The vehicle routing problem with time windows (VRPTW) is a core challenge in logistics optimization, requiring the minimization of transportation costs under constraints such as time windows and vehicle capacity. Deep reinforcement learning (DRL) provides an effective approach for solving such complex combinatorial optimization problems. However, existing DRL methods still suffer from shortcomings, including insufficient modeling of spatiotemporal correlations among customer nodes, inadequate capture of path temporal dependencies, and policy exploration prone to local optima. To address these issues, this paper proposes an end-to-end hybrid DRL framework: the encoder employs a graph attention network (GATv2) with adaptive gating to effectively model the coupling between customer spatial proximity and time window constraints; the decoder integrates multi-head attention (MHA) and a dynamic context-aware long short-term memory network (LSTM) to synergistically enhance the overall quality and constraint feasibility of route solutions; during the training phase, an improved proximal policy optimization (PPO) algorithm and a constraint-aware composite reward function are used to enhance optimization stability. Experiments on random instances, Solomon benchmark datasets, and real-world logistics datasets show that, compared to mainstream DRL methods and classical heuristic algorithms, the proposed framework reduces transportation costs by 2–10%, achieves a demand fulfillment rate exceeding 99%, and exhibits a performance degradation of only 3.2% in cross-distribution testing. This study provides an integrated DRL solution paradigm for combinatorial optimization problems with complex constraints, promoting the application of DRL in the field of intelligent logistics.

This article investigates the role of the marketing distribution mechanism in Ukraine’s agricultural sector as a critical driver of post-war economic recovery. The study addresses the urgent need to modernize distribution systems in the context of ongoing military conflict and future reconstruction efforts. The research examines the conceptual foundations of marketing distribution mechanisms specifically adapted to agricultural enterprises operating under martial law conditions, analyzing how these mechanisms can be optimized to support both immediate operational needs and long-term strategic development.The methodology of this research combines systematic analysis, comparative methods, and strategic forecasting to evaluate the effectiveness of current distribution channels and identify opportunities for improvement. The study draws on empirical data regarding the impact of the full-scale Russian invasion on agricultural production and supply chains, examining both quantitative indicators of disruption and qualitative assessments of adaptive responses by agricultural enterprises. Particular attention is devoted to analyzing alternative export routes, including land corridors through European Union countries and river transportation via the Danube, which have partially compensated for the blockade of Black Sea ports.The research findings demonstrate that effective marketing distribution mechanisms serve as critical tools for maintaining agricultural production stability and ensuring food security during crisis periods. The study reveals that despite unprecedented challenges, Ukraine’s agricultural sector has shown remarkable resilience through the development of innovative distribution solutions. Key innovations include the establishment of new logistics partnerships, implementation of digital technologies for supply chain management, and diversification of market channels. The article emphasizes the strategic importance of integrating risk management principles into distribution planning, drawing on contemporary research in agricultural risk mitigation and adaptive management strategies.The practical value of this research lies in providing agricultural enterprises with actionable recommendations for adapting their distribution strategies to post-war recovery conditions. These recommendations include diversifying export destinations, strengthening domestic market channels, investing in digital infrastructure for logistics optimization, and developing flexible distribution models capable of rapid adjustment to changing circumstances. The study concludes that a modernized marketing distribution mechanism, incorporating technological innovation and strategic flexibility, will be instrumental in positioning Ukraine’s agricultural sector as a key driver of national economic recovery and a reliable partner in global food security.

