Employing machine learning for advanced gap imputation in solar power generation databases.

This research evaluates the application of advanced machine learning algorithms, specifically Random Forest and Gradient Boosting, for the imputation of missing data in solar energy generation databases and their impact on the size of green hydrogen production systems. The study demonstrates that the Random Forest model notably excels in harnessing solar data to optimize hydrogen production, achieving superior prediction accuracy with mean absolute error (MAE) of 0.0364, mean squared error (MSE) of 0.0097, root mean squared error (RMSE) of 0.0985, and a coefficient of determination (R2) of 0.9779. These metrics surpass those obtained from baseline models including linear regression and recurrent neural networks, highlighting the potential of accurate imputation to significantly enhance the efficiency and output of renewable energy systems. The findings advocate for the integration of robust data imputation methods in the design and operation of photovoltaic systems, contributing to the reliability and sustainability of energy resource management. Furthermore, this research makes significant contributions by showcasing the comparative performance of traditional machine learning models in handling data gaps, emphasizing the practical implications of data imputation on optimizing hydrogen production systems. By providing a detailed analysis and validation of the imputation models, this work offers valuable insights for future advancements in renewable energy technology.

Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble.

The employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy providers. In this work, we propose a data-driven ensemble that combines five single well-known models in the forecasting literature: a statistical linear autoregressive model and four artificial neural networks: (radial basis function, multilayer perceptron, extreme learning machines, and echo state networks). The proposed ensemble employs extreme learning machines as the combination model due to its simplicity, learning speed, and greater ability of generalization in comparison to other artificial neural networks. The experiments were conducted on real consumption data collected from a smart meter in a one-step-ahead forecasting scenario. The results using five different performance metrics demonstrate that our solution outperforms other statistical, machine learning, and ensembles models proposed in the literature.

Validação de um instrumento para controle de cura sifilítica em puérperas e recém-nascidos / Validation of an instrument for control syphilitic cure control in puerperal women and newborns / Validación de un instrumento para el control de la curación sifilítica en puérperas y recién nacidos

OBJETIVO: Validar um instrumento para controle de cura sifilítica em puérperas e seus RN, após alta da maternidade. MÉTODO: Design Science Research, com juízes escolhidos pela técnica "bola de neve". Seguiram-se as etapas de: levantamento bibliográfico; elaboração da tecnologia; validação pelos especialistas, avaliando a tecnologia através de um instrumento de coleta de dados ­ com uma escala de Likert e espaços para justificativas abertas. A análise dos dados foi feita pelo cálculo do Índice de Validade de Conteúdo (IVC) para cada item para o instrumento. O contato entre pesquisador e juízes se deu via e-mail. RESULTADOS: Participaram da avaliação 5 juízes especialistas. Todos os itens foram considerados relevantes (IVC≥ 0,80), gerando, para o instrumento como um todo, um IVC= 1. Os itens da seção "Identificação do(a) usuário(a)" foram incrementados; na seção "Informações diagnósticas e terapêuticas", julgou-se pertinente manter campo para registro do teste não-treponêmico, excluindo teste treponêmico. CONCLUSÃO: O instrumento foi validado, apresentando confiabilidade de implementação. A tecnologia será capaz de auxiliar profissionais da atenção primária a conduzir o controle de cura sifilítica de RN e puérperas; e poderá fortificar a comunicação entre os níveis de atenção à saúde. (AU)

Objective: To validate an instrument to control syphilitic cure in puerperal women and their newborns, after discharge from the maternity hospital. Methods: Design Science Research, with judges chosen by the "snowball" technique. The following steps were taken: bibliographic survey; development of the technology; validation by specialists, who evaluated the technology through a data collection instrument - with a Likert scale and spaces for open justifications. Data analysis was performed by calculating the Content Validity Index (CVI) at each item for the instrument. The contact between the researcher and the judges was done via e-mail. Results: Five expert judges participated in the evaluation. All items were considered relevant (CVI≥ 0.80), generating, for the instrument as a whole, a CVI= 1. The items in the section "User identification" were increased; in the section "Diagnostic and therapeutic information", it was deemed pertinent to keep the field for recording the non-treponemal test, excluding the treponemal test. Conclusion: The instrument was validated, showing its reliability for implementation. The technology will be able to assist Primary Health Care professionals to conduct the control of syphilitic cure of newborns and postpartum women; in addition, it can strengthen communication between levels of health care. (AU)

Objetivo: Validar un instrumento para el control de la curación sifilítica en puérperas y sus recién nacidos, luego del alta de la maternidad. Métodos: Design science research, con jueces elegidos mediante la técnica de "bola de nieve". Se dieron los siguientes pasos: estudio bibliográfico; desarrollo tecnológico; validación por especialistas, evaluando la tecnología a través de un instrumento de recolección de datos - con escala Likert y espacios para justificaciones abiertas. El análisis de los datos se realizó calculando el Índice de Validez de Contenido (IVC) para cada ítem del instrumento. El contacto entre el investigador y los jueces se realizó vía correo electrónico. Resultados: Cinco jueces expertos participaron en la evaluación. Todos los ítems fueron considerados relevantes (IVC ≥ 0,80), generando, para el instrumento en su conjunto, un IVC = 1. Se incrementaron los ítems del apartado "Identificación del usuario"; en el apartado "Información diagnóstica y terapéutica", se consideró pertinente mantener el campo para el registro de la prueba no treponémica, excluyendo la prueba treponémica. Conclusión: El instrumento fue validado, mostrando confiabilidad de implementación. La tecnología podrá ayudar a los profesionales de atención primaria a realizar el control de la curación sifilítica de recién nacidos y puérperas; y puede fortalecer la comunicación entre los niveles de atención de la salud. (AU)

Cross-cultural adaptation of the Pain Medication Questionnaire for use in Brazil.

