RESUMO

In recent years, there has been significant growth in the development of Machine Learning (ML) models across various fields, such as image and sound recognition and natural language processing. They need to be trained with a large enough data set, ensuring predictions or results are as accurate as possible. When it comes to models for audio recognition, specifically the detection of car horns, the datasets are generally not built considering the specificities of the different scenarios that may exist in real traffic, being limited to collections of random horns, whose sources are sometimes collected from audio streaming sites. There are benefits associated with a ML model trained on data tailored for horn detection. One notable advantage is the potential implementation of horn detection in smartphones and smartwatches equipped with embedded models to aid hearing-impaired individuals while driving and alert them in potentially hazardous situations, thus promoting social inclusion. Given these considerations, we developed a dataset specifically for car horns. This dataset has 1,080 one-second-long .wav audio files categorized into two classes: horn and not horn. The data collection followed a carefully established protocol designed to encompass different scenarios in a real traffic environment, considering diverse relative positions between the involved vehicles. The protocol defines ten distinct scenarios, incorporating variables within the car receiving the horn, including the presence of internal conversations, music, open or closed windows, engine status (on or off), and whether the car is stationary or in motion. Additionally, there are variations in scenarios associated with the vehicle emitting the horn, such as its relative position-behind, alongside, or in front of the receiving vehicle-and the types of horns used, which may include a short honk, a prolonged one, or a rhythmic pattern of three quick honks. The data collection process started with simultaneous audio recordings on two smartphones positioned inside the receiving vehicle, capturing all scenarios in a single audio file on each device. A 400-meter route was defined in a controlled area, so the audio recordings could be carried out safely. For each established scenario, the route was covered with emissions of different types of horns in distinct positions between the vehicles, and then the route was restarted in the next scenario. After the collection phase, the data preprocessing involved manually cutting each horn sound in multiple one-second windowing profiles, saving them in PCM stereo .wav files with a 16-bit depth and a 44.1 kHz sampling rate. For each horn clipping, a corresponding non-horn clipping in close proximity was performed, ensuring a balanced model. This dataset was designed for utilization in various machine learning algorithms, whether for detecting horns with the binary labels, or classifying different patterns of horns by rearranging labels considering the file nomenclature. In technical validation, classifications were performed using a convolutional neural network trained with spectrograms from the dataset's audio, achieving an average accuracy of 89% across 100 trained models.

RESUMO

Objetivo: descrever as dificuldades de adaptação dos familiares cuidadores de pacientes portadores de Esclerose Lateral Amiotrófica (ELA), cadastrados na central de Medicamentos de Alto Custo da Regional de Saúde Pirineus, na cidade de Anápolis -GO. Método: Trata-se de um estudo de abordagem qualitativa com o método descritivo. Os participantes foram previamente selecionados mediante adequação aos critérios de inclusão e concordância em fazer parte da pesquisa. A coleta de dados deu-se em local escolhido pelos mesmos, por meio de entrevista gravada em smartphone. A análise dos dados deu-se concomitante e após o termino da coleta. Resultados:Para a obtenção dos resultados e discussão foram entrevistados 4 (quatro) estão apresentados em 6 categorias, sendo elas: dificuldades para o cuidado; sobrecarga do cuidador; aceitação familiar; arendizado e dúvidas dos cuidadores; sobre atendimento; adaptação para os cuidados no núcleo familiar. Diante disto evidenciou-se as implicações ligadas a equipe de saúde, que são: a necessidade da equipe de saúde se manter informada não só sobre as mudanças relacionadas a doença, como também as dificuldades enfrentadas pela família, para que seja auxiliada em relação às suas dúvidas e durante a adaptação e a progressão da doença. Conclusão:estudo procura trazer um novo olhar que vai além do paciente, evidenciando as necessidades da família, tratando não somente o paciente, mas também cada família dentro de suas particularidades

Objective:describe the adaptation difficulties of family caregivers of patients with Amyotrophic Lateral Sclerosis (ALS), registered at the High-Cost Medication center of the Pirineus Regional Health in the city of Anápolis -GO. Method:This is a qualitative approach study using a descriptive method. Participants were previously selected based on inclusion criteria and agreement to participate in the research. Data collection took place at a location chosen by them, through interviews recorded on a smartphone. Dataanalysis was conducted concurrently with and after data collection. Results:For the results and discussion, 4 (four) were interviewed and are presented in 6 categories: difficulties in care; caregiver burden; family acceptance; learning and doubts of caregivers; about care; adaptation to care in the family nucleus. This evidenced the implications linked to the health team, which are: the need for the health team to stay informed not only about changes related to the disease but also about the difficultiesfaced by the family, so that they can be assisted regarding their doubts and during the adaptation and progression of the disease. Conclusion:the study seeks to bring a new perspective that goes beyond the patient, highlighting the needs of the family, treating not only the patient but also each family within its particularities.

