Stimulated Electromagnetic Emissions SEEs may provide important diagnostic information about space plasma composition, energetics, and dynamics during active experiments in which ground-based high powered radio waves are transmitted into the ionosphere. The nonlinear plasma processes producing this secondary radiation are not well understood particularly for some recent observations where the transmitter (pump) frequency is near the second harmonic of the electron gyro-frequency. New, more comprehensive, experimental observations of spectral features within 1kHz of the pump wave frequency are reported here in order to begin more careful comparisons of the experimental observations and a possible theoretical underpinning which is also provided. The experimental observations typically show two distinct types of secondary radiation spectra which are a) discrete narrowband harmonic spectral structures ordered by the ion gyro-frequency, so-called stimulated ion Bernstein Scatter (SIBS) and, b) broadband spectral structure with center frequency near 500 Hz and similar spectral bandwidth named ion acoustic parametric decay (IAPD). A theoretical model is provided that interprets these spectral features as resulting from parametric decay instabilities in which the pump field ultimately decays into high frequency upper hybrid/electron Bernstein and low frequency neutralized ion Bernstein and/or obliquely propagating ion acoustic waves at the upper hybrid interaction altitude. Detailed calculations of the threshold level, growth rate, unstable wavenumber and frequency bandwidth of the instabilities are provided for comparisons with experimental observations. An assessment of the effect of the critical instability parameters are provided including pump electric field strength, proximity of the pump frequency to the electron gyro-frequency and pump electric field geometry. The model shows quite reasonable agreement with the experimental observations. Next, a two dimensional Particle-In-Cell Monte-Carlo Collision computational model (PIC-MCC) is employed in order to consider nonlinear aspects such as 1) electron acceleration through wave-particle heating, 2) more complex nonlinear wave-wave processes and 3) temporal evolution of electron irregularities through nonlinear saturation. The simulation results show that the IB associated parametric decay is primarily associated with electron acceleration perpendicular to the geomagnetic field. More gyro-harmonic lines are typically associated with more intense heating. Heating is reduced when the pump frequency is sufficiently close to 2fce. The IA associated parametric decay instability is primarily associated with electron tail heating along the magnetic field and heating is reduced when the pump frequency is sufficiently close to 2fce. Characteristics of caviton collapse behavior become prevalent in this case. Results are discussed within the context of some recent experimental observations. Further discussions are provided of connections with past observed SEE spectral features and potential new diagnostic information provided by these newly categorized spectra. / Ph. D.

O Processamento e Análise Digital de Imagens é utilizado cada vez mais para agilizar processos, aumentar a precisão, segurança e confiabilidade de dados extraídos de imagens nas mais diversas áreas de pesquisa. No entanto, muitas vezes é necessário que o pesquisador faça, ele próprio, o pré-processamento das imagens, mesmo não sendo um especialista nesta área. Isto coloca em risco o próprio objetivo do uso do Processamento e Análise Digital de Imagens. Este trabalho analisa a relação dos dados extraídos de uma imagem (micrografia) através do software livre ImageJ com relação ao seu processamento final desejado, avaliando assim, a necessidade ou não, de uma ou mais sequencias de pré-processamento para adequar a imagem para o processamento final, indicando ainda quais fatores de influência apresentam informações irrelevantes ou incompletas para o processamento final utilizando ferramentas da Lógica Paraconsistente Anotada. Os resultados obtidos mostram que esta abordagem carece de informações diversificadas sobre a imagem original capturada que possam subsidiar a tomada de decisão quanto aos procedimentos necessários e, para o pré-processamento adequado ao objetivo desejado. / Processing and Analysis of Digital Images is increasingly used to streamline processes, improve accuracy, safety and reliability of data extracted from images in various research areas. However, it is often necessary for the researcher to make himself, the preprocessing of images, although not an expert in this area. This puts at risk the very purpose of using the Processing and Analysis of Digital Images. This paper analyzes the relationship of the data extracted from an image (micrograph) through the free software ImageJ, with respect to its desired final processing. Thus, evaluating the necessity or not, of one or more sequences of preprocessing to adjust the image to the final processing, further indicating which factors influence presents incomplete or irrelevant information for final processing using tools of Annotaded Paraconsistent Logic. The results show that this approach lacks diversified information about the original image captured that can support decision making about procedures for appropriate preprocessing to the desired goal.

