Recent research has indicated that the pupil diameter (PD) in humans varies with their affective states. However, this signal has not been fully investigated for affective sensing purposes in human-computer interaction systems. This may be due to the dominant separate effect of the pupillary light reflex (PLR), which shrinks the pupil when light intensity increases. In this dissertation, an adaptive interference canceller (AIC) system using the H∞ time-varying (HITV) adaptive algorithm was developed to minimize the impact of the PLR on the measured pupil diameter signal. The modified pupil diameter (MPD) signal, obtained from the AIC was expected to reflect primarily the pupillary affective responses (PAR) of the subject. Additional manipulations of the AIC output resulted in a processed MPD (PMPD) signal, from which a classification feature, PMPDmean, was extracted. This feature was used to train and test a support vector machine (SVM), for the identification of stress states in the subject from whom the pupil diameter signal was recorded, achieving an accuracy rate of 77.78%. The advantages of affective recognition through the PD signal were verified by comparatively investigating the classification of stress and relaxation states through features derived from the simultaneously recorded galvanic skin response (GSR) and blood volume pulse (BVP) signals, with and without the PD feature. The discriminating potential of each individual feature extracted from GSR, BVP and PD was studied by analysis of its receiver operating characteristic (ROC) curve. The ROC curve found for the PMPDmean feature encompassed the largest area (0.8546) of all the single-feature ROCs investigated. The encouraging results seen in affective sensing based on pupil diameter monitoring were obtained in spite of intermittent illumination increases purposely introduced during the experiments. Therefore, these results confirmed the benefits of using the AIC implementation with the HITV adaptive algorithm to isolate the PAR and the potential of using PD monitoring to sense the evolving affective states of a computer user.

