Semi-supervised learning of statistical models for natural language understanding

Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.

Detecting Precipitation Climate Changes: An Approach Based on a Stochastic Daily Precipitation Model

2002 Mathematics Subject Classification: 62M10.

DIMUSE: An integrated framework for distributed multimedia system with database management and security support

With the recent explosion in the complexity and amount of digital multimedia data, there has been a huge impact on the operations of various organizations in distinct areas, such as government services, education, medical care, business, entertainment, etc. To satisfy the growing demand of multimedia data management systems, an integrated framework called DIMUSE is proposed and deployed for distributed multimedia applications to offer a full scope of multimedia related tools and provide appealing experiences for the users. This research mainly focuses on video database modeling and retrieval by addressing a set of core challenges. First, a comprehensive multimedia database modeling mechanism called Hierarchical Markov Model Mediator (HMMM) is proposed to model high dimensional media data including video objects, low-level visual/audio features, as well as historical access patterns and frequencies. The associated retrieval and ranking algorithms are designed to support not only the general queries, but also the complicated temporal event pattern queries. Second, system training and learning methodologies are incorporated such that user interests are mined efficiently to improve the retrieval performance. Third, video clustering techniques are proposed to continuously increase the searching speed and accuracy by architecting a more efficient multimedia database structure. A distributed video management and retrieval system is designed and implemented to demonstrate the overall performance. The proposed approach is further customized for a mobile-based video retrieval system to solve the perception subjectivity issue by considering individual user's profile. Moreover, to deal with security and privacy issues and concerns in distributed multimedia applications, DIMUSE also incorporates a practical framework called SMARXO, which supports multilevel multimedia security control. SMARXO efficiently combines role-based access control (RBAC), XML and object-relational database management system (ORDBMS) to achieve the target of proficient security control. A distributed multimedia management system named DMMManager (Distributed MultiMedia Manager) is developed with the proposed framework DEMUR; to support multimedia capturing, analysis, retrieval, authoring and presentation in one single framework.

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) interven- tions 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.

Hipertensão em segmentos sociais pauperizados da região do Vale do Paraíba São Paulo

O objetivo deste trabalho foi verificar as relações entre fatores socioeconômicos, ambientais e biológicos com a hipertensão, segundo gênero. A população estudada foi formada por adultos residentes em dois municípios do Vale do Paraíba (SP), uma das regiões mais pobres do estado de São Paulo. Foi composta por 274 (39,8%) homens e 415 (60,2 %) mulheres. O estudo foi realizado por meio de um modelo de regressão logística hierarquizada, aplicado separadamente para homens e mulheres. Foram estimados os odds ratios ajustados (ORaj), com intervalo de confiança de 95% e a = 0,05. Para os homens, os seguintes fatores de risco estiveram associados à hipertensão: viver na zona rural (ORaj=2,00; p=0,01); etilismo (ORaj= 1,90; p=0,03) e idade acima de 40 anos (ORaj=3,10; p<0,0001). Famílias numerosas, com mais de seis pessoas exerceram efeito protetor (ORaj=0,46; p=0,02). Para mulheres, os fatores de risco associados foram: ausência de escolaridade (ORaj= 2,37; p=0,0003); sedentarismo (ORaj=1,71; p=0,04); obesidade acompanhada de baixa estatura (ORaj= 4,66; p <0,0001) e idade acima de 40 anos ( ORaj=5,29; p=0,01). A obesidade isolada não se associou à hipertensão, nos níveis pressóricos iguais ou maiores do que os correspondentes ao estágio II do padrão de referência.

