Search

The SARS-CoV-2 virus causes a respiratory disease in humans, known as COVID-19. The confirmatory diagnostic of this disease occurs through the real-time reverse transcription and polymerase chain reaction test (RT-qPCR). However, the period of obtaining the results limits the application of the mass test. Thus, chest X-ray computed tomography (CT) images are analyzed to help diagnose the disease. However, during an outbreak of a disease that causes respiratory problems, radiologists may be overwhelmed with analyzing medical images. In the literature, some studies used feature extraction techniques based on CNNs, with classification models to identify COVID-19 and non-COVID-19. This work compare the performance of applying pre-trained CNNs in conjunction with classification methods based on machine learning algorithms. The main objective is to analyze the impact of the features extracted by CNNs, in the construction of models to classify COVID-19 and non-COVID-19. A SARS-CoV-2 CT data-set is used in experimental tests. The CNNs implemented are visual geometry group (VGG-16 and VGG-19), inception V3 (IV3), and EfficientNet-B0 (EB0). The classification methods were k-nearest neighbor (KNN), support vector machine (SVM), and explainable deep neural networks (xDNN). In the experiments, the best results were obtained by the EfficientNet model used to extract data and the SVM with an RBF kernel. This approach achieved an average performance of 0.9856 in the precision macro, 0.9853 in the sensitivity macro, 0.9853 in the specificity macro, and 0.9853 in the F1 score macro.

People use Online Social Networks (OSNs) to express their opinions and feelings about many topics. Depending on the nature of an event and its dissemination rate in OSNs, and considering specific regions, the users’ behavior can drastically change over a specific period of time. In this context, this work aims to propose an event detection system at the early stages of an event based on changes in the users’ behavior in an OSN. This system can detect an event of any subject, and thus, it can be used for different purposes. The proposed event detection system is composed of the following main modules: (1) determination of the user’s location, (2) message extraction from an OSN, (3) topic identification using natural language processing (NLP) based on the Deep Belief Network (DBN), (4) the user behavior change analyzer in the OSN, and (5) affective analysis for emotion identification based on a tree-convolutional neural network (tree-CNN). In the case of public health, the early event detection is very relevant for the population and the authorities in order to be able take corrective actions. Hence, the new coronavirus disease (COVID-19) is used as a case study in this work. For performance validation, the modules related to the topic identification and affective analysis were compared with other similar solutions or implemented with other machine learning algorithms. In the performance assessment, the proposed event detection system achieved an accuracy higher than 0.90, while other similar methods reached accuracy values less than 0.74. Additionally, our proposed system was able to detect an event almost three days earlier than the other methods. Furthermore, the information provided by the system permits to understand the predominant characteristics of an event, such as keywords and emotion type of messages.

The frequency of heat waves has increased over the last years, with an impact on animal production and health, including the death of animals. Therefore, the aim of this study was to evaluate the dynamics of thermoregulation and hormonal responses in non-pregnant and pregnant ewes exposed to successive heat waves. Twenty-four non-pregnant and 18 pregnant Santa Ines ewes with black coat color (live weight: 55 ± 9.03 kg; age: 60 months) were used. Weather variables such air temperature, relative humidity, and solar radiation were continuously recorded. The rectal and tympanic temperatures and respiratory rate were measured daily. Serum triiodothyronine (T3) and prolactin were evaluated during the heat wave and thermoneutral periods. The physiological variables were higher under the heat wave conditions and were related to the activation of the thermoregulatory system for maintaining homeothermy (P 0.05). The core body temperature was higher during successive heat waves (P 0.05), as was the tympanic temperature, which are both affected by changes in air temperature (P 0.05). T3 and prolactin levels were not influenced by successive heat waves (P 0.05) and rectal temperature and respiratory rate were highest in non-pregnant ewes (P 0.05). Prolactin was not affected by temperature. The results indicate that the Santa Ines breed overcomes the thermal challenge during a heat wave without showing severe signs of thermal stress regardless of being pregnant or not.

