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

Abstract
Objective: This study investigates the applicability of systematic methods in the identification and evaluation of studies on sustainable urban mobility, providing subsidies to guide managers and policymakers in the development of efficient and environmentally responsible public policies.   Method: The methodology adopted for this research comprises a Systematic Literature Review (SLR) associated with the Fuzzy-TOPSIS method, a multi-criteria model capable of evaluating and prioritizing studies considering the imprecision inherent in decision-making processes. The PICO technique was used to define the analysis criteria, and the PRISMA protocol ensured the transparency and replicability of the results. Six criteria were established in the qualitative analyses for treatment in the Fuzzy-TOPSIS method.   Results and Discussion: The proposed approach proved effective in selecting the most relevant studies. The discussion points to the need to integrate Fuzzy-TOPSIS with complementary methods, such as DEMATEL and Social Network Analysis (SNA), in order to improve the modeling of causal relationships and strengthen the reliability of prioritization.   Research Implications: The results offer important insights for urban planning and the formulation of public policies, contributing to energy efficiency, reducing GHG emissions and improving the quality of public transport.   Originality/Value: The innovation of this study lies in the combination of quantitative and qualitative approaches to the analysis of sustainable mobility, providing a robust benchmark that can positively influence practices and strategies in urban management.

Abstract
In real-world scenarios, numerous phenomena generate a series of events that occur in continuous time. Point processes provide a natural mathematical framework for modeling these event sequences. In this comprehensive survey, we aim to explore probabilistic models that capture the dynamics of event sequences through temporal processes. We revise the notion of event modeling and provide the mathematical foundations that underpin the existing literature on this topic. To structure our survey effectively, we introduce an ontology that categorizes the existing approaches considering three horizontal axes: modeling, inference and estimation, and application. We conduct a systematic review of the existing approaches, with a particular focus on those leveraging deep learning techniques. Finally, we delve into the practical applications where these proposed techniques can be harnessed to address real-world problems related to event modeling. Additionally, we provide a selection of benchmark datasets that can be employed to validate the approaches for point processes.

Abstract
Evaluating and documenting the robustness of forecasting models to different input conditions is important for their responsible deployment in real-world applications. Time series forecasting models often exhibit degraded performance in the form of unusually large errors, high uncertainty, or hubris (high errors coupled with low uncertainty). Traditional stress testing approaches rely on manually designed adverse scenarios that fail to systematically identify unknown stress factors, in which data characteristics indicate potential issues. To overcome this limitation, this paper introduces MAST (Meta-learning and data Augmentation for Stress Testing), a novel method for stress testing forecasting models. MAST leverages model outputs (error scores and prediction intervals) to automatically identify and characterize input conditions that induce stress. Specifically, MAST is a binary probabilistic classifier that predicts the likelihood of forecasting model stress based on time series features. An additional contribution is a novel time series data augmentation approach based on oversampling or synthetic time series generation, that improves the information about stress factors in the input space, resulting in increased stress classification performance. Experiments were conducted using 6 benchmark datasets containing a total of 97.829 time series. We demonstrate how MAST is able to identify and explain input conditions that lead to manifestations of stress, namely large errors, high uncertainty, or hubris.