Scholarly Work - Western Transportation Institute

Permanent URI for this collectionhttps://scholarworks.montana.edu/handle/1/9749

Browse

Search Results

Now showing 1 - 10 of 21

Risk mapping of wildlife–vehicle collisions across the state of Montana, USA: a machine-learning approach for imbalanced data along rural roads
(Oxford University Press, 2024-05) Bell, Matthew; Wang, Yiyi; Ament, Rob
Wildlife–vehicle collisions (WVCs) with large animals are estimated to cost the USA over 8 billion USD in property damage, tens of thousands of human injuries and nearly 200 human fatalities each year. Most WVCs occur on rural roads and are not collected evenly among road segments, leading to imbalanced data. There are a disproportionate number of analysis units that have zero WVC cases when investigating large geographic areas for collision risk. Analysis units with zero WVCs can reduce prediction accuracy and weaken the coefficient estimates of statistical learning models. This study demonstrates that the use of the synthetic minority over-sampling technique (SMOTE) to handle imbalanced WVC data in combination with statistical and machine-learning models improves the ability to determine seasonal WVC risk across the rural highway network in Montana, USA. An array of regularized variables describing landscape, road and traffic were used to develop negative binomial and random forest models to infer WVC rates per 100 million vehicle miles travelled. The random forest model is found to work particularly well with SMOTE-augmented data to improve the prediction accuracy of seasonal WVC risk. SMOTE-augmented data are found to improve accuracy when predicting crash risk across fine-grained grids while retaining the characteristics of the original dataset. The analyses suggest that SMOTE augmentation mitigates data imbalance that is encountered in seasonally divided WVC data. This research provides the basis for future risk-mapping models and can potentially be used to address the low rates of WVCs and other crash types along rural roads.
Statewide GNSS-RTN Systems: Current Practices
(Scientific Research Publishing, Inc., 2023-01) Raza, Sajid; Al-Kaisy, Ahmed
The applications of geospatial technologies and positioning data embrace every sphere of modern-day science and industry. With technological advancement, the demands for highly accurate positioning services in real-time led to the development of the Global Navigation Satellite System—Real-Time Network (GNSS-RTN). While there is numerous published information on the technical aspects of the GNSS-RTN technology, information on the best practices or guidelines in building, operating, and managing the GNSS-RTN networks is lacking in practice. To better understand the current practice in establishing and operating the GNSS-RTN systems, an online questionnaire survey was sent to the GNSS-RTN system owners/operators across the U.S. Additionally, a thorough review of available literature on business models and interviews with representatives of two major manufacturers/vendors of GNSS-RTN products and services were conducted. Study results revealed a great deal of inconsistency in current practices among states in the way the GNSS-RTN systems are built, operated, and managed. Aspects of the diversity in state practices involved the business models for the GNSS-RTN systems besides the technical attributes of the network and system products. The information gathered in this study is important in helping state agencies make informed decisions as they build, expand or manage their own GNSS-RTN systems.
The Role of GNSS-RTN in Transportation Applications
(MDPI AG, 2022-07) Raza, Sajid; Al-Kaisy, Ahmed; Teixeira, Rafael; Meyer, Benjamin
The Global Navigation Satellite System—Real-Time Network (GNSS-RTN) is a satellite-based positioning system using a network of ground receivers (also called continuously operating reference stations (CORSs)) and a central processing center that provides highly accurate location services to the users in real-time over a broader geographic region. Such systems can provide geospatial location data with centimeter-level accuracy anywhere within the network. Geospatial location services are not only used in measuring ground distances and mapping topography; they have also become vital in many other fields such as aerospace, aviation, natural disaster management, and agriculture, to name but a few. The innovative and multi-disciplinary applications of geospatial data drive technological advancement towards precise and accurate location services available in real-time. Although GNSS-RTN technology is currently utilized in a few industries such as precision farming, construction industry, and land surveying, the implications of precise real-time location services would be far-reaching and more critical to many advanced transportation applications. The GNSS-RTN technology is promising in meeting the needs of automation in most advanced transportation applications. This article presents an overview of the GNSS-RTN technology, its current applications in transportation-related fields, and a perspective on the future use of this technology in advanced transportation applications.
Statewide GNSS-RTN Systems: Current Practices
(Scientific Research Publishing, Inc., 2023-01) Raza, Sajid; Al-Kaisy, Ahmed