O Processamento e Análise Digital de Imagens é utilizado cada vez mais para agilizar processos, aumentar a precisão, segurança e confiabilidade de dados extraídos de imagens nas mais diversas áreas de pesquisa. No entanto, muitas vezes é necessário que o pesquisador faça, ele próprio, o pré-processamento das imagens, mesmo não sendo um especialista nesta área. Isto coloca em risco o próprio objetivo do uso do Processamento e Análise Digital de Imagens. Este trabalho analisa a relação dos dados extraídos de uma imagem (micrografia) através do software livre ImageJ com relação ao seu processamento final desejado, avaliando assim, a necessidade ou não, de uma ou mais sequencias de pré-processamento para adequar a imagem para o processamento final, indicando ainda quais fatores de influência apresentam informações irrelevantes ou incompletas para o processamento final utilizando ferramentas da Lógica Paraconsistente Anotada. Os resultados obtidos mostram que esta abordagem carece de informações diversificadas sobre a imagem original capturada que possam subsidiar a tomada de decisão quanto aos procedimentos necessários e, para o pré-processamento adequado ao objetivo desejado. / Processing and Analysis of Digital Images is increasingly used to streamline processes, improve accuracy, safety and reliability of data extracted from images in various research areas. However, it is often necessary for the researcher to make himself, the preprocessing of images, although not an expert in this area. This puts at risk the very purpose of using the Processing and Analysis of Digital Images. This paper analyzes the relationship of the data extracted from an image (micrograph) through the free software ImageJ, with respect to its desired final processing. Thus, evaluating the necessity or not, of one or more sequences of preprocessing to adjust the image to the final processing, further indicating which factors influence presents incomplete or irrelevant information for final processing using tools of Annotaded Paraconsistent Logic. The results show that this approach lacks diversified information about the original image captured that can support decision making about procedures for appropriate preprocessing to the desired goal.

In this thesis, we analyze the performance of the Post Detection Integration (PDI) techniques used for detection of weak DS/CDMA signals in the presence of uncertainty in the frequency, noise variance and data bits. Such weak signal detection problems arise, for example, in the first step of code acquisition for applications such as the Global Navigation Satellite Systems (GNSS) based position localization. Typically, in such applications, a combination of coherent and post-coherent integration stages are used to improve the reliability of signal detection. We show that the feasibility of using fully coherent processing is limited due to the presence of unknown data-bits and/or frequency uncertainty. We analyze the performance of the two conventional PDI techniques, namely, the Non-coherent PDI (NC-PDI) and the Differential-PDI (D-PDI), in the presence of noise and data bit uncertainty, to establish their robustness for weak signal detection. We show that the NC-PDI technique is robust to uncertainty in the data bits, but a fundamental detection limit exists due to uncertainty in the noise variance. The D-PDI technique, on the other hand, is robust to uncertainty in the noise variance, but its performance degrades in the presence of unknown data bits. We also analyze the following different variants of the NC-PDI and D-PDI techniques: Quadratic NC-PDI technique, Non-quadratic NC-PDI, D-PDI with real component (D-PDI (Real)) and D-PDI with absolute component (D-PDI (Abs)). We show that the likelihood ratio based test statistic derived in the presence of data bits is non-robust in the presence of noise uncertainty. We propose two novel PDI techniques as a solution to the above mentioned shortcomings in the conventional PDI methods. The first is a cyclostationarity based sub-optimal PDI technique, that exploits the periodicity introduced due to the data bits. We establish the exact mathematical relationship between the D-PDI and cyclostationarity-based signal detection methods. The second method we propose is a modified PDI technique, which is robust against both noise and data bit uncertainties. We derive two variants of the modified technique, which are tailored for data and pilot channels, respectively. We characterize the performance of the conventional and proposed PDI techniques in terms of their false alarm and detection probabilities and compare them through the receiver operating characteristic (ROC) curves. We derive the sample complexity of the test-statistic in order to achieve a given performance in terms of detection and false alarm probabilities in the presence of model uncertainties. We validate the theoretical results and illustrate the improved performance that can be obtained using our proposed PDI protocols through Monte-Carlo simulations.