Orientador: Walmir de Freitas Filho / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-27T12:29:12Z (GMT). No. of bitstreams: 1 Pinto_AdrianoCosta_M.pdf: 2073375 bytes, checksum: e1c68a8598816ca4909e74ba53dee76d (MD5) Previous issue date: 2015 / Resumo: A crescente demanda por energia elétrica, por vezes em ritmo mais acelerado que os investimentos em expansão das redes de distribuição, tem levado as distribuidoras a operarem próximo aos limites aceitáveis, o que torna toda a operação da rede mais complexa. Um dos desafios atuais é estabelecer um efetivo controle de tensão e potência reativa (Volt/var) na rede buscando melhorar o nível de operação e de eficiência energética da rede. Muitas propostas para encontrar a solução do problema partiram de uma abordagem de forma desacoplada: o controle de tensão e o controle de potência reativa foram resolvidos separadamente. Neste trabalho, porém, foram estudados métodos de solução do problema visando à segurança da operação e à otimização global dos recursos da rede de modo integrado, ou seja, considerando a dependência entre tensão e potência reativa. Na literatura, grande parte dos trabalhos reportam soluções baseadas em modelos elétricos da rede de distribuição. Os métodos estudados nessa dissertação são baseados em técnicas de aprendizado de máquina com o objetivo de construir um modelo capaz de utilizar apenas as medições de tensão e corrente provenientes dos medidores instalados ao longo da rede e obter o melhor despacho dos ajustes dos dispositivos de controle, sem a necessidade de um modelo elétrico do sistema. A grande vantagem de não depender dos dados e modelo elétrico do sistema está associada às imprecisões tipicamente existentes na base de dados elétricos das concessionárias de distribuição de energia elétrica. Neste contexto, primeiramente, propõe-se o uso de aprendizado por reforço, no qual o agente interage com a rede enquanto acumula experiência de operação dos controles. A implementação através do algoritmo Q-Learning permite a construção de um operador virtual da rede de distribuição a partir dos dados provenientes dos medidores instalados em determinadas barras do sistema, dos quais é extraído o estado corrente da condição de carregamento da rede. Os principais aspectos da aplicação do método ao problema de controle integrado de tensão e potência reativa são simulados em redes típicas e as capacidades de aplicação prática ao cenário atual do sistema elétrico são discutidas. Em uma segunda etapa, propõe-se utilizar um algoritmo de aprendizado supervisionado através de Máquinas de Vetores de Suporte (em inglês, Support Vector Machine ¿ SVM), uma técnica eficientemente aplicada a problemas de mineração de dados. O modelo é implementado através de técnicas de classificação, que extraem características relevantes nos conjuntos de dados, a fim de otimizar a operação da rede para cada condição de carregamento, eliminando a necessidade de repetir o treinamento do modelo ou calcular uma nova solução do problema de otimização a cada novo cenário. Discute-se o desempenho do método baseado em SVM para diferentes características de entrada. Investiga-se ainda a generalização do modelo proposto na presença de ruídos nos dados e no caso de reconfiguração da rede. Estudos em sistemas típicos de distribuição mostram que o método proposto é eficiente na solução de problemas práticos do dia-a-dia das concessionárias, principalmente em ambientes com grande volume de dados / Abstract: The growing demand for electricity, sometimes at a faster rate than investments in distribution network expansion, has led utilities operating close to acceptable limits, which makes the network operation more complex. One of current challenges is to establish an effective voltage and reactive power control, improving the operation as well as the efficiency of the distribution network. There are many methods reported to find a solutions for the voltage and reactive power problem. Most of them have adopted a decoupled form, solving the voltage control and reactive power (Volt/var) control separately. However, in this work, methods for the problem solution aiming the operation safety and the global assets optimization are approached in an integrated fashion, i. e., considering the dependence between voltage and reactive power. Most papers reports solution based on electrical models of distribution network. In this dissertation, the methods studied are based on machine learning techniques aiming to build a model with directly power meter data using capability, and set optimal dispatch of controls devices adjustments, without the need of an electrical model of the system and, therefore, not susceptible to inaccuracies of the model of the distribution network under study. Firstly, it proposes a reinforcement learning use, in which the agent interacts with the network while earns control operating experience. The implementation, thought de Q-Learning algorithm allows a construction of a distribution network virtual operation from data obtained from the meters installed on buses. From the meter data, is extracted the current state of the network loading condition. The main aspects of the application of the method to the integrated voltage and reactive power control are simulated in a typical network and the possibilities of practical application in the current scenario of the electrical system are discussed. In a second step, an algorithm for supervised learning via the Support Vector Machine (SVM), a technique applied efficiently to problems in data mining is proposed. The model is implemented by classification techniques, extracting relevant features in the data sets from the power meters in order to optimize the operation of the network for each loading condition. Thus it eliminates the need to retraining model or calculating a new optimization problem solution for each new scenario. Discusses the performance based on different features for SVM model input. Also the generalization capabilities of the proposed model in the presence of noise and in the case of network reconfiguration are studied. Studies in typical distribution systems show that proposed method is a good candidate to solve the practical problem of the system, especially in large networks with large amounts of data / Mestrado / Energia Eletrica / Mestre em Engenharia Elétrica

Problemas reais em áreas como aprendizado de máquina têm chamado atenção pela enorme quantidade de variáveis (> 10^6) e volume de dados. Em problemas dessa escala o custo para se obter e trabalhar com informações de segunda ordem são proibitivos. Tais problemas apresentam características que podem ser aproveitadas por métodos de busca em coordenada. Essa classe de métodos é caracterizada pela alteração de apenas uma ou poucas variáveis a cada iteração. A variante do método comumente descrita na literatura é a minimização cíclica de variáveis. Porém, resultados recentes sugerem que variantes aleatórias do método possuem melhores garantias de convergência. Nessa variante, a cada iteração, a variável a ser alterada é sorteada com uma probabilidade preestabelecida não necessariamente uniforme. Neste trabalho estudamos algumas variações do método de busca em coordenada. São apresentados aspectos teóricos desses métodos, porém focamos nos aspectos práticos de implementação e na comparação experimental entre variações do método de busca em coordenada aplicados a diferentes problemas com aplicações reais. / Real world problemas in areas such as machine learning are known for the huge number of decision variables (> 10^6) and data volume. For such problems working with second order derivatives is prohibitive. These problems have properties that benefits the application of coordinate descent/minimization methods. These kind of methods are defined by the change of a single, or small number of, decision variable at each iteration. In the literature, the commonly found description of this type of method is based on the cyclic change of variables. Recent papers have shown that randomized versions of this method have better convergence properties. This version is based on the change of a single variable chosen randomly at each iteration, based on a fixed, but not necessarily uniform, distribution. In this work we present some theoretical aspects of such methods, but we focus on practical aspects.

