Autonomous pagination for newspaper from a predefined plan

Description of the development of a product able to deliver an autonomous page construction from a predefined plan. The processes involve Machine Learning techniques for text fitting on shapes, Beam Search for associations and Deep Learning for autonomous cropping of images.

Synthetic generation of amyloid PET images by non-linear dimensionality reduction inversion

Privacy issues and data scarcity in PET field call for efficient methods to expand datasets via synthetic generation of new data that cannot be traced back to real patients and that are also realistic. In this thesis, machine learning techniques were applied to 1001 amyloid-beta PET images, which had undergone a diagnosis of Alzheimer’s disease: the evaluations were 540 positive, 457 negative and 4 unknown. Isomap algorithm was used as a manifold learning method to reduce the dimensions of the PET dataset; a numerical scale-free interpolation method was applied to invert the dimensionality reduction map. The interpolant was tested on the PET images via LOOCV, where the removed images were compared with the reconstructed ones with the mean SSIM index (MSSIM = 0.76 ± 0.06). The effectiveness of this measure is questioned, since it indicated slightly higher performance for a method of comparison using PCA (MSSIM = 0.79 ± 0.06), which gave clearly poor quality reconstructed images with respect to those recovered by the numerical inverse mapping. Ten synthetic PET images were generated and, after having been mixed with ten originals, were sent to a team of clinicians for the visual assessment of their realism; no significant agreements were found either between clinicians and the true image labels or among the clinicians, meaning that original and synthetic images were indistinguishable. The future perspective of this thesis points to the improvement of the amyloid-beta PET research field by increasing available data, overcoming the constraints of data acquisition and privacy issues. Potential improvements can be achieved via refinements of the manifold learning and the inverse mapping stages during the PET image analysis, by exploring different combinations in the choice of algorithm parameters and by applying other non-linear dimensionality reduction algorithms. A final prospect of this work is the search for new methods to assess image reconstruction quality.

New Techniques in Deep Representation Learning

Thesis (Ph.D.)--University of Washington, 2016-06

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Optimization techniques to detect early ventilation extubation in intensive care units

The decision support models in intensive care units are developed to support medical staff in their decision making process. However, the optimization of these models is particularly difficult to apply due to dynamic, complex and multidisciplinary nature. Thus, there is a constant research and development of new algorithms capable of extracting knowledge from large volumes of data, in order to obtain better predictive results than the current algorithms. To test the optimization techniques a case study with real data provided by INTCare project was explored. This data is concerning to extubation cases. In this dataset, several models like Evolutionary Fuzzy Rule Learning, Lazy Learning, Decision Trees and many others were analysed in order to detect early extubation. The hydrids Decision Trees Genetic Algorithm, Supervised Classifier System and KNNAdaptive obtained the most accurate rate 93.2%, 93.1%, 92.97% respectively, thus showing their feasibility to work in a real environment.

Deep learning via semi-supervised embedding

We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multilayer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This provides a simple alternative to existing approaches to deep learning whilst yielding competitive error rates compared to those methods, and existing shallow semi-supervised techniques.

Alternative Techniques of Neural Signal Processing in Neuroengineering

Neural signal processing is a discipline within neuroengineering. This interdisciplinary approach combines principles from machine learning, signal processing theory, and computational neuroscience applied to problems in basic and clinical neuroscience. The ultimate goal of neuroengineering is a technological revolution, where machines would interact in real time with the brain. Machines and brains could interface, enabling normal function in cases of injury or disease, brain monitoring, and/or medical rehabilitation of brain disorders. Much current research in neuroengineering is focused on understanding the coding and processing of information in the sensory and motor systems, quantifying how this processing is altered in the pathological state, and how it can be manipulated through interactions with artificial devices including brain–computer interfaces and neuroprosthetics.