Made available in DSpace on 2017-07-21T14:19:27Z (GMT). No. of bitstreams: 1 Elvis Canteri.pdf: 1285842 bytes, checksum: f2c5d9e754ae68692d585d59818e0e5f (MD5) Previous issue date: 2015-09-11 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Nitrogen (N) is a nutrient that is directly related to the plants development and proper nitrogen fertilization can provide harvest in less time and increase productivity. The N have been handled incorrectly and often non-satisfactory supplied to the land. Proper management depends on constant monitoring of nutritional status that can be accomplished by predicting the leaf nitrogen content. This work aims to evaluate digital image processing algorithms, in order to establish a valid method to estimate the nutritional stress of N (nitrogen) on maize, and the feasibility of its implementation on mobile devices using photos sampled in the field under natural lighting environment. It was found that the thresholding process should use the HSV factor, more suitable under natural light if the sampling in the field was conducted between 11:15 am and 14:55. Among the algorithms we highlight the results of the DGCI (Dark Green Color Index) obtained from factor HSV (Hue, Saturation, Vibration), with significant correlation to leaf analysis of corn (R² = 0.92) and the adoption of NDVI (Normalized Difference Vegetation Index) obtained from the RGB histogram (Red, Green, Blue). This is the same method studied considering the FieldScout CM 1000 and GreenSeeker chlorophyll meters used in this research. No significant correlation among the readings was found when considering values from chlorophyll meters obtained in any moment of the day or from different light conditions. However, there is a positive correlation among the FieldScout CM 1000 and GreenSeeker, corresponding to sampling among 11h16m and 14h32m (R² = 0.75) and among 12h15m and 14h53m (R² = 0.92), as well is possible to estimate the IRC of maize based on the DGCI to V5 to V7 phenological stages directly at crop field using a mobile device. / O nitrogênio (N) é um nutriente que é diretamente relacionado ao desenvolvimento das plantas e a adubação nitrogenada adequada pode proporcionar a colheita em menor tempo e com aumento na produtividade. O N vêm sendo manejado incorretamente e frequentemente suprido de modo insatisfatório pelo solo. O manejo adequado depende do monitoramento constante do estado nutricional que pode ser realizado estimando-se o teor de N foliar. O objetivo principal deste trabalho visa qualificar a utilização de algoritmos de processamento digital de imagens, com a finalidade de estabelecer um método válido para estimar o estresse nutricional de N (nitrogênio) da cultura do milho, bem como a viabilidade de sua implementação em dispositivos móveis, utilizando fotos amostradas em ambiente de campo sob iluminação natural. Constatou-se que o processo de limiarização deve ter base no fator HSV, mais adequado sob iluminação natural se considerarmos a amostragem em ambiente de campo, compreendido entre as 11h15min e 14h55min. Dentre os algoritmos destacam-se os resultados do DGCI (Dark Green Color Index) obtido do fator HSV (Hue, Saturation, Vibration), com significativa correlação para análise foliar do milho (R²=0,92) e a adoção do NDVI (Normalized Difference Vegetation Index) obtido a partir do histograma RGB (Red, Green, Blue), sendo o mesmo método investigado com o uso dos clorofilômetros FieldScout CM 1000 e GreenSeeker, Não há correlação significativa entre as leituras efetuadas pelos clorofilômetros se forem consideradas leituras em qualquer momento do dia e sob diversas condições de luminosidade. Porém, há correlação positiva das leituras dos clorofilômetros FieldScout CM 1000 e GreenSeeker, correspondendo a amostragem entre as 11h16m e 14h32m (R²=0,75) e entre as 12h15m e 14h53m (R²=0,92), bem como torna-se possível estimar o IRC da cultura do milho com base no DGCI para o estádio fenológico V5 a V7 em ambiente de campo utilizando um dispositivo móvel.

