Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

All over the place localization system

The MAP-i Doctoral Programme in Informatics, of the Universities of Minho, Aveiro and Porto

Structured output SVM for remote sensing image classification

In the recent years, kernel methods have revealed very powerful tools in many application domains in general and in remote sensing image classification in particular. The special characteristics of remote sensing images (high dimension, few labeled samples and different noise sources) are efficiently dealt with kernel machines. In this paper, we propose the use of structured output learning to improve remote sensing image classification based on kernels. Structured output learning is concerned with the design of machine learning algorithms that not only implement input-output mapping, but also take into account the relations between output labels, thus generalizing unstructured kernel methods. We analyze the framework and introduce it to the remote sensing community. Output similarity is here encoded into SVM classifiers by modifying the model loss function and the kernel function either independently or jointly. Experiments on a very high resolution (VHR) image classification problem shows promising results and opens a wide field of research with structured output kernel methods.

Clustering and hot spot detection in socio-economic spatio-temporal data

Distribution of socio-economic features in urban space is an important source of information for land and transportation planning. The metropolization phenomenon has changed the distribution of types of professions in space and has given birth to different spatial patterns that the urban planner must know in order to plan a sustainable city. Such distributions can be discovered by statistical and learning algorithms through different methods. In this paper, an unsupervised classification method and a cluster detection method are discussed and applied to analyze the socio-economic structure of Switzerland. The unsupervised classification method, based on Ward's classification and self-organized maps, is used to classify the municipalities of the country and allows to reduce a highly-dimensional input information to interpret the socio-economic landscape. The cluster detection method, the spatial scan statistics, is used in a more specific manner in order to detect hot spots of certain types of service activities. The method is applied to the distribution services in the agglomeration of Lausanne. Results show the emergence of new centralities and can be analyzed in both transportation and social terms.

Collective intelligence

Estudio e implantación de algoritmos de recomendación, búsqueda, ranking y aprendizaje.

Aplicació de visió per dispositius mòbils

En aquest projecte es presenta l’aplicació per a dispositius mòbils Doppelganger. La seva funció és, a partir d’una fotografia, detectar la cara i mostrar la persona famosa de la nostra base de dades que més s’assembla a la persona en la fotografia. Per la implementació s’han utilitzat algoritmes de visió per computador i d’aprenentatge automàtic com per exemple el PCA i el K-Nearest Neighbor, tot utilitzant llibreries gratuïtes com són les OpenCV.

Mapping of Environmental Data Using Kernel-Based Methods

Recently, kernel-based Machine Learning methods have gained great popularity in many data analysis and data mining fields: pattern recognition, biocomputing, speech and vision, engineering, remote sensing etc. The paper describes the use of kernel methods to approach the processing of large datasets from environmental monitoring networks. Several typical problems of the environmental sciences and their solutions provided by kernel-based methods are considered: classification of categorical data (soil type classification), mapping of environmental and pollution continuous information (pollution of soil by radionuclides), mapping with auxiliary information (climatic data from Aral Sea region). The promising developments, such as automatic emergency hot spot detection and monitoring network optimization are discussed as well.

Decision making in uncertain and changing environments

We consider an agent who has to repeatedly make choices in an uncertainand changing environment, who has full information of the past, who discountsfuture payoffs, but who has no prior. We provide a learning algorithm thatperforms almost as well as the best of a given finite number of experts orbenchmark strategies and does so at any point in time, provided the agentis sufficiently patient. The key is to find the appropriate degree of forgettingdistant past. Standard learning algorithms that treat recent and distant pastequally do not have the sequential epsilon optimality property.

