Abstract
The Machine Learning approach is used in several application domains, and its exploitation in predicting accidents in occupational safety is relatively recent. The present study aims to apply different Machine Learning algorithms for classifying the occurrence or non-occurrence of accidents at work in the retail sector. The approach consists of obtaining an impact score for each store and work unit, considering two databases of a retail company, the preventive safety actions, and the action plans. Subsequently, each score is associated with the occurrence or non-occurrence of accidents during January and May 2023. Of the five classification algorithms applied, the Support Vector Machine was the one that obtained the best accuracy and precision values for the preventive safety actions. As for the set of actions plan, the Logistic Regression reached the best results in all calculated metrics. With this study, estimating the impact score of the study variables makes it possible to identify the occurrence of accidents at work in the retail sector with high precision and accuracy.

Abstract
Weather change plays an important role in work-related accidents, it impairs people's cognitive abilities, increasing the risk of injuries and accidents. Furthermore, weather conditions can cause an increase or decrease in daily sales in the retail sector by influencing individual behaviors. The increase in transactions, in turn, leads employees to fatigue and overload, which can also increase the risk of injuries and accidents. This work aims to conduct a case study in a company in the retail sector to verify whether the transactions records in stores and the weather conditions of each district in mainland Portugal impact the occurrence of work accidents, as well as to perform predictive analysis of the occurrence or non-occurrence of work accidents in each district using these data and comparing different machine learning techniques. The correlation analysis of the occurrence or non-occurrence of work accidents with weather conditions and some transactions pointed out the nonexistence of correlation between the data. Evaluating the precision and the confusion matrix of the predictive models, the study indicates a predisposition of the models to predict the non-occurrence of work accidents to the detriment of the ability to predict the occurrence of work accidents.

Abstract
Research have been driven by the increased demand for delivery and pick-up services to develop new formulations and algorithms for solving Vehicle Routing Problems (VRP). The main objective is to create algorithms that can identify paths considering execution time in real-world scenarios. This study focused on using the Guided Local Search (GLS) metaheuristic available in OR-Tools to solve the Capacitated Vehicle Routing Problem with Time Windows using the Solomons instances. The execution time was used as a stop criterion, with short runs ranging from 1 to 10 s and a long run of 360 s for comparison. The results showed that the GLS metaheuristic from OR-Tools is applicable for achieving high performance in finding the shortest path and optimizing routes within constrained execution times. It outperformed the best-known solutions from the literature in longer execution times and even provided a close-to-optimal solution within 10 s. These findings suggest the potential application of this tool for dynamic VRP scenarios that require faster algorithms.

Abstract
Deep learning networks, more specifically convolutional neural networks, have shown a notable distinction when it comes to computer vision problems. Their versatility spans various domains, where they are applied for tasks such as classification and regression, contingent primarily on the availability of a representative dataset. This work explores the feasibility of employing this approach in the domain of agriculture, particularly within the context of olive growing. The objective is to enhance and facilitate cultivar identification techniques by using images of olive tree leaves. To achieve this, a comparative analysis involving ten distinct convolutional networks (VGG16, VGG19, ResNet50, ResNet152-V2, Inception V3, Inception ResNetV2, XCeption, MobileNet, MobileNetV2, EfficientNetB7) was conducted, all initiated with transfer learning as a common starting point. Also, the impact of adjusting network hyperparameters and structural elements was explored. For the training and evaluation of the networks, a dedicated dataset was created and made available, consisting of approximately 4200 images from the four most representative categories of the region. The findings of this study provide compelling evidence that the majority of the examined methods offer a robust foundation for cultivar identification, ensuring a high level of accuracy. Notably, the first nine methods consistently attain accuracy rates surpassing 95%, with the top three methods achieving an impressive 98% accuracy (ResNet50, EfficientNetB7). In practical terms, out of approximately 2016 images, 1976 were accurately classified. These results signify a substantial advancement in olive cultivar identification through computer vision techniques.

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
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.