A Clinical Support System Based on Quality of Life Estimation

Quality of life is a concept influenced by social, economic, psychological, spiritual or medical state factors. More specifically, the perceived quality of an individual's daily life is an assessment of their well-being or lack of it. In this context, information technologies may help on the management of services for healthcare of chronic patients such as estimating the patient quality of life and helping the medical staff to take appropriate measures to increase each patient quality of life. This paper describes a Quality of Life estimation system developed using information technologies and the application of data mining algorithms to access the information of clinical data of patients with cancer from Otorhinolaryngology and Head and Neck services of an oncology institution. The system was evaluated with a sample composed of 3013 patients. The results achieved show that there are variables that may be significant predictors for the Quality of Life of the patient: years of smoking (p value 0.049) and size of the tumor (p value < 0.001). In order to assign the variables to the classification of the quality of life the best accuracy was obtained by applying the John Platt's sequential minimal optimization algorithm for training a support vector classifier. In conclusion data mining techniques allow having access to patients additional information helping the physicians to be able to know the quality of life and produce a well-informed clinical decision.

Intelligent decision support to predict patient barotrauma risk in intensive care units

The occurrence of Barotrauma is identified as a major concern for health professionals, since it can be fatal for patients. In order to support the decision process and to predict the risk of occurring barotrauma Data Mining models were induced. Based on this principle, the present study addresses the Data Mining process aiming to provide hourly probability of a patient has Barotrauma. The process of discovering implicit knowledge in data collected from Intensive Care Units patientswas achieved through the standard process Cross Industry Standard Process for Data Mining. With the goal of making predictions according to the classification approach they several DM techniques were selected: Decision Trees, Naive Bayes and Support Vector Machine. The study was focused on identifying the validity and viability to predict a composite variable. To predict the Barotrauma two classes were created: “risk” and “no risk”. Such target come from combining two variables: Plateau Pressure and PCO2. The best models presented a sensitivity between 96.19% and 100%. In terms of accuracy the values varied between 87.5% and 100%. This study and the achieved results demonstrated the feasibility of predicting the risk of a patient having Barotrauma by presenting the probability associated.

A drug administration decision support system

Drug delivery is one of the most common clinical routines in hospitals, and is critical to patients' health and recovery. It includes a decision making process in which a medical doctor decides the amount (dose) and frequency (dose interval) on the basis of a set of available patients' feature data and the doctor's clinical experience (a priori adaptation). This process can be computerized in order to make the prescription procedure in a fast, objective, inexpensive, non-invasive and accurate way. This paper proposes a Drug Administration Decision Support System (DADSS) to help clinicians/patients with the initial dose computing. The system is based on a Support Vector Machine (SVM) algorithm for estimation of the potential drug concentration in the blood of a patient, from which a best combination of dose and dose interval is selected at the level of a DSS. The addition of the RANdom SAmple Consensus (RANSAC) technique enhances the prediction accuracy by selecting inliers for SVM modeling. Experiments are performed for the drug imatinib case study which shows more than 40% improvement in the prediction accuracy compared with previous works. An important extension to the patient features' data is also proposed in this paper.

Apprentissage de représentations sur-complètes par entraînement d’auto-encodeurs

Les avancés dans le domaine de l’intelligence artificielle, permettent à des systèmes informatiques de résoudre des tâches de plus en plus complexes liées par exemple à la vision, à la compréhension de signaux sonores ou au traitement de la langue. Parmi les modèles existants, on retrouve les Réseaux de Neurones Artificiels (RNA), dont la popularité a fait un grand bond en avant avec la découverte de Hinton et al. [22], soit l’utilisation de Machines de Boltzmann Restreintes (RBM) pour un pré-entraînement non-supervisé couche après couche, facilitant grandement l’entraînement supervisé du réseau à plusieurs couches cachées (DBN), entraînement qui s’avérait jusqu’alors très difficile à réussir. Depuis cette découverte, des chercheurs ont étudié l’efficacité de nouvelles stratégies de pré-entraînement, telles que l’empilement d’auto-encodeurs traditionnels(SAE) [5, 38], et l’empilement d’auto-encodeur débruiteur (SDAE) [44]. C’est dans ce contexte qu’a débuté la présente étude. Après un bref passage en revue des notions de base du domaine de l’apprentissage machine et des méthodes de pré-entraînement employées jusqu’à présent avec les modules RBM, AE et DAE, nous avons approfondi notre compréhension du pré-entraînement de type SDAE, exploré ses différentes propriétés et étudié des variantes de SDAE comme stratégie d’initialisation d’architecture profonde. Nous avons ainsi pu, entre autres choses, mettre en lumière l’influence du niveau de bruit, du nombre de couches et du nombre d’unités cachées sur l’erreur de généralisation du SDAE. Nous avons constaté une amélioration de la performance sur la tâche supervisée avec l’utilisation des bruits poivre et sel (PS) et gaussien (GS), bruits s’avérant mieux justifiés que celui utilisé jusqu’à présent, soit le masque à zéro (MN). De plus, nous avons démontré que la performance profitait d’une emphase imposée sur la reconstruction des données corrompues durant l’entraînement des différents DAE. Nos travaux ont aussi permis de révéler que le DAE était en mesure d’apprendre, sur des images naturelles, des filtres semblables à ceux retrouvés dans les cellules V1 du cortex visuel, soit des filtres détecteurs de bordures. Nous aurons par ailleurs pu montrer que les représentations apprises du SDAE, composées des caractéristiques ainsi extraites, s’avéraient fort utiles à l’apprentissage d’une machine à vecteurs de support (SVM) linéaire ou à noyau gaussien, améliorant grandement sa performance de généralisation. Aussi, nous aurons observé que similairement au DBN, et contrairement au SAE, le SDAE possédait une bonne capacité en tant que modèle générateur. Nous avons également ouvert la porte à de nouvelles stratégies de pré-entraînement et découvert le potentiel de l’une d’entre elles, soit l’empilement d’auto-encodeurs rebruiteurs (SRAE).