Made available in DSpace on 2017-07-21T14:19:28Z (GMT). No. of bitstreams: 1 Teruo Matos.pdf: 2738201 bytes, checksum: 54ed354d6ee1a18f2c735e38746cafc8 (MD5) Previous issue date: 2016-09-30 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The study of roots is used to monitor and optimize the uptake of water and nutrients. The evaluation of the plant root system by traditional methods is slow, exhaustive, complex and in many cases does not provide the required accuracy. This research aimed to develop a computational method to assist in the assessing of the average diameter and length of root maize. It was developed using Java programming language, JavaCV interface, and OpenCV library, subsequently its accuracy was compared to the traditional methods and the macro IJ_Rhizo accuracy, for measuring the average diameter and length of roots. The tests were performed using images of maize roots with 300 dpi and using images of nylon threads with resolutions of 300 dpi and 600 dpi. The method validation was performed using nylon thread samples with known lengths and diameters. For length measurements, the proposed method obtained coefficients of variation from 0.05% to 3.80% and 0.06% to 9,27%, with 300 dpi and 600 dpi images, respectively. For diameter measurements, the proposed method obtained coefficients of variation from 0.23% to 77.49% and 0.54% to 96,61%, with 300 dpi and 600 dpi images, respectively. The proposed method obtained coefficients of variation lower than traditional methods for length and diameter measurements, and the macro IJ_Rhizo in more than 95% of test cases. Thus, the presented method is shown to be the most appropriate, and with greater accuracy for measurement of average diameter and length of root, among the assessed methods. / O estudo de raízes é usado para monitorar e otimizar a utilização de água e nutrientes pelas plantas. A avaliação do sistema radicular de plantas por meio dos métodos tradicionais é demorada, exaustiva, complexa e, em muitos casos, não fornece a acurácia necessária. Este trabalho teve como objetivo desenvolver um método computacional que auxiliasse na avaliação do diâmetro médio e comprimento radicular da cultura de milho. Ele foi desenvolvido utilizando a linguagem de programação Java, a interface JavaCV, e a biblioteca OpenCV, posteriormente a acurácia dele foi comparado a dos métodos tradicionais e a da macro IJ_Rhizo, para medição do comprimento e do diâmetro médio de raízes. Os testes foram realizados utilizando imagens de raízes de milho com 300 dpi e imagens de fios de náilon com 300 dpi e 600 dpi. A validação do método foi realizada utilizando amostras de fios de náilon com comprimento e diâmetros conhecidos. Para as medidas de comprimento, o método proposto obteve coeficientes de variação de 0,05% a 3,80% e de 0,06% a 9,27%, com imagens de 300 dpi e 600 dpi, respectivamente. Para as medidas de diâmetro, o método proposto obteve coeficientes de variação de 0,23% a 77,49% e de 0,54% a 96,61% , com imagens de 300 e 600 dpi, respectivamente. O método proposto obteve coeficientes de variação inferiores aos métodos tradicionais para a medição do comprimento e do diâmetro, e a macro IJ_Rhizo em mais de 95% dos casos de teste. Assim, o método apresentado mostra-se o mais adequado e o com maior acurácia para a medição do comprimento e diâmetro radicular médio dentre os métodos avaliados.