The applications of geospatial technologies and positioning data embrace every sphere of modern-day science and industry. With technological advancement, the demands for highly accurate positioning services in real-time led to the development of the Global Navigation Satellite System—Real-Time Network (GNSS-RTN). While there is numerous published information on the technical aspects of the GNSS-RTN technology, information on the best practices or guidelines in building, operating, and managing the GNSS-RTN networks is lacking in practice. To better understand the current practice in establishing and operating the GNSS-RTN systems, an online questionnaire survey was sent to the GNSS-RTN system owners/operators across the U.S. Additionally, a thorough review of available literature on business models and interviews with representatives of two major manufacturers/vendors of GNSS-RTN products and services were conducted. Study results revealed a great deal of inconsistency in current practices among states in the way the GNSS-RTN systems are built, operated, and managed. Aspects of the diversity in state practices involved the business models for the GNSS-RTN systems besides the technical attributes of the network and system products. The information gathered in this study is important in helping state agencies make informed decisions as they build, expand or manage their own GNSS-RTN systems.
Transportation Research Record: Journal of the Transportation Research Board
(SAGE Publications, 2023-02) Raza, Sajid; Al-Kaisy, Ahmed; Washburn, Scott; Barrios, Jorge; Tsui Moreno, Ana; Schroeder, Bastian
Understanding the influence of intersections on operating conditions along connecting roadway segments is important for the analysis of highway facilities and corridors. This study aims at assessing the influence area at signalized and stop-control intersections along rural corridors. The study used speed as a performance measure in examining the spatial extent of operational effects at intersections. High-fidelity connected vehicle (CV) trajectory data, collected at 11 different sites in Florida, was used in this study. The CV trajectory data consists of individual waypoints that included timestamps and location coordinates along with other attributes. Drivers’ speed profiles while driving through the intersection were established and analyzed to determine the length of upstream and downstream influence areas. Quantile regression models were developed to estimate the 50th, 70th, and 85th percentiles of upstream and downstream influence areas separately for signalized and stop-control intersections. Study results indicate that the upstream influence area is longer for a signalized intersection than for a stop-control intersection for comparable segment running speeds. Further, the downstream influence area is significantly longer than the upstream influence area at signalized intersections, and this was consistent at all study sites. Traffic flow level did not have a significant effect on the upstream or downstream influence area; however, midblock running speed, percent heavy vehicles, and facility type (multilane versus two-lane) were found to significantly affect the upstream and downstream influence areas at signalized intersections.
Statewide GNSS-RTN Systems: Current Practices
(Scientific Research Publishing, Inc., 2023-01) Raza, Sajid; Al-Kaisy, Ahmed
The applications of geospatial technologies and positioning data embrace every sphere of modern-day science and industry. With technological advancement, the demands for highly accurate positioning services in real-time led to the development of the Global Navigation Satellite System—Real-Time Network (GNSS-RTN). While there is numerous published information on the technical aspects of the GNSS-RTN technology, information on the best practices or guidelines in building, operating, and managing the GNSS-RTN networks is lacking in practice. To better understand the current practice in establishing and operating the GNSS-RTN systems, an online questionnaire survey was sent to the GNSS-RTN system owners/operators across the U.S. Additionally, a thorough review of available literature on business models and interviews with representatives of two major manufacturers/vendors of GNSS-RTN products and services were conducted. Study results revealed a great deal of inconsistency in current practices among states in the way the GNSS-RTN systems are built, operated, and managed. Aspects of the diversity in state practices involved the business models for the GNSS-RTN systems besides the technical attributes of the network and system products. The information gathered in this study is important in helping state agencies make informed decisions as they build, expand or manage their own GNSS-RTN systems.
Influence Area at Signalized and Stop-Control Intersections: Operational Analysis
(SAGE Publications, 2023-02) Raza, Sajid; Al-Kaisy, Ahmed; Washburn, Scott; Barrios, Jorge; Moreno, Ana Tsui; Schroeder, Bastian
Understanding the influence of intersections on operating conditions along connecting roadway segments is important for the analysis of highway facilities and corridors. This study aims at assessing the influence area at signalized and stop-control intersections along rural corridors. The study used speed as a performance measure in examining the spatial extent of operational effects at intersections. High-fidelity connected vehicle (CV) trajectory data, collected at 11 different sites in Florida, was used in this study. The CV trajectory data consists of individual waypoints that included timestamps and location coordinates along with other attributes. Drivers’ speed profiles while driving through the intersection were established and analyzed to determine the length of upstream and downstream influence areas. Quantile regression models were developed to estimate the 50th, 70th, and 85th percentiles of upstream and downstream influence areas separately for signalized and stop-control intersections. Study results indicate that the upstream influence area is longer for a signalized intersection than for a stop-control intersection for comparable segment running speeds. Further, the downstream influence area is significantly longer than the upstream influence area at signalized intersections, and this was consistent at all study sites. Traffic flow level did not have a significant effect on the upstream or downstream influence area; however, midblock running speed, percent heavy vehicles, and facility type (multilane versus two-lane) were found to significantly affect the upstream and downstream influence areas at signalized intersections.