Rural freight mobility and logistics face persistent challenges, including inadequate road infrastructure, high transportation costs, safety risks, tolls at link access points, and dispersed demand. Traditional inventory routing models often fail to address these complexities, especially in rural contexts where alternative routing options and integrated in-haul/back-haul operations are essential for improving efficiency and reducing empty miles. This study proposes a bi-objective mathematical model for the inventory routing problem in rural logistics, incorporating multiple routing attributes (transportation costs, risks, link-access tolls, and distances) and inventory dynamics (integrated in-haul and back-haul visits). The model aims to minimize total logistics costs and accident risk while balancing operational expenses and safety considerations. Risk estimation is derived from crash data along rural road links connecting distribution nodes. A real-world case study involving Walmart distribution centers in Macclenny, Baker County, Florida, and several rural Supercenters is conducted to validate the model. A modified Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is developed and compared with CPLEX for solution efficiency across small and large-scale problem instances. Results indicate that the proposed approach outperforms classical methods, improves routing decisions in rural logistics systems, and achieves cost savings of up to 17% for the evaluated objectives, emphasizing the importance of using multi-attribute, multi-route network structures in rural logistics optimization.

Abstract This study aimed to present spatial planning for the selection of alternative sites in terms of carbon footprint based on waste transport in the installation of facilities that will produce low-carbon solutions for industrial waste. Designed to point out the importance of symbiotic solutions that encourage circular economy practices, the approach offers a novel solution for both reducing global carbon emissions and determining optimal facility locations. A three-stage GIS-based FAHP (Fuzzy Analytic Hierarchy Process) workflow was developed for selecting proper site for a particular industrial symbiosis facility in Türkiye, using Marble Processing Wastewater sludge (MPW) and plastic wastes (PP/PET) as representative materials. In Stage 1, provinces were screened according to their waste potential. Stage 2 involved the development of a 10-factor suitability (spatial index) map, identifying six candidate sites which were compared in Stage 3 based on transport-related CO 2 emissions using Tier-1 factors and ArcGIS Network Analyst routing. The implementation of the proposed method in Stage 3 resulted in ranking the candidate sites, and 56.4% less carbon footprint was determined between the candidate site with highest and the lowest calculated carbon footprint (0.106: GgCO 2 ). Therefore, in site selection works appending the third stage to the GIS-FAHP methodology was suggested as useful approach that enables logistical optimization, thereby reducing not only environmental impacts but also transportation costs. The proposed methodology supports effective waste management, minimizes the environmental–financial burdens of transportation, and promotes sustainable spatial planning in both urban and rural areas. Graphical abstract

ABSTRACT The adoption of Artificial Intelligence (AI) in the meat industry signifies a transformative shift toward intelligent, secure, and sustainable food production systems. This review paper explores how AI is enhancing operations across the entire meat supply chain—including processing, quality assessment, spoilage identification, regulatory compliance, and logistics optimization. Conventional methods, often limited by human bias, workforce shortages, and inefficiencies, are being replaced by AI‐powered solutions such as machine learning, computer vision, hyperspectral imaging, smart sensors, and edge computing, enabling real‐time, non‐invasive, and data‐centric decision‐making. Beyond process automation, AI facilitates predictive safety controls, smart packaging technologies, and customized consumer engagement. Applications like robotic meat processing, cloud‐based traceability platforms, and smartphone‐integrated spoilage sensors highlight AI's contribution to precision meat processing. In addition, AI promotes clean‐label formulation, operational energy savings, and automated hygiene management via intelligent Cleaning‐in‐Place (CIP) systems. Global implementations—ranging from carcass grading systems in Australia and blockchain traceability in Europe to biosensor deployment in Asian markets—demonstrate the adaptability and impact of AI‐based solutions. Although barriers such as high implementation costs, lack of algorithmic transparency, and regulatory conservatism remain, the integration of AI with the Internet of Things (IoT), blockchain technology, and explainable AI (XAI) offers a promising pathway. This technological convergence is set to enhance food safety, boost consumer confidence, expand export potential, and redefine industrial competitiveness in the evolving post‐pandemic marketplace.

