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

An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks

Connectivity is the basic factor for the proper operation of any wireless network. In a mobile wireless sensor network it is a challenge for applications and protocols to deal with connectivity problems, as links might get up and down frequently. In these scenarios, having knowledge of the node remaining connectivity time could both improve the performance of the protocols (e.g. handoff mechanisms) and save possible scarce nodes resources (CPU, bandwidth, and energy) by preventing unfruitful transmissions. The current paper provides a solution called Genetic Machine Learning Algorithm (GMLA) to forecast the remainder connectivity time in mobile environments. It consists in combining Classifier Systems with a Markov chain model of the RF link quality. The main advantage of using an evolutionary approach is that the Markov model parameters can be discovered on-the-fly, making it possible to cope with unknown environments and mobility patterns. Simulation results show that the proposal is a very suitable solution, as it overcomes the performance obtained by similar approaches.

Using Threads to Overcome Synchronization Delays in Parallel Multiple Progressive Alignment Algorithms

Sao Paulo State Research Foundation-FAPESP

Learning HMMs for nucleotide sequences from amino acid alignments

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

A avaliação da efetividade de um modelo de intervenção breve (método BASICS) para o uso de risco de álcool em estudantes do ensino médio

Pós-graduação em Saúde Coletiva - FMB

Studying the influence of a secondary variable in Collocated Cokriging estimates

In this paper the influence of a secondary variable as a function of the correlation with the primary variable for collocated cokriging is examined. For this study five exhaustive data sets were generated in computer, from which samples with 60 and 104 data points were drawn using the stratified random sampling method. These exhaustive data sets were generated departing from a pair of primary and secondary variables showing a good correlation. Then successive sets were generated by adding an amount of white noise in such a way that the correlation gets poorer. Using these samples, it was possible to find out how primary and secondary information is used to estimate an unsampled location according to the correlation level.

Processi markoviani nascosti

We introduce the notation of Markov chains and their properties, and give the definition of ergodic, irreducible and aperiodic chains with correspective examples. Then, the definition of hidden Markov models is given and their characteristics are examined. We formulate three basic problems regarding the hidden Markov models and discuss the solution of two of them - the Viterbi algorithm and the forward-backward algorithm.

Simulation-based cost-utility analysis of population screening-based alendronate use in Switzerland

A simulation model adopting a health system perspective showed population-based screening with DXA, followed by alendronate treatment of persons with osteoporosis, or with anamnestic fracture and osteopenia, to be cost-effective in Swiss postmenopausal women from age 70, but not in men. INTRODUCTION: We assessed the cost-effectiveness of a population-based screen-and-treat strategy for osteoporosis (DXA followed by alendronate treatment if osteoporotic, or osteopenic in the presence of fracture), compared to no intervention, from the perspective of the Swiss health care system. METHODS: A published Markov model assessed by first-order Monte Carlo simulation was refined to reflect the diagnostic process and treatment effects. Women and men entered the model at age 50. Main screening ages were 65, 75, and 85 years. Age at bone densitometry was flexible for persons fracturing before the main screening age. Realistic assumptions were made with respect to persistence with intended 5 years of alendronate treatment. The main outcome was cost per quality-adjusted life year (QALY) gained. RESULTS: In women, costs per QALY were Swiss francs (CHF) 71,000, CHF 35,000, and CHF 28,000 for the main screening ages of 65, 75, and 85 years. The threshold of CHF 50,000 per QALY was reached between main screening ages 65 and 75 years. Population-based screening was not cost-effective in men. CONCLUSION: Population-based DXA screening, followed by alendronate treatment in the presence of osteoporosis, or of fracture and osteopenia, is a cost-effective option in Swiss postmenopausal women after age 70.

