Abstract
Numerous studies in waste management propose solutions to the Waste Collection Problem, often focusing on constraints such as time windows and truck capacity. Travel times between points play a vital role in optimizing waste collection. However, the methods for determining them are frequently omitted. Another parameter that has a great influence on waste collection is the time window. Here, the impact of time windows and travel times on the capacitated waste collection problem with time windows solution was assessed for collecting three waste types. Surprisingly, travel times were found to have minimal influence on route optimization, while time windows significantly affected the algorithm's ability to identify the most efficient collection route. Addressing these considerations is crucial for practical application and improving the performance of waste collection algorithms in real-world contexts.

Abstract
The Eurasian grapevine (\textit{Vitis vinifera L.}) is the most widely grown horticultural crop in the world and is important for the economy of many countries. In the wine production chain, grape varieties play an important role, as they directly influence the authenticity and classification of the product. Identifying the different grape varieties is therefore fundamental for quality control and control activities, as well as for regulating production. Currently, ampelography and molecular analysis are the main approaches to identifying grape varieties. However, both methods have limitations. Ampelography is subjective and prone to errors and is experiencing enormous difficulties as ampelographers are increasingly scarce. On the other hand, molecular analyses are very demanding in terms of cost and time. In this scenario, Deep Learning (DL) methods have emerged as a classification alternative to deal with the scarcity of ampelographers and avoid molecular analyses. In this study, the most recent and current methods for identifying grapevine varieties using DL classification-based approaches are presented through a systematic literature review. The steps of the standard DL-based classification pipeline were described for the 18 most relevant studies found in the literature, highlighting their pros and cons. Potential directions for improving this field of research were also presented.

Abstract
The gastrointestinal tract is part of the digestive system, fundamental to digestion. Digestive problems can be symptoms of chronic illnesses like cancer and should be treated seriously. Endoscopic exams in the tract make detecting these diseases in their initial stages possible, enabling an effective treatment. Modern endoscopy has evolved into the Wireless Capsule Endoscopy procedure, where patients ingest a capsule with a camera. This type of exam usually exports videos up to 8 hours in length. Support systems for specialists to detect and diagnose pathologies in this type of exam are desired. This work uses a rarely used dataset, the ERS dataset, containing 121.399 labelled images, to evaluate three models from the EfficientNet family of architectures for the binary classification of Endoscopic images. The models were evaluated in a 5-fold cross-validation process. In the experiments, the best results were achieved by EfficientNetB0, achieving average accuracy and F1-Score of, respectively, 77.29% and 84.67%. Copyright © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

Abstract
Federated Learning (FL) is emerging in the medical field to address the need for diverse datasets while complying with data protection regulations. This decentralised learning paradigm allows hospitals (clients) to train machine learning models locally, ensuring that patient data remains within the confines of its originating institution. Nonetheless, FL by itself is not enough to guarantee privacy, as the central aggregation process may still be susceptible to identity-exposing attacks, potentially compromising data protection compliance. To strengthen privacy, differential privacy (DP) is often introduced. In this work, we conduct a comprehensive comparative analysis to evaluate the impact of DP in both traditional Centralised Learning (CL) frameworks and FL for polyp segmentation, a common medical image analysis task. Experiments are performed in PolypGen, a multi-centre publicly available dataset designed for polyp segmentation. The results show a clear drop in performance with the introduction of DP, exposing the trade-off between privacy and performance and highlighting the need to develop novel privacy-preserving techniques.

Abstract
Artificial intelligence encapsulates a black box of undiscovered knowledge, propelling the exploration of Explainable Artificial Intelligence (XAI) in generative data synthesis and deep learning. Focused on unveiling these black box areas, pointed into interpretability and validation in synthetic data generation, shedding light on the intricacies of generative processes. XAI techniques illuminate decision-making in complex algorithms, enhancing transparency and fostering a comprehensive understanding of non-linear relationships. Addressing the complexity of explaining deep learning models, this paper proposes an XAI solution for deep synthetic data generation explanation. The model integrates a clustering approach to identify similar training instances, reducing interpretation time for large datasets. Explanations, available in various formats, are tailored to diverse user profiles through integration with language models, generating texts with different technical detail levels. This research contributes to ethically deploying AI, bridging the gap between advanced model complexities and human interpretability in the dynamic landscape of artificial intelligence.

Abstract
Considering the rising energy needs and the depletion of conventional energy sources, microgrid systems combining wind energy and solar photovoltaic power with diesel generators are promising and considered economically viable for usage. To evaluate system cost and dependability, optimizing the size of microgrid system elements, including energy storage systems connected with the principal network, is crucial. In this line, a study has already been performed using a uni-objective optimization approach for the techno-economic sizing of a microgrid. It was noted that, despite the economic criterion, the environmental criterion can have a considerable impact on the elements constructing the microgrid system. In this paper, two multi-objective optimization approaches are proposed, including a non-dominated sorting genetic algorithm (NSGA-II) and the Pareto Search algorithm (PS) for the eco-environmental design of a microgrid system. The k-means clustering of the non-dominated point on the Pareto front has delivered three categories of scenarios: best economic, best environmental, and trade-off. Energy management, considering the three cases, has been applied to the microgrid over a period of 24 h to evaluate the impact of system design on the energy production system's behavior.