Reconhecimento de voz para aplicações em automação implementado em FPGA

In many movies of scientific fiction, machines were capable of speaking with humans. However mankind is still far away of getting those types of machines, like the famous character C3PO of Star Wars. During the last six decades the automatic speech recognition systems have been the target of many studies. Throughout these years many technics were developed to be used in applications of both software and hardware. There are many types of automatic speech recognition system, among which the one used in this work were the isolated word and independent of the speaker system, using Hidden Markov Models as the recognition system. The goals of this work is to project and synthesize the first two steps of the speech recognition system, the steps are: the speech signal acquisition and the pre-processing of the signal. Both steps were developed in a reprogrammable component named FPGA, using the VHDL hardware description language, owing to the high performance of this component and the flexibility of the language. In this work it is presented all the theory of digital signal processing, as Fast Fourier Transforms and digital filters and also all the theory of speech recognition using Hidden Markov Models and LPC processor. It is also presented all the results obtained for each one of the blocks synthesized e verified in hardware

Human activity recognition by inertial signals obtained from a smartphone

Human Activity Recognition (HAR) is an emerging research field with the aim to identify the actions carried out by a person given a set of observations and the surrounding environment. The wide growth in this research field inside the scientific community is mainly explained by the high number of applications that are arising in the last years. A great part of the most promising applications are related to the healthcare field, where it is possible to track the mobility of patients with motor dysfunction as also the physical activity in patients with cardiovascular risk. Until a few years ago, by using distinct kind of sensors, a patient follow-up was possible. However, far from being a long-term solution and with the smartphone irruption, that monitoring can be achieved in a non-invasive way by using the embedded smartphone’s sensors. For these reasons this Final Degree Project arises with the main target to evaluate new feature extraction techniques in order to carry out an activity and user recognition, and also an activity segmentation. The recognition is done thanks to the inertial signals integration obtained by two widespread sensors in the greater part of smartphones: accelerometer and gyroscope. In particular, six different activities are evaluated walking, walking-upstairs, walking-downstairs, sitting, standing and lying. Furthermore, a segmentation task is carried out taking into account the activities performed by thirty users. This can be done by using Hidden Markov Models and also a set of tools tested satisfactory in speech recognition: HTK (Hidden Markov Model Toolkit).

Bayesian Hidden Markov Modeling of Array CGH Data

Genomic alterations have been linked to the development and progression of cancer. The technique of Comparative Genomic Hybridization (CGH) yields data consisting of fluorescence intensity ratios of test and reference DNA samples. The intensity ratios provide information about the number of copies in DNA. Practical issues such as the contamination of tumor cells in tissue specimens and normalization errors necessitate the use of statistics for learning about the genomic alterations from array-CGH data. As increasing amounts of array CGH data become available, there is a growing need for automated algorithms for characterizing genomic profiles. Specifically, there is a need for algorithms that can identify gains and losses in the number of copies based on statistical considerations, rather than merely detect trends in the data. We adopt a Bayesian approach, relying on the hidden Markov model to account for the inherent dependence in the intensity ratios. Posterior inferences are made about gains and losses in copy number. Localized amplifications (associated with oncogene mutations) and deletions (associated with mutations of tumor suppressors) are identified using posterior probabilities. Global trends such as extended regions of altered copy number are detected. Since the posterior distribution is analytically intractable, we implement a Metropolis-within-Gibbs algorithm for efficient simulation-based inference. Publicly available data on pancreatic adenocarcinoma, glioblastoma multiforme and breast cancer are analyzed, and comparisons are made with some widely-used algorithms to illustrate the reliability and success of the technique.

