9 June 2021 in IEEE Access
Utilizing unmanned aerial vehicles for delivery service has been drawing attention in the logistics industry. Since commercial unmanned aerial vehicles have fundamental limitations on payloads and battery capacities, hybrid ground vehicle and unmanned aerial vehicle models have been actively investigated as practical solutions. However, these studies have focused on linehaul (delivery) demands, excluding a large number of backhaul (pickup) demands. If we consider both demands at the same time, an empty unmanned aerial vehicle that finished linehaul service can be immediately used to serve a backhaul customer. In this study, we investigate the differences that arise by considering backhauls as an additional element of the routing problem. A mixed integer linear programming model is developed, and a heuristic is constructed to solve large-scale problems. To demonstrate the effectiveness of our model, we compare it to existing models using a real-world example. Our solution is also evaluated based on experiments employing a large number of randomly generated datasets.
21 March 2022 in IEEE Access
Overcrowding in emergency departments (EDs) has long been a problem worldwide and has serious consequences for patient satisfaction and safety. Typically, overcrowding is caused by delays in the boarding time of ED patients waiting for inpatient beds. If the hospitalization of patients is predicted early enough in EDs, inpatient beds can be prepared in advance and the boarding time can be reduced. We design machine learning-based hospitalization predictive models using data on 27,747 patients and compare the experimental results. Five predictive models are designed: 1) logistic regression, 2) XGBoost, 3) NGBoost, 4) support vector machine, and 5) decision tree models. Based on the predictive results, we estimate the quantitative effects of hospitalization predictions on EDs and wards. Using the data from the ED of a general hospital in South Korea, our experiments show that the ED length of stay of a patient can be reduced by 12.3 minutes on average and the ED can reduce the total length of stay by 340,147 minutes for a year.
28 June 2022 in Transportation Letters
Innovation in logistics industry is now implicit, and the use of unmanned aerial vehicles is at the center of logistics innovation. To effectively utilize unmanned aerial vehicles for last-mile delivery, collaborative delivery using ground vehicles and unmanned aerial vehicles has recently been investigated. However, previous studies neglected proper management of batteries, assuming their constant replacement whenever unmanned aerial vehicles land, and hence numerous batteries are required for unmanned aerial vehicles. Given this research gap, we present a new routing model for collaborative delivery wherein an unmanned aerial vehicle uses a ground vehicle as a power source. A mathematical formulation is presented, and noticing the complexity, a heuristic algorithm is developed. We present a case study to verify the operational efficiency of the model. We test the performance of the heuristic and draw insights based on geographical locations of customers via computational experiments.
16 April 2024 in IEEE Transactions on Intelligent Transportation Systems
The hazardous material transportation requires extensive care owing to the disastrous consequences of accidents, such as chemical spills or radioactive exposures. Consequently, a minimum risk delivery plan that is dynamically decided by the cargo load of the vehicle at each customer must be scheduled. We introduce a traveling salesman problem (TSP) with a sequence-and-load dependent risk, which differs from the conventional TSP as the arc costs are determined by the hazardous cargo load at each decision epoch. We define our problem in a dynamic programming formulation and present mixed-integer linear program with a nonlinear objective function. To efficiently retrieve exact optimal solutions, we propose an iterative-deepening A*-based tree search algorithm using admissible lower and efficient upper bound algorithms for guaranteed optimality. Numerical experiments indicate that the proposed algorithm outperforms a current state-of-the-art solver. An ablation study and sensitivity analysis demonstrate the effectiveness of the proposed algorithm and derive managerial insights.
31 October 2025 in International Journal of Production Research