BIO-INSPIRED COMPUTATIONAL TECHNIQUES APPLIED TO THE CLUSTERING AND VISUALIZATION OF SPATIO-TEMPORAL GEOSPATIAL DATA

The coverage and volume of geo-referenced datasets are extensive and incessantly¦growing. The systematic capture of geo-referenced information generates large volumes¦of spatio-temporal data to be analyzed. Clustering and visualization play a key¦role in the exploratory data analysis and the extraction of knowledge embedded in¦these data. However, new challenges in visualization and clustering are posed when¦dealing with the special characteristics of this data. For instance, its complex structures,¦large quantity of samples, variables involved in a temporal context, high dimensionality¦and large variability in cluster shapes.¦The central aim of my thesis is to propose new algorithms and methodologies for¦clustering and visualization, in order to assist the knowledge extraction from spatiotemporal¦geo-referenced data, thus improving making decision processes.¦I present two original algorithms, one for clustering: the Fuzzy Growing Hierarchical¦Self-Organizing Networks (FGHSON), and the second for exploratory visual data analysis:¦the Tree-structured Self-organizing Maps Component Planes. In addition, I present¦methodologies that combined with FGHSON and the Tree-structured SOM Component¦Planes allow the integration of space and time seamlessly and simultaneously in¦order to extract knowledge embedded in a temporal context.¦The originality of the FGHSON lies in its capability to reflect the underlying structure¦of a dataset in a hierarchical fuzzy way. A hierarchical fuzzy representation of¦clusters is crucial when data include complex structures with large variability of cluster¦shapes, variances, densities and number of clusters. The most important characteristics¦of the FGHSON include: (1) It does not require an a-priori setup of the number¦of clusters. (2) The algorithm executes several self-organizing processes in parallel.¦Hence, when dealing with large datasets the processes can be distributed reducing the¦computational cost. (3) Only three parameters are necessary to set up the algorithm.¦In the case of the Tree-structured SOM Component Planes, the novelty of this algorithm¦lies in its ability to create a structure that allows the visual exploratory data analysis¦of large high-dimensional datasets. This algorithm creates a hierarchical structure¦of Self-Organizing Map Component Planes, arranging similar variables' projections in¦the same branches of the tree. Hence, similarities on variables' behavior can be easily¦detected (e.g. local correlations, maximal and minimal values and outliers).¦Both FGHSON and the Tree-structured SOM Component Planes were applied in¦several agroecological problems proving to be very efficient in the exploratory analysis¦and clustering of spatio-temporal datasets.¦In this thesis I also tested three soft competitive learning algorithms. Two of them¦well-known non supervised soft competitive algorithms, namely the Self-Organizing¦Maps (SOMs) and the Growing Hierarchical Self-Organizing Maps (GHSOMs); and the¦third was our original contribution, the FGHSON. Although the algorithms presented¦here have been used in several areas, to my knowledge there is not any work applying¦and comparing the performance of those techniques when dealing with spatiotemporal¦geospatial data, as it is presented in this thesis.¦I propose original methodologies to explore spatio-temporal geo-referenced datasets¦through time. Our approach uses time windows to capture temporal similarities and¦variations by using the FGHSON clustering algorithm. The developed methodologies¦are used in two case studies. In the first, the objective was to find similar agroecozones¦through time and in the second one it was to find similar environmental patterns¦shifted in time.¦Several results presented in this thesis have led to new contributions to agroecological¦knowledge, for instance, in sugar cane, and blackberry production.¦Finally, in the framework of this thesis we developed several software tools: (1)¦a Matlab toolbox that implements the FGHSON algorithm, and (2) a program called¦BIS (Bio-inspired Identification of Similar agroecozones) an interactive graphical user¦interface tool which integrates the FGHSON algorithm with Google Earth in order to¦show zones with similar agroecological characteristics.

On Automatic Diagnosis of Alzheimer's Disease based on Spontaneous Speech Analysis and Emotional Temperature

Alzheimer's disease is the most prevalent form of progressive degenerative dementia; it has a high socio-economic impact in Western countries. Therefore it is one of the most active research areas today. Alzheimer's is sometimes diagnosed by excluding other dementias, and definitive confirmation is only obtained through a post-mortem study of the brain tissue of the patient. The work presented here is part of a larger study that aims to identify novel technologies and biomarkers for early Alzheimer's disease detection, and it focuses on evaluating the suitability of a new approach for early diagnosis of Alzheimer’s disease by non-invasive methods. The purpose is to examine, in a pilot study, the potential of applying Machine Learning algorithms to speech features obtained from suspected Alzheimer sufferers in order help diagnose this disease and determine its degree of severity. Two human capabilities relevant in communication have been analyzed for feature selection: Spontaneous Speech and Emotional Response. The experimental results obtained were very satisfactory and promising for the early diagnosis and classification of Alzheimer’s disease patients.