Kernel-Based Ranking. Methods for Learning and Performance Estimation

Machine learning provides tools for automated construction of predictive models in data intensive areas of engineering and science. The family of regularized kernel methods have in the recent years become one of the mainstream approaches to machine learning, due to a number of advantages the methods share. The approach provides theoretically well-founded solutions to the problems of under- and overfitting, allows learning from structured data, and has been empirically demonstrated to yield high predictive performance on a wide range of application domains. Historically, the problems of classification and regression have gained the majority of attention in the field. In this thesis we focus on another type of learning problem, that of learning to rank. In learning to rank, the aim is from a set of past observations to learn a ranking function that can order new objects according to how well they match some underlying criterion of goodness. As an important special case of the setting, we can recover the bipartite ranking problem, corresponding to maximizing the area under the ROC curve (AUC) in binary classification. Ranking applications appear in a large variety of settings, examples encountered in this thesis include document retrieval in web search, recommender systems, information extraction and automated parsing of natural language. We consider the pairwise approach to learning to rank, where ranking models are learned by minimizing the expected probability of ranking any two randomly drawn test examples incorrectly. The development of computationally efficient kernel methods, based on this approach, has in the past proven to be challenging. Moreover, it is not clear what techniques for estimating the predictive performance of learned models are the most reliable in the ranking setting, and how the techniques can be implemented efficiently. The contributions of this thesis are as follows. First, we develop RankRLS, a computationally efficient kernel method for learning to rank, that is based on minimizing a regularized pairwise least-squares loss. In addition to training methods, we introduce a variety of algorithms for tasks such as model selection, multi-output learning, and cross-validation, based on computational shortcuts from matrix algebra. Second, we improve the fastest known training method for the linear version of the RankSVM algorithm, which is one of the most well established methods for learning to rank. Third, we study the combination of the empirical kernel map and reduced set approximation, which allows the large-scale training of kernel machines using linear solvers, and propose computationally efficient solutions to cross-validation when using the approach. Next, we explore the problem of reliable cross-validation when using AUC as a performance criterion, through an extensive simulation study. We demonstrate that the proposed leave-pair-out cross-validation approach leads to more reliable performance estimation than commonly used alternative approaches. Finally, we present a case study on applying machine learning to information extraction from biomedical literature, which combines several of the approaches considered in the thesis. The thesis is divided into two parts. Part I provides the background for the research work and summarizes the most central results, Part II consists of the five original research articles that are the main contribution of this thesis.

Towards Evaluating and Modelling the Impacts of Mobile-Based Augmented Reality Applications on Learning and Engagement

Mobile augmented reality applications are increasingly utilized as a medium for enhancing learning and engagement in history education. Although these digital devices facilitate learning through immersive and appealing experiences, their design should be driven by theories of learning and instruction. We provide an overview of an evidence-based approach to optimize the development of mobile augmented reality applications that teaches students about history. Our research aims to evaluate and model the impacts of design parameters towards learning and engagement. The research program is interdisciplinary in that we apply techniques derived from design-based experiments and educational data mining. We outline the methodological and analytical techniques as well as discuss the implications of the anticipated findings.