[pt] O presente trabalho teve por objetivo mapear a logística na gestão do portfólio de projetos de pesquisa, desenvolvimento e inovação tecnológica do Programa regulado de P e D da ANEEL. Desenvolvido no contexto regulatório e empresarial, avalia em que medida a realização desses projetos resultam em benefícios econômicos para concessionária. O trabalho examinou (i) gargalos que dificultam a apropriação dos resultados dos projetos de P e D pela própria concessionária e (ii) os aspectos motivacionais induzidos pela introdução de políticas públicas de incentivo ao setor. Esse foi o caso da Lei 9991/2000 que cria condições favoráveis à sustentabilidade corporativa e à introdução de inovações no mercado das concessionárias distribuidoras de energia elétrica pela aplicação de um percentual da sua receita operacional líquida no desenvolvimento de projetos de P e D. Os resultados da pesquisa confirmam uma tendência de crescimento dos montantes anuais de investimento no Programa e uma determinação de concentrar recursos num número menor de projetos direcionados às linhas de pesquisa de maior relevância da concessionária. A maioria dos projetos foi desenvolvida por universidades, com ou sem parceria com outras instituições, por um valor médio mais baixo do que o praticado pelas demais instituições executoras. Já as indústrias não tomam a iniciativa de propor projetos de P e D, provavelmente por não disporem de laboratórios próprios. Como medida para evitar a pulverização dos recursos de pesquisa observou-se uma preocupação do gestor em concentrar recursos em iniciativas de centros de pesquisa comprometidos com a solução de temas relevantes que têm afligindo o setor. / [en] The present study aimed to map the logistics management of the portfolio of R, D and I (research, technological development and innovation) projects developed under the ANEEL regulated Program. Developed under the regulatory and business environment, it assesses the extent to which the realization of these projects results in economic benefits to the energy concessionaire. The study examined (i) bottlenecks that hinder the appropriation of the results achieved by the R, D and I projects contracted by the concessionaire and (ii) the motivational aspects induced by the introduction of public policies to incite the sector. This was the case of the 9991/2000-Act that created favourable conditions for corporate sustainability and the introduction of innovations in the market of electric energy operated by distribution concessionaires as it defines that a percentage of the net operating revenues must be applied in the development of R, D and I projects. The results of the survey carried out confirm a growing trend of the annual investment in the program and a determination to concentrate resources on fewer projects targeted to areas of research most relevant to the concessionaire. Most projects were developed by universities, with or without partnership with other institutions, for an average of investments lower than that charged by other executing agencies. The reason why industries do not take the initiative to propose R and D projects may be explained by the fact that they do not have their own laboratories. As a measure to avoid spraying of research resources there was a concern of the manager to concentrate resources on initiatives of research centres committed to the solution of important issues that have afflicted the sector.

Magister Commercii - MCom / The study has three objectives; firstly to assess the (manner of) implementation of black economic empowerment (BEE) principles by casino licence operators in the Western Cape, namely GrandWest, Casino Mykonos, and Caledon Casino & Spa, during the construction and initial operation phases; secondly, to discuss casino gambling from a marketing strategy theory perspective; and thirdly, to measure consumer behaviour theory as demonstrated by casino patrons. Government(s) and casino industry executives present casino gambling as a source of revenue and employment, and disregard the social costs incurred by society in the production of this revenue and employment sustenance.This study is an evaluability assessment study where reports from the Western Cape Gambling and Racing Board‟s social equity committee where used for the objective of the study. As a result, the sample of the study was formed by the three above-mentioned casinos that were operating in the Western Cape at the beginning of the project. The proposed government strategy on Black Economic Empowerment (BEE) was critiqued to try and understand the government‟s position relative to the initiative. The social equity committee monitoring reports where analysed to assess the performance of casino operators relative to their BEE undertakings in their licences. Data formed by reports and literature has been summarised and presented to try and help in clarifying the position of casino gambling on black economic empowerment and specifically the (economic) empowering of host communities and society at large.Recommendations where made with the view highlighting the need for a strategy towards greater empowerment of host communities. As a result, the researcher suggests that further research be conducted into the relationship between the profitability of a casino and proliferation of social problems attributed directly to the presence of a casino complex.

