Decision Science and Intelligent Systems

The logistics management of strategic petroleum products is essential for providing timely and appropriate services. Accordingly, the present study aimed to present a dynamic capabilities-based model of petroleum products logistics management using a qualitative–quantitative approach. The research method was multiple content analysis (deductive and inductive) in the qualitative section and causal in the quantitative section. The statistical population of the study consisted of participants including managers and senior experts in the logistics sector of the National Iranian Oil Products Distribution Company, among whom 21 individuals were selected through purposive non-probability sampling. Data were collected through semi-structured interviews in the qualitative section and a questionnaire in the quantitative section. The qualitative findings showed that the model consists of four dimensions: “strategic capability,” “organizational integration capability,” “infrastructure and technology capability,” and “service operational capability.” These dimensions were confirmed using the fuzzy Delphi method. The causal relationship findings obtained through fuzzy DEMATEL indicated that “strategic capability,” “infrastructure and technology capability,” and “organizational integration capability” are causal factors, while “service operational capability” is an effect factor and receives the greatest influence. The components of “transportation management,” “service organization,” “order management,” “data and information management,” and “advanced technology” had the highest weight and importance. These findings highlight the importance of collaborative transportation scheduling and planning, procurement planning, and timely responsiveness to customer requests, indicating that managers can achieve superior logistics objectives by focusing on capabilities, facilities, and technological infrastructures.

Managing the risks associated with smart technologies in Industry 4.0 within the circular supply chain is important for preventing organizational failure. This study aimed to identify the cause-and-effect relationships among circular supply chain risks in the context of Industry 4.0 in the petrochemical industry using the Total Interpretive Structural Modeling method. The qualitative findings, obtained through content analysis based on a systematic review of the theoretical literature and semi-structured interviews with 18 experts, including senior and middle managers of petrochemical companies, researchers, and university professors, showed that the risks included “organizational risk,” “employee risk,” “technological infrastructure risk,” “circular framework risk,” “financial and economic risk,” “policy and regulatory risk,” and “operations and supply risk.” The causal findings of Total Interpretive Structural Modeling in the quantitative phase indicated that “policy and regulatory risk” was the most influential factor and the main driver of other risks, affecting “organizational risk.” “Financial and economic risk” and “technological infrastructure risk” played mediating roles in the model and had a fundamental role in system complexity. “Circular framework risk,” “employee risk,” and “supply and operations risk” were respectively the most dependent risks and influenced system performance. The results indicate that the lack of governmental support is highly important and influential in creating legal and regulatory risks and disruptions. On the other hand, as supply and operations risk increases, the supply chain shifts from a closed-loop state back to a linear state.

This research presents a novel hybrid methodology for designing cellular layouts in mass customization systems. The proposed method requires only production routing information and consists of three components: (1) Gower's similarity coefficient for mixed-type data, (2) gravity-based clustering for initial cell formation, and (3) a Chaotic K-best Gravitational Search Algorithm (CKGSA) for final layout optimization. A hypothetical example with several products and machines was considered for validation. Results showed that Gower's coefficient successfully identified main machine clusters. The CKGSA significantly improved the fitness function, achieving zero inter-cell movement and considerably increasing intra-cell similarity. A systematic literature review confirmed that the combination of Gower's coefficient, gravity approach, and chaotic gravitational search is unique in the literature. The main novelty lies at three levels: first application of Gower's coefficient in cellular layout problems, development of gravity-based clustering for virtual coordinate assignment, and presentation of an improved chaotic version of the gravitational search algorithm. By significantly reducing data requirements, the proposed method enables small and medium enterprises to implement cellular manufacturing systems quickly and cost-effectively.

Supply chain management in manufacturing industries, particularly the construction industry and its related products, such as uPVC windows, faces numerous challenges. Owing to market dynamics and the qualitative nature of the relevant variables, these challenges are often characterized by ambiguity and uncertainty. This study aimed to identify, screen, and prioritize the key challenges and problems associated with supply chain management in the uPVC window industry. For this purpose, following a comprehensive review of the research literature and consultation with industry experts, the identified challenges were classified into six overarching evaluation criteria. In the first stage, the main criteria were weighted using the fuzzy Step-wise Weight Assessment Ratio Analysis (SWARA) method. Subsequently, the 20 identified challenges were ranked using the fuzzy Weighted Aggregated Sum Product Assessment (WASPAS) method. The findings indicate that, among the evaluation criteria, “resistance to change and adaptation to innovation” has the highest level of importance. Furthermore, according to the results of the fuzzy WASPAS model, “lack of market demand” was identified as the most important and critical challenge facing the uPVC window supply chain. The results of this study can assist managers and decision-makers in this industry in optimizing resource allocation and mitigating operational risks.