Modelling ecological niches with support vector machines

1. The ecological niche is a fundamental biological concept. Modelling species' niches is central to numerous ecological applications, including predicting species invasions, identifying reservoirs for disease, nature reserve design and forecasting the effects of anthropogenic and natural climate change on species' ranges. 2. A computational analogue of Hutchinson's ecological niche concept (the multidimensional hyperspace of species' environmental requirements) is the support of the distribution of environments in which the species persist. Recently developed machine-learning algorithms can estimate the support of such high-dimensional distributions. We show how support vector machines can be used to map ecological niches using only observations of species presence to train distribution models for 106 species of woody plants and trees in a montane environment using up to nine environmental covariates. 3. We compared the accuracy of three methods that differ in their approaches to reducing model complexity. We tested models with independent observations of both species presence and species absence. We found that the simplest procedure, which uses all available variables and no pre-processing to reduce correlation, was best overall. Ecological niche models based on support vector machines are theoretically superior to models that rely on simulating pseudo-absence data and are comparable in empirical tests. 4. Synthesis and applications. Accurate species distribution models are crucial for effective environmental planning, management and conservation, and for unravelling the role of the environment in human health and welfare. Models based on distribution estimation rather than classification overcome theoretical and practical obstacles that pervade species distribution modelling. In particular, ecological niche models based on machine-learning algorithms for estimating the support of a statistical distribution provide a promising new approach to identifying species' potential distributions and to project changes in these distributions as a result of climate change, land use and landscape alteration.

Robust Nonlinear Mapping of Soil Contamination Using Support Regression

Spatial data analysis mapping and visualization is of great importance in various fields: environment, pollution, natural hazards and risks, epidemiology, spatial econometrics, etc. A basic task of spatial mapping is to make predictions based on some empirical data (measurements). A number of state-of-the-art methods can be used for the task: deterministic interpolations, methods of geostatistics: the family of kriging estimators (Deutsch and Journel, 1997), machine learning algorithms such as artificial neural networks (ANN) of different architectures, hybrid ANN-geostatistics models (Kanevski and Maignan, 2004; Kanevski et al., 1996), etc. All the methods mentioned above can be used for solving the problem of spatial data mapping. Environmental empirical data are always contaminated/corrupted by noise, and often with noise of unknown nature. That's one of the reasons why deterministic models can be inconsistent, since they treat the measurements as values of some unknown function that should be interpolated. Kriging estimators treat the measurements as the realization of some spatial randomn process. To obtain the estimation with kriging one has to model the spatial structure of the data: spatial correlation function or (semi-)variogram. This task can be complicated if there is not sufficient number of measurements and variogram is sensitive to outliers and extremes. ANN is a powerful tool, but it also suffers from the number of reasons. of a special type ? multiplayer perceptrons ? are often used as a detrending tool in hybrid (ANN+geostatistics) models (Kanevski and Maignank, 2004). Therefore, development and adaptation of the method that would be nonlinear and robust to noise in measurements, would deal with the small empirical datasets and which has solid mathematical background is of great importance. The present paper deals with such model, based on Statistical Learning Theory (SLT) - Support Vector Regression. SLT is a general mathematical framework devoted to the problem of estimation of the dependencies from empirical data (Hastie et al, 2004; Vapnik, 1998). SLT models for classification - Support Vector Machines - have shown good results on different machine learning tasks. The results of SVM classification of spatial data are also promising (Kanevski et al, 2002). The properties of SVM for regression - Support Vector Regression (SVR) are less studied. First results of the application of SVR for spatial mapping of physical quantities were obtained by the authorsin for mapping of medium porosity (Kanevski et al, 1999), and for mapping of radioactively contaminated territories (Kanevski and Canu, 2000). The present paper is devoted to further understanding of the properties of SVR model for spatial data analysis and mapping. Detailed description of the SVR theory can be found in (Cristianini and Shawe-Taylor, 2000; Smola, 1996) and basic equations for the nonlinear modeling are given in section 2. Section 3 discusses the application of SVR for spatial data mapping on the real case study - soil pollution by Cs137 radionuclide. Section 4 discusses the properties of the modelapplied to noised data or data with outliers.