Managing server energy and reducing operational cost for online service providers

The past decade has seen the energy consumption in servers and Internet Data Centers (IDCs) skyrocket. A recent survey estimated that the worldwide spending on servers and cooling have risen to above $30 billion and is likely to exceed spending on the new server hardware . The rapid rise in energy consumption has posted a serious threat to both energy resources and the environment, which makes green computing not only worthwhile but also necessary. This dissertation intends to tackle the challenges of both reducing the energy consumption of server systems and by reducing the cost for Online Service Providers (OSPs). Two distinct subsystems account for most of IDC’s power: the server system, which accounts for 56% of the total power consumption of an IDC, and the cooling and humidifcation systems, which accounts for about 30% of the total power consumption. The server system dominates the energy consumption of an IDC, and its power draw can vary drastically with data center utilization. In this dissertation, we propose three models to achieve energy effciency in web server clusters: an energy proportional model, an optimal server allocation and frequency adjustment strategy, and a constrained Markov model. The proposed models have combined Dynamic Voltage/Frequency Scaling (DV/FS) and Vary-On, Vary-off (VOVF) mechanisms that work together for more energy savings. Meanwhile, corresponding strategies are proposed to deal with the transition overheads. We further extend server energy management to the IDC’s costs management, helping the OSPs to conserve, manage their own electricity cost, and lower the carbon emissions. We have developed an optimal energy-aware load dispatching strategy that periodically maps more requests to the locations with lower electricity prices. A carbon emission limit is placed, and the volatility of the carbon offset market is also considered. Two energy effcient strategies are applied to the server system and the cooling system respectively. With the rapid development of cloud services, we also carry out research to reduce the server energy in cloud computing environments. In this work, we propose a new live virtual machine (VM) placement scheme that can effectively map VMs to Physical Machines (PMs) with substantial energy savings in a heterogeneous server cluster. A VM/PM mapping probability matrix is constructed, in which each VM request is assigned with a probability running on PMs. The VM/PM mapping probability matrix takes into account resource limitations, VM operation overheads, server reliability as well as energy effciency. The evolution of Internet Data Centers and the increasing demands of web services raise great challenges to improve the energy effciency of IDCs. We also express several potential areas for future research in each chapter.

Genotype 3 is associated with accelerated fibrosis progression in chronic hepatitis C

BACKGROUND/AIMS: While several risk factors for the histological progression of chronic hepatitis C have been identified, the contribution of HCV genotypes to liver fibrosis evolution remains controversial. The aim of this study was to assess independent predictors for fibrosis progression. METHODS: We identified 1189 patients from the Swiss Hepatitis C Cohort database with at least one biopsy prior to antiviral treatment and assessable date of infection. Stage-constant fibrosis progression rate was assessed using the ratio of fibrosis Metavir score to duration of infection. Stage-specific fibrosis progression rates were obtained using a Markov model. Risk factors were assessed by univariate and multivariate regression models. RESULTS: Independent risk factors for accelerated stage-constant fibrosis progression (>0.083 fibrosis units/year) included male sex (OR=1.60, [95% CI 1.21-2.12], P<0.001), age at infection (OR=1.08, [1.06-1.09], P<0.001), histological activity (OR=2.03, [1.54-2.68], P<0.001) and genotype 3 (OR=1.89, [1.37-2.61], P<0.001). Slower progression rates were observed in patients infected by blood transfusion (P=0.02) and invasive procedures or needle stick (P=0.03), compared to those infected by intravenous drug use. Maximum likelihood estimates (95% CI) of stage-specific progression rates (fibrosis units/year) for genotype 3 versus the other genotypes were: F0-->F1: 0.126 (0.106-0.145) versus 0.091 (0.083-0.100), F1-->F2: 0.099 (0.080-0.117) versus 0.065 (0.058-0.073), F2-->F3: 0.077 (0.058-0.096) versus 0.068 (0.057-0.080) and F3-->F4: 0.171 (0.106-0.236) versus 0.112 (0.083-0.142, overall P<0.001). CONCLUSIONS: This study shows a significant association of genotype 3 with accelerated fibrosis using both stage-constant and stage-specific estimates of fibrosis progression rates. This observation may have important consequences for the management of patients infected with this genotype.