Implementing wildlife fences along highways at the appropriate spatial scale: A case study of reducing road mortality of Florida Key deer
(Pensoft Publishers, 2022-03) Huijser, Marcel P.; Begley, James S.
Florida Key deer mortality data (1966–2017) showed that about 75% of all reported deer mortalities were related to collisions with vehicles. In 2001–2002, the eastern section of US Hwy 1 on Big Pine Key (Florida, USA) was mitigated with a wildlife fence, 2 underpasses, and 4 deer guards. After mitigation, the number of reported Key deer road mortalities reduced substantially in the mitigated section, but this was negated by an increase in collisions along the unmitigated section of US Hwy 1 on Big Pine Key, both in absolute numbers and expressed as a percentage of the total deer population size. The data also showed that the increase in Key deer collisions along the unmitigated highway section on the island could not be explained through an increase in Key deer population size, or by a potential increase in traffic volume. The overall Key deer road mortality along US Hwy 1 was not reduced but was moved from the mitigated section to the nearby unmitigated section. Thus, there was no net benefit of the fence in reducing collisions. After mitigation, a significant hotspot of Key deer-vehicle collisions appeared at the western fence-end, and additional hotspots occurred further west along the unmitigated highway. Exploratory spatial analyses led us to reject the unmitigated highway section on Big Pine Key as a suitable control for a Before-After-Control-Impact (BACI) analysis into the effectiveness of the mitigation measures in reducing deer-vehicle collisions. Instead, we selected highway sections west and east of Big Pine Key as a control. The BACI analysis showed that the wildlife fence and associated mitigation measures were highly effective (95%) in reducing deer-vehicle collisions along the mitigated highway section. Nonetheless, in order to reduce the overall number of deer-vehicle collisions along US Hwy 1, the entire highway section on Big Pine Key would need to be mitigated. However, further mitigation is complicated because of the many buildings and access roads for businesses and residences. This case study illustrates that while fences and associated measures can be very effective in reducing collisions, wildlife fences that are too short may result in an increase in collisions in nearby unmitigated road sections, especially near fence-ends. Therefore it is important to carefully consider the appropriate spatial scale over which highway mitigation measures are implemented and evaluated.
Intercity Bus Service Funding and Assessment Methodology
(University of South Florida Libraries, 2012-09) Ye, Zhirui; Kack, David; Chaudhari, Jaydeep; Ewan, Levi
The Federal Transit Administration (FTA)’s 5311(f) program requires that 15 percent of 5311 program funds given to a state be used to develop and support intercity bus (ICB) service. This 15 percent can be waived if the governor certifies that the ICB needs are being met within the state. This certification became harder to justify when FTA began requiring a more stringent consultation process before certification could be given. The objectives of this study are to learn about current practices of ICB service funding mechanisms, funds prioritization, and determination processes and strategies that promote ICB service. An assessment methodology for Montana was developed to determine whether ICB needs are being adequately met and how to allocate funds to support service. The results of this study will be valuable to other states considering developing methodologies for certification and funding allocation purposes.
Role of Trusted Sources and Behavioral Beliefs in Promoting Mitigation Behaviors: Lessons from the COVID-19 Pandemic (Preprint)
(JMIR Publications Inc., 2022-02) Hanson, Bridget L.; Finley, Kari; Otto, Jay; Ward, Nicholas J.
Background: During the ongoing COVID-19 pandemic and in preparation for future public health crises, it is important to understand the relationship between individuals’ health beliefs, including their trust in various sources of health information, and their engagement in mitigation behaviors. Objective: We sought to identify relationships between trust in various sources of health information and the behavioral beliefs related to vaccination and mask wearing as well as to understand how behavioral beliefs related to vaccination differ by willingness to be vaccinated. Methods: We conducted an online survey of 1034 adults in the United States and assessed their trust in federal, local, and media sources of health information; their beliefs about vaccination; and their masking intention and vaccination willingness. Results: Using regression, masking intention was predicted by trust in the World Health Organization (P<.05) and participants’ state public health offices (P<.05), while vaccine willingness was predicted by trust in participants’ own health care providers (P<.05) and pharmaceutical companies (P<.001). Compared to individuals with low willingness to be vaccinated, individuals with high willingness indicated greater endorsement of beliefs that vaccines would support a return to normalcy, are safe, and are a social responsibility (P<.001 for all). Conclusions: Results can be used to inform ongoing public health messaging campaigns to manage the COVID-19 pandemic and increase readiness for the next pandemic. Additionally, results support the need to bolster the public’s trust in health care agencies as well as to enhance trust and respect in health care providers to increase people’s adoption of mitigation behaviors.

Scholarly Work - Western Transportation Institute

Browse

Filters

Settings

Sort By

Results per page

Search Results