Péter Veres

Urban last-mile logistics systems must improve service responsiveness while reducing environmental impact. While micromobility-based delivery fleets offer significant emission advantages compared to conventional vans, their operational efficiency depends on adaptive, data-driven capacity allocation. We develop and analyze a real-time optimization framework that explicitly integrates sustainability considerations into zone-level fleet allocation decisions. The continuous-time backlog dynamics admit a closed-form discrete-time prediction, enabling computationally efficient rolling-horizon fleet reallocation. Sustainability is explicitly embedded through zone-specific emission factors and a multi-criteria objective function balancing backlog reduction, environmental impact, and operational stability. In a ten-zone numerical case study with a fleet of 40 vehicles, the proposed method reduced backlog in all zones within a 15-min interval while preserving strict feasibility and stability (spectral radius is less than 1). The framework also demonstrated a controllable emission–service trade-off via sensitivity analysis. These results suggest the practical applicability and real-time suitability of the proposed Industry 4.0-aligned optimization approach.

Time series forecasting performance is strongly influenced by the structural properties of the underlying data, yet learning-based models are often applied without sufficient validation of this dependency. This study evaluates a uniformly configured Long Short-Term Memory (LSTM) model on five real-world weekly time series with different levels of periodicity, noise, and volatility. Forecasting is performed in a single-step setting using a fixed sliding window of 12 weeks under a consistent training, validation, and testing framework. Model performance is assessed using mean squared error (MSE) and the coefficient of determination R². The results show that for well-structured series, both the LSTM model and Holt’s exponential smoothing achieve very low MSE values with R² scores close to one, indicating excellent predictive accuracy. For other items, performance varies across methods, with either the LSTM or Holt model providing the best results depending on the data structure. These findings confirm that high forecasting accuracy can be achieved with both advanced and classical methods, and that data characteristics play a more decisive role than model complexity.

In the field of physical logistics, efficient and precise control of material flow is regarded as a crucial aspect of modern manufacturing management. To address the challenges of limited transport capacity and variable demand, three alternative inventory and procurement strategies have been examined through Solver-based optimization. The first approach, a Reorder Point model with fixed order quantity, has been evaluated for its simplicity and responsiveness. The second, a Min–Max inventory policy, has been assessed for its adaptive replenishment and stability under uncertainty. The third, a Fixed Interval Ordering model, has been analyzed for its predictable scheduling and reduced logistics costs. Each method has been tested under identical cost structures, including purchase price, transportation, and shortage penalties. The obtained results are intended to demonstrate how optimized selection among these models can contribute to improved cost efficiency and reliability in constrained industrial supply systems.

Background: Accurate route planning is a core challenge in logistics, particularly for small- and medium-sized enterprises that lack access to costly geospatial tools. This study explores whether usable distance matrices and routing outputs can be generated solely from geographic coordinates without relying on full map-based infrastructure. Methods: A dataset of over 5000 Hungarian postal locations was used to evaluate five models: Haversine-based scaling with circuity, linear regression, second- and third-degree polynomial regressions, and a trained artificial neural network. Models were tested on the full dataset, and three example routes representing short, medium, and long distances. Both statistical accuracy and route-level performance were assessed, including a practical optimization task. Results: Statistical models maintained internal consistency, but systematically overestimated longer distances. The ANN model provided significantly better accuracy across all scales and produced routes more consistent with map-based paths. A new evaluation method was introduced to directly compare routing outputs. Conclusions: Practical route planning can be achieved without GIS services. ML-based estimators offer a cost-effective alternative, with potential for further improvement using larger datasets, additional input features, and the integration of travel time prediction. This approach bridges the gap between simplified approximations and commercial routing systems.

Artificial Intelligence continues to demand robust and adaptable training methods for neural networks, particularly in scenarios involving limited computational resources or noisy, complex data. This study presents a comparative analysis of four training algorithms, Backpropagation, Genetic Algorithm, Black-hole Algorithm, and Particle Swarm Optimization, evaluated across both classification and regression tasks. Each method was implemented from scratch in MATLAB ver. R2024a, avoiding reliance on pre-optimized libraries to isolate algorithmic behavior. Two types of datasets were used, namely a synthetic benchmark dataset and a real-world dataset preprocessed into classification and regression formats. All algorithms were tested in both basic and advanced forms using consistent network architectures and training constraints. Results indicate that while Backpropagation maintained strong performance in smooth regression settings, the Black-hole and PSO algorithms demonstrated more stable and faster initial progress in noisy or discrete classification tasks. These findings highlight the practical viability of the Black-hole Algorithm as a competitive, gradient-free alternative for neural network training, particularly in early-stage learning or hybrid optimization frameworks.

In recent years, there has been a growing demand for education in the field of intralogistics, as companies began to treat this segment as a separate area, not just as part of procurement or storage. As a result, the demand for professionals specialized in this area has increased, not only in Europe but worldwide. The University of Miskolc, in collaboration with its former partner, the Kyrgyz State Technical University, has established a dual degree program with a significant emphasis on production logistics. This article presents the origin and background of the program, the initial challenges of course launches and how they were overcome, as well as providing insights into the future of logistics education.

Research on the Sustainable Supply Chain is a significant focus within the academic community, highlighting the importance of smart logistics, smart transportation, and digital technologies. This paper reviews current research trends from 2014 to 2023 by analyzing publications from the Web of Science database. The bibliometric analysis covers publication counts, document types, top-cited papers, leading journals, main funding sponsors, and distribution by subject categories, countries, and institutions. Additionally, co-authorship and keyword co-occurrence were examined to identify key knowledge components and research clusters. The analysis underscores the need for expanded international research and continuous integration of Sustainable Supply Chain concepts for future development. The goal of the document is to provide a comprehensive review of research and industrial trends and key insights in the fields of smart logistics, smart transportation, and digital technologies in recent years.

Building an effective distribution network is a significant advantage for any company. This is especially true for easily damaged or perishable items, where the length and speed of the transport, as well as the loading time, play a major role in maintaining quality. In this article, we examined the transport/distribution options for the creation of a vaccine distribution network in Hungary, which can meet strict rules. We took into account the driver’s working hours, the maximum delivery time of the vaccine, the storage options of the county seats, and as a result we got the most efficient distribution plan of Hungary. To solve the problem, we use conventional-, greedy-, and heuristic algorithms, which were compiled by Excel and its SOLVER extension.

Cuba's economy has fluctuated strongly due to COVID-19 and natural disasters. In addition, sugar production, which is Cuba's main export product, also fell sharply. In the absence of underdeveloped industrial technologies and digitization, Cuba currently has to allocate its resources with even greater consideration. That's why utilization and optimization of sugar production and transport can take advantage of its inherent potential and reserves. After presenting the history of sugar production and its current, mainly local, technology, we present three simple methods, which do not require very professional knowledge nor expensive software or hardware to optimise these processes. We recommend the establishment of basic collection points, which would operate as specific logistics centres, with the role of service provision and pre-production in addition to the collection. Also, the paper proposes a method that can be used to design layouts in 3D, making the current sugar production process more compact and efficient.