Data-driven optimization for maritime logistics: integrating transport network mining with ship fleet routing

ResSqueezeXNet: A Lightweight Deep Learning Framework for Real-Time Agricultural Logistics Optimization in IoT Environments

Abstract The frequency and severity of disasters are increasing, and promoting the adoption of digital technologies could enhance the agility, reach, and resilience of humanitarian supply chains. Global patterns of digital innovation in humanitarian supply chains are examined through a systematic quantitative literature review and bibliometric analysis of 4,780 Scopus-indexed documents (2015–2025). Combined with targeted qualitative syntheses, co-word analysis, co-citation mapping, and bibliographic coupling, the analysis reveals digitalisation as an expanding technology-led field, dominated by response-phase applications. Dominant clusters centre on: artificial intelligence-driven forecasting, emerging logistics optimisation, last-mile operations, and data analytics platforms. We interpreted these patterns through the Technology–Organisation–Environment model. It is found that digital technologies are necessary and applicable throughout disaster management phases. A conceptual framework reconfigures Technology–Organisation–Environment domains reflecting the context-driven dynamics of humanitarian supply chains, emphasising resilience. Future research should focus on longitudinal, co-designed case and action research into digital adoption, integration challenges, and community-based knowledge in fostering innovation.

Purpose Despite extensive research on Internet of Things (IoT) applications in the construction industry, there remains a critical gap in understanding its systematic implementation and effectiveness, specifically within construction supply chain management (CSCM). This study aims to provide a systematic review of IoT applications in CSCM, highlighting their current applications, associated challenges and emerging integration pathways. Design/methodology/approach A PRISMA-based systematic literature review was conducted, drawing on 28 peer-reviewed journal articles and conference papers from Scopus and Web of Science for bibliometric and qualitative content analysis. Findings The review shows that IoT has moved from isolated tracking solutions (e.g. Radio Frequency Identification-based logistics) to integrated ecosystems that combine Building Information Modelling, blockchain and digital twins to enhance visibility, traceability and coordination. Applications span areas such as real-time tracking, logistics optimisation, risk management, sustainability reporting and automated financial trust mechanisms (e.g. IoT-enabled smart contracts). However, widespread adoption is constrained by technical limitations, data governance issues, trust and cybersecurity concerns, organisational inertia and uncertain return on investment (ROI). The findings of this study highlight that IoT’s transformative value lies in its integration with complementary digital technologies, creating interoperable, governance-driven systems that improve collaboration, resilience and sustainability. Originality/value This study consolidates fragmented knowledge on IoT in CSCM, offering a structured synthesis of the construction supply chain’s current landscape. This review contributes a foundational roadmap for researchers and practical guidance for industry stakeholders seeking to leverage IoT for enhanced transparency, efficiency and sustainability in construction supply chains.

Storks’ migration route planning capabilities have long been a focus of attention as a natural phenomenon. This study aims to examine these capabilities and provide a new perspective to the logistics sector. Inspired by the migration behavior of storks, the study presents a new logistics optimization model. The model is designed based on stork migration route planning strategies by combining nature-inspired approaches. By simulating the natural behavior of storks, the model aims to achieve basic logistics goals such as energy saving, cost reduction and effective time management. The stork-inspired logistics model is expected to provide significant advantages in logistics operations. It has the potential to increase energy efficiency, reduce costs, and improve operational efficiency in route planning. In addition, the model takes into account other important factors such as environmental sustainability and social impact. Although further research is needed to evaluate the real-world applicability and effectiveness of this model in logistics operations, it is clear that this approach provides several potential benefits to the sector. Future studies should focus on adapting the model to large-scale enterprises.

