RESUMO
Dengue causes approximately 10.000 deaths and 100 million symptomatic infections annually worldwide, making it a significant public health concern. To address this, artificial intelligence tools like machine learning can play a crucial role in developing more effective strategies for control, diagnosis, and treatment. This study identifies relevant variables for the screening of dengue cases through machine learning models and evaluates the accuracy of the models. Data from reported dengue cases in the states of Rio de Janeiro and Minas Gerais for the years 2016 and 2019 were obtained through the National Notifiable Diseases Surveillance System (SINAN). The mutual information technique was used to assess which variables were most related to laboratory-confirmed dengue cases. Next, a random selection of 10,000 confirmed cases and 10,000 discarded cases was performed, and the dataset was divided into training (70%) and testing (30%). Machine learning models were then tested to classify the cases. It was found that the logistic regression model with 10 variables (gender, age, fever, myalgia, headache, vomiting, nausea, back pain, rash, retro-orbital pain) and the Decision Tree and Multilayer Perceptron (MLP) models achieved the best results in decision metrics, with an accuracy of 98%. Therefore, a tree-based model would be suitable for building an application and implementing it on smartphones. This resource would be available to healthcare professionals such as doctors and nurses.
Assuntos
Dengue , Aprendizado de Máquina , Programas de Rastreamento , Dengue/diagnóstico , Programas de Rastreamento/métodos , Programas de Rastreamento/normas , Brasil , Árvores de Decisões , HumanosRESUMO
(1) Background: The human microbiota is essential for maintaining a healthy body. The gut microbiota plays a protective role against pathogenic bacteria. Probiotics are live microorganisms capable of preventing and controlling gastrointestinal and balancing the immune system. They also aid in better nutrients and vitamins absorption. Examples of natural probiotic cultures are kefir and kombucha. (2) Methods: Therefore, the aim of this review was to address the beneficial properties of probiotic kefir and kombucha using a Boxplot analysis to search for scientific data in the online literature up to January 2024: (Latin American and Caribbean Health Sciences (LILACS), PubMed, Medical Literature Analysis (MED-LINE), Science Direct, Google Scholar/Google Academic, Bioline Inter-national and Springer Link). Boxplots showed the summary of a set of data "Index Terms-Keywords" on kefir and kombucha in three languages (English, Portuguese and Spanish). (3) Results: Google Scholar was the database with the highest number of articles found, when the search for the keywords used in the study (containing ~4 × 106-~4 million articles available). This was Followed by the Science Direct database, containing ~3 × 106-~3 million articles available, and the BVS databases-Biblioteca Virtual de Saúde (Virtual Health Library) e Lilacs, both containing a value of ~2 × 106-~2 million articles available. The databases containing the smallest number of articles found were Nutrients and Medline, both containing a value of ≤0.1 × 106-≤100 thousand articles. (4) Conclusions: Scientific studies indicate that kefir and kombucha certainly contain various functional properties, such as antimicrobial, antitumor, anticarcinogenic and immunomodulatory activity, in addition to having a microbiological composition of probiotic bacteria and yeasts. Kefir and kombucha represent key opportunities in the food and clinic/medical fields.
RESUMO
BACKGROUND AND OBJECTIVE: Diabetes Mellitus (DM) is a chronic disease with a high worldwide prevalence. Diabetic foot is one of the DM complications and compromises health and quality of life, due to the risk of lower limb amputation. This work aimed to build a risk classification system for the evolution of diabetic foot, using Artificial Neural Networks (ANN). METHODS: This methodological study used two databases, one for system design (training and validation) containing 250 participants with DM and another for testing, containing 141 participants. Each subject answered a questionnaire with 54 questions about foot care and sociodemographic information. Participants from both databases were classified by specialists as high or low risk for diabetic foot. Supervised ANN (multi-layer Perceptron-MLP) models were exploited and a smartphone app was built. The app returns a personalized report indicating self-care for each user. The System Usability Scale (SUS) was used for the usability evaluation. RESULTS: MLP models were built and, based on the principle of parsimony, the simplest model was chosen to be implemented in the application. The model achieved accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 85%, 76%, 91%, 89%, and 79%, respectively, for the test data. The app presented good usability (93.33 points on a scale from 0 to 100). CONCLUSIONS: The study showed that the proposed model has satisfactory performance and is simple, considering that it requires only 10 variables. This simplicity facilitates its use by health professionals and patients with diabetes.
