oalib
Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations
Souza, Murilo Barreto;Medeiros, Fabricio Witzel;Souza, Danilo Barreto;Garcia, Renato;Alves, Milton Ruiz;
Clinics , 2010, DOI: 10.1590/S1807-59322010001200002
Abstract: purpose: to evaluate the performance of support vector machine, multi-layer perceptron and radial basis function neural network as auxiliary tools to identify keratoconus from orbscan ii maps. methods: a total of 318 maps were selected and classified into four categories: normal (n = 172), astigmatism (n = 89), keratoconus (n = 46) and photorefractive keratectomy (n = 11). for each map, 11 attributes were obtained or calculated from data provided by the orbscan ii. ten-fold cross-validation was used to train and test the classifiers. besides accuracy, sensitivity and specificity, receiver operating characteristic (roc) curves for each classifier were generated, and the areas under the curves were calculated. results: the three selected classifiers provided a good performance, and there were no differences between their performances. the area under the roc curve of the support vector machine, multi-layer perceptron and radial basis function neural network were significantly larger than those for all individual orbscan ii attributes evaluated (p<0.05). conclusion: overall, the results suggest that using a support vector machine, multi-layer perceptron classifiers and radial basis function neural network, these classifiers, trained on orbscan ii data, could represent useful techniques for keratoconus detection.
Simula??o de moagem mista por rede neural artificial
Rosa, Germano Mendes;Luz, José Aurélio Medeiros da;
Rem: Revista Escola de Minas , 2012, DOI: 10.1590/S0370-44672012000200014
Abstract: this paper discusses the results of a mixed grinding simulator application based on an artificial neural network (multiple-layer perceptron using a back-propagation-like algorithm with moment). the data used came from a previous paper entitled "selective grinding of dolomite and quartz mixes". the shewhart control chart for individual values was used in order to verify the statistical stability of the simulation process results, which was useful for testing acceptance. the results have displayed good performance of this tool related to mix grinding simulation, a common issue in the mining and metallurgical sectors.
Rede neural artificial para detec o de sobremortalidade atribuível à cólera no Ceará  [cached]
Penna Maria Lúcia F
Revista de Saúde Pública , 2004,
Abstract: OBJETIVO: Avaliar as redes neurais recorrentes enquanto técnica preditiva para séries temporais em saúde. MéTODOS: O estudo foi realizado durante uma epidemia de cólera ocorrida no Estado do Ceará, em 1993 e 1994, a partir da sobremortalidade tendo como causa básica as infec es intestinais mal definidas (CID-9). O número mensal de óbitos por essa causa, referente ao período de 1979 a 1995 no Estado do Ceará, foram obtidos do Sistema de Informa o de Mortalidade (SIM) do Ministério da Saúde. Estruturou-se uma rede com dois neur nios na camada de entrada, 12 na camada oculta, um neur nio na camada de saída e um na camada de memória. Todas as fun es de ativa o eram a fun o logística. O treinamento foi realizado pelo método de backpropagation, com taxa de aprendizado de 0,01 e momentum de 0,9, com dados de janeiro de 1979 a junho de 1991. O critério para fim do treinamento foi atingir 22.000 epochs. Compararam-se os resultados com os de um modelo de regress o binomial negativa. RESULTADOS: A predi o da rede neural a médio prazo foi adequada, em dezembro de 1993 e novembro e dezembro de 1994. O número de óbitos registrados foi superior ao limite do intervalo de confian a. Já o modelo regressivo detectou sobremortalidade a partir de mar o de 1992. CONCLUS ES: A rede neural se mostrou capaz de predi o, principalmente no início do período, como também ao detectar uma altera o concomitante e posterior à ocorrência da epidemia de cólera. No entanto, foi menos precisa do que o modelo de regress o binomial, que se mostrou mais sensível para detectar aberra es concomitantes à circula o da cólera.
Ceratocone: fatores prognósticos
Elias, Rosana Molina Saraiva;Lipener, César;Uras, Ricardo;Pavês, Luis;
Arquivos Brasileiros de Oftalmologia , 2005, DOI: 10.1590/S0004-27492005000400013
Abstract: purpose: to study keratoconus disease carrier patients in an age range under the usual one and try to detect any factor which can influence in disease evolution and prognosis. methods: patients under 15 years old with a keratoconus diagnosis where analyzed. all of them answered a questionnaire, and were submitted to ocular examination and also computerized ceratoscopy. these patients were divided into three groups and went through a contact lens test: 1) it was possible for this group to adapt to contact lenses; 2) a cornea transplant for this group was recommended; 3) for this group it was suggested that they use glasses. results: patients who had 20/40 or greater visual acuity usually did not progress to transplant in the studied period. on the other hand, patients who had 20/60 or less acuity, progress to a deep transplant very quickly. other cases, related to a lower age range (10-15 years old) pregressed to a transplant. we can observe that the cornea apex has a very unsteady location, which explains the different difficulty levels regarding adaptation to contact lenses. in all patients who had a superior out of place apex and values greater than 66 d adaptation was successful. in the central apex eyes the adaptation was easier. in the inferior apex eyes it was not possible to set a standard to indicate the person for surgery. in the eyes which were adapted to the contact lenses and whose curvature was smaller than 51.10 d there were fewer chances of evolution to a cornea transplant, on comparison with patients who had a curvature of 57.60 or even greater. conclusion: patients who have curvatures greater than 57.40, acuity lower than 20/60 and are under 18 years old have more chances to evolve to a cornea transplant. when the ceratocone apex is central the contact lens adaptation becomes easier.
