Universidade de Pernambuco

About: Universidade de Pernambuco is a education organization based out in Recife, Brazil. It is known for research contribution in the topics: Population & Artificial neural network. The organization has 6147 authors who have published 6948 publications receiving 73648 citations.

A multimodal approach using deep learning for fall detection

Abstract: A computational system able to automatically and efficiently detect and classify falls would be beneficial for monitoring the elderly population and speed up the assistance proceedings, reducing the risk of prolonged injuries and death. One of the most common problems in such systems is the high number of false-positives in their recognition scheme, which may cause an overload on surveillance system calls. We address this problem by proposing different topologies of a multimodal convolution neural network, which is trained to detect falls based on RGB images and information from accelerometers. We train and evaluate our networks with the UR Fall Detection dataset and UP-Fall dataset, and provide an extensive comparison with state-of-the-art models. Our model reached good results on UR Fall Detection dataset and achieved the state-of-art on UP-Fall detection dataset, relying on easily available sensors to do so, demonstrating it can be a scalable solution for robust fall detection in the real world.

Cutaneous leishmaniasis in northeastern Brazil: a critical appraisal of studies conducted in State of Pernambuco

Abstract: American cutaneous leishmaniasis (ACL) is a complex disease with clinical and epidemiological features that may vary from region to region. In fact, at least seven different Leishmania species, including Leishmania (Viannia) braziliensis, Leishmania (Viannia) guyanensis, Leishmania (Viannia) lainsoni, Leishmania (Viannia) naiffi, Leishmania (Viannia) shawi, Leishmania (Viannia) lindenbergi, and Leishmania (Leishmania) amazonensis, have been implicated in the etiology of ACL in Brazil, and numerous phlebotomine sandfly species of the genus Lutzomyia have been regarded as putative or proven vectors. Because ACL is a focal disease, understanding the disease dynamics at the local level is essential for the implementation of more effective control measures. The present paper is a narrative review about the ACL epidemiology in Pernambuco, northeastern Brazil. Furthermore, the need for more effective diagnosis, treatment, control and prevention strategies for the affected populations is highlighted. This paper will provide researchers with a critical appraisal of ACL in Pernambuco. Hopefully, it will also be helpful for public health authorities to improve current control strategies against ACL at the state and country levels.

Perfil epidemiológico da tuberculose no Município de Teresina-PI, no período de 1999 a 2005

Abstract: Summary This work describes the epidemiological features of tuberculosis in the city of Teresina, Piaui State, Brazil, from 1999 to 2005. This is a descriptive epidemiologic study of historical series on newly reported tuberculosis cases among residents of Teresina, State of Piaui, by analyzing their demographic, socioeconomic and clinical characteristics. Data were collected from the Information System for Notifiable Diseases (Sinan) and from the Information System on Mortality in Teresina. The median incidence rate of new cases was 50.1/100,000 population and the mean mortality coefficient was 3.3/100,000 population. The disease has affected mostly males (64.0%), those who had less than 7 ye ars of formal education (70.33%) and in young adults (58.8%), although the highest incidence rate was found in the age group of 50 and over. Pulmonary tuberculosis was found in 80.23% of all cases. As for the course of the disease, 71.07% of patients were cured and 17.15% were transferred from one health service to another. This study has helped understand the characteristics of the population studied and the difficulties of the Tuberculosis Control Program in the city of Teresina as far as Sinan is concerned.