Assuntos
Diabetes Mellitus , Pé Diabético , Aplicativos Móveis , Humanos , Pé Diabético/diagnóstico , Pé Diabético/epidemiologia , Qualidade de Vida , Amputação Cirúrgica , Valor Preditivo dos TestesRESUMO
BACKGROUND AND OBJECTIVE: To automatically identify patients with diabetes mellitus (DM) who have high risk of developing diabetic foot, via an unsupervised machine learning technique. METHODS: We collected a new database containing 54 known risk factors from 250 patients diagnosed with diabetes mellitus. The database also contained a separate validation cohort composed of 73 subjects, where the perceived risk was annotated by expert nurses. A competitive neuron layer-based method was used to automatically split training data into two risk groups. RESULTS: We found that one of the groups was composed of patients with higher risk of developing diabetic foot. The dominant variables that described group membership via our method agreed with the findings from other studies, and indicated a greater risk for developing such a condition. Our method was validated on the available test data, reaching 71% sensitivity, 100% specificity, and 90% accuracy. CONCLUSIONS: Unsupervised learning may be deployed to screen patients with diabetes mellitus, pointing out high-risk individuals who require priority follow-up in the prevention of diabetic foot with very high accuracy. The proposed method is automatic and does not require clinical examinations to perform risk assessment, being solely based on the information of a questionnaire answered by patients. Our study found that discriminant variables for predicting risk group membership are highly correlated with expert opinion.
Assuntos
Diabetes Mellitus Tipo 2 , Pé Diabético , Pé Diabético/epidemiologia , Humanos , Medição de Risco , Fatores de Risco , Inquéritos e QuestionáriosRESUMO
BACKGROUND: Intermittent photic stimulation (IPS) leads to phase- and time-locked activities in the electroencephalogram (EEG). While the first are easily obtained by means of averaging techniques (the evoked response), this latter reflects changes in the ongoing EEG that are important in event-related synchronization/desynchronization (ERS/ERD) studies. Techniques have been proposed for assessing such changes but they only provide the spectral estimate of the time-locked activities. NEW METHOD: An independent component analysis-based method is proposed for the EEG analysis during IPS. Artificially generated sinusoidal functions at the stimulation frequency and harmonics are used together with the acquired EEG signal to build the observed vector that is presented to the ICA algorithm. RESULTS: The proposed method was evaluated with simulated data and applied to EEG signals acquired on two electrodes placed over the occipital region showing that this method is capable of providing a suitable estimation of the ongoing EEG activities in both time and frequency domains. COMPARISON WITH EXISTING METHOD(S): The results were compared with a coherence-based method, showing that the proposed method can estimate the power spectrum of the ongoing EEG activity as precisely as the coherence-based method with the advantage of allowing the ongoing EEG activity in time domain to be also obtained. CONCLUSIONS: The application of the proposed method could be used for ERS/ERD studies, since it separates evoked responses, which are phase-locked to the stimuli, from those that change the ongoing EEG in a time-locked manner to the external stimulation.
Assuntos
Eletroencefalografia/métodos , Estimulação Luminosa/métodos , Processamento de Sinais Assistido por Computador , Algoritmos , Humanos , Lobo Occipital/fisiologia , Percepção Visual/fisiologiaRESUMO
ABSTRACT: This paper presents the main applications of electric vehicles in rural areas, pointing out the trends and challenges for the future. Technological conditions and difficulties faced by the industry for a wide dissemination of this technology are discussed. The paper described the main researches with proposals to overcome the problems of implementing electric tractors, as supply and electricity storage. Technical and economic comparisons between conventional internal combustion tractors and electric tractors are also presented and discussed. The paper showed the existence of barriers to the implementation of electric vehicles in rural areas, as well as the need for batteries technological evolution, which have high costs and for that reason they are very heavy for these purposes, but there are already systems that can be applied to minimize dependence of fossil fuels in this sector and increase the use of sustainable energy.
RESUMO: Este artigo apresenta as principais aplicações de veículos elétricos no meio rural, apontanto as tendências e mudanças futuras. O trabalho discute também as condições tecnológicas e dificuldades enfrentadas pelo setor industrial para a inserção do veículo elétrico no mercado. São apresentados os principais pesquisadores da área com propostas para superar os problemas da implementação dos tratores elétricos, tais como abastecimento e armazenamento de energia elétrica. As comparações técnicas e econômicas entre tratores convencionais, a combustão interna, e tratores elétricos são apresentadas e discutidas. A revisão mostra a existência de barreiras para a implantação dos veículos elétricos no meio rural, como a necessidade de evolução tecnológica das baterias, que apresentam alto custo e ainda são pesadas para este propósito, mas mostra também que já existem sistemas que podem minimizar a dependência de compubstíveis fóceis do setor e aumentar o uso de energia sustentável.
