigation strategies are essential in reducing transportation's impacts on the environment. In order to effectively develop and evaluate on-road emissions reduction strategies, it is important to have an information support system which can estimate and monitor on-road emissions under real world traffic operations. Emission data provided by such a system can be used to identify emission hot spots and their causes, and to develop and evaluate reduction strategies. In this paper, a system is developed to estimate and monitor operational on-road emissions with high accuracy and resolution in real time. The two sets of critical information for emission estimation, vehicle mix and vehicle activity, are directly generated from traffic detection using inductive vehicle signature technology. An initial implementation on a section of the I-405 freeway at Irvine, California is demonstrated. With more widespread deployment, the system can be used to perform before-and-after evaluation of certain mitigation strategies, to develop time sensitive optimal traffic control strategies with the purpose to control emissions, and to provide high fidelity greenhouse gas and air quality information to policymakers, researchers, and the general public.

Research paper thumbnail of Goal Programming Approach to Allocate Freight Analysis Framework Mode Flow Data

Transportation Research Record, 2014

Research paper thumbnail of Sponsored research report: Assessment and development of commodity flow, logistics, and other relevant goods movement data sources to facilitate statewide freight modeling

Research paper thumbnail of Sponsored research report: Conceptual and methodological development of a California statewide freight demand model: Final report of scoping study

Research paper thumbnail of A Real-Time Expert System Approach To Freeway Incident Management - eScholarship

Fundamental to the operation of most Intelligent Vehicle-Highway System (IVHS) projects are advan... more Fundamental to the operation of most Intelligent Vehicle-Highway System (IVHS) projects are advanced systems for surveillance, control and management of integrated freeway and arterial networks. A major concern in the development of such Smart Roads, and the focus of this paper, is the provision of decision support for traffic management center personnel, particularly for addressing non-recurring congestion in large or complex networks. Decision support for control room staff is necessary to effectively detect, verify and develop response strategies for traffic incidents. These are events that disrupt the orderly flow of traffic, and cause non-recurring congestion and motorist delay. Non-recurring congestion can be caused by accidents, spilled loads, stalled or broken down vehicles, maintenance and construction activities, signal and detector malfunctions, and special and unusual events. The ultimate objective of our research is to implement a novel artificial intelligence-based solution approach to the problem of providing operator decision support in integrated freeway and arterial traffic management systems, as part of a more general IVHS. In this paper, we present and discuss the development of FRED (Freeway Real-Time Expert System Demonstration), a component prototype real-time expert system for managing non-recurring congestion on urban freeways in Southern California. The application of FRED to a section of the Riverside Freeway (SR-91) in Orange County is presented as a case study, and illustrates the current capabilities of the system.

Research paper thumbnail of Real-Time Knowledge-Based Integration of Freeway Surveillance Data

Transportation Research Record, 1991

This paper describes an advanced processing capability that is based on the use of real-time know... more This paper describes an advanced processing capability that is based on the use of real-time knowledge-based expert system (KBES) technology integrate diverse types of traffic surveillance data for freeway monitoring and control purposes, particularly as part of future "Smart Roads" projects. One of the major functions of the prototype system developed is the acquisition and processing of input data drawn from sensors and processes in the real world. The real-time nature of these processes, and the associated need for decisionmaking information and recommendations, places particular importance on the efficient handling of data to avoid unnecessary overloading of the expert system. The relevant types of data include traffic occupancies and volumes from loop detectors in the pavement, information on traffic conditions from closed circuit television cameras, field reports from police officers and other official personnel, and cellular and emergency telephone calls from motorists. The paper emphasizes the way in which the data are acquired, processed and integrated within a prototype KBES framework in order to achieve the objectives of the incident management tasks, and specifically those of incident detection and verification. Examples are given of the implementation of these features.

Research paper thumbnail of Health Impacts of Moving Freight In and Out of the Ports of Long Beach and Los Angeles

University of California Transportation Center, Apr 1, 2010

Research paper thumbnail of A Deep Ensemble Neural Network Approach for FHWA Axle-based Vehicle Classification using Advanced Single Inductive Loops

The Federal Highway Administration (FHWA) vehicle classification scheme is designed to serve vari... more The Federal Highway Administration (FHWA) vehicle classification scheme is designed to serve various transportation needs such as pavement design, on-road emission estimation, and transportation planning. Many transportation agencies rely on Weigh-In-Motion and Automatic Vehicle Classification sites to collect these essential vehicle classification count data. However, the spatial coverage of these detection sites across the highway network are limited due to high installation and maintenance costs. One cost-effective approach investigated by researchers has been the use of single inductive loop sensors as an alternative to obtain FHWA vehicle classification data. However, most datasets used to develop such models are skewed since many classes belonging to larger truck configurations are rarely observed in the roadway network. This increases the challenge to accurately classify under-represented classes, even though many of these minority classes may pose disproportionately adverse impacts on pavement infrastructure and the environment. As a consequence, previous models have been unable to adequately classify under-represented classes, and the overall performance of the models are often masked by excellent classification accuracy of majority classes, such as passenger vehicles and five-axle tractor trailers. To resolve the challenge of imbalanced datasets in the FHWA vehicle classification problem, this paper describes a study that developed a bootstrap aggregating (bagging) deep neural network (DNN) model on a truck-focused dataset using single inductive loop signatures. The proposed method significantly improved the model performance on several truck classes, especially minority classes such as Classes 7 and 11 which were overlooked in previous research studies.

