College of Engineering
Permanent URI for this communityhttps://scholarworks.montana.edu/handle/1/27
The College of Engineering at Montana State University will serve the State of Montana and the nation by fostering lifelong learning, integrating learning and discovery, developing and sharing technical expertise, and empowering students to be tomorrow's leaders.
Browse
2 results
Search Results
Item 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, RobWildlife–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.Item Calculating the limit of detection for a dilution series(Elsevier BV, 2023-05) Sharp, Julia L.; Parker, Albert E.; Hamilton, Martin A.Aims. Microbial samples are often serially diluted to estimate the number of microbes in a sample, whether as colony-forming units of bacteria or algae, plaque forming units of viruses, or cells under a microscope. There are at least three possible definitions for the limit of detection (LOD) for dilution series counts in microbiology. The statistical definition that we explore is that the LOD is the number of microbes in a sample that can be detected with high probability (commonly 0.95). Methods and results. Our approach extends results from the field of chemistry using the negative binomial distribution that overcomes the simplistic assumption that counts are Poisson. The LOD is a function of statistical power (one minus the rate of false negatives), the amount of overdispersion compared to Poisson counts, the lowest countable dilution, the volume plated, and the number of independent samples. We illustrate our methods using a data set from Pseudomonas aeruginosa biofilms. Conclusions. The techniques presented here can be applied to determine the LOD for any counting process in any field of science whenever only zero counts are observed. Significance and impact of study. We define the LOD when counting microbes from dilution experiments. The practical and accessible calculation of the LOD will allow for a more confident accounting of how many microbes can be detected in a sample.