Abstract

Abstract
This paper presents a game-simulated environment that mimics real-world conditions, with a focus on autonomous vehicle navigation. Despite significant advances in the field of games and simulations, there are still a number of challenges to overcome, in particular, the ability to accurately transfer what has been learned in virtual environments to the real world. This project recreates an agent (a motorcycle), modeled with complex physics, navigating autonomously on a detailed map based on the urban geography of Vila Real, Portugal, recreated from real data, implemented in the Unity game engine. In this paper, we provide a detailed overview of the environment and agent creation processes, highlighting the integration of realistic road networks, obstacles, and interaction mechanics that enhance the fidelity of the simulation. The experimental phase demonstrates the motorcycle’s ability to navigate efficiently, adapting to road layouts, avoiding obstacles, and adjusting to dynamic conditions. The insights from this study can be applied and transferred to real-world application scenarios, particularly in optimizing route planning and driving behaviour for electric motorcycles. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Time series forecasting is an important tool for planning and decision-making. Considering this, several forecasting algorithms can be used, with results depending on the characteristics of the time series. The recommendation of the most suitable algorithm is a frequent concern. Metalearning has been successfully used to recommend the best algorithm for a time series analysis task. Additionally, it has been shown that decomposition methods can lead to better results. Based on previously published studies, in the experiments carried out, time series components were used. This work proposes and empirically evaluates METAFORE, a new time series forecasting approach that uses seasonal trend decomposition with Loess and metalearning to recommend suitable algorithms for time series forecasting combinations. Experimental results show that METAFORE can obtain a better predictive performance than single models with statistical significance. In the experiments, METAFORE also outperformed models widely used in the state-of-the-art, such as the long short-term memory neural network architectures, in more than 70%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$70\%$$\end{document} of the time series tested. Finally, the results show that the joint use of metalearning and time series decomposition provides a competitive approach to time series forecasting.

Abstract
In the study, a new method for analyzing Electrocardiogram (ECG) signals is suggested, which is vital for detecting and treating heart diseases. The technique focuses on improving ECG signal classification, particularly in identifying different heart conditions like arrhythmias and myocardial infarctions. An enhanced version of the differential evolution (DE) algorithm integrated with neural networks is leveraged to classify these signals effectively. The process starts with preprocessing and extracting key features from ECG signals. These features are then processed by a multi-layer perceptron (MLP), a common neural network for ECG analysis. However, traditional MLP training methods have limitations, such as getting trapped in suboptimal solutions. To overcome this, an advanced DE algorithm is used, incorporating a partition-based strategy, opposition-based learning, and local search mechanisms. This improved DE algorithm optimizes the MLP by fine-tuning its weights and biases, using them as starting points for further refinement by the Gradient Descent with Momentum (GDM) local search algorithm. Extensive experiments demonstrate that this novel training approach yields better results than the traditional method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
This paper compares the performance of Simulated Annealing and Tabu Search meta-heuristics in addressing a parallel machine scheduling problem aimed at minimizing weighted earliness, tardiness, total flowtime, and machine deterioration costs-a multi-objective optimization problem. The problem is transformed into a single-objective problem using weighting and weighting relative distance methods. Four scenarios, varying in the number of jobs and machines, are created to evaluate these metaheuristics. Computational experiments indicate that Simulated Annealing consistently yields superior solutions compared to Tabu Search in scenarios with lower dimensions despite longer run times. Conversely, Tabu Search performs better in higher-dimensional scenarios. Furthermore, it is observed that solutions generated by different weighting methods exhibit similar performance. © 2025 The Author(s).

Abstract
Nim is a mathematical combinatorial game in which two players take turns removing, or nimming, objects from distinct heaps or piles Although its rules are simple, which makes it extremely easy to play, it requires a solid strategic reasoning in order to win against experienced players. This study presents an optimised strategic approach to the game of Nim, which represents the guaranteed winning strategy for this game for the first player to take action. The proposed approach is a fundamental combinatorial game rooted in Boolean algebra and the XOR operation. Unlike traditional strategies that solely rely on XOR calculations to determine winning and losing positions, this research identifies and analyses anomalous strategic behaviours that challenge conventional Nim theory, revealing previously unexplored patterns in specific game configurations. To validate these findings, a Python-based application has been developed, implementing the proposed strategy to ensure consistent victory. The algorithm systematically applies XOR calculations, executes optimal moves, and dynamically adapts to anomalies, demonstrating how these irregularities can be leveraged for strategic advantage. This computational validation reinforces the theoretical framework and provides new insights into the limitations and extensions of classical Nim strategies. Beyond its implications for Nim, this research highlights the broader potential of AI-driven decision-making in combinatorial games. By demonstrating how algorithmic intelligence can analyse game states, predict outcomes, and refine strategies, this study contributes to advancements in artificial intelligence, optimisation algorithms, and complex strategic decision-making models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.