[pt] A construção de poços marítimos tem se mostrado uma atividade complexa e de alto risco. Para efetuar esta atividade as empresas se valem principalmente das unidades de intervenção de poços, também conhecidas como sondas. Estas possuem altos valores de taxas diárias de uso devido à manutenção preventiva da unidade em si, mas também por falhas as quais seus equipamentos estão sujeitos. No cenário específico da Petrobras, em junho de 2011, foi implantado no banco de dados da empresa um maior detalhamento na classificação das falhas de equipamentos de sonda. Com isso gerou-se uma descontinuidade nos registros da empresa e a demanda para adequar estes casos menos detalhados à classificação atual, mais completa. Os registros são compostos basicamente de informação textual. Para um passivo de 3384 registros, seria inviável alocar uma pessoa para classificá-los. Com isso vislumbrou-se uma ferramenta que pudesse efetuar esta classificação da forma mais automatizada possível, utilizando os registros feitos após junho de 2011 como base. O objetivo principal deste trabalho é de sanar esta descontinuidade nos registros de falha de equipamentos de sonda. Os dados foram tratados e transformados por meio de ferramentas de mineração textual bem como processados pelo algoritmo de aprendizado supervisionado SVM (Support Vector Machines). Ao final, após obter a melhor configuração do modelo, este foi aplicado às informações textuais do passivo de anormalidades, atribuindo suas classes de acordo com o novo sistema de classificação. / [en] Off-shore well construction has shown to be a complex and risky activity. In order to build off-shore wells, operators rely mainly on off-shore rigs. These rigs have an expensive day rate, related to their rental and maintenance, but also due to their equipment failure. At off-shore Petrobras scenario, on June of 2011, was implemented at the company database a better detailing on the classification of rig equipment failure. That brought a discontinuity to the database records and created a demand for adequacy of the former classification to the new classification structure. Basically, rig equipment failure records are based on textual information. For a liability of 3384 records, it was unable for one person to manage the task. Therefore, an urge came for a tool that could classify these records automatically, using database records already classified under the new labels. The main purpose of this work is to overcome this database discontinuity. Data was treated and transformed through text mining tools and then processed by supervised learning algorithm SVM (Support Vector Machines). After obtaining the best model configuration, the old records were submitted under this model and were classified according to the new classification structure.

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18872号 / 医博第3983号 / 新制||医||1008(附属図書館) / 31823 / 京都大学大学院医学研究科医学専攻 / (主査)教授 河野 憲二, 教授 古川 壽亮, 教授 髙橋 良輔 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DGAM

Rapporten undersöker hur man ska gå tillväga för att implementera en support vector machinesom kan klassificera olika former i bilder med hjälp av OpenCV libraryt i Python. Dettakommer att göras genom att beräkna scale-invariant features. De scale-invariant features somkommer undersökas är simple features och Hu moments. Dessa features ska sedantillsammans med sina tillhörande labels matas in i en SVM för träning. SVM ska därefterkunna urskilja mellan olika former baserat på deras scale-invariant feature. Rapportenundersöker även vilken av Hu moments och simple features som fungerar bäst för attklassificera former i bilder. Rapporten tittar också på tidigare forskning i området ochrapporter som täcker olika sätt att extrahera former ut bilder.Nyckelord: Flerklass klassificering, SVM, stödvektormaskin, övervakat / The report examines the possibility to implement a support vector machine that can classifydifferent shapes in images, with the help of the OpenCV library in Python. This will be donethrough calculating scale-invariant features. The scale-invariant features that will beimplemented are simple features and Hu moments. These features will in combination withtheir labels be fed to the SVM for training. The SVM should then be able to distinguishbetween different shapes based on scale-invariant features. The report will also examinewhich of the Hu moments and simple features give the best results in classifying shapes inimages. The report also looks at earlier reports in the same area and reports covering differentways of detecting shapes in images.