Central Corneal Thickness Measurement by Ultrasound versus Orbscan II  [cached]
Amir Faramarzi,Hossein Ziai
Journal of Ophthalmic & Vision Research , 2008,
Abstract: PURPOSE: To compare Orbscan II and ultrasonic pachymetry for measurement of central corneal thickness (CCT) in eyes scheduled for keratorefractive surgery. METHODS: CCT was measured using Orbscan II (Bausch & Lomb, USA) and then by ultrasonic pachymetry (Tomey SP-3000, Tomey Ltd, Japan) in 100 eyes of 100 patients with no history of ocular surgery scheduled for excimer laser refractive surgery. RESULTS: Mean CCT was 544.7±35.5 (range 453-637) μm by ultrasonic pachymetry versus 546.9±41.6 (range 435-648) μm measured by Orbscan II applying an acoustic factor of 0.92 (P=0.14). The standard deviation of measurements was greater with Orbscan pachymetry but the difference was not statistically significant. CONCLUSION: CCT measurements by Orbscan II (applying an acoustic factor) and by ultrasonic pachymetry are not significantly different; however, when CCT readings by Orbscan II are in the lower range, it is advisable to recheck the measurements using ultrasonic pachymetry.
Comparison of Eyemetrics and Orbscan automated method to determine horizontal corneal diameter  [cached]
Venkataraman Arvind,Mardi Sapna,Pillai Sarita
Indian Journal of Ophthalmology , 2010,
Abstract: Purpose: To compare horizontal corneal diameter measurements using the Orbscan Eyemetrics function and Orbscan corneal topographer. Materials and Methods: Seventy-three eyes of 37 patients were included in the study. In all cases, the automated white-to-white (WTW) measurements were obtained using Orbscan by two observers. Using the Eyemetrics function, the WTW was measured manually by the same observers from limbus to limbus using the digital caliper passing through the five point corneal reflections on the Orbscan real image. The data was analyzed using SPSS software for correlation, reliability and inter-rater repeatability. Results: The mean horizontal corneal diameter was 11.74±0.32mm (SD) with the Orbscan and 11.92±0.33mm (SD) with Eyemetrics Software-based measurement. A good positive correlation (Spearman r = 0.720, P = 0.026) was found between these two measurements. The coefficient of inter-rater repeatability was 0.89 for the Orbscan and 0.94 for the Eyemetrics software measurements on the anterior segment images. The Bland and Altman analysis showed large limits of agreement between Orbscan WTW and Eyemetrics WTW measurements. The intra-session repeatability scores for repeat measurements for the Orbscan WTW and Eyemetrics measurements were good. Conclusion: Eyemetrics can be used to measure WTW and the Eyemetrics measured WTW was longer than the WTW measured by Orbscan.
Implementa o de um sistema de controle para o rob puma 560 usando uma rede neural auto-organizável
Barreto Guilherme de A.,Dücker Christof,Araújo Aluizio F. R.,Ritter Helge
Sba: Controle & Automa??o Sociedade Brasileira de Automatica , 2002,
Abstract: Neste trabalho é proposta uma rede neural auto-organizável, chamada rede Competitiva e Hebbiana Temporal (CHT), capaz de aprender e reproduzir seqüências temporais complexas. Tais seqüências possuem elementos repetidos e/ou compartilham elementos com outras seqüências. Em ambos os casos ocorrem incertezas durante a fase de reprodu o das seqüências armazenadas, sendo estas resolvidas por meio de informa o de contexto. Pesos sinápticos competitivos codificam a parte estática das seqüências, enquanto a ordem temporal é codificada através de conex es laterais. A rede CHT faz uso eficiente de memória, pois armazena apenas uma única cópia de cada elemento repetido/compartilhado. Além disso, redundancia no armazenamento dos elementos de uma seqüência a torna tolerante a ruídos e falhas. Foi utilizada uma plataforma de controle distribuído para avaliar a rede CHT no problema de planejamento de trajetórias para controle ponto-a-ponto, em tempo real, do rob PUMA 560. A performance do sistema de controle é comparada com a de outras redes neurais.