Modeling High-Dimensional Audio Sequences with Recurrent Neural Networks

Cette thèse étudie des modèles de séquences de haute dimension basés sur des réseaux de neurones récurrents (RNN) et leur application à la musique et à la parole. Bien qu'en principe les RNN puissent représenter les dépendances à long terme et la dynamique temporelle complexe propres aux séquences d'intérêt comme la vidéo, l'audio et la langue naturelle, ceux-ci n'ont pas été utilisés à leur plein potentiel depuis leur introduction par Rumelhart et al. (1986a) en raison de la difficulté de les entraîner efficacement par descente de gradient. Récemment, l'application fructueuse de l'optimisation Hessian-free et d'autres techniques d'entraînement avancées ont entraîné la recrudescence de leur utilisation dans plusieurs systèmes de l'état de l'art. Le travail de cette thèse prend part à ce développement. L'idée centrale consiste à exploiter la flexibilité des RNN pour apprendre une description probabiliste de séquences de symboles, c'est-à-dire une information de haut niveau associée aux signaux observés, qui en retour pourra servir d'à priori pour améliorer la précision de la recherche d'information. Par exemple, en modélisant l'évolution de groupes de notes dans la musique polyphonique, d'accords dans une progression harmonique, de phonèmes dans un énoncé oral ou encore de sources individuelles dans un mélange audio, nous pouvons améliorer significativement les méthodes de transcription polyphonique, de reconnaissance d'accords, de reconnaissance de la parole et de séparation de sources audio respectivement. L'application pratique de nos modèles à ces tâches est détaillée dans les quatre derniers articles présentés dans cette thèse. Dans le premier article, nous remplaçons la couche de sortie d'un RNN par des machines de Boltzmann restreintes conditionnelles pour décrire des distributions de sortie multimodales beaucoup plus riches. Dans le deuxième article, nous évaluons et proposons des méthodes avancées pour entraîner les RNN. Dans les quatre derniers articles, nous examinons différentes façons de combiner nos modèles symboliques à des réseaux profonds et à la factorisation matricielle non-négative, notamment par des produits d'experts, des architectures entrée/sortie et des cadres génératifs généralisant les modèles de Markov cachés. Nous proposons et analysons également des méthodes d'inférence efficaces pour ces modèles, telles la recherche vorace chronologique, la recherche en faisceau à haute dimension, la recherche en faisceau élagué et la descente de gradient. Finalement, nous abordons les questions de l'étiquette biaisée, du maître imposant, du lissage temporel, de la régularisation et du pré-entraînement.

Option pricing in market models driven by telegraph processes with jumps

Esta tesis está dividida en dos partes: en la primera parte se presentan y estudian los procesos telegráficos, los procesos de Poisson con compensador telegráfico y los procesos telegráficos con saltos. El estudio presentado en esta primera parte incluye el cálculo de las distribuciones de cada proceso, las medias y varianzas, así como las funciones generadoras de momentos entre otras propiedades. Utilizando estas propiedades en la segunda parte se estudian los modelos de valoración de opciones basados en procesos telegráficos con saltos. En esta parte se da una descripción de cómo calcular las medidas neutrales al riesgo, se encuentra la condición de no arbitraje en este tipo de modelos y por último se calcula el precio de las opciones Europeas de compra y venta.

Modeling of average growth curve in Santa Ines sheep using random regression models

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Estimating parameters in Markov models for longitudinal studies with missing data or surrogate outcomes

The discrete-time Markov chain is commonly used in describing changes of health states for chronic diseases in a longitudinal study. Statistical inferences on comparing treatment effects or on finding determinants of disease progression usually require estimation of transition probabilities. In many situations when the outcome data have some missing observations or the variable of interest (called a latent variable) can not be measured directly, the estimation of transition probabilities becomes more complicated. In the latter case, a surrogate variable that is easier to access and can gauge the characteristics of the latent one is usually used for data analysis. ^ This dissertation research proposes methods to analyze longitudinal data (1) that have categorical outcome with missing observations or (2) that use complete or incomplete surrogate observations to analyze the categorical latent outcome. For (1), different missing mechanisms were considered for empirical studies using methods that include EM algorithm, Monte Carlo EM and a procedure that is not a data augmentation method. For (2), the hidden Markov model with the forward-backward procedure was applied for parameter estimation. This method was also extended to cover the computation of standard errors. The proposed methods were demonstrated by the Schizophrenia example. The relevance of public health, the strength and limitations, and possible future research were also discussed. ^