RESUMO
This paper presents the main applications of electric vehicles in rural areas, pointing out the trends and challenges for the future. Technological conditions and difficulties faced by the industry for a wide dissemination of this technology are discussed. The paper described the main researches with proposals to overcome the problems of implementing electric tractors, as supply and electricity storage. Technical and economic comparisons between conventional internal combustion tractors and electric tractors are also presented and discussed. The paper showed the existence of barriers to the implementation of electric vehicles in rural areas, as well as the need for batteries technological evolution, which have high costs and for that reason they are very heavy for these purposes, but there are already systems that can be applied to minimize dependence of fossil fuels in this sector and increase the use of sustainable energy.(AU)
Este artigo apresenta as principais aplicações de veículos elétricos no meio rural, apontando as tendências e mudanças futuras. O trabalho discute também as condições tecnológicas e dificuldades enfrentadas pelo setor industrial para a inserção do veículo elétrico no mercado. São apresentados os principais pesquisadores da área com propostas para superar os problemas da implementação dos tratores elétricos, tais como abastecimento e armazenamento de energia elétrica. As comparações técnicas e econômicas entre tratores convencionais, a combustão interna, e tratores elétricos são apresentadas e discutidas. A revisão mostra a existência de barreiras para a implantação dos veículos elétricos no meio rural, como a necessidade de evolução tecnológica das baterias, que apresentam alto custo e ainda são pesadas para este propósito, mas mostra também que já existem sistemas que podem minimizar a dependência de combustíveis fósseis do setor e aumentar o uso de energia sustentável.(AU)
Assuntos
Veículos Automotores , Zona Rural , Baterias , Equipamentos e Provisões ElétricasRESUMO
This paper presents the main applications of electric vehicles in rural areas, pointing out the trends and challenges for the future. Technological conditions and difficulties faced by the industry for a wide dissemination of this technology are discussed. The paper described the main researches with proposals to overcome the problems of implementing electric tractors, as supply and electricity storage. Technical and economic comparisons between conventional internal combustion tractors and electric tractors are also presented and discussed. The paper showed the existence of barriers to the implementation of electric vehicles in rural areas, as well as the need for batteries technological evolution, which have high costs and for that reason they are very heavy for these purposes, but there are already systems that can be applied to minimize dependence of fossil fuels in this sector and increase the use of sustainable energy.
Este artigo apresenta as principais aplicações de veículos elétricos no meio rural, apontando as tendências e mudanças futuras. O trabalho discute também as condições tecnológicas e dificuldades enfrentadas pelo setor industrial para a inserção do veículo elétrico no mercado. São apresentados os principais pesquisadores da área com propostas para superar os problemas da implementação dos tratores elétricos, tais como abastecimento e armazenamento de energia elétrica. As comparações técnicas e econômicas entre tratores convencionais, a combustão interna, e tratores elétricos são apresentadas e discutidas. A revisão mostra a existência de barreiras para a implantação dos veículos elétricos no meio rural, como a necessidade de evolução tecnológica das baterias, que apresentam alto custo e ainda são pesadas para este propósito, mas mostra também que já existem sistemas que podem minimizar a dependência de combustíveis fósseis do setor e aumentar o uso de energia sustentável.
Assuntos
Baterias , Equipamentos e Provisões Elétricas , Veículos Automotores , Zona RuralRESUMO
RESUMO: A competitividade no mercado agrícola tem tornado intensa a busca pela redução de custo nos processos de produção, como é o caso da colheita do café ( Coffea arabica L.), que tem migrado da colheita manual para a semi mecanizada e mecanizada. Essa transição proporcionou o surgimento de novas tecnologias e diversos modelos de colhedoras, as quais permitem regulagens que influenciam diretamente na eficiência de derriça. Entretanto, entender o comportamento dinâmico dos componentes e sistemas das colhedoras é de extrema importância para o desenvolvimento de novos produtos e recomendações de regulagem para colheita plena ou seletiva. Nesse contexto, objetivou-se analisar a vibração das hastes derriçadoras de uma colhedora de café, em diferentes regulagens, a fim de entender seu comportamento dinâmico em termos de amplitude e frequência de vibração, e inferir sobre a recomendação de regulagens para a colheita mecânica do café. A metodologia utilizada, baseada na análise dos sinais de vibração das hastes derriçadoras, possibilitou a recomendação de regulagens para a colheita mecânica do café, em função das amplitudes de vibração das hastes derriçadoras. O estudo mostrou que as maiores amplitudes de vibração das hastes no sentido vertical ocorreram para as regulagens de 8 e 10Kgf no freio, na vibração de 950 ciclos min-1 do cilindro e com hastes de 570mm de comprimento. Os resultados permitem associar o comportamento de vibração das hastes derriçadoras com os objetivos da colheita, plena ou seletiva, apontando qual a regulagem específica a ser utilizada para cada finalidade.