Objetivo: Describir las dificultades de adaptación de los cuidadores familiares de pacientes con Esclerosis Lateral Amiotrófica (ELA), registrados en el Centro de Medicamentos de Alto Costo de la Región Sanitaria Pirineus, en la ciudad de Anápolis -GO. Método:Estudio cualitativo con método descriptivo. Los participantes fueron previamente seleccionados de acuerdo con el cumplimiento de los criterios de inclusión y el acuerdo para participar en la investigación. La recolección de datos se llevó a cabo en un lugar elegido por ellos, a través de entrevistas grabadas en un teléfono inteligente. El análisis de los datos se realizó de forma concomitante y una vez finalizada la recolección de datos. Resultados:Para obtener los resultados y la discusión, 4 (cuatro) encuestados son presentados en 6 categorías, a saber: dificultades para el cuidado; carga del cuidador; aceptación familiar; y dudas de los cuidadores; sobre el servicio al cliente; Adaptación al cuidado en el núcleo familiar. Frente a esto, se evidenciaron las implicaciones relacionadas con el equipo de salud, las cuales son: la necesidad de que el equipo de salud esté informado no solo sobre los cambios relacionados a la enfermedad, sino también sobre las dificultades enfrentadas por la familia, para que puedan ser ayudados en relación a sus dudas y durante la adaptación y progresión de la enfermedad. Conclusión:este estudio busca aportar una nueva mirada que vaya más allá del paciente, resaltando las necesidades de la familia, tratando no solo al paciente, sinotambién a cada familia dentro de sus particularidades.

Assuntos

RESUMO

Antimicrobial resistance is a significant public health problem worldwide. In recent years, the scientific community has been intensifying efforts to combat this problem; many experiments have been developed, and many articles are published in this area. However, the growing volume of biological literature increases the difficulty of the biocuration process due to the cost and time required. Modern text mining tools with the adoption of artificial intelligence technology are helpful to assist in the evolution of research. In this article, we propose a text mining model capable of identifying and ranking prioritizing scientific articles in the context of antimicrobial resistance. We retrieved scientific articles from the PubMed database, adopted machine learning techniques to generate the vector representation of the retrieved scientific articles, and identified their similarity with the context. As a result of this process, we obtained a dataset labeled "Relevant" and "Irrelevant" and used this dataset to implement one supervised learning algorithm to classify new records. The model's overall performance reached 90% accuracy and the f-measure (harmonic mean between the metrics) reached 82% accuracy for positive class and 93% for negative class, showing quality in the identification of scientific articles relevant to the context. The dataset, scripts and models are available at https://github.com/engbiopct/TextMiningAMR.

Assuntos

RESUMO

This study developed a computational tool with a graphical interface and a web-service that allows the identification of phage regions through homology search and gene clustering. It uses G+C content variation evaluation and tRNA prediction sites as evidence to reinforce the presence of prophages in indeterminate regions. Also, it performs the functional characterization of the prophages regions through data integration of biological databases. The performance of PhageWeb was compared to other available tools (PHASTER, Prophinder, and PhiSpy) using Sensitivity (Sn) and Positive Predictive Value (PPV) tests. As a reference for the tests, more than 80 manually annotated genomes were used. In the PhageWeb analysis, the Sn index was 86.1% and the PPV was approximately 87%, while the second best tool presented Sn and PPV values of 83.3 and 86.5%, respectively. These numbers allowed us to observe a greater precision in the regions identified by PhageWeb while compared to other prediction tools submitted to the same tests. Additionally, PhageWeb was much faster than the other computational alternatives, decreasing the processing time to approximately one-ninth of the time required by the second best software. PhageWeb is freely available at http://computationalbiology.ufpa.br/phageweb.

RESUMO

Dam constructions in the Amazon have increased exponentially in the last decades, causing several environmental impacts and serious anthropogenic impacts in certain hydroelectric power plant reservoirs in the region have been identified. The assessment of the trophic status of these reservoirs is of interest to indicate man-made changes in the environment, but must take into account the hydrological cycle of the area. This can be relevant for environmental management actions, aiding in the identification of the ecological status of water bodies. In this context, physico-chemical parameters and eutrophication indicators were determined in a hydroelectric power plant reservoir in the Brazilian Amazon to assess trophic variations during the regional hydrological regime phases on the reservoir, namely dry, filling, full and emptying stages. The local hydrological regimes were shown to significantly influence TSS and turbidity, as well as NH4, NO3, PO4, with higher values consistently observed during the filling stage of the reservoir. In addition, differences among the sampling stations regarding land use, population and anthropogenic activities were reflected in the PO43- values during the different hydrological phases.

Assuntos

RESUMO

The mechanisms of action of physical agents commonly used to treat skeletal muscle lesions are not well understood. In this study, we examined whether the modulation of oxidative stress is involved in the beneficial effects of cold and heat on gastrocnemius muscle strain injury. Adult male Wistar rats were submitted to a strain injury and treated with therapeutic agents in an isolated or combined form. Strain damage caused an increase in muscle and blood oxidative damage. We suggest that this oxidative damage might be related to the impairment of the muscle cell structure, since we observed a significant positive correlation between increased plasma creatine kinase activity and both oxidized dichlorofluoresceine and lipid peroxidation levels in muscle and blood. The intensity of the inflammatory response appears also to be an important factor in the genesis of oxidative damage immediately following a muscle strain injury. Therapeutic cold seems to be more effective in preventing the damage induced by a strain injury, possibly due to its capacity to control the impairment of muscle cell structure and to modulate the intensity of the inflammatory response that follows a muscle strain injury.

Assuntos