NMR analog of Bell's inequalities violation test

In this paper, we present an analog of Bell's inequalities violation test for N qubits to be performed in a nuclear magnetic resonance (NMR) quantum computer. This can be used to simulate or predict the results for different Bell's inequality tests, with distinct configurations and a larger number of qubits. To demonstrate our scheme, we implemented a simulation of the violation of the Clauser, Horne, Shimony and Holt (CHSH) inequality using a two-qubit NMR system and compared the results to those of a photon experiment. The experimental results are well described by the quantum mechanics theory and a local realistic hidden variables model (LRHVM) that was specifically developed for NMR. That is why we refer to this experiment as a simulation of Bell's inequality violation. Our result shows explicitly how the two theories can be compatible with each other due to the detection loophole. In the last part of this work, we discuss the possibility of testing some fundamental features of quantum mechanics using NMR with highly polarized spins, where a strong discrepancy between quantum mechanics and hidden variables models can be expected.

Evaluation of algorithms used to order markers on genetic maps

When building genetic maps, it is necessary to choose from several marker ordering algorithms and criteria, and the choice is not always simple. In this study, we evaluate the efficiency of algorithms try (TRY), seriation (SER), rapid chain delineation (RCD), recombination counting and ordering (RECORD) and unidirectional growth (UG), as well as the criteria PARF (product of adjacent recombination fractions), SARF (sum of adjacent recombination fractions), SALOD (sum of adjacent LOD scores) and LHMC (likelihood through hidden Markov chains), used with the RIPPLE algorithm for error verification, in the construction of genetic linkage maps. A linkage map of a hypothetical diploid and monoecious plant species was simulated containing one linkage group and 21 markers with fixed distance of 3 cM between them. In all, 700 F(2) populations were randomly simulated with and 400 individuals with different combinations of dominant and co-dominant markers, as well as 10 and 20% of missing data. The simulations showed that, in the presence of co-dominant markers only, any combination of algorithm and criteria may be used, even for a reduced population size. In the case of a smaller proportion of dominant markers, any of the algorithms and criteria (except SALOD) investigated may be used. In the presence of high proportions of dominant markers and smaller samples (around 100), the probability of repulsion linkage increases between them and, in this case, use of the algorithms TRY and SER associated to RIPPLE with criterion LHMC would provide better results. Heredity (2009) 103, 494-502; doi:10.1038/hdy.2009.96; published online 29 July 2009

Methods for prediction of peptide binding to MHC molecules: A comparative study

Background: A variety of methods for prediction of peptide binding to major histocompatibility complex (MHC) have been proposed. These methods are based on binding motifs, binding matrices, hidden Markov models (HMM), or artificial neural networks (ANN). There has been little prior work on the comparative analysis of these methods. Materials and Methods: We performed a comparison of the performance of six methods applied to the prediction of two human MHC class I molecules, including binding matrices and motifs, ANNs, and HMMs. Results: The selection of the optimal prediction method depends on the amount of available data (the number of peptides of known binding affinity to the MHC molecule of interest), the biases in the data set and the intended purpose of the prediction (screening of a single protein versus mass screening). When little or no peptide data are available, binding motifs are the most useful alternative to random guessing or use of a complete overlapping set of peptides for selection of candidate binders. As the number of known peptide binders increases, binding matrices and HMM become more useful predictors. ANN and HMM are the predictive methods of choice for MHC alleles with more than 100 known binding peptides. Conclusion: The ability of bioinformatic methods to reliably predict MHC binding peptides, and thereby potential T-cell epitopes, has major implications for clinical immunology, particularly in the area of vaccine design.