A Note on the Generalization Performance of Kernel Classifiers with Margin

We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the $V_gamma$ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.

On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces

This paper presents a computation of the $V_gamma$ dimension for regression in bounded subspaces of Reproducing Kernel Hilbert Spaces (RKHS) for the Support Vector Machine (SVM) regression $epsilon$-insensitive loss function, and general $L_p$ loss functions. Finiteness of the RV_gamma$ dimension is shown, which also proves uniform convergence in probability for regression machines in RKHS subspaces that use the $L_epsilon$ or general $L_p$ loss functions. This paper presenta a novel proof of this result also for the case that a bias is added to the functions in the RKHS.

Multiclassificador inteligente de falhas no domínio do tempo em motores de indução trifásicos alimentados por inversores de frequência

Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes.

Aplicação de técnicas inteligentes com análise no domínio do tempo para reconhecimento de defeitos em motores de indução trifásicos

Os motores de indução trifásicos são os principais elementos de conversão de energia elétrica em mecânica motriz aplicados em vários setores produtivos. Identificar um defeito no motor em operação pode fornecer, antes que ele falhe, maior segurança no processo de tomada de decisão sobre a manutenção da máquina, redução de custos e aumento de disponibilidade. Nesta tese são apresentas inicialmente uma revisão bibliográfica e a metodologia geral para a reprodução dos defeitos nos motores e a aplicação da técnica de discretização dos sinais de correntes e tensões no domínio do tempo. É também desenvolvido um estudo comparativo entre métodos de classificação de padrões para a identificação de defeitos nestas máquinas, tais como: Naive Bayes, k-Nearest Neighbor, Support Vector Machine (Sequential Minimal Optimization), Rede Neural Artificial (Perceptron Multicamadas), Repeated Incremental Pruning to Produce Error Reduction e C4.5 Decision Tree. Também aplicou-se o conceito de Sistemas Multiagentes (SMA) para suportar a utilização de múltiplos métodos concorrentes de forma distribuída para reconhecimento de padrões de defeitos em rolamentos defeituosos, quebras nas barras da gaiola de esquilo do rotor e curto-circuito entre as bobinas do enrolamento do estator de motores de indução trifásicos. Complementarmente, algumas estratégias para a definição da severidade dos defeitos supracitados em motores foram exploradas, fazendo inclusive uma averiguação da influência do desequilíbrio de tensão na alimentação da máquina para a determinação destas anomalias. Os dados experimentais foram adquiridos por meio de uma bancada experimental em laboratório com motores de potência de 1 e 2 cv acionados diretamente na rede elétrica, operando em várias condições de desequilíbrio das tensões e variações da carga mecânica aplicada ao eixo do motor.

Laser-induced breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model

Abstract A new LIBS quantitative analysis method based on analytical line adaptive selection and Relevance Vector Machine (RVM) regression model is proposed. First, a scheme of adaptively selecting analytical line is put forward in order to overcome the drawback of high dependency on a priori knowledge. The candidate analytical lines are automatically selected based on the built-in characteristics of spectral lines, such as spectral intensity, wavelength and width at half height. The analytical lines which will be used as input variables of regression model are determined adaptively according to the samples for both training and testing. Second, an LIBS quantitative analysis method based on RVM is presented. The intensities of analytical lines and the elemental concentrations of certified standard samples are used to train the RVM regression model. The predicted elemental concentration analysis results will be given with a form of confidence interval of probabilistic distribution, which is helpful for evaluating the uncertainness contained in the measured spectra. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples have been carried out. The multiple correlation coefficient of the prediction was up to 98.85%, and the average relative error of the prediction was 4.01%. The experiment results showed that the proposed LIBS quantitative analysis method achieved better prediction accuracy and better modeling robustness compared with the methods based on partial least squares regression, artificial neural network and standard support vector machine.

