Abstract
Imbalanced data are present in various business sectors and must be handled with the proper resampling methods and classification algorithms. To handle imbalanced data, there are numerous resampling and learning method combinations; nonetheless, their effective use necessitates specialised knowledge. In this paper, several approaches, ranging from more accessible to more advanced in the domain of data resampling techniques, will be considered to handle imbalanced data. The application developed delivers recommendations of the most suitable combinations of techniques for a specific dataset by extracting and comparing dataset meta-feature values recorded in a knowledge base. It facilitates effortless classification and automates part of the machine learning pipeline with comparable or better results than state-of-the-art solutions and with a much smaller execution time.

Abstract
Identifying stress in people is not a trivial or straightforward task, as several factors are involved in detecting the presence or absence of stress. The problem of detect stress has attracted much attention in the last decade and is mainly addressed with physiological signals and in a controlled ambience with specific tasks. However, the widespread use of video cameras permitted the creation of a new non-invasive data collection techniques. The goal of this work is to provide an alternative way to detect stress in the workplace without the need of specific laboratory conditions. For that, a stress detection model based on images analysed with deep learning neural networks was developed. The trained model achieved a F1 = 79.9% on a binary dataset, of stress/non-stress, with an imbalanced ratio of 0.49. This model can be used in a non-invasive application to detect stress and provide recommendations to the collaborators in the workplace in order to help them to control their stress condition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Stress is a common feeling in people's day-to-day life, especially at work, being the cause of several health problems and absenteeism. Despite the difficulty in identifying it properly, several studies have established a correlation between stress and perceivable human features. The problem of detecting stress has attracted significant attention in the last decade. It has been mainly addressed through the analysis of physiological signals in the execution of specific tasks in controlled environments. Taking advantage of technological advances that allow to collect stress-related data in a non-invasive way, the goal of this work is to provide an alternative approach to detect stress in the workplace without requiring specific controlled conditions. To this end, a video-based plethysmography application that analyses the person's face and retrieves several physiological signals in a non-invasive way was used. Moreover, in an initial phase, additional information that complements and labels the physiological data was obtained through a brief questionnaire answered by the participants. The data collection pilot took place over a period of two months, having involved 28 volunteers. Several stress detection models were developed; the best trained model achieved an accuracy of 86.8% and a F1 score of 87% on a binary stress/non-stress prediction.

Abstract
In this paper a load forecasting methodology for 2days-ahead based on functional clustering and on ensemble learning is presented. Due to the longitudinal nature of the load diagrams, these are segmented using a functional clustering procedure to group together similar daily load curves concerning its phase and amplitude. Next, ensemble learning of extreme learning machine models, developed for several load curves groups, is made to fully integrate the advantages of all models and improve the accuracy of the final load forecasting. The quality of this methodology is illustrated with a real case study concerning load consumption patterns of clients with different economic activities from a Portuguese energy trading company. The forecasting results for 2days-ahead are good for practical use, yielding a R-2 = 0.967.

Abstract

Abstract
Due to its historical nature, data warehouses require that large volumes of data need to be stored in their repositories. Some organizations are beginning to have problems to manage and analyze these huge volumes of data. This is due, in large part, to the relational databases which are the primary method of data storage in a data warehouse, and start underperforming, crumbling under the weight of the data stored. In opposition to these systems, arise the NoSQL databases that are associated with the storage of very large volumes of data inherent to the Big Data paradigm. Thus, this article focuses on the study of the feasibility and the implications of the adoption of a NoSQL database, within the data warehousing context. MongoDB was selected to represent the NoSQL systems in this investigation. In this paper will be explained the processes required to design the structure of a data warehouse and typically dimensional queries in the MongoDB system. The undertaken research culminates in the performance analysis of queries executed in a traditional data warehouse, based on the SQL Server system, and an equivalent data warehouse based on the MongoDB system.