Purpose In late 2019, the SARS-CoV-2 virus spread worldwide. The virus has high rates of proliferation and causes severe respiratory symptoms, such as pneumonia. The standard diagnostic method for pneumonia is chest X-ray image. There are many advantages to using COVID-19 diagnostic X-rays: low cost, fast, and widely available. Methods We propose an intelligent system to support diagnosis by X-ray images. We tested Haralick and Zernike moments for feature extraction. Experiments with classic classifiers were done. Results Support vector machines stood out, reaching an average accuracy of 89.78%, average sensitivity of 0.8979, and average precision and specificity of 0.8985 and 0.9963, respectively. Conclusion Using features based on textures and shapes combined with classical classifiers, the developed system was able to differentiate COVID-19 from viral and bacterial pneumonia with low computational cost.

In late 2019, the SARS-Cov-2 spread worldwide. The virus has high rates of proliferation and causes severe respiratory symptoms, such as pneumonia. There is still no specific treatment and diagnosis for the disease. The standard diagnostic method for pneumonia is chest X-ray image. There are many advantages to using Covid-19 diagnostic X-rays: low cost, fast and widely available. We propose an intelligent system to support diagnosis by X-ray images.We tested Haralick and Zernike moments for feature extraction. Experiments with classic classifiers were done. Support vector machines stood out, reaching an average accuracy of 89.78%, average recall and sensitivity of 0.8979, and average precision and specificity of 0.8985 and 0.9963 respectively. The system is able to differentiate Covid-19 from viral and bacterial pneumonia, with low computational cost.

In December 2019, in the city of Wuhan, capital of the Province of Central China, a new specimen of coronavirus crossed the barriers between species and hit humans for the first time. A member of the Coronaviridae family and also associated with Severe Acute Respiratory Syndrome (SARS), similarly to its predecessor, SARS-CoV, the virus was named SARS-CoV-2 [46,51]. The new coronavirus is responsible for 2019 coronavirus disease, or Covid-19, a blood disorder that strongly affects the respiratory system, causing, in mild and moderate cases, fever, dry cough, decreased or loss of sense of smell and taste.In the most severe cases, the disease leads to decreased oxygen saturation in the blood and destruction of the surfactant inside the alveoli, which can lead to collapse, causing a respiratory deficiency that can worsen until death. SARS-CoV-2

In late 2019, the SARS-Cov-2 spread worldwide. The virus has high rates of proliferation and causes severe respiratory symptoms, such as pneumonia. There is still no specific treatment and diagnosis for the disease. The standard diagnostic method for pneumonia is chest X-ray image. There are many advantages to using Covid-19 diagnostic X-rays: low cost, fast and widely available. We propose an intelligent system to support diagnosis by X-ray images. We tested Haralick and Zernike moments for feature extraction. Experiments with classic classifiers were done. Support vector machines stood out, reaching an average accuracy of 89.78%, average recall and sensitivity of 0.8979, and average precision and specificity of 0.8985 and 0.9963 respectively. The system is able to differentiate Covid-19 from viral and bacterial pneumonia, with low computational cost.

Este artigo tem como objetivo apresentar um modelo de inferência para classificar processos jurídicos relacionados à Justiça Estadual utilizando dados documentados de jurisprudência, tais como: comentários dos juízes realizados durante os veredictos, classes jurídicas do processo e UF. Os dados foram extraídos de websites de cortes judiciais, como o Portal do Tribunal de Justiça do Estado de Minas Gerais e o Poder Judiciário do Estado de Alagoas. Em toda a base de dados, foi realizada uma seleção no campo textual da descrição da sentença para extrair as leis que foram consideradas nos veredictos. Para tal seleção, o atributo de publicação e a quantidade de ocorrências da lei na base de dados foram considerados. As técnicas utilizadas para realizar a mineração de dados e classificar os processos como procedentes ou improcedentes foram a árvore de decisão e as redes neurais artificiais. Os testes realizados mostraram resultados satisfatórios e superiores ao valor comum para classificação de dados de jurisprudência, de normalmente 60%.