Author(s): Almeida, Larissa Medeiros de
Date: 2015
Origin: Oasisbr
Subject(s): Redes Neurais Artificiais; Mal??ria - Avalia????o de gravidade; Mal??ria - An??lise Discriminante Linear; Analytic Hierarchy Process (AHP); Redes Neurais Artificiais (RNA); Linear Discriminant Analysis (LDA); ENGENHARIAS: ENGENHARIA EL??TRICA
Submitted by Kamila Costa (kamilavasconceloscosta@gmail.com) on 2015-06-15T21:53:52Z No. of bitstreams: 1 Disserta????o-Larissa M de Almeida.pdf: 5516102 bytes, checksum: e49d2bccd21168f811140c6accd54e8f (MD5)
Approved for entry into archive by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2015-06-16T15:05:39Z (GMT) No. of bitstreams: 1 Disserta????o-Larissa M de Almeida.pdf: 5516102 bytes, checksum: e49d2bccd21168f811140c6accd54e8f (MD5)
Approved for entry into archive by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2015-06-16T15:07:25Z (GMT) No. of bitstreams: 1 Disserta????o-Larissa M de Almeida.pdf: 5516102 bytes, checksum: e49d2bccd21168f811140c6accd54e8f (MD5)
Made available in DSpace on 2015-06-16T15:07:25Z (GMT). No. of bitstreams: 1 Disserta????o-Larissa M de Almeida.pdf: 5516102 bytes, checksum: e49d2bccd21168f811140c6accd54e8f (MD5) Previous issue date: 2015-04-17
N??o Informada
About half the world's population lives in malaria risk areas. Moreover, given the globalization of travel, these diseases that were once considered exotic and mostly tropical are increasingly found in hospital emergency rooms around the world. And often when it comes to experience in tropical diseases, expert opinion most of the time is not available or not accessible in a timely manner. The task of an accurate and efficient diagnosis of malaria, essential in medical practice, can become complex. And the complexity of this process increases as patients have non-specific symptoms with a large amount of data and inaccurate information involved. In this approach, Uzoka and colleagues (2011a), from clinical information of 30 Nigerian patients with confirmed malaria, used the Analytic Hierarchy Process method (AHP) and Fuzzy methodology to conduct the evaluation of the severity of malaria. The results obtained were compared with the diagnosis of medical experts. This paper develops a new methodology to evaluate the severity of malaria and compare with the techniques used by Uzoka and colleagues (2011a). For this purpose the data set used is the same of that study. The technique used is the Artificial Neural Networks (ANN). Are evaluated three architectures with different numbers of neurons in the hidden layer, two training methodologies (leave-one-out and 10-fold cross-validation) and three stopping criteria, namely: the root mean square error, early stop and regularization. In the first phase, we use the full database. Subsequently, the feature extraction methods are used: in the second stage, the Principal Component Analysis (PCA) and in the third stage, the Linear Discriminant Analysis (LDA). The best result obtained in the three phases, it was with the full database, using the criterion of regularization associated with the leave-one-out method, of 83.3%. And the best result obtained in (Uzoka, Osuji and Obot, 2011) was with the fuzzy network which revealed 80% accuracy
Cerca de metade da popula????o mundial vive em ??reas de risco da mal??ria. Al??m disso, dada a globaliza????o das viagens, essas doen??as que antes eram consideradas ex??ticas e principalmente tropicais s??o cada vez mais encontradas em salas de emerg??ncia de hospitais no mundo todo. E frequentemente quando se trata de experi??ncia em doen??as tropicais, a opini??o de especialistas na maioria das vezes est?? indispon??vel ou n??o acess??vel em tempo h??bil. A tarefa de chegar a um diagn??stico da mal??ria preciso e eficaz, fundamental na pr??tica m??dica, pode tornar-se complexa. E a complexidade desse processo aumenta ?? medida que os pacientes apresentam sintomas n??o espec??ficos com uma grande quantidade de dados e informa????o imprecisa envolvida. Nesse sentido, Uzoka e colaboradores (2011a), a partir de informa????es cl??nicas de 30 pacientes nigerianos com diagn??stico confirmado de mal??ria, utilizaram a metodologia Analytic Hierarchy Process (AHP) e metodologia Fuzzy para realizar a avalia????o da gravidade da mal??ria. Os resultados obtidos foram comparados com o diagn??stico de m??dicos especialistas. Esta disserta????o desenvolve uma nova metodologia para avalia????o da gravidade da mal??ria e a compara com as t??cnicas utilizadas por Uzoka e colaboradores (2011a). Para tal o conjunto de dados utilizados ?? o mesmo do referido estudo. A t??cnica utilizada ?? a de Redes Neurais Artificiais (RNA). S??o avaliadas tr??s arquiteturas com diferentes n??meros de neur??nios na camada escondida, duas metodologias de treinamento (leave-one-out e 10-fold cross-validation) e tr??s crit??rios de parada, a saber: o erro m??dio quadr??tico, parada antecipada e regulariza????o. Na primeira fase, ?? utilizado o banco de dados completo. Posteriormente, s??o utilizados os m??todos de extra????o de caracter??sticas: na segunda fase, a An??lise dos Componentes Principais (do ingl??s, Principal Component Analysis - PCA) e na terceira fase, a An??lise Discriminante Linear (do ingl??s, Linear Discriminant Analysis ??? LDA). O melhor resultado obtido nas tr??s fases, foi com o banco de dados completo, utilizando o crit??rio de regulariza????o, associado ao leave-one-out, de 83.3%. J?? o melhor resultado obtido em (Uzoka, Osuji e Obot, 2011) foi com a rede fuzzy onde obteve 80% de acur??cia.
