Abstract
Efficient public transportation management is essential for the development of large urban centers, providing several benefits such as comprehensive coverage of population mobility, reduction of transport costs, better control of traffic congestion, and significant reduction of environmental impact limiting gas emissions and pollution. Realizing these benefits requires a deeply understanding the population and transit patterns and the adoption of approaches to model multiple relations and characteristics efficiently. This work addresses these challenges by providing a novel dataset that includes various public transportation components from three different systems: regular buses, subway, and BRT (Bus Rapid Transit). Our dataset comprises daily information from about 700,000 passengers in Salvador, one of Brazil's largest cities, and local public transportation data with approximately 2,000 vehicles operating across nearly 400 lines, connecting almost 3,000 stops and stations. With data collected from March 2024 to March 2025 at a frequency lower than one minute, SUNT stands as one of the largest, most comprehensive, and openly available urban datasets in the literature.

Abstract
[No abstract available]

Abstract
The reliability and robustness of cyber-physical systems (CPS) are critical aspects of the current industrial landscape. The high level of autonomous and distributed components associated with a large number of devices makes CPS prone to faults. Despite their importance and benefits, traditional fault tolerance methodologies, namely local and/or centralized, often overlook the potential benefits of collaboration between cyber-physical components. This paper introduces a collaborative fault diagnosis methodology for CPS, integrating self-fault diagnosis capabilities in agents and leveraging collaborative behavior to enhance fault diagnosis. The contribution of this paper relay in propose a methodology for fault diagnosis for CPS, based on multi-agent system (MAS) technology as a backbone of infra-structure, highlighting the components, agent behavior, functionalities, and interaction protocols, to explore the benefits of communication and collaboration between agents. The proposed methodology enhance the accuracy of fault diagnosis when compared with local approach. A case study was conducted in a laboratory-scale warehouse, focusing on diagnosing drift, bias, and precision faults in temperature and humidity sensors. Experimental results reveal that the collaborative methodology significantly outperforms the local approach in fault diagnosis, as evidenced by performance improvements in diagnosis classification. The statistical significance of these results was validated using the Wilcoxon signed-ranks test for paired samples.

Abstract
Combining data from different sensing modalities has been a promising research topic for building better and more reliable data-driven models. In particular, it is known that multimodal spectral imaging can improve the analytical capabilities of standalone spectroscopy techniques through fusion, hyphenation, or knowledge distillation techniques. In this manuscript, we focus on the latter, exploring how one can increase the performance of a Laser-induced Breakdown Spectroscopy system for mineral classification problems using additional spectral imaging techniques. Specifically, focusing on a scenario where Raman spectroscopy delivers accurate mineral classification performance, we show how to deploy a knowledge distillation pipeline where Raman spectroscopy may act as an autonomous supervisor for LIBS. For a case study concerning a challenging Li-bearing mineral identification of spodumene and petalite, our results demonstrate the advantages of this method in improving the performance of a single-technique system. LIBS trained with labels obtained by Raman presents an enhanced classification performance. Furthermore, leveraging the interpretability of the model deployed, the workflow opens opportunities for the deployment of assisted feature discovery pipelines, which may impact future academic and industrial applications.

Abstract
Study Objectives Unsupervised machine learning-an approach that identifies patterns and structures within data without relying on labels-has demonstrated remarkable success in various domains of sleep research. This underscores the broader utility of machine learning, suggesting that its capabilities extend beyond current applications and warrant further exploration for novel insights in sleep studies, focusing specifically on unsupervised machine learning.Methods This paper outlines a scoping review conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines for scoping reviews. A comprehensive search covering various search terms focusing on the intersection between unsupervised machine learning and sleep led to 3960 publications. After screening all titles and abstracts with two independent reviewers, ultimately, 356 publications were included in the full-text review. The data extracted from the full texts included information about the machine learning methods and types of sleep data, as well as the study population.Results There has been a steep increase in the number of publications in this research area in the past 10 years. Clustering is the most commonly used method, but other methods are gaining popularity. Apart from classical polysomnography, data from wearable devices, nearables, video, audio, and medical imaging techniques have been used as input to unsupervised machine learning. The broad search allowed us to explore various applications within sleep research, ranging from the general population to populations with various sleep disorders.Conclusion The review mapped existing research on unsupervised learning in sleep research, identified gaps in the literature, and derived directions for future research. Statement of Significance Sleep is a transdisciplinary research field. With the rise of unsupervised machine learning and its emergence in sleep research, there is a pressing need to cultivate a mutual understanding across disciplinary boundaries to curate meaningful applications of unsupervised machine learning. This scoping review aims to serve as a foundation to facilitate collaboration across disciplines and ultimately contribute to the elevation of sleep research, by identifying novel ways of applying unsupervised machine learning.

Abstract
Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (llms). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose llms using simple prompts; (ii) effectiveness of different emotion prompt designs with llms; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that llms require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.