Improving resource management in virtualized data centers using application performance models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity.^ We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. ^ This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.^

Improving Resource Management in Virtualized Data Centers using Application Performance Models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity. We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.

Authentification biométrique par dynamique de frappe pour évaluation à distance utilisant SVM à une classe

La machine à vecteurs de support à une classe est un algorithme non-supervisé qui est capable d’apprendre une fonction de décision à partir de données d’une seule classe pour la détection d’anomalie. Avec les données d’entraînement d’une seule classe, elle peut identifier si une nouvelle donnée est similaire à l’ensemble d’entraînement. Dans ce mémoire, nous nous intéressons à la reconnaissance de forme de dynamique de frappe par la machine à vecteurs de support à une classe, pour l’authentification d’étudiants dans un système d’évaluation sommative à distance à l’Université Laval. Comme chaque étudiant à l’Université Laval possède un identifiant court, unique qu’il utilise pour tout accès sécurisé aux ressources informatiques, nous avons choisi cette chaîne de caractères comme support à la saisie de dynamique de frappe d’utilisateur pour construire notre propre base de données. Après avoir entraîné un modèle pour chaque étudiant avec ses données de dynamique de frappe, on veut pouvoir l’identifier et éventuellement détecter des imposteurs. Trois méthodes pour la classification ont été testées et discutées. Ainsi, nous avons pu constater les faiblesses de chaque méthode dans ce système. L’évaluation des taux de reconnaissance a permis de mettre en évidence leur dépendance au nombre de signatures ainsi qu’au nombre de caractères utilisés pour construire les signatures. Enfin, nous avons montré qu’il existe des corrélations entre le taux de reconnaissance et la dispersion dans les distributions des caractéristiques des signatures de dynamique de frappe.

Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs) for glaucoma diagnosis using Spectral Domain OCT (SD-OCT) and standard automated perimetry (SAP). METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP) and retinal nerve fiber layer (RNFL) imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG), Naive-Bayes (NB), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Random Forest (RAN), Ensemble Selection (ENS), Classification Tree (CTREE), Ada Boost M1(ADA),Support Vector Machine Linear (SVML) and Support Vector Machine Gaussian (SVMG). Areas under the receiver operating characteristic curves (aROC) obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE) to 0.946 (RAN).The best OCT+SAP aROC obtained with RAN (0.946) was significantly larger the best single OCT parameter (p<0.05), but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19). CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

A framework for electricity price spike analysis with advanced data mining methods

There are many techniques for electricity market price forecasting. However, most of them are designed for expected price analysis rather than price spike forecasting. An effective method of predicting the occurrence of spikes has not yet been observed in the literature so far. In this paper, a data mining based approach is presented to give a reliable forecast of the occurrence of price spikes. Combined with the spike value prediction techniques developed by the same authors, the proposed approach aims at providing a comprehensive tool for price spike forecasting. In this paper, feature selection techniques are firstly described to identify the attributes relevant to the occurrence of spikes. A simple introduction to the classification techniques is given for completeness. Two algorithms: support vector machine and probability classifier are chosen to be the spike occurrence predictors and are discussed in details. Realistic market data are used to test the proposed model with promising results.

Use of SVM Methods with Surface-Based Cortical and Volumetric Subcortical Measurements to Detect Alzheimer`s Disease

Here, we examine morphological changes in cortical thickness of patients with Alzheimer`s disease (AD) using image analysis algorithms for brain structure segmentation and study automatic classification of AD patients using cortical and volumetric data. Cortical thickness of AD patients (n = 14) was measured using MRI cortical surface-based analysis and compared with healthy subjects (n = 20). Data was analyzed using an automated algorithm for tissue segmentation and classification. A Support Vector Machine (SVM) was applied over the volumetric measurements of subcortical and cortical structures to separate AD patients from controls. The group analysis showed cortical thickness reduction in the superior temporal lobe, parahippocampal gyrus, and enthorhinal cortex in both hemispheres. We also found cortical thinning in the isthmus of cingulate gyrus and middle temporal gyrus at the right hemisphere, as well as a reduction of the cortical mantle in areas previously shown to be associated with AD. We also confirmed that automatic classification algorithms (SVM) could be helpful to distinguish AD patients from healthy controls. Moreover, the same areas implicated in the pathogenesis of AD were the main parameters driving the classification algorithm. While the patient sample used in this study was relatively small, we expect that using a database of regional volumes derived from MRI scans of a large number of subjects will increase the SVM power of AD patient identification.