In today’s highly competitive business environment, integrating smart transformation objectives—such as the adoption of the Internet of Things and artificial intelligence—with environmental, social, and economic sustainability goals is essential for achieving sustainable competitive advantage. The literature indicates that previous studies have often examined these dimensions separately or have exhibited considerable methodological gaps in addressing uncertainty and prioritizing strategies. Against this background, the present study aims to identify and evaluate key strategies for transitioning toward a smart and sustainable supply chain in the home appliance industry. Using fuzzy–stochastic multi-criteria decision-making methods, the study identifies and assesses a set of influential strategies and criteria. First, the principal criteria associated with the research problem were weighted using the fuzzy–stochastic Best–Worst Method. Subsequently, the identified strategies were ranked under different uncertainty scenarios—pessimistic, most likely, and optimistic—using the fuzzy–stochastic Complex Proportional Assessment method. The required data were collected through a survey of five groups of experts with relevant expertise in the field under investigation. The study was conducted as a case study in the home appliance industry. The findings indicate that flexibility, operational feasibility, investment cost, safety, scalability, and global warming were identified as the most important criteria. Furthermore, the results showed that smart circular economy and the application of advanced technologies in production processes were the highest-ranked strategies. These findings provide valuable managerial insights that can assist managers in allocating resources more effectively and making more informed strategic decisions to achieve smart transformation and sustainability objectives.

Community detection is a fundamental problem in the analysis of complex and social networks. It aims to identify groups of nodes whose internal connections are denser than their connections with other parts of the network. The primary challenges in this field are the unknown number of communities and the large number of nodes in real-world networks. This study proposes a novel multistage approach that combines the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm with the Reptile Search Algorithm (RSA). In the first stage, the network is initially clustered using DBSCAN and features extracted from the nodes, particularly their neighbor lists. In the second stage, RSA identifies the final communities through three phases: initialization, exploration, and exploitation. The objective function is defined based on two criteria: modularity (Q) and conductance (Cond). The proposed method was evaluated in MATLAB using eight real-world datasets: ca-GrQc, ca-HepPh, ca-HepTh, ca-AstroPh, ca-CondMat, Zachary’s Karate Club network, the American college football network, and the dolphin social network. The experimental results demonstrate that the proposed method outperforms existing methods in most cases, achieving higher values for normalized mutual information (NMI) and modularity (Q).

In this paper, we consider non-parametric production technologies with multiple component production processes, where each component uses both specific and shared inputs to produce specific and shared outputs. Investigating the issue of target setting within these technologies, we show that how efficient benchmarks for in-efficient units within the multi-component production technologies can be obtained by using basic envelopment and multiplier Data Envelopment Analysis models. Furthermore, we formulate efficient frontier of multi-component technology and develop a mixed integer optimization model that obtains closest targets for each in-efficient activity. The proposed models are finally illustrated on a real data set consisting 102 public universities in the UK.  

Software testing plays a critical role in maintaining the dependability and overall quality of software applications. Nevertheless, it often demands significant time and computational resources, especially in unit testing environments. With the continuous expansion of test suites, running every available test case is no longer a practical strategy. Test Case Prioritization (TCP) addresses this challenge by arranging test cases in an order that increases the likelihood of detecting faults earlier while minimizing testing effort and cost. Conventional TCP techniques are often limited in their ability to adapt to the fast-paced nature of current software development practices. To overcome these shortcomings, this research explores the application of machine learning (ML) methods within the TCP framework to improve prioritization effectiveness. In contrast to fixed or rule-based techniques, ML-based approaches can learn patterns from historical test data and make adaptive prioritization decisions. For this purpose, a dataset was generated using several metaheuristic methods, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), and a hybrid GWO model, implemented on the triangle classification benchmark problem. The collected test cases were categorized into five classes according to coverage criteria and then prepared for model training. Four supervised ML classifiers were developed and assessed using stratified 10-fold cross-validation. Their performance was evaluated based on widely used metrics, including accuracy, precision, recall, F1-score, and AUC. Experimental findings showed that the proposed approach reached an accuracy of 97.31% and an F1-score of 92.94%, surpassing traditional TCP methods. These findings indicate that integrating ML into TCP can improve early fault discovery, decrease unnecessary test executions, and offer an automated and scalable approach for more effective unit testing.