Interest rates mapping

The present study deals with the analysis and mapping of Swiss franc interest rates. Interest rates depend on time and maturity, defining term structure of the interest rate curves (IRC). In the present study IRC are considered in a two-dimensional feature space - time and maturity. Exploratory data analysis includes a variety of tools widely used in econophysics and geostatistics. Geostatistical models and machine learning algorithms (multilayer perceptron and Support Vector Machines) were applied to produce interest rate maps. IR maps can be used for the visualisation and pattern perception purposes, to develop and to explore economical hypotheses, to produce dynamic asset-liability simulations and for financial risk assessments. The feasibility of an application of interest rates mapping approach for the IRC forecasting is considered as well. (C) 2008 Elsevier B.V. All rights reserved.

Scalable Feature Selection Applications for Genome-Wide Association Studies of Complex Diseases

Personalized medicine will revolutionize our capabilities to combat disease. Working toward this goal, a fundamental task is the deciphering of geneticvariants that are predictive of complex diseases. Modern studies, in the formof genome-wide association studies (GWAS) have afforded researchers with the opportunity to reveal new genotype-phenotype relationships through the extensive scanning of genetic variants. These studies typically contain over half a million genetic features for thousands of individuals. Examining this with methods other than univariate statistics is a challenging task requiring advanced algorithms that are scalable to the genome-wide level. In the future, next-generation sequencing studies (NGS) will contain an even larger number of common and rare variants. Machine learning-based feature selection algorithms have been shown to have the ability to effectively create predictive models for various genotype-phenotype relationships. This work explores the problem of selecting genetic variant subsets that are the most predictive of complex disease phenotypes through various feature selection methodologies, including filter, wrapper and embedded algorithms. The examined machine learning algorithms were demonstrated to not only be effective at predicting the disease phenotypes, but also doing so efficiently through the use of computational shortcuts. While much of the work was able to be run on high-end desktops, some work was further extended so that it could be implemented on parallel computers helping to assure that they will also scale to the NGS data sets. Further, these studies analyzed the relationships between various feature selection methods and demonstrated the need for careful testing when selecting an algorithm. It was shown that there is no universally optimal algorithm for variant selection in GWAS, but rather methodologies need to be selected based on the desired outcome, such as the number of features to be included in the prediction model. It was also demonstrated that without proper model validation, for example using nested cross-validation, the models can result in overly-optimistic prediction accuracies and decreased generalization ability. It is through the implementation and application of machine learning methods that one can extract predictive genotype–phenotype relationships and biological insights from genetic data sets.

Training deep convolutional architectures for vision

Les tâches de vision artificielle telles que la reconnaissance d’objets demeurent irrésolues à ce jour. Les algorithmes d’apprentissage tels que les Réseaux de Neurones Artificiels (RNA), représentent une approche prometteuse permettant d’apprendre des caractéristiques utiles pour ces tâches. Ce processus d’optimisation est néanmoins difficile. Les réseaux profonds à base de Machine de Boltzmann Restreintes (RBM) ont récemment été proposés afin de guider l’extraction de représentations intermédiaires, grâce à un algorithme d’apprentissage non-supervisé. Ce mémoire présente, par l’entremise de trois articles, des contributions à ce domaine de recherche. Le premier article traite de la RBM convolutionelle. L’usage de champs réceptifs locaux ainsi que le regroupement d’unités cachées en couches partageant les même paramètres, réduit considérablement le nombre de paramètres à apprendre et engendre des détecteurs de caractéristiques locaux et équivariant aux translations. Ceci mène à des modèles ayant une meilleure vraisemblance, comparativement aux RBMs entraînées sur des segments d’images. Le deuxième article est motivé par des découvertes récentes en neurosciences. Il analyse l’impact d’unités quadratiques sur des tâches de classification visuelles, ainsi que celui d’une nouvelle fonction d’activation. Nous observons que les RNAs à base d’unités quadratiques utilisant la fonction softsign, donnent de meilleures performances de généralisation. Le dernière article quand à lui, offre une vision critique des algorithmes populaires d’entraînement de RBMs. Nous montrons que l’algorithme de Divergence Contrastive (CD) et la CD Persistente ne sont pas robustes : tous deux nécessitent une surface d’énergie relativement plate afin que leur chaîne négative puisse mixer. La PCD à "poids rapides" contourne ce problème en perturbant légèrement le modèle, cependant, ceci génère des échantillons bruités. L’usage de chaînes tempérées dans la phase négative est une façon robuste d’adresser ces problèmes et mène à de meilleurs modèles génératifs.