Deep learning of representations and its application to computer vision

L’objectif de cette thèse par articles est de présenter modestement quelques étapes du parcours qui mènera (on espère) à une solution générale du problème de l’intelligence artificielle. Cette thèse contient quatre articles qui présentent chacun une différente nouvelle méthode d’inférence perceptive en utilisant l’apprentissage machine et, plus particulièrement, les réseaux neuronaux profonds. Chacun de ces documents met en évidence l’utilité de sa méthode proposée dans le cadre d’une tâche de vision par ordinateur. Ces méthodes sont applicables dans un contexte plus général, et dans certains cas elles on tété appliquées ailleurs, mais ceci ne sera pas abordé dans le contexte de cette de thèse. Dans le premier article, nous présentons deux nouveaux algorithmes d’inférence variationelle pour le modèle génératif d’images appelé codage parcimonieux “spike- and-slab” (CPSS). Ces méthodes d’inférence plus rapides nous permettent d’utiliser des modèles CPSS de tailles beaucoup plus grandes qu’auparavant. Nous démontrons qu’elles sont meilleures pour extraire des détecteur de caractéristiques quand très peu d’exemples étiquetés sont disponibles pour l’entraînement. Partant d’un modèle CPSS, nous construisons ensuite une architecture profonde, la machine de Boltzmann profonde partiellement dirigée (MBP-PD). Ce modèle a été conçu de manière à simplifier d’entraînement des machines de Boltzmann profondes qui nécessitent normalement une phase de pré-entraînement glouton pour chaque couche. Ce problème est réglé dans une certaine mesure, mais le coût d’inférence dans le nouveau modèle est relativement trop élevé pour permettre de l’utiliser de manière pratique. Dans le deuxième article, nous revenons au problème d’entraînement joint de machines de Boltzmann profondes. Cette fois, au lieu de changer de famille de modèles, nous introduisons un nouveau critère d’entraînement qui donne naissance aux machines de Boltzmann profondes à multiples prédictions (MBP-MP). Les MBP-MP sont entraînables en une seule étape et ont un meilleur taux de succès en classification que les MBP classiques. Elles s’entraînent aussi avec des méthodes variationelles standard au lieu de nécessiter un classificateur discriminant pour obtenir un bon taux de succès en classification. Par contre, un des inconvénients de tels modèles est leur incapacité de générer deséchantillons, mais ceci n’est pas trop grave puisque la performance de classification des machines de Boltzmann profondes n’est plus une priorité étant donné les dernières avancées en apprentissage supervisé. Malgré cela, les MBP-MP demeurent intéressantes parce qu’elles sont capable d’accomplir certaines tâches que des modèles purement supervisés ne peuvent pas faire, telles que celle de classifier des données incomplètes ou encore celle de combler intelligemment l’information manquante dans ces données incomplètes. Le travail présenté dans cette thèse s’est déroulé au milieu d’une période de transformations importantes du domaine de l’apprentissage à réseaux neuronaux profonds qui a été déclenchée par la découverte de l’algorithme de “dropout” par Geoffrey Hinton. Dropout rend possible un entraînement purement supervisé d’architectures de propagation unidirectionnel sans être exposé au danger de sur- entraînement. Le troisième article présenté dans cette thèse introduit une nouvelle fonction d’activation spécialement con ̧cue pour aller avec l’algorithme de Dropout. Cette fonction d’activation, appelée maxout, permet l’utilisation de aggrégation multi-canal dans un contexte d’apprentissage purement supervisé. Nous démontrons comment plusieurs tâches de reconnaissance d’objets sont mieux accomplies par l’utilisation de maxout. Pour terminer, sont présentons un vrai cas d’utilisation dans l’industrie pour la transcription d’adresses de maisons à plusieurs chiffres. En combinant maxout avec une nouvelle sorte de couche de sortie pour des réseaux neuronaux de convolution, nous démontrons qu’il est possible d’atteindre un taux de succès comparable à celui des humains sur un ensemble de données coriace constitué de photos prises par les voitures de Google. Ce système a été déployé avec succès chez Google pour lire environ cent million d’adresses de maisons.

Development of Hierarchical Clustering Techniques for Gridded Data from Mixed Data Sequences

Knowledge discovery in databases is the non-trivial process of identifying valid, novel potentially useful and ultimately understandable patterns from data. The term Data mining refers to the process which does the exploratory analysis on the data and builds some model on the data. To infer patterns from data, data mining involves different approaches like association rule mining, classification techniques or clustering techniques. Among the many data mining techniques, clustering plays a major role, since it helps to group the related data for assessing properties and drawing conclusions. Most of the clustering algorithms act on a dataset with uniform format, since the similarity or dissimilarity between the data points is a significant factor in finding out the clusters. If a dataset consists of mixed attributes, i.e. a combination of numerical and categorical variables, a preferred approach is to convert different formats into a uniform format. The research study explores the various techniques to convert the mixed data sets to a numerical equivalent, so as to make it equipped for applying the statistical and similar algorithms. The results of clustering mixed category data after conversion to numeric data type have been demonstrated using a crime data set. The thesis also proposes an extension to the well known algorithm for handling mixed data types, to deal with data sets having only categorical data. The proposed conversion has been validated on a data set corresponding to breast cancer. Moreover, another issue with the clustering process is the visualization of output. Different geometric techniques like scatter plot, or projection plots are available, but none of the techniques display the result projecting the whole database but rather demonstrate attribute-pair wise analysis

