Wei ZHANG, Chuang ZHU, Yunchao QU, Guanhua LIU, Der-Horng LEE

With the ongoing urbanisation, the subway has become a vital component of modern cities, catering to the escalating demands of a mobile population. However, the increasing complexity of passenger flows within subway stations poses challenges to operations management. To optimise subway operations and enhance safety, researchers focus on extracting and analysing pedestrian trajectories within subway stations. Traditional trajectory extraction methods face limitations due to manual feature design and multi-stage processing. Leveraging advancements in deep learning, this paper integrates M-DeepSORT with YOLOv5 and proposes a feature association matching approach that addresses trajectory drift issues through simultaneous consideration of motion and appearance matching. The confidence-based (CB) Kalman filtering method is proposed to address the issue of random noise in pedestrian detection within subway scenes. The introduction of a momentum-based passenger trajectory centre update method reduces jitter, resulting in smoother trajectory extraction. Experimental results affirm the effectiveness of the proposed algorithm in detecting, tracking and statistically analysing subway station corridor passenger flow trajectories, demonstrating robust performance in diverse subway station scenarios.

2025 (Vol 37), Issue 2

Patricija BAJEC, Eva PODOVŠOVNIK

Crowdshipping has garnered increasing interest due to its potential benefits for various stakeholders. However, despite challenges in attracting crowdshippers, limited research explores their preferences, including socio-demographic factors and the practical challenges providers face when testing or implementing crowdshipping. This study aims to identify key factors influencing willingness-to-work (WTW) among potential crowdshippers, both in general and within business-to-business (B2B) and business-to-customer (B2C) contexts. Based on the literature review, this paper identifies 19 barriers influencing WTW and develops 22 corresponding enablers to address these barriers. Using a survey of 432 participants from Slovenia, the overall significance of these factors without differentiating business models was first assessed. Then, chi-squared automatic interaction detection analysis was applied to predict WTW in B2B and B2C contexts, identifying variations across these models. The disclosure of a mobile number emerged as the most influential predictor in both settings. Other notable differences in enablers and barriers were observed depending on the business model. These findings emphasise the need to consider business models in future preference analyses and provide a foundation for targeted recruitment strategies for crowdshippers.

2025 (Vol 37), Issue 2

Adisa MEDIĆ, Amel KOSOVAC, Ermin MUHAREMOVIĆ, Muhamed BEGOVIĆ

Machine learning (ML) is a crucial component of artificial intelligence that has recently attracted attention for its application in logistics. ML algorithms are used on large datasets. They create logic correlations among given data and provide predictions of specific values. This research paper aims to conduct a systematic literature review to showcase the potential applications of machine learning in urban logistics systems, specifically focusing on enhancing satisfaction for postal logistics operators and their customers. The authors used various research publication databases in this context (Web of Science, Scopus, Google Scholar etc). The analysis of different models provides insights into diverse aspects, such as predicting product prices and types of cargo, evaluating user satisfaction, forecasting user departures, assessing optimal geographical locations for implementing postal centres, predicting purchase times before online orders, estimating delivery times in the last phase of the logistics chain and more. The significance of this research is highlighted through the identification of shortcomings in existing literature, offering guidelines for future research in developing new machine learning model for optimal operator selection. This model aims to achieve improvements in both customer and operator satisfaction simultaneously.

2025 (Vol 37), Issue 2

Yanhong YIN, Zihao YE, Qiuyan HAN, Li'ao HUANG

This study focuses on understanding the effects of shared mobility on travel behaviours and transport energy in the university campus. Using survey data collected from college students in Ningbo, China, a substitution model was developed to identify changes in travel modes with the introduction of shared mobility on college campuses and to quantify its impact on net energy saving. Considering the average time travelled and the life cycle energy unit of the trip, the before-and-after analysis was conducted to determine the travel behaviours and related transport energy of college students in 2016 and 2019. Compared with the data of 2016 when no shared mobility was introduced, 2019 data revealed three changes in travel behaviours. First, although the total number of trips per person decreased slightly, the trip distance increased in 2019. Second, the energy for trips by each student increased by 25% from 19,809 KJ in 2016 to 24,897 KJ in 2019. Third, the overall energy efficiency of the trips decreased. In conclusion, the effect of shared mobility introduced in the university campus on reducing the transport energy of college students has not been satisfactory.

2025 (Vol 37), Issue 2

Kaliprasana MUDULI, Deorishabh SAHU, Indrajit GHOSH

This study introduces a novel, adaptable framework for identifying and prioritising road traffic accident hotspots using the Getis Ord Gi* spatial autocorrelation tool. The framework classifies regions as hotspots or coldspots based on accident severity and frequency. A unique weighting system is developed to compute the Crash Severity Index (CSI), considering the severity of crashes in terms of fatalities and injuries. The identified hotspots are prioritised using the CSI, providing policymakers with a structured approach to allocate resources for crash remedial measures. The main contribution of this work is the development of a flexible framework applicable to various cities, states or countries to improve road safety. The framework’s effectiveness is demonstrated through a case study in Punjab, India, revealing that Sangrur, Hoshiarpur and Police Commissionerate Ludhiana are the top three hotspots. The study also offers a detailed analysis of crash statistics in Punjab, emphasising the severity of pedestrian crashes. This approach addresses the current lack of structured hotspot identification and prioritization strategies, marking a significant advancement in road safety management.

2025 (Vol 37), Issue 2

Fei LU, Jian ZHANG, Erli ZHAO, Jingjie TENG

This study asserts that paired aircraft can withstand specific wake turbulence levels and explores the longitudinal collision risk in closely spaced parallel runway approaches. The goal is to enhance the safety margin of the paired approach and allow for more flexible implementation. Based on QAR data, a theoretical spacing model for paired aircraft and a probability distribution of acceleration error are established to facilitate the analysis of the actual spacing of paired aircraft. Wake turbulence attenuation is modelled using large eddy simulation, creating a vortex attenuation model. Drawing inspiration from the Hallock-Burnham vortex model, new models for induced velocity and vortex core motion are proposed. The study assumes that trailing aircraft can handle certain wake intensities, leading to a new model for calculating wake turbulence safety intervals, limiting the trailing aircraft’s maximum roll angle to its critical limit. Using probability theory, a model for longitudinal collision risk is formulated, combining wake turbulence safety separation and the actual separation of paired aircraft. The study also examines various factors influencing longitudinal collision risk, emphasising the significant impact of crosswind conditions. It concludes that a stronger crosswind component reduces the wake turbulence safety separation, thereby increasing the risk of longitudinal collisions, particularly during the final stage of the approach. Notably, collision risk is directly proportional to the crosswind component and initial longitudinal separation, but inversely proportional to runway spacing.

2025 (Vol 37), Issue 2