Abstract
Falls, especially in the elderly, are one of the main factors of hospitalization. Time-consuming intervention can be fatal or cause irreversible damages to the victims. On the other hand, there is currently a significant amount of smart clothing equipped with various sensors, particularly gyroscopes and accelerometers, which can be used to detect accidents. The creation of a tool that automatically detects eventual falls allows helping the victims as soon as possible. This works focuses in the automatic fall detection from sensors signals using long short-term memory networks. To train and test this approach, the Sisfall dataset is used, which considers the simulation of 23 adults and 15 older people. These simulations are based on everyday activities and the falls that may result from their execution. The results indicate that the procedure provides an accuracy score of 97.1% on the test set.

Abstract

Abstract
Legumes are an important and sustainable source of protein, dietary fiber and phytochemicals. Due to their composition, legumes have been used in enriched foodstuffs and recognized as a vital food resource for human diet, reducing the risk of cardiovascular disease and cancer. In the last years, in order to replace conventional analysis, more eco-friendly and faster methodologies have been applied to evaluate legumes' quality. The aim of this review is to encourage the consumption and production of legumes by promoting their dissemination, understanding their nutritional and functional value, and promoting the use of innovative methodologies to assess the composition of legumes.

Abstract
Task scheduling in fog paradigm is highly complex and in the literature, there are still few studies. In the cloud architecture, it is widely studied and in many researches, it is approached from the perspective of service providers. Trying to bring innovative contributions in these areas, in this paper, we propose a model to the context-aware task-scheduling problem for fog paradigm. In our proposal, different context parameters are normalized through Min-Max normalization; requisition priorities are defined through the application of the Multiple Linear Regression (MLR) technique and scheduling is performed using Multi-Objective Non-Linear Programming Optimization (MONLIP) technique.

Abstract
In the context of SaaS (Software as a Service) where software has to be up and miming 7 days a week and 24 hours a day, keeping the requirements specification and related test cases up to date can be difficult. Managing requirements in this context has additional challenges that need to be taken into account, for instance, re-prioritize requirements continuously and identify/update new dependencies among them. When requirements change, related test cases need to be updated accordingly. We claim that extracting and analyzing the usage of the SaaS can help to maintain requirements and test cases updated and contribute to improve the overall quality of the services provided. This paper presents an extension to REQAnalytics. REQAnalytics is a recommendation system that collects information about the usage of a SaaS and generates recommendations to improve the SaaS provided. The evolution involves extending the analysis performed over the sequences of functionalities (requirements) and refining the data provided for Software Requirements Specification, with the purpose of helping the requirements engineers in the requirement maintenance activities, and to improve the overall quality of the services. Furthermore, the extension presented in this paper is able to generate test cases in a regression testing context. (C) 2021 The Authors. Published by Elsevier B.V.

Abstract
It is known that academic performance is not correlated with the way people understand and deal with their own emotions and other peoples’ emotions. Active methodologies allow students to be constantly involved in the learning process and thus allow Higher Education students to cognitively develop Emotional Intelligence (EI). This study is guided by the following research question: what are the learning strategies for developing EI skills in Higher Education students? This is a qualitative study and two focus groups were held with two institutions of Public and Private Higher Education, in which 10 students and 4 Professors participated. The content of the interviews was analyzed using the qualitative analysis software webQDA®. One concludes that the active methodologies, Problem Based Learning and Inverted Classroom, can contribute to develop EI skills in Higher Education students, as they enable mental skills such as reasoning and problem solving, from the perception and knowledge of emotion patterns. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.