Article
Public, Environmental & Occupational Health
Qinzhong Hou, Xiaoyan Huo, Andrew P. Tarko, Junqiang Leng
Summary: This study thoroughly evaluated six different models for handling unobserved heterogeneity and found that the random parameters approach is the most effective. Complex models can provide more insights but come with higher computational costs.
ANALYTIC METHODS IN ACCIDENT RESEARCH
(2021)
Article
Ergonomics
Sonu Mathew, Srinivas S. Pulugurtha, Sarvani Duvvuri
Summary: This research examines the impact of road network, demographic, and land use characteristics on teen crash frequency. By comparing different models, significant explanatory variables related to teen crash frequency were identified. Among them, the geographically weighted negative binomial regression models better capture the spatial characteristics of the associated risk factors.
ACCIDENT ANALYSIS AND PREVENTION
(2022)
Article
Ergonomics
Jacob Mathew, Rahim F. Benekohal
Summary: The new FRA model uses a single equation for all three warning devices, while the ZINEBS model gives three different equations depending on the type of warning device used, showing closer agreement with field data. The ZINEBS model complements the new FRA model by addressing the shortcomings of the single equation.
JOURNAL OF SAFETY RESEARCH
(2021)
Article
Ergonomics
Vikash V. Gayah, Eric T. Donnell
Summary: The relationship between expected crash frequency and traffic volume is non-linear, with a proposed alternative functional form allowing for different elasticities within different traffic volume ranges. The new model, applied to two-lane rural roadways in Pennsylvania, offers improved fit and predictive performance compared to traditional and Hoerl functional forms, potentially for future SPF development.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Ergonomics
Ali Khodadadi, Ioannis Tsapakis, Subasish Das, Dominique Lord, Yingfeng Li
Summary: Research indicates that the application of NB-L models is more effective than traditional NB models for NFAS roads. Appropriate variance structure and dispersion function selection can further enhance model performance.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Multidisciplinary Sciences
Varun Kumar Sharma, Pardeep Kumar Gupta, R. K. Khitoliya
Summary: The delays in highway construction projects lead to additional costs, and factors such as land acquisition, utility shifting, construction under traffic conditions, and project planning and design changes are identified as the most critical causes of time overrun.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Biology
Dwueng-Chwuan Jhwueng, Chi-Yu Wu
Summary: A new phylogenetic negative binomial regression model was developed to analyze count-dependent variables in species related through a shared ancestry. This model overcomes the limitations of traditional regression models and provides a more accurate analysis tool for species data, emphasizing the influence of shared ancestry. It promises enhanced research methodologies and has valuable implications for evolutionary biology and ecology.
Article
Engineering, Multidisciplinary
Yan Tu, Jian Chu, Mohd Asif Shah
Summary: The input of scientific research resources plays a key role in the development of solar thermal technology, while the demand for photothermal technology and green innovation are complementary.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2022)
Article
Automation & Control Systems
Thomas Veran, Pierre-Edouard Portier, Francois Fouquet
Summary: This paper introduces a framework for discovering interpretable regression models for high-stakes decision making in safety-critical systems. The proposed framework utilizes a hierarchical symbolic regression algorithm to compute cluster-specific rankings of regression models based on increasing complexity. The results show promising performance compared to other interpretable or black-box predictive models on various datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Transportation
Syeda Rubaiyat Aziz, Sunanda Dissanayake
Summary: To improve accuracy in results, Kansas developed specific safety performance functions (SPFs) for local conditions. Through calibration and validation, these new SPFs were found to more accurately predict crashes than the HSM-provided models.
JOURNAL OF TRANSPORTATION SAFETY & SECURITY
(2021)
Article
Urban Studies
Liang Luo, Min Deng, Yan Shi, Shijuan Gao, Baoju Liu
Summary: Urban geographical environments have a significant impact on the occurrences of street crimes. This study utilizes deep learning models and various variables to construct a regression model, revealing the effects of single factors and pairwise interactions on street crime instances, which can contribute to enhancing public security.
Article
Ergonomics
Shamsunnahar Yasmin, Tanmoy Bhowmik, Moshiur Rahman, Naveen Eluru
Summary: Traditionally, safety researchers have used land use and urban form variables as surrogate for exposure information in non-motorized crash prediction models, but the lack of true non-motorized exposure data affects the quality of these models. This study aims to develop an integrated non-motorized demand and crash prediction framework to address this issue, and demonstrates the applicability of the framework through extensive policy scenario analysis.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Engineering, Environmental
Wasim Iqbal, Yuk Ming Tang, Ka Yin Chau, Muhammad Irfan, Muhammad Mohsin
Summary: The study reveals a positive correlation between air pollution, particularly nitrogen dioxide and PM2.5, and the number of NCOV-2019 cases and deaths in China. A slight rise in air pollution, as represented by PM2.5, has caused a significant increase in both cases and deaths of NCOV-2019.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Medicine, Research & Experimental
Kyung Hyun Lee, Claudia Pedroza, Elenir B. C. Avritscher, Ricardo A. Mosquera, Jon E. Tyson
Summary: This study evaluated the performance of two generalized linear models, negative binomial and zero-inflated negative binomial, for analyzing zero-inflated count data through simulation experiments. The results showed that the mean and skewness of the non-zero part of the data were stronger predictors of model preference than the percentage of zero counts.
Article
Ergonomics
Rune Elvik, Tor-Olav Naevestad
Summary: The objective of this paper is to evaluate the effectiveness of the Safe System approach to road safety management, as implemented in Norway. The findings suggest that the Safe System approach has contributed to a larger improvement in road safety in Norway. The study uses negative binomial regression models to examine the relationship between key elements of the Safe System approach and changes in the number of killed or seriously injured road users over time.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Engineering, Civil
Ross McCarthy, Gerardo Flintsch, Edgar de Leon Izeppi
Summary: The study suggests that skid resistance can impact crash risk on both wet and dry pavements, with a greater impact observed in wet conditions. Considering dry crashes in highway safety management can lead to better maintenance decisions by increasing the number of crash observations and improving safety analysis.
JOURNAL OF TRANSPORTATION ENGINEERING PART B-PAVEMENTS
(2021)