Human Motion Analysis Based on Sequential Modeling of Radar Signal and Stereo Image Features

Falls are one of the greatest threats to elderly health in their daily living routines and activities. Therefore, it is very important to detect falls of an elderly in a timely and accurate manner, so that immediate response and proper care can be provided, by sending fall alarms to caregivers. Radar is an effective non-intrusive sensing modality which is well suited for this purpose, which can detect human motions in all types of environments, penetrate walls and fabrics, preserve privacy, and is insensitive to lighting conditions. Micro-Doppler features are utilized in radar signal corresponding to human body motions and gait to detect falls using a narrowband pulse-Doppler radar. Human motions cause time-varying Doppler signatures, which are analyzed using time-frequency representations and matching pursuit decomposition (MPD) for feature extraction and fall detection. The extracted features include MPD features and the principal components of the time-frequency signal representations. To analyze the sequential characteristics of typical falls, the extracted features are used for training and testing hidden Markov models (HMM) in different falling scenarios. Experimental results demonstrate that the proposed algorithm and method achieve fast and accurate fall detections. The risk of falls increases sharply when the elderly or patients try to exit beds. Thus, if a bed exit can be detected at an early stage of this motion, the related injuries can be prevented with a high probability. To detect bed exit for fall prevention, the trajectory of head movements is used for recognize such human motion. A head detector is trained using the histogram of oriented gradient (HOG) features of the head and shoulder areas from recorded bed exit images. A data association algorithm is applied on the head detection results to eliminate head detection false alarms. Then the three dimensional (3D) head trajectories are constructed by matching scale-invariant feature transform (SIFT) keypoints in the detected head areas from both the left and right stereo images. The extracted 3D head trajectories are used for training and testing an HMM based classifier for recognizing bed exit activities. The results of the classifier are presented and discussed in the thesis, which demonstrates the effectiveness of the proposed stereo vision based bed exit detection approach.

Modelling data and voice traffic over IP networks using continuous-time Markov models

Common approaches to IP-traffic modelling have featured the use of stochastic models, based on the Markov property, which can be classified into black box and white box models based on the approach used for modelling traffic. White box models, are simple to understand, transparent and have a physical meaning attributed to each of the associated parameters. To exploit this key advantage, this thesis explores the use of simple classic continuous-time Markov models based on a white box approach, to model, not only the network traffic statistics but also the source behaviour with respect to the network and application. The thesis is divided into two parts: The first part focuses on the use of simple Markov and Semi-Markov traffic models, starting from the simplest two-state model moving upwards to n-state models with Poisson and non-Poisson statistics. The thesis then introduces the convenient to use, mathematically derived, Gaussian Markov models which are used to model the measured network IP traffic statistics. As one of the most significant contributions, the thesis establishes the significance of the second-order density statistics as it reveals that, in contrast to first-order density, they carry much more unique information on traffic sources and behaviour. The thesis then exploits the use of Gaussian Markov models to model these unique features and finally shows how the use of simple classic Markov models coupled with use of second-order density statistics provides an excellent tool for capturing maximum traffic detail, which in itself is the essence of good traffic modelling. The second part of the thesis, studies the ON-OFF characteristics of VoIP traffic with reference to accurate measurements of the ON and OFF periods, made from a large multi-lingual database of over 100 hours worth of VoIP call recordings. The impact of the language, prosodic structure and speech rate of the speaker on the statistics of the ON-OFF periods is analysed and relevant conclusions are presented. Finally, an ON-OFF VoIP source model with log-normal transitions is contributed as an ideal candidate to model VoIP traffic and the results of this model are compared with those of previously published work.