The aim was to investigate the strategies adopted for the preparation of the Institutional Development Plan (IDP) at the Federal University of Santa Maria (UFSM) and the Federal University of Paraná (UFPR). To conduct this study used a qualitative approach through a case study. The research was descriptive, so that the insights presented the planning team and UFSM UFPR regarding strategies for the preparation of the IDP. With regard to the object of the study was to research and internal documents UFSM UFPR. The subjects of this study were the Deans and Technical-administrative planning team who work or worked in the IDP of the institutions under study were applied in the research tool compounds with nineteen open questions. The research was through the internet. This study investigates the process of PDI in UFSM UFPR and analysis in the following categories: preparation, implementation, monitoring and evaluation, and difficulties. The strategies adopted in the IDP (2011-2015) / UFSM showed that the institution is concerned with the management of knowledge, collective decisions, with the widest possible participation of the university community in the IDP process. Strategies PDI (2012-2016) / UFPR were deliberated by the Central Administration, which determined the modules, themes and units responsible, showing formal characteristics in the process, the strategies were flexible, participatory, and dynamic. The 2nd category analysis of the IDP implementation, monitoring and evaluation can be concluded that the two institutions experiencing different moments of this phase. The main barriers identified in implementing the IDP / (2011-2015) / UFSM were the lack of a monitoring system of actions, lack of knowledge of the actions contained in the IDP and the lack of culture of planning. UFPR in the process of IDPs (2012-2016) is to have recent reviews. The research found that the process of sensitization in IFESs PDI should preferably be initiated early in the process, because the main factor to be discredited PDI and lack of knowledge of the importance of it, so that should be performed an intense raising the university community. / O objetivo foi investigar as estratégias adotadas para a elaboração do Plano de Desenvolvimento Institucional (PDI) na Universidade Federal de Santa Maria (UFSM) e Universidade Federal do Paraná (UFPR). Para realizar este estudo utilizou-se uma abordagem qualitativa por meio de estudo de caso. A pesquisa foi descritiva, de maneira que apresentou as percepções da equipe de planejamento da UFSM e UFPR em relação às estratégias para a elaboração do PDI. No que diz respeito ao objeto do estudo foi realizada a pesquisa em documentos internos da UFSM e UFPR. Os sujeitos deste estudo foram os Pró-Reitores e Técnico-administrativos da equipe de planejamento que trabalham ou trabalharam no PDI das instituições em estudo, aos quais foram aplicados o instrumento de pesquisa compostos com dezenove perguntas abertas. A pesquisa foi por meio da internet. Este estudo buscou analisar o processo do PDI na UFSM e UFPR nas seguintes categorias de análise: elaboração; implementação, controle e avaliação; e dificuldades. As estratégias adotadas no PDI(2011-2015)/UFSM mostraram que a instituição está preocupada com a gestão do conhecimento, com as decisões coletivas, com a maior participação possível da comunidade universitária no processo do PDI. As estratégias PDI(2012-2016)/UFPR foram deliberadas pela Administração Central, que determinou os módulos, temas e unidades responsáveis, mostrando características formais no processo, as estratégias foram: flexíveis; participativas; e dinâmicas. A 2ª categoria de análise do PDI a implementação, controle e avaliação pode-se concluir que as duas instituições vivenciam momentos distintos desta fase. As principais barreiras identificadas na implementação do PDI/(2011-2015)/UFSM foram a falta de um sistema de acompanhamento das ações, falta de conhecimento das ações constantes no PDI e a falta da cultura do planejamento. Na UFPR, o processo do PDI/(2012-2016) é recente para ter avaliações. A pesquisa verificou que o processo de sensibilização ao PDI nas IFESs deve ser desencadeado de preferência no inicio do processo, devido o principal fator ser o descrédito ao PDI e falta de conhecimento da importância do mesmo, de maneira que deve ser realizado um intenso trabalho de sensibilização a comunidade universitária.