Predicting when a customer is about to turn to a competitor can be difficult, yet extremely valuable from a business perspective. The moment a customer stops being considered a customer is known as churn, a widely researched topic in several industries when dealing with subscription-services. However, in industries with non-subscription services and products, defining churn can be a daunting task and the existing literature does not fully cover this field. Therefore, this thesis can be seen as a contribution to current research, specially when not having a set definition for churn. A definition for churn, adjusted to DIAKRIT’s business, is created. DIAKRIT is a company working in the real estate industry, which faces many challenges, such as a huge seasonality. The prediction was approached as a supervised problem, where three different Machine Learning methods were used: Logistic Regression, Random Forest and Support Vector Machine. The variables used in the predictions are predominantly activity data. With a relatively high accuracy and AUC-score, Random Forest was concluded to be the most reliable model. It is however clear that the model cannot separate between the classes perfectly. It was also visible that the Random Forest model produces a relatively high precision. Thereby, it can be settled that even though the model is not flawless the customers predicted to churn are very likely to churn. / Att prediktera när en kund är påväg att vända sig till en konkurrent kan vara svårt, dock kan det visa sig extremt värdefullt ur ett affärsperspektiv. När en kund slutar vara kund benäms det ofta som kundbortfall eller ”churn”. Detta är ett ämne som är brett forskat på i flertalet olika industrier, men då ofta i situationer med prenumenationstjänster. När man inte har en prenumerationstjänst försvåras uppgiften att definera churn och existerande studier brister i att analysera detta. Denna uppsats kan därför ses som ett bidrag till nuvarande litteratur, i synnerhet i fall där ingen tydlig definition för churn existerar. En definition för churn, anpassad efter DIAKRIT och deras affärsstruktur har skapats i det här projektet. DIAKRIT är verksamma i fastighetsbranschen, en industri som har flera utmaningar, bland annat en extrem säsongsvariaton. För att genomföra prediktionerna användes tre olika maskininlärningamodeller: Logistisk Regression, Random Forest och Support Vector Machine. De variabler som användes är mestadels aktivitetsdata. Med relativt hög noggranhet och AUC-värde anses Random Forest vara mest pålitlig. Modellen kan dock inte separera mellan de två klasserna perfekt. Random Forest modellen visade sig också genera en hög precision. Därför kan slutsatsen dras att även om modellen inte är felfri verkar det som att kunderna predikterade som churn mest sannolikt kommer churna.

Topic of this master thesis is classification of free living data sensed with Faros. Faros is small compatible device which measure ECG and 3-axes accelerometric data. The first part of master thesis is find out how automatically measure free living activities by accelerometer and ECG. In next part was measured data of 8 activities from 10 probands. Automatic algorithms are made for this data in Matlab. This algorithms were used for this datasets and compare with manually recorded references. In the end of master thesis data were statistically evaluated.

Detta arbete presenterar en icke-destruktiv metod för att detektera och klassificera mognadsgraden hos äpplen med användning av hyperspektrala bilder. Fastställning av mognadsgraden hos äpplen är intressant för bland annat äppelodlare och musterier vid lagring och beredning. Äpplens mognadsgrad är även intressant inom växtförädling. För att fastställa mognadsgraden idag krävs att det skärs i frukten, en så kallad destruktiv metod. Hyperspektrala bilder kan idag användas inom områden som jordbruk, miljöövervakning och militär spaning. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

This thesis deals with an automatic counting of cylinders placed on the back of a truck using images taken by a camera mounted above the car. To achieve this goal, an SVM classifier based on HOG image descriptors has been trained to detect the cylinders. Further, a tracking method based on optical flow estimation has been designed to track the cylinders through image sequences. The result of the thesis is an application that counts bottles with precision 93,08 % placed on the truck and visualizes results of the detection.