BACKGROUND: The Pain Medication Questionnaire (PMQ) assesses the risk of opioid abuse in people with non-oncological chronic pain. METHODS: This is a methodological study conducted at a hemotherapy centre in Recife, Pernambuco state, Brazil. A Cross-cultural adaptation was carried out by a committee of nine specialists, and we applied the PMQ to a pre-final sample of 40 individuals with sickle cell anemia, in addition to a sociodemographic and clinical questionnaire. RESULTS: The mean agreement indexes for PMQ equivalences were the following: semantic (0.996), idiomatic (0.970), experiential (0.991), conceptual (0.953), language clarity (0.991), practical relevance (0.906), and theoretical relevance (0.945). Assessment of the PMQ showed that 50% of participants obtained a score equivalent to medium risk of opioid abuse. Cronbach's alpha coefficient for the adapted PMQ instrument was 0.705, ranging from 0.641 to 0.736 among its items. CONCLUSION: The cross-cultural adaptation of the Pain Medication Questionnaire was satisfactory and easy to apply in the Brazilian population. It is clinically relevant, contributing professional practice and enlightening patients with sickle cell anemia on their behavioral dynamics with respect to opioid consumption. It will also contribute to teaching and research, because it is a useful tool for investigating the risk of abusive behavior in people with chronic pain.

Self-efficacy assessment tools for individuals with depression: protocol for a systematic review of the literature.

INTRODUCTION: Depression is a common debilitating disease that affects individuals in all age groups. The impact of the diagnosis extends beyond the individual, with negative effects on mental health, physical health and social well-being. Self-efficacy has been referenced as an important aspect to the prognosis of mood disorders by conferring co-responsibility to the affected individual to face his/her health problems. Several assessment tools are found in the literature for measuring self-efficacy, but it is not yet clear which of these measures are more applicable to individuals with mood disorders, particularly depression. Thus, the aim of present study is to propose a systematic review to examine the psychometric properties and applicability of assessment tools designed to measure self-efficacy in individuals with symptoms and/or a diagnosis of depression. METHODS AND ANALYSIS: This protocol is reported in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols statement and the review will be reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. The evaluation of the psychometric properties of the health outcome measures will be conducted according to COSMIN guidelines. Two independent reviewers will perform the electronic searches in the PubMed, Web of Science, PsycInfo, SCOPUS and CINAHL databases, followed by the use of the 'snowball' strategy. The inclusion criteria will be (1) instrument validation studies, (2) developed with individuals of any age (3) with symptoms or a diagnosis of depression. Two independent reviewers will analyse the titles and abstracts of the articles retrieved during the search for pre-selection, followed by full-text analyses to determine inclusion in the review based on the eligibility criteria. Cases of a divergence of opinion will be resolved by a third reviewer. Descriptive analysis of the articles will be performed (data on participants, characteristics, psychometric properties and clinical usefulness of the assessment tools). ETHICS AND DISSEMINATION: The proposed systematic review will provide information on assessment tools employed to measure self-efficacy with regard to coping with depression, offering data on the psychometric properties, strong and weak points, and clinical applicability. As a secondary analysis of the literature, the approval of an ethics committee is not required. PROSPERO REGISTRATION NUMBER: CRD42017078707.

Risk of behaviour suggestive of opioid abuse: a protocol for a systematic review of validated assessment tools.

INTRODUCTION: Opioid use patterns of individuals with non-cancer pain are influenced by the behavioural dynamics of the individual in managing and properly following the prescription. The use of assessment tools for measuring the risk of behaviour suggestive of opioid abuse is important for health professionals who provide care to individuals with non-cancer pain. The aim of the proposed review is to analyse the psychometric properties of tools for measuring the risk of behaviour suggestive of opioid abuse in adults with non-cancer pain. METHODS AND ANALYSIS: The review process will be based on the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols. The Consensus-Based Standards for the Selection of Health Measurement Instruments will be used to analyse the assessment tools. Two independent reviewers will perform the literature search and analysis procedures. Searches will be performed on PubMed, Web of Science, Cochrane, Scopus, and Cumulative Index to Nursing and Allied Health Literature databases, and the 'snowball' strategy will be employed. The inclusion criteria will be (1) validation studies, (2) assessment tools designed exclusively for measuring the risk of behaviour suggestive of opioid abuse and (3) assessment tools designed for evaluation of adults with chronic non-cancer pain. The titles and abstracts of the studies retrieved from the databases will be analysed for the preselection of articles, which will be submitted to a full-text analysis to define the final sample. Divergence of opinion between two reviewers will be resolved by consulting a third reviewer. ETHICS AND DISSEMINATION: The review will offer an overview of assessment tools available for measuring the risk of behaviour suggestive of opioid abuse, which is relevant to reducing the risk of deaths due to abusive consumption and for clinical management of adults with chronic non-cancer pain. PROSPERO REGISTRATION NUMBER: CRD42018081577.