Submitted by Lucienne Costa (lucienneferreira@ufcg.edu.br) on 2018-04-25T18:49:44Z No. of bitstreams: 1 GIRLENE LIMA RIBEIRO – DISSERTAÇÃO (PPGEE) 2017.pdf: 3769966 bytes, checksum: 1e2c04beeac23084837591c1bfec0869 (MD5) / Made available in DSpace on 2018-04-25T18:49:44Z (GMT). No. of bitstreams: 1 GIRLENE LIMA RIBEIRO – DISSERTAÇÃO (PPGEE) 2017.pdf: 3769966 bytes, checksum: 1e2c04beeac23084837591c1bfec0869 (MD5) Previous issue date: 2017-03-31 / CNPq / Nesta pesquisa é desenvolvida uma metodologia para aprimoramento da classificação de isoladores poliméricos por medições termográficas e radiação UV utilizando o Processamento Digital de Imagens (PDI) e Redes Neurais Artificiais (RNAs). A metodologia é baseada na análise da ocorrência de descargas corona e nas variações de temperatura ao longo do isolador a fim de classificá-los quanto seu estado de degradação. Cada isolador utilizado foi submetido à tensão de 133 kV fase-terra durante um período de 30 minutos, com o objetivo de ocasionar aquecimento e evidenciar descargas corona nos isoladores. As medições foram realizadas utilizando um detector de corona para medição de UV e os dados de temperatura foram adquiridos utilizando-se um termovisor. As imagens adquiridas pelos instrumentos de monitoramento, durante os ensaios, foram submetidas a um processamento digital de imagem, para extrair informações de densidade de pixels, persistência das descargas e distâncias relativas das áreas de descargas ao isolador. A partir de informações obtidas de imagens de infravermelho (temperatura) foi aplicada a estatística descritiva e o teste discriminante de Fisher, para apresentar ao sistema de classificação, parâmetros objetivos e com alto nível de separabilidade. O sistema de classificação utilizou RNA para determinar o estado de degradação dos isoladores. A classificação foi realizada de forma individual e combinada, com vetores formados pelos atributos UV e infravermelho. O sistema desenvolvido permitiu o auxílio à tomada de decisões quanto à necessidade de intervenção ou não aos isoladores. A classificação dos isoladores, de forma individual, obteve acurácia média para temperatura de 80,00% e UV 74,05%. A classificação dos isoladores, de forma combinada (UV e infravermelho), obteve acurácia média de 92,58%, evidenciando o aprimoramento na classificação. / This research presents a methodology for the improvement of the classification of polymeric insulators by using thermographic measurements and UV radiation in combination with Digital Image Processing (DIP) and Artificial Neural Networks (ANNs). The methodology is based on the analysis of the occurrence of corona discharges and temperature variations along the insulator in order to classify their stage of degradation. Each insulator was subjected to the 133 kV phase-to-ground voltage over a period of 30 minutes, in order to cause heating and corona discharges in the insulators. The experiments were performed using a corona detector for UV measurement and the temperature data were acquired using a thermal imager. The images acquired by the monitoring instruments during the tests were subjected to digital image processing to extract information of pixel density, persistence of discharges and relative distances from the discharge areas to the insulator. From information obtained through infrared (temperature) images descriptive statistics and Fisher's discriminant test were applied to present objective parameters with high level of separability to the classification system. The classification system used ANN to determine the insulators degradation state. The classification was performed in individual and in combination ways, with vectors formed by UV and infrared attributes. The developed system helped on the decision making, concerning to the necessity of intervention or not to the insulators. The classification of the insulators, in an individual way, obtained accuracy for temperature of 80.00% and UV 74.05%. The classification of the isolators, combined (UV and infrared), obtained an average accuracy of 92.58%, evidencing the improvement in the classification.