ABSTRACT: Growers need to reduce costs of the coffee production to meet the demand and stay competitive in the market. Such a need has led to the application of mechanization in the coffee harvest ( Coffea Arabica L.), which is a costly process and requires high cost of manpower, and this last is increasingly scarce. The migration from manual harvest to semi-mechanized or super-mechanized made new technologies and diverse models of coffee harvesting machines emerge. These coffee harvesting machines have settings that directly influence the harvesting efficiency. To understand the dynamic behavior of coffee harvesting machines components and systems is very important to develop new products, setting and operation norms. In this context, this reseach aimed to analyze the vibration of the harvester rods of an automatic coffee harvesting, by considering different adjustments, in order to understand its dynamic behavior in terms of amplitude and frequency of vibration, and to infer about adjustment recommendations for the mechanical harvesting coffee. Results showed that the harvesting studied presented larger amplitudes of vibration of stems vertically when set for 8 and 10Kgf of curb, at vibration of 950 cycles min1 of cylinder and with the stems of 570mm of length; the highest efficiency occurs when the rods vibrate vertically, promoting greater contact between the rods and side branches and fruit of the coffee plant. Also, the achieved results can be very useful as a guide for adjusting coffee harvesting machines, for research anddevelopment of new technologies to the benefit of the grower.
RESUMO
Growers need to reduce costs of the coffee production to meet the demand and stay competitive in the market. Such a need has led to the application of mechanization in the coffee harvest ( Coffea Arabica L.), which is a costly process and requires high cost of manpower, and this last is increasingly scarce. The migration from manual harvest to semi-mechanized or super-mechanized made new technologies and diverse models of coffee harvesting machines emerge. These coffee harvesting machines have settings that directly influence the harvesting efficiency. To understand the dynamic behavior of coffee harvesting machines components and systems is very important to develop new products, setting and operation norms. In this context, this reseach aimed to analyze the vibration of the harvester rods of an automatic coffee harvesting, by considering different adjustments, in order to understand its dynamic behavior in terms of amplitude and frequency of vibration, and to infer about adjustment recommendations for the mechanical harvesting coffee. Results showed that the harvesting studied presented larger amplitudes of vibration of stems vertically when set for 8 and 10Kgf of curb, at vibration of 950 cycles min1 of cylinder and with the stems of 570mm of length; the highest efficiency occurs when the rods vibrate vertically, promoting greater contact between the rods and side branches a(AU)
A competitividade no mercado agrícola tem tornado intensa a busca pela redução de custo nos processos de produção, como é o caso da colheita do café ( Coffea arabica L.), que tem migrado da colheita manual para a semi mecanizada e mecanizada. Essa transição proporcionou o surgimento de novas tecnologias e diversos modelos de colhedoras, as quais permitem regulagens que influenciam diretamente na eficiência de derriça. Entretanto, entender o comportamento dinâmico dos componentes e sistemas das colhedoras é de extrema importância para o desenvolvimento de novos produtos e recomendações de regulagem para colheita plena ou seletiva. Nesse contexto, objetivou-se analisar a vibração das hastes derriçadoras de uma colhedora de café, em diferentes regulagens, a fim de entender seu comportamento dinâmico em termos de amplitude e frequência de vibração, e inferir sobre a recomendação de regulagens para a colheita mecânica do café. A metodologia utilizada, baseada na análise dos sinais de vibração das hastes derriçadoras, possibilitou a recomendação de regulagens para a colheita mecânica do café, em função das amplitudes de vibração das hastes derriçadoras. O estudo mostrou que as maiores amplitudes de vibração das hastes no sentido vertical ocorreram para as regulagens de 8 e 10Kgf no freio, na vibração de 950 ciclos min-1 do cilindro e com hastes de 570mm de comprimento. Os resultados (AU)
Assuntos
Coffea , Produtos Agrícolas , Ensaios de Triagem em Larga EscalaRESUMO
A coerência simples entre o sinal de estimulação e o eletroencefalograma (EEG) tem sido utilizado na detecção de respostas evocadas à estimulação rítmica. Neste trabalho, técnicas para detecção objetiva de respostas e par investigação do sincronismo no EEG durante foto-estimulação intermitente (FEI), baseadas na coerência múltipla e parcial (extensões multi-variáveis da coerência simples) entre o sinal de estimulação e os sinais de EEG, são apresentadas. Tais técnicas, além de avaliadas por simulação Monte Carlo, foram aplicadas ao EEG de indivíduos normais durante FEI. Os resultados da simulação indicam que a coerência parcial, removendo-se a contribuição do sinal de estimulação, é adequada para a quantificação da inter-relação das atividades não sincronizaças com a estimulação. Os resultados com sinais de EEG foram compatíveis com os da simulação. A metodologia proposta mostrou-se, portanto, promissora na avaliação da relação entre sinais de EEG adquiridos em diferentes regiões do escalpo durante estimulação sensorial rítmica.