In the current e-commerce domain, rising customer demands for diversity, responsiveness, and service quality create major challenges in inventory management and logistics optimisation. To address these, this paper introduces the multi-period and multi-product inventory routeing problem with procurement decisions (MIRP-PD) in self-operated e-commerce, supported by a generative AI and discriminative AI–based forecasting method. The goal is to optimise (i) procurement from geographically dispersed suppliers, (ii) transportation to a central warehouse, and (iii) product pickup from suppliers to the warehouse. Based on AI-generated forecasts, an integer programming model for MIRP-PD is developed. To solve medium- and large-scale problems, a hybrid bi-level heuristic is proposed, combining genetic algorithms (GA) for procurement planning and ant colony optimisation (ACO) for routeing, enhanced by a Lagrangian constraint–based repair operator. A rolling-horizon framework is further applied to mitigate forecast errors. A real-life case study with 15 scenarios demonstrates that the proposed GA–ACO achieves superior performance compared with Gurobi and a GA-only baseline. Comparative execution tests confirm that AI-based forecasting substantially reduces excess holding, transportation, and stockout costs. Sensitivity analyses provide managerial insights into transport strategies, warehousing–transport trade-offs, and service-level penalties, highlighting the role of generative and discriminative AI in enabling robust replenishment decisions.

The study aims to explore the intersection of Operations Research (OR), Artificial Intelligence (AI), and simulation by examining how classical OR methodologies strengthen AI models, particularly in machine learning, robotics, natural language processing, and autonomous systems. It further investigates the critical role of simulation in training, testing, and validating AI algorithms, emphasizing its relevance for optimization, intelligent decision-making, and real-world system modelling. The study adopts a comprehensive analytical and literature-based methodology, reviewing foundational OR techniques, simulation principles, and modern AI applications. It synthesizes interdisciplinary research across mathematics, computer science, and engineering, supported by case analyses in robotics, healthcare, transportation, and autonomous systems. Additionally, a demonstration algorithm is developed to simulate automatic gear-control behavior in vehicles, illustrating how simulation models practically support AI-oriented operational decision-making. Findings reveal that OR optimization techniques significantly enhance AI efficiency, particularly in parameter tuning, resource allocation, and adaptive decision-making. Simulation is shown to be indispensable for AI training, offering controlled, safe, scalable, and cost-effective environments. The study identifies persistent challenges—including the reality gap, computational demands, and model bias—yet confirms that simulation and OR jointly accelerate AI development and broaden its practical reliability. The integrated OR–AI–simulation framework is applicable to numerous fields, including autonomous vehicle navigation, robotic motion planning, intelligent healthcare systems, logistics optimization, and smart city management. Industries benefit from improved forecasting, reduced operational costs, enhanced safety, and high-fidelity algorithm testing. Simulated environments also support reinforcement learning, surgical training, autonomous decision-making, and large-scale scenario evaluation, contributing to more efficient and intelligent real-world systems. The study’s novelty lies in its unified perspective that connects classical OR optimization principles with AI advancements through simulation-based experimentation. It uniquely synthesizes concepts from mathematics, computer science, and AI to highlight simulation as a bridge enabling intelligent automation. The inclusion of a practical simulation algorithm for automatic vehicle gear control further demonstrates how OR-driven simulation can concretely operationalize AI-based decision systems. Operations Research (OR) and Artificial Intelligence (AI) have both independently evolved as transformative fields which have shown impact on decision-making and problem-solving across diverse domains. While Operations Research makes available a foundation of mathematical modeling and optimization techniques, Artificial Intelligence sets up intelligence through learning, reasoning, and data-driven methods. This seminar paper presented by us explores how Operations Research gets involved in the development and enhancement of Artificial Intelligence (AI) systems. We, in this paper, have tried to discuss Key applications and case studies to highlight the synergies between these fields, remarkably in optimization, logistics, resource allocation, and automated decision-making. Simulation, an approach of Operations Research, has become a cornerstone in the field of Artificial Intelligence (AI), suggesting an experimental platform for testing hypotheses, training algorithms, and evaluating systems in controlled, cost-effective, and scalable environments. Our paper explores the central role simulations play in advancing Artificial Intelligence (AI) research and applications, with a focus on their integration in machine learning, robotics, and decision-making systems.