A survey of data mining techniques for social media analysis

Social network has gained remarkable attention in the last decade. Accessing social network sites such as Twitter, Facebook LinkedIn and Google+ through the internet and the web 2.0 technologies has become more affordable. People are becoming more interested in and relying on social network for information, news and opinion of other users on diverse subject matters. The heavy reliance on social network sites causes them to generate massive data characterised by three computational issues namely; size, noise and dynamism. These issues often make social network data very complex to analyse manually, resulting in the pertinent use of computational means of analysing them. Data mining provides a wide range of techniques for detecting useful knowledge from massive datasets like trends, patterns and rules [44]. Data mining techniques are used for information retrieval, statistical modelling and machine learning. These techniques employ data pre-processing, data analysis, and data interpretation processes in the course of data analysis. This survey discusses different data mining techniques used in mining diverse aspects of the social network over decades going from the historical techniques to the up-to-date models, including our novel technique named TRCM. All the techniques covered in this survey are listed in the Table.1 including the tools employed as well as names of their authors.

Computer techniques towards the automatic characterization of graphite particles in metallographic images of industrial materials

The automatic characterization of particles in metallographic images has been paramount, mainly because of the importance of quantifying such microstructures in order to assess the mechanical properties of materials common used in industry. This automated characterization may avoid problems related with fatigue and possible measurement errors. In this paper, computer techniques are used and assessed towards the accomplishment of this crucial industrial goal in an efficient and robust manner. Hence, the use of the most actively pursued machine learning classification techniques. In particularity, Support Vector Machine, Bayesian and Optimum-Path Forest based classifiers, and also the Otsu's method, which is commonly used in computer imaging to binarize automatically simply images and used here to demonstrated the need for more complex methods, are evaluated in the characterization of graphite particles in metallographic images. The statistical based analysis performed confirmed that these computer techniques are efficient solutions to accomplish the aimed characterization. Additionally, the Optimum-Path Forest based classifier demonstrated an overall superior performance, both in terms of accuracy and speed. © 2012 Elsevier Ltd. All rights reserved.

NodePM: A Remote Monitoring Alert System for Energy Consumption Using Probabilistic Techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Determination of trace elements in bovine semen samples by inductively coupled plasma mass spectrometry and data mining techniques for identification of bovine class

The reproductive performance of cattle may be influenced by several factors, but mineral imbalances are crucial in terms of direct effects on reproduction. Several studies have shown that elements such as calcium, copper, iron, magnesium, selenium, and zinc are essential for reproduction and can prevent oxidative stress. However, toxic elements such as lead, nickel, and arsenic can have adverse effects on reproduction. In this paper, we applied a simple and fast method of multi-element analysis to bovine semen samples from Zebu and European classes used in reproduction programs and artificial insemination. Samples were analyzed by inductively coupled plasma spectrometry (ICP-MS) using aqueous medium calibration and the samples were diluted in a proportion of 1:50 in a solution containing 0.01% (vol/vol) Triton X-100 and 0.5% (vol/vol) nitric acid. Rhodium, iridium, and yttrium were used as the internal standards for ICP-MS analysis. To develop a reliable method of tracing the class of bovine semen, we used data mining techniques that make it possible to classify unknown samples after checking the differentiation of known-class samples. Based on the determination of 15 elements in 41 samples of bovine semen, 3 machine-learning tools for classification were applied to determine cattle class. Our results demonstrate the potential of support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF) chemometric tools to identify cattle class. Moreover, the selection tools made it possible to reduce the number of chemical elements needed from 15 to just 8.