Research paper thumbnail of New Methods for Monitoring Spatial Truck Travel Patterns in California Using Existing Detector Infrastructure

This study developed a methodology to accurately estimate network-wide truck flows by leveraging ... more This study developed a methodology to accurately estimate network-wide truck flows by leveraging existing point detection infrastructure, namely inductive loop detectors. The tracking model identifies individual trucks at detector locations using advanced inductive signatures and matches vehicle pairs at detector locations, using an extended form of the Bayesian classification model to estimate matching and non-matching probabilities of the vehicle pairs Several vehicle feature selection and weighting methods including Self Organizing Map and K-means clustering were applied to better identify individual vehicles from signature data. It was shown that the proposed extensive feature processing enhanced vehicle identification performance even among vehicle pools sharing similar physical configurations. The developed model was tested along an approximately 5.5-mile freeway segment on I-5 and CA-78 in San Diego, California where only 67 percent of the total trucks were observed at both up-and downstream detector sites. Results showed balanced performances in exactness and completeness of matching with 91 percent of correct outcomes for multi-unit trucks.

Research paper thumbnail of Driving California’s Transportation Emissions to Zero

The purpose of this report is to provide a research-driven analysis of options that can put Calif... more The purpose of this report is to provide a research-driven analysis of options that can put California on a pathway to achieve carbon-neutral transportation by 2045. The report comprises thirteen sections. Section 1 provides an overview of the major components of transportation systems and how those components interact. Section 2 discusses the impacts the COVID-19 pandemic has had on transportation. Section 3 discusses California’s current transportation-policy landscape. These three sections were previously published as a synthesis report. Section 4 analyzes the different carbon scenarios, focusing on “business as usual” (BAU) and Low Carbon (LC1). Section 5 provides an overview of key policy mechanisms to utilize in decarbonizing transportation. Section 6 is an analysis of the light-duty vehicle sector, section 7 is the medium- and heavy-duty vehicle sectors, section 8 is reducing and electrifying vehicle miles traveled, and section 9 is an analysis of transportation fuels and the...

Research paper thumbnail of Integration of Weigh-in-Motion and Inductive Signature Technology for Advanced Truck Monitoring

Transportation Research Board 93rd Annual Meeting, Washington, D.C., January 13-17, 2014

Trucks have a significant impact on infrastructure, traffic congestion, energy consumption, pollu... more Trucks have a significant impact on infrastructure, traffic congestion, energy consumption, pollution and quality of life. To better understand truck characteristics, comprehensive high resolution truck data is needed. Higher quality truck data can enable more accurate estimates of GHGs and emissions, allow for better management of infrastructure, provide insight to truck travel behavior, and enhance freight forecasting. Currently, truck traffic data is collected through limited means and with limited detail. Agencies can obtain or estimate truck travel statistics from surveys, inductive loop detectors (ILD) and weigh-in-motion (WIM) stations, or from manual counts, each of which have various limitations. Of these sources, WIM and ILD seem to be the most promising tools for capturing detailed truck information. Axle spacing and weight from existing WIM devices and unique inductive signatures indicative of body type from ILDs equipped with high sampling rate detector cards are complementary data sources that can be integrated to provide a synergistic resource that otherwise does not exist in practice, a resource that is able to overcome the drawbacks of the traditional truck data collection methods by providing data that is detailed, link specific, temporally continuous, up-to-date, and representative of the full truck population. This integrated data resource lends itself very readily toward detailed truck body classification which is presented as a case study. This body classification model is able to predict 35 different trailer body types for FHWA class 9 semi-tractors, achieving an 80 percent correct classification rate. In addition to the body classification model, the large data set resulting from the case study is itself a valuable and novel resource for truck studies.

Research paper thumbnail of Accurate individual vehicle speeds from single inductive loop signatures

88th Annual Meeting of the Transportation Research Board, Jan 1, 2009

The paper presents a new model for estimating individual vehicle speeds from conventional round s... more The paper presents a new model for estimating individual vehicle speeds from conventional round single inductive loop sensors equipped with advanced high-speed scanning detector cards. The model presented improves upon existing models with final results of individual vehicle estimated speeds showing average errors of less than 2 mph and 4 mph, respectively, for two independent test datasets. Improvements to individual vehicle speed estimations can help to enhance analysis in traffic operations and planning fields which depend on accurate speed values such as traffic safety, where knowledge of speed variance is critical. The ability to estimate speed from a single loop, as opposed to double loop speed traps, reduces the need to install double loops and can assist in collecting data when information from double loops is not available.