Uso da rede neural artificial no planejamento cirúrgico da corre??o do estrabismo
Souza, Murilo Barreto;Tomikawa, Vivian Onoda;Oliveira, Bráulio Folco Telles de;Polati, Mariza;
Arquivos Brasileiros de Oftalmologia , 2004, DOI: 10.1590/S0004-27492004000300017
Abstract: purpose: to develop a neural network model for planning of the surgical strategy of patients with sensorial strabismus. methods: in this retrospective study, medical records of 95 patients with sensorial strabismus were reviewed. all patients were seen at the strabismus sector of the hospital das clínicas of the university of s?o paulo. the neural network was designed containing 3 layers. sixty-eight patients were used in the training and validation set, and 27 in the test set. results: in the 68 patients used in the training and validation set, 37 had exotropia, and 31 esotropia. the backpropagation approach was used for training the neural network. a learning rate of 0.6, and a tolerance error of 0.05 were used. in the 27 patients used in the test set, 18 had exotropia, and 9 had esotropia. the efficacy of the neural network was analyzed using the average of the difference between the indication supplied by the network and the original indication. in patients with exotropia, the average error was 0.4 mm (±0.4), for recession of the lateral rectus muscle, and 0.3 mm (±0.3), for the resection of the medial rectus muscle. in the esotropia group, the average error was 0.2 mm (±0.2) for the recession of the medial rectus muscle, and 0.5 mm (±0.3) for resection of the lateral rectus muscle. conclusion: as the artificial neural network can simulate a biological central nervous system, and is able to carry out cognitive tasks, it can be a viable option to help the surgical planning for strabismus correction.
Rede neural artificial para detec??o de sobremortalidade atribuível à cólera no Ceará
Penna,Maria Lúcia F;
Revista de Saúde Pública , 2004, DOI: 10.1590/S0034-89102004000300003
Abstract: objective: to evaluate recurrent neural networks as a predictive technique for time-series in the health field. methods: the study was carried out during a cholera epidemic which took place in 1993 and 1994 in the state of ceará, northeastern brazil, and was based on excess deaths having 'poorly defined intestinal infections' as the underlying cause (icd-9). the monthly number of deaths with due to this cause between 1979 and 1995 in the state of ceará was obtained from the ministry of health's mortality information system (sim). a network comprising two neurons in the input layer, twelve in the hidden layer, one in the output layer, and one in the memory layer was trained by backpropagation using the fist 150 observations, with 0.01 learning rate and 0.9 momentum. training was ended after 22,000 epochs. we compare the results with those of a negative binomial regression. results: ann forecasting was adequate. excessive mortality (number of deaths above the upper limit of the confidence interval) was detected in december 1993 and october/november 1994. however, negative binomial regression detected excess mortality from march 1992 onwards. conclusions: the artificial neural network showed good predictive ability, especially in the initial period, and was able to detect alterations concomitant and a subsequent to the cholera epidemic. however, it was less precise that the binomial regression model, which was more sensitive to abnormal data concomitant with cholera circulation.
Anel intracorneano de Ferrara em ceratocone
Moreira Hamilton,Oliveira Cinara Sakuma de,Godoy Glaucio de,Wahab Samia Ali
Arquivos Brasileiros de Oftalmologia , 2002,
Abstract: Objetivo: Análise dos resultados dos dez primeiros pacientes com ceratocone submetidos a implante do anel de Ferrara no Hospital de Olhos do Paraná. Métodos: Foi realizado um estudo prospectivo em 10 pacientes com ceratocone. Os critérios de inclus o foram: intolerancia a lentes de contato, acuidade visual sem corre o inferior ou igual a 20/100, ausência de cicatrizes corneanas significativas e ausência de doen as oculares ou sistêmicas que contra-indicassem a cirurgia. Acuidade visual (LogMAR), refra o e topografia pré e pós-operatórias foram as variáveis analisadas. Os pacientes foram seguidos pelo período mínimo de três meses. Resultados: Das complica es cirúrgicas encontradas, destacaram-se dois casos de microperfura o corneana durante a confec o das incis es para os túneis inferiores, um de extrus o e quatro de deslocamento pós-operatório do anel. A acuidade visual corrigida melhorou de 0,750 ± 0,374, para 0,438 ± 0,342 (p=0,026). A média da acuidade visual n o corrigida no primeiro dia pós-operatório foi de 0,667 ± 0,447 (n=9), e a acuidade visual final n o corrigida foi de 0,562 ± 0,272. De acordo com a refra o realizada após o terceiro mês pós-operatório, cinco pacientes evoluíram com acuidade visual com corre o melhor do que ou igual a 0,5 unidades LogMAR. Um paciente n o apresentou aplanamento significativo do cone segundo a topografia corneana. Conclus o: O presente estudo demonstrou melhora nos valores pós-operatórios de acuidade visual, refra o e topografia na maioria dos pacientes avaliados, em rela o aos valores pré-operatórios.
Page 1 /100
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.