Cost-Effectiveness of Palliation of Unresectable Esophageal Cancer

Introduction Different modalities of palliation for obstructive symptoms in patients with unresectable esophageal cancer (EC) exist. However, these therapeutic alternatives have significant differences in costs and effectiveness. Methods A Markov model was designed to compare the cost-effectiveness (CE) of self-expandable stent (SES), brachytherapy and laser in the palliation of unresectable EC. Patients were assigned to one of the strategies, and the improvement in swallowing function was compared given the treatment efficacy, probability of survival, and risks of complications associated to each strategy. Probabilities and parameters for distribution were based on a 9-month time frame. Results Under the base-case scenario, laser has the lowest CE ratio, followed by brachytherapy at an incremental cost-effectiveness ratio (ICER) of $4,400.00, and SES is a dominated strategy. In the probabilistic analysis, laser is the strategy with the highest probability of cost-effectiveness for willingness to pay (WTP) values lower than $3,201 and brachytherapy for all WTP yielding a positive net health benefit (NHB) (threshold $4,440). The highest probability of cost-effectiveness for brachytherapy is 96%, and consequently, selection of suboptimal strategies can lead to opportunity losses for the US health system, ranging from US$ 4.32 to US$ 38.09 million dollars over the next 5-20 years. Conclusion Conditional to the WTP and current US Medicare costs, palliation of unresectable esophageal cancers with brachytherapy provides the largest amount of NHB and is the strategy with the highest probability of CE. However, some level of uncertainly remains, and wrong decisions will be made until further knowledge is acquired.

On the nonlocality of the quantum channel in the standard teleportation protocol

By exhibiting a violation of a novel form of the Bell-CHSH inequality, Żukowski has recently established that the quantum correlations exploited in the standard perfect teleportation protocol cannot be recovered by any local hidden variables model. In the case of imperfect teleportation, we show that a violation of a generalized form of Żukowski's teleportation inequality can only occur if the channel state, considered by itself, already violates a Bell-CHSH inequality. On the other hand, the fact that the channel state violates a Bell-CHSH inequality is not sufficient to imply a violation of Żukowski's teleportation inequality (or any of its generalizations). The implication does hold, however, if the fidelity of the teleportation exceeds ≈ 0.90. © 2001 Elsevier Science B.V. All rights reserved.

A new method for analysing the equilibrium and time-dependent behaviour of Markovian models

Many large-scale stochastic systems, such as telecommunications networks, can be modelled using a continuous-time Markov chain. However, it is frequently the case that a satisfactory analysis of their time-dependent, or even equilibrium, behaviour is impossible. In this paper, we propose a new method of analyzing Markovian models, whereby the existing transition structure is replaced by a more amenable one. Using rates of transition given by the equilibrium expected rates of the corresponding transitions of the original chain, we are able to approximate its behaviour. We present two formulations of the idea of expected rates. The first provides a method for analysing time-dependent behaviour, while the second provides a highly accurate means of analysing equilibrium behaviour. We shall illustrate our approach with reference to a variety of models, giving particular attention to queueing and loss networks. (C) 2003 Elsevier Ltd. All rights reserved.

Short-term Feature Space and Music Genre Classification

In music genre classification, most approaches rely on statistical characteristics of low-level features computed on short audio frames. In these methods, it is implicitly considered that frames carry equally relevant information loads and that either individual frames, or distributions thereof, somehow capture the specificities of each genre. In this paper we study the representation space defined by short-term audio features with respect to class boundaries, and compare different processing techniques to partition this space. These partitions are evaluated in terms of accuracy on two genre classification tasks, with several types of classifiers. Experiments show that a randomized and unsupervised partition of the space, used in conjunction with a Markov Model classifier lead to accuracies comparable to the state of the art. We also show that unsupervised partitions of the space tend to create less hubs.

Reconhecimento de língua gestual

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Informática e Computadores

Kalman tracking linear predictor for vowel intelligibility enhancement on european portuguese HMM based speech synthesis

The recent developments on Hidden Markov Models (HMM) based speech synthesis showed that this is a promising technology fully capable of competing with other established techniques. However some issues still lack a solution. Several authors report an over-smoothing phenomenon on both time and frequencies which decreases naturalness and sometimes intelligibility. In this work we present a new vowel intelligibility enhancement algorithm that uses a discrete Kalman filter (DKF) for tracking frame based parameters. The inter-frame correlations are modelled by an autoregressive structure which provides an underlying time frame dependency and can improve time-frequency resolution. The system’s performance has been evaluated using objective and subjective tests and the proposed methodology has led to improved results.