Journal of Sustainable Development of Transport and Logistics

An assessment of machine learning and data balancing techniques for evaluating downgrade truck crash severity prediction in Wyoming

Vincent Michael Ampadu — 2022-11-19

This study involved the investigation of various machine learning methods, including four classification tree-based ML models, namely the Adaptive Boosting tree, Random Forest, Gradient Boost Decision Tree, Extreme Gradient Boosting tree, and three non-tree-based ML models, namely Support Vector Machines, Multi-layer Perceptron and k-Nearest Neighbors for predicting the level of severity of large truck crashes on Wyoming road networks. The accuracy of these seven methods was then compared. The Final ROC AUC score for the optimized random forest model is 95.296 %. The next highest performing model was the k-NN with 92.780 %, M.L.P. with 87.817 %, XGBoost with 86.542 %, Gradboost with 74.824 %, SVM with 72.648 % and AdaBoost with 67.232 %. Based on the analysis, the top 10 predictors of severity were obtained from the feature importance plot. These may be classified into whether safety equipment was used, whether airbags were deployed, the gender of the driver and whether alcohol was involved.

Heavy vehicle crashes in Addis Ababa: Relationship between contributing factors and severity of outcomes

Getu Segni Tulu — 2022-11-19

Random parameter logit regression is used to analyze police-reported data on 8,253 heavy vehicle-related crashes in Addis Ababa between July 2014 and June 2017. The analysis shows that fatal crashes are more likely to occur during the day and on weekdays, particularly when the circulation of trucks is high. It also shows the disproportionately high involvement of young drivers in heavy vehicle crashes in the city. However, the likelihood of crashes resulting in fatalities and serious injuries increases slightly compared to those resulting only in property damage as the age of drivers increases. Low levels of drivers' education, the fact that drivers are often not the owners of vehicles, ownership of vehicles by companies and government organizations, and inappropriate road medians' inappropriate design are also significant contributors to fatal crashes. Curbing deaths and injuries from heavy vehicle crashes in Addis Ababa requires strict enforcement of traffic rules and regulations, particularly speed limits; reforms in driver's training and certification; improved safety culture of vehicle owners and design of road infrastructure. Ethiopia's national road safety strategy launched in July 2022 addresses these issues. Hence the government is taking steps in the right direction.

An Assessment of pedestrian infrastructures of road transport: A case study of Jimma Town

Tarekegn Reta Mesfin — 2022-11-19

Pedestrian infrastructures are a critical part of the sustainable transportation system of a city across the world. The key risks to pedestrians are well documented, including infrastructure in terms of the lack of dedicated pedestrian facilities, such as sidewalks, crossings, and raised medians. This paper aimed to assess pedestrian infrastructures of the road transport system in Jimma city. The P-index (Pedestrian-index) method was used to evaluate pedestrian infrastructures, computed with the formula containing the four pedestrian indicators: mobility, safety, pedestrian facility, and accessibility indicator. For this method, sixteen road segments were selected. The result of the mobility indicator shows that the star rating obtained was two stars, which means impaired mobility for the pedestrian. For safety, a 1-star of star-rating was obtained, indicating that the road segments were very unsafe. For the facility indicator, the star-rating value was 2-star which shows inadequate pedestrian facility. For the accessibility indicator, two star-rating was obtained, meaning there was poor accessibility to land uses by walking. Overall P-index value has got a 2-star rating that, which indicates that the existing roads were unfavorable to a pedestrian walking.

Automating the updated grade severity rating system (GSRS) using the Visual Basic.net programming language

Vincent Michael Ampadu — 2022-11-19

Truck crashes on steep downgrades due to excessive brake heating, resulting from brake applications to control speeding, are a continuing cause of concern for the Wyoming Department of Transportation (WYDOT). In 2016, WYDOT funded a project to update the existing Grade Severity Rating System. Furthermore, in 2020, WYDOT commissioned a research project to automate the updated version of the mathematical model through an interactive, intuitive, aesthetically appealing and user-friendly Visual Basic.net objected-oriented software to simplify the computation of the maximum safe descent speed on these downgrades based on the truck weight. The software provides functionality for both the continuous Slope and separate downgrade methods. The primary beneficiaries of this software will be the highway agencies who will be able to estimate the maximum safe speed of descent for trucks with various weight categories and hence produce Weight Specific Speed (WSS) signs for each downgrade or a multigrade section.

The dynamic programming model for optimal allocation of laden shipping containers to Nigerian seaports

Harrison O. Amuji — 2022-11-19

In highly competitive shipping market environment, container network operators-Freight forwarders, shipping companies etc. are concerned about design, development and deployment of optimized allocation model to achieve cost savings through improved container storage yard operations, crane productivity, outbound container allocation/distribution to seaport terminals and hence reduction in ships’ waiting times. In this paper, we developed two models, the Dynamic programming model and optimal allocation policy (model), for the optimal allocation of units of outbound laden cargo containers of sizes: 20ft and 40ft to six (6) major seaports in Nigeria. The distributions of the laden containers were allocated as follows: Port-Harcourt, Tincan Island, Onne, and Calabar seaports were allocated with 1,064 units of stuffed containers each. Apapa seaport was allocated with 2,128 units of laden containers, and zero allocation was made to Warri seaport. These results were arrived at through the implementation of the optimal allocation policy. The zero units allocation made to Warri seaport could be attributed to poor shipper patronage and hence the low frequency of ship visits. Apapa seaport was allocated double the number of containers moved to the remaining ports because it attracted more shipper patronage and hence more ship visits. Hence, freight forwarding companies will be assured of cargo spaces and make more profit by allocating more containers. Policy implications of the developed models were discussed.

Influence of artificial intelligence on warehouse performance: The case study of the Colombo area, Sri Lanka

Janani Shamindika Kumari Angammana — 2022-11-19

This study is focused on the influence that artificial intelligence can bring on warehouse performance. A sample of 329 workers from selected warehouses was used for this study, and a self-administered questionnaire was used to collect data. An index was constructed using the Principal Component Analysis (PCA) method to measure the influence on warehouse performance. Mann Whitney U test and Kruskal-Wallis H test were used to determine the effect of demographic factors on warehouse performance. The association among the variables was identified by employing correlation analysis. A regression analysis was performed to determine the relationship between the identified factors and warehouse performance. When the study tests for the association among the variables, it depicts a positive correlation. Finally, based on the analysis, it illustrates the influence of machine learning, robotics, the Internet of things (IoT), and fuzzy logic on warehouse performance. The warehouse performance was mentioned in three categories: time, inventory, and cost.