Submitted by DOUGLAS HENRIQUE SILVA ALMEIDA (silva7henrique@hotmail.com) on 2018-09-10T23:02:08Z No. of bitstreams: 1 DISSERTAÇÃO - correções pós defesa.pdf: 1026602 bytes, checksum: 4bf6c3970fb4c49b88cfd54f2732571d (MD5) Approved for entry into archive by Neli Silvia Pereira null (nelisps@fcav.unesp.br) on 2018-09-11T13:24:12Z (GMT) No. of bitstreams: 1 almeida_dhs_me_jabo.pdf: 1026602 bytes, checksum: 4bf6c3970fb4c49b88cfd54f2732571d (MD5) Made available in DSpace on 2018-09-11T13:24:12Z (GMT). No. of bitstreams: 1 almeida_dhs_me_jabo.pdf: 1026602 bytes, checksum: 4bf6c3970fb4c49b88cfd54f2732571d (MD5) Previous issue date: 2018-06-14 Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) As bezerras leiteiras são submetidas a uma série de manejos estressantes, dentre eles a desmama. O objetivo com o presente trabalho foi avaliar o efeito da estimulação multissensorial (EM) no comportamento e desempenho de bezerras no período de peri-desmama, esperando minimizar os efeitos potenciais do estresse neste período. Foram utilizadas 28 bezerras Girolando, todas nascidas de partos eutócicos e bem colostradas. Durante a fase de cria (do 1º ao 35º dia de idade) as bezerras foram mantidas em um bezerreiro tropical, onde receberam estimulação tátil. A partir dos 47 dias de idade, os dois grupos de bezerras foram separadas, e levadas para lugares novos, sem contato visual e auditivo entre os animais de cada grupo. No grupo 1 (GM1) foram submetidas ao manejo rotineiro de desmama convencional, com o mínimo de contato com os manejadores. E no grupo 2 (GM2) receberam estimulação multissensorial (visual, tátil e auditiva) dos 50 aos 80 dias de idade e a desmama de ambos os grupos foi realizada no 70º dia de vida. O bem-estar dos animais foi avaliado mediante indicadores fisiológicos como frequência cardíaca (FC), frequência respiratória (FR) e temperatura retal (TR), indicadores de saúde como ocorrências de diarreia (DIR), pneumonia (PN), tristeza parasitária bovina (TPB) e hipertermia inespecífica (HIP); comportamentais com os testes distância de fuga (TDF), índice do novo objeto (INO), escore de condução (COND), escore composto de reatividade no tronco de contenção (REA) e velocidade de saída (VS) e indicadores de desempenho (peso corporal e ganho médio diário - GMD). O Índice de novo objeto (INO) foi gerado a partir de uma análise de componentes principais envolvendo as variáveis avaliadas no teste de novo objeto: latência de primeiro contato (LATO), interação com o novo objeto (DINO), número de interações com o novo objeto (INTO) número de quadrantes visitados durante o teste (QUADR) e a frequência de vocalização (VOC); utilizando o programa STATISTICA 7. Os dados foram analisados pelo método de modelos lineares generalizados utilizando-se o PROC GLIMMIX do programa SAS. Houve diferença significativa para o índice do novo objeto (INO) entre os grupos (p= 0.0338) aos 93 dias de vida, após a EM (GM1= -0,29 e GM2= 0,17), com melhor resposta para GM2 (EM). E para os indicadores fisiológicos, de saúde, desempenho e comportamentais, exceto o teste do novo objeto não houveram diferenças significativas entre os grupos (GM1 e GM2). Conclui-se que a EM reduziu a expressão de medo aos 93 dias de idade em bezerras leiteiras e maior exploração do ambiente no teste do novo objeto. Dairy calves are often submitted to stressful situations, among them those related to weaning procedure. The aim of this study was to evaluate the effect of multisensory stimulation (MS) on the welfare and performance of calves in the peri-weaning period, hoping to minimize the potential effects of stress that occurs during in this period. Twenty-eight Girolando calves were used, all born from normal births and received good colostrum. During the create phase (from the 1st to the 35th day of age), the calves were kept in a calves calf, where they received tactile stimulation. From the age of 47 days the calves were separated into two groups, and kept in distinct locations without visual contact between the animals of each group. In group 1 (GM1), they were submitted to routine weaning, with minimal contact with handlers. In group 2 (GM2) they received multisensory stimulation (visual, tactile and auditory) from 50 to 80 days of age. Weaning from both groups was performed on the 70th day of life. Animal welfare was evaluated using the following indicators: physiological (heart rate (HR), respiratory rate (RR) and rectal temperature (TR); (DIR), pneumonia (PN), tick born disease (TPB) and non-specific hyperthermia (HIP)); behavioral (flight distance (DF), reaction new object index (INO), conduction score (COND), reactivity score (REA) and flight speed (VS)) and performance (body weight and ADG). INO was generated from an principal component analysis involving the variables obtained in the test of new object, using the program Statistica 7. The data were analyzed by the generalized linear models, method using PROC GLIMMIX of the SAS program. There was a significant difference between the INO groups at 93 days of life (after MS), with GM2 presented the best reaction (p = 0.0338, GM1 = -0.29 and G2 = 0.17). For the other behavioral indicators and physiological, health and performance indicators, there was no significant difference between the groups (GM1 and GM2). It was concluded that MS reduced the expression of fear at 93 days of age in dairy heifers, as indicated by the greater environmental exploration during the test of the new object. 134257/2016-2