Environmental impact and economic performance analysis of two faecal sludge treatment plants in Beijing: A life cycle perspective.

Relevance. The article explores the potential applications of artificial intelligence technologies in managing the export activities of pharmaceutical companies. It examines the key directions of the digital transformation of the industry, including the use of machine learning algorithms, natural language processing, intelligent analytics, and predictive monitoring within the Pharma 4.0 framework. The aim of this study was to examine the using artificial intelligence to improve the management of pharmaceutical exports and to develop an objective system for assessing the export readiness of pharmaceutical companies. Material and methods. Special attention is given to the formation of integrated intelligent ecosystems that establish interconnections between the levels of Technological Readiness (TRL), Manufacturing Readiness (MRL), and Export Readiness (ERL) of enterprises. The development of the ERL concept has become one of the essential steps toward creating a universal system for measuring the maturity of export-oriented pharmaceutical companies. However, the practical implementation of this methodology requires tools capable of continuously collecting, processing, and interpreting data from various sources – from manufacturing and regulatory to financial and logistics. At this stage, artificial intelligence becomes a central element, transforming ERL assessment from a static audit into a dynamic monitoring process. Results. The introduction of AI-driven systems enables the transition from descriptive management models to predictive and prescriptive strategies, based on data analysis from corporate information systems and external regulatory databases. Conclusion. The article presents practical examples of AI applications for regulatory analytics automation, prediction of manufacturing deviations, optimization of pharmaceutical logistics, and assessment of reputational risks using open-source data. Particular emphasis is placed on data interoperability and standardization, which form the foundation for harmonizing national and international readiness assessment systems. The study demonstrates that artificial intelligence is becoming an integral component of the pharmaceutical export management system, enhancing the transparency, resilience, and global competitiveness of the Russian pharmaceutical industry.

This study investigates the optimization of reverse logistics in manufacturing enterprises, emphasizing its role as an essential component of modern supply chain management and a strategic instrument for sustainable development. The paper first reviews and systematizes the theoretical foundations of reverse logistics, clarifying its concepts, characteristics, and scope of application, as well as its linkages with supply chain management and the circular economy. On this basis, an analytical framework is developed to evaluate the level of reverse logistics implementation in manufacturing firms in Vietnam, with a focus on product return management, reverse material flow handling, internal coordination mechanisms, and the integration of environmental objectives into production and business strategies. The analysis of empirical evidence highlights several key challenges in the adoption of reverse logistics, including limitations in managerial capabilities, infrastructure, financial and technological resources, and insufficient awareness of the long-term economic and environmental benefits. In response, the study proposes a set of comprehensive and feasible solutions aimed at improving internal governance, enhancing coordination across supply chain stages, and promoting the adoption of management models consistent with circular economy principles. These measures are expected to improve operational efficiency, reduce environmental impacts, and strengthen the competitive position of manufacturing enterprises in the context of economic integration and increasing sustainability requirements.

The implementation of the Goods and Services Tax (GST) in India on July 1, 2017, marked a transformational shift in the nation's indirect taxation system, fundamentally altering the operational landscape for the Fast-Moving Consumer Goods (FMCG) sector. This research examines stakeholder perceptions of GST implementation in Rajasthan's FMCG sector, with particular emphasis on the strategic implications of GST 2.0 reforms announced in 2025. Through a comprehensive analysis of recent empirical studies and policy developments, this paper evaluates the multi-dimensional impact of GST on manufacturers, distributors, retailers, and consumers within Rajasthan's FMCG ecosystem. The study reveals that stakeholder confidence has significantly increased from 59% in 2022 to 85% in 2025 (Deloitte India, 2025; Chaudhri&Jaising, 2025), reflecting growing acceptance of the GST regime despite persistent challenges in compliance, logistics optimization, and price rationalization. The GST 2.0 reforms, particularly the simplification to a two-slab structure (5% and 18%), represent a critical evolution that addresses many stakeholder concerns while introducing new strategic considerations for FMCG businesses operating in Rajasthan and across India (Kotak Mahindra Asset Management, 2025).

