Using k-means clustering in international location decision

Many objective optimization and decision support for dairy cattle feed formulation

Livestock feed formulation has significant impacts on livestock production and the environment. Linear and nonlinear constraints, framed as nutritional requirements and specific objectives, present a continuous challenge in achieving optimal feed formulation. Many mathematical models, including linear programming, have been adopted to tackle this issue. However, this approach is often excessively restrictive, primarily focusing on cost minimization and overlooking variability in nutrient content and fulfillment of other objectives. Conventional feed formulation approaches, characterized by their limited operational scope and inadequacy for a robust decision-making process, present challenges to growers aiming to achieve objectives beyond cost minimization. This study proposes a many-objective optimization approach to solving the feed formulation problem and addressing this challenge. The framework optimizes nine objectives, including minimizing cost, weight and the number of feed components, and five nutritional constraints. By integrating feed nutritional constraints and objectives into a comprehensive framework, we aim to introduce flexibility and enhance decision-making. The proposed framework successfully balances the nine objectives, providing growers with a potentially adaptable and tailored solutions. Growers can achieve trade-offs across various objectives, enabling informed decision-making to optimize feed formulation, enhance livestock productivity, and promote environmental sustainability. Furthermore, visualization tools were utilized to improve the interpretability of the generated solutions. The results obtained demonstrate acceptable compromise across various objectives.

Enhancing home delivery of emergency medicine and medical supplies through clustering and simulation techniques: A case study of COVID-19 home isolation in Bangkok

This study investigates the enhancement of the home delivery distribution network for COVID-19 Home Isolation (HI) kits during the Delta variant outbreak of the SARS-CoV-2 virus in Bangkok Metropolitan Area, Thailand. It addresses challenges related to limited resources and delays in delivering HI kits, which can exacerbate symptoms and increase mortality rates. A k-means clustering approach is utilized to optimize the assignment of service areas within the COVID-19 HI program, while discrete event simulation (DES) evaluates potential changes in the home delivery logistics network. Real-world data from the peak outbreak is used to determine the optimal allocation of resources and propose a new logistics network based on proximity to patients' residences. Experimental results demonstrate a significant 44.29 % improvement in overall performance and a substantial 40.80 % decrease in maximum service time. The findings offer theoretical and managerial implications for effective HI management, supporting practitioners and policymakers in mitigating the impact of future outbreaks.

A systematic review of machine learning in logistics and supply chain management: current trends and future directions

Purpose

This paper presents a review of the existing state-of-the-art literature on machine learning (ML) in logistics and supply chain management (LSCM) by analyzing the current literature, contemporary concepts, data and gaps and suggesting potential topics for future research.

Design/methodology/approach

A systematic/structured literature review in the subject discipline and a bibliometric analysis were organized. Information regarding industry involvement, geographic location, research design and methods, data analysis techniques, university, affiliation, publishers, authors, year of publications is documented. A wide collection of eight databases from 1994 to 2019 were explored using the keywords “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract. A total of 110 articles were found, and information on a chain of variables was gathered.

Findings

Over the last few decades, the application of emerging technologies has attracted significant interest all around the world. Analysis of the collected data shows that only nine literature reviews have been published in this area. Further, key findings show that 53.8 per cent of publications were closely clustered on transportation and manufacturing industries and 54.7 per cent were centred on mathematical models and simulations. Neural network is applied in 22 papers as their exclusive algorithms. Finally, the main focuses of the current literature are on prediction and optimization, where detection is contributed by only seven articles.

Research limitations/implications

This review is limited to examining only academic sources available from Scopus, Elsevier, Web of Science, Emerald, JSTOR, SAGE, Springer, Taylor and Francis and Wiley which contain the words “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract.

Originality/value

This paper provides a systematic insight into research trends in ML in both logistics and the supply chain.