Using structural equation modeling to assess two theoretical models that explain dropout

This study evaluated the relative fit of both Finn's (1989) Participation-Identification and Wehlage, Rutter, Smith, Lesko and Fernandez's (1989) School Membership models of high school completion to a sample of 4,597 eighth graders taken from the National Educational Longitudinal Study of 1988, (NELS:88), utilizing structural equation modeling techniques. This study found support for the importance of educational engagement as a factor in understanding academic achievement. The Participation-Identification model was particularly well fitting when applied to the sample of high school completers, dropouts (both overall and White dropouts) and African-American students. This study also confirmed the contribution of school environmental factors (i.e., size, diversity of economic and ethnic status among students) and family resources (i.e., availability of learning resources in the home and parent educational level) to students' educational engagement. Based on these findings, school social workers will need to be more attentive to utilizing macro-level interventions (i.e., community organization, interagency coordination) to achieve the organizational restructuring needed to address future challenges. The support found for the Participation-Identification model supports a shift in school social workers' attention from reactive attempts to improve the affective-interpersonal lives of students to proactive attention to their academic lives. The model concentrates school social work practices on the central mission of schools, which is educational engagement. School social workers guided by this model would be encouraged to seek changes in school policies and organization that would facilitate educational engagement. ^

A path-based framework for analyzing large markov models

Reliability and dependability modeling can be employed during many stages of analysis of a computing system to gain insights into its critical behaviors. To provide useful results, realistic models of systems are often necessarily large and complex. Numerical analysis of these models presents a formidable challenge because the sizes of their state-space descriptions grow exponentially in proportion to the sizes of the models. On the other hand, simulation of the models requires analysis of many trajectories in order to compute statistically correct solutions. This dissertation presents a novel framework for performing both numerical analysis and simulation. The new numerical approach computes bounds on the solutions of transient measures in large continuous-time Markov chains (CTMCs). It extends existing path-based and uniformization-based methods by identifying sets of paths that are equivalent with respect to a reward measure and related to one another via a simple structural relationship. This relationship makes it possible for the approach to explore multiple paths at the same time,· thus significantly increasing the number of paths that can be explored in a given amount of time. Furthermore, the use of a structured representation for the state space and the direct computation of the desired reward measure (without ever storing the solution vector) allow it to analyze very large models using a very small amount of storage. Often, path-based techniques must compute many paths to obtain tight bounds. In addition to presenting the basic path-based approach, we also present algorithms for computing more paths and tighter bounds quickly. One resulting approach is based on the concept of path composition whereby precomputed subpaths are composed to compute the whole paths efficiently. Another approach is based on selecting important paths (among a set of many paths) for evaluation. Many path-based techniques suffer from having to evaluate many (unimportant) paths. Evaluating the important ones helps to compute tight bounds efficiently and quickly.

Learning data-driven models of non-verbal behaviors for building rapport using an intelligent virtual agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness.^ Evidence-based patient-centered Brief Motivational Interviewing (BMI) interventions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary.^ Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems.^ To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].^

A next application prediction service using the BaranC framework

Predicting user behaviour enables user assistant services provide personalized services to the users. This requires a comprehensive user model that can be created by monitoring user interactions and activities. BaranC is a framework that performs user interface (UI) monitoring (and collects all associated context data), builds a user model, and supports services that make use of the user model. A prediction service, Next-App, is built to demonstrate the use of the framework and to evaluate the usefulness of such a prediction service. Next-App analyses a user's data, learns patterns, makes a model for a user, and finally predicts, based on the user model and current context, what application(s) the user is likely to want to use. The prediction is pro-active and dynamic, reflecting the current context, and is also dynamic in that it responds to changes in the user model, as might occur over time as a user's habits change. Initial evaluation of Next-App indicates a high-level of satisfaction with the service.

Identification of nonlinear systems using generalized kernel models

Nonlinear system identification is considered using a generalized kernel regression model. Unlike the standard kernel model, which employs a fixed common variance for all the kernel regressors, each kernel regressor in the generalized kernel model has an individually tuned diagonal covariance matrix that is determined by maximizing the correlation between the training data and the regressor using a repeated guided random search based on boosting optimization. An efficient construction algorithm based on orthogonal forward regression with leave-one-out (LOO) test statistic and local regularization (LR) is then used to select a parsimonious generalized kernel regression model from the resulting full regression matrix. The proposed modeling algorithm is fully automatic and the user is not required to specify any criterion to terminate the construction procedure. Experimental results involving two real data sets demonstrate the effectiveness of the proposed nonlinear system identification approach.