This article examines key aspects of the digital transformation of Russian industrial enterprises under sanctions pressure. Based on real-world cases, it analyzes effective solutions in the areas of quality management automation, logistics optimization, cybersecurity, and occupational safety. Particular attention is paid to import substitution of digital platforms and the integration of IoT (Internet of Things) and artificial intelligence (AI) into production processes. This article will be useful for industrial managers, CIOs, and digitalization specialists facing the need to modernize production in an environment with limited access to foreign technologies.

The arrival of drone technology has completely changed various industries, with delivery services by known as a prominent application. The design and development of delivery drone involves a more than one field of study approach integrating aerodynamics, electronics, and logistics optimization. This paper mainly focused on creating an efficient and robust delivery drone mechanism which is tailored to urban and rural environments. The major problems addressed includes energy efficiency, regulatory compliance, and weather adaptability. To get better of these, the study incorporates modular designs for adaptability, renewable energy solutions and compliance with aviation safety standards. Extensive testing in simulated and real-world conditions validates the system's scalability and reliability. This mechanism has transformative potential, enabling faster, cost effective and environmentally friendly delivery solutions. It bridges logistical gaps particularly in remote areas, and sets the foundation for future innovations in autonomous aerial systems. The delivery drone system presented in this project offers a futuristic solution for logistics and delivery services. By utilizing autonomous flight, advanced navigation, and secure package handling, the drone enables rapid, efficient, and reliable delivery of packages, paving the way for a new era in logistics.  <div> We propose a cutting-edge Autonomous Delivery Drone system, featuring a unique combination of automation, security, and convenience. The system incorporates a vending machine mechanism, secure collecting box, and winch mechanism, ensuring rapid and reliable delivery of packages, while a mobile app provides customers with a seamless ordering and tracking experience. This project develops an Autonomous Multi-Order Delivery Drone system, leveraging advanced technologies to transform the delivery industry. The system integrates automation, robotics, and IoT, enabling efficient, secure, and reliable delivery of multiple orders, while providing customers with real-time tracking and updates through a dedicated mobile app. </div>

Abstract Assembly is one of the key phases of the production process, as it significantly affects productivity and the smoothness of logistics flows. Eliminating logistical and process-related waste therefore represents one of the most effective approaches for improving the performance of assembly systems while simultaneously supporting the smooth flow of materials throughout the entire organization. The paper focuses on the optimization of the intra-company logistics of an assembly line for the production of automatic elevator doors using a discrete simulation method. The digital model of the line was created in the Tecnomatix Plant Simulation environment based on real data on operation times, work distribution and material flows in a system without inter-operational bins. The simulation analysis identified the main bottlenecks caused by uneven worker workload and long cycle times of selected operations. Several improvement options were designed and verified using the trial-and-error method. A significant increase in productivity was achieved by introducing a new workstation and redistributing activities among workers, which increased production from 72 to 81 pieces per shift.

Global logistics networks face increasing volatility driven by geopolitical tensions, climate disruptions, demand variability, and operational uncertainty. Although artificial intelligence has improved predictive capabilities in logistics, classical and standalone learning models remain limited by data sparsity, non-stationarity, and scalability constraints. This study proposes a hybrid logistics intelligence framework that integrates time-series forecasting, synthetic data generation, and AI-based optimization. The framework is designed to enhance forecasting robustness and translate predictions into actionable operational decisions. A FedEx case study demonstrates how historical shipment data, real-time telemetry, and synthetically generated disruption scenarios can be jointly leveraged to improve demand forecasting, routing efficiency, and service reliability. Performance is evaluated across real, simulated, and hybrid datasets. Results show that the proposed approach consistently outperforms traditional statistical and machine-learning methods in accuracy, robustness, and operational scalability.