Improved cerebellar tissue classification on magnetic resonance images of brain.

PURPOSE: To develop and implement a method for improved cerebellar tissue classification on the MRI of brain by automatically isolating the cerebellum prior to segmentation. MATERIALS AND METHODS: Dual fast spin echo (FSE) and fluid attenuation inversion recovery (FLAIR) images were acquired on 18 normal volunteers on a 3 T Philips scanner. The cerebellum was isolated from the rest of the brain using a symmetric inverse consistent nonlinear registration of individual brain with the parcellated template. The cerebellum was then separated by masking the anatomical image with individual FLAIR images. Tissues in both the cerebellum and rest of the brain were separately classified using hidden Markov random field (HMRF), a parametric method, and then combined to obtain tissue classification of the whole brain. The proposed method for tissue classification on real MR brain images was evaluated subjectively by two experts. The segmentation results on Brainweb images with varying noise and intensity nonuniformity levels were quantitatively compared with the ground truth by computing the Dice similarity indices. RESULTS: The proposed method significantly improved the cerebellar tissue classification on all normal volunteers included in this study without compromising the classification in remaining part of the brain. The average similarity indices for gray matter (GM) and white matter (WM) in the cerebellum are 89.81 (+/-2.34) and 93.04 (+/-2.41), demonstrating excellent performance of the proposed methodology. CONCLUSION: The proposed method significantly improved tissue classification in the cerebellum. The GM was overestimated when segmentation was performed on the whole brain as a single object.

A search for prompt lepton-jets in pp collisions at sqrts=7 TeV with the ATLAS detector

We present a search for a light (mass < 2 GeV) boson predicted by Hidden Valley supersymmetric models that decays into a final state consisting of collimated muons or electrons, denoted "lepton-jets". The analysis uses 5 fb(-1) of root s = 7 TeV proton-proton collision data recorded by the ATLAS detector at the Large Hadron Collider to search for the following signatures: single lepton-jets with at least four muons; pairs of lepton-jets, each with two or more muons; and pairs of lepton-jets with two or more electrons. This study finds no statistically significant deviation from the Standard Model prediction and places 95% confidence-level exclusion limits on the production cross section times branching ratio of light bosons for several parameter sets of a Hidden Valley model.

gems: An R Package for Simulating from Disease Progression Models

Mathematical models of disease progression predict disease outcomes and are useful epidemiological tools for planners and evaluators of health interventions. The R package gems is a tool that simulates disease progression in patients and predicts the effect of different interventions on patient outcome. Disease progression is represented by a series of events (e.g., diagnosis, treatment and death), displayed in a directed acyclic graph. The vertices correspond to disease states and the directed edges represent events. The package gems allows simulations based on a generalized multistate model that can be described by a directed acyclic graph with continuous transition-specific hazard functions. The user can specify an arbitrary hazard function and its parameters. The model includes parameter uncertainty, does not need to be a Markov model, and may take the history of previous events into account. Applications are not limited to the medical field and extend to other areas where multistate simulation is of interest. We provide a technical explanation of the multistate models used by gems, explain the functions of gems and their arguments, and show a sample application.

Passive wireless sensor systems can recognize activites of daily living

The ability to determine what activity of daily living a person performs is of interest in many application domains. It is possible to determine the physical and cognitive capabilities of the elderly by inferring what activities they perform in their houses. Our primary aim was to establish a proof of concept that a wireless sensor system can monitor and record physical activity and these data can be modeled to predict activities of daily living. The secondary aim was to determine the optimal placement of the sensor boxes for detecting activities in a room. A wireless sensor system was set up in a laboratory kitchen. The ten healthy participants were requested to make tea following a defined sequence of tasks. Data were collected from the eight wireless sensor boxes placed in specific places in the test kitchen and analyzed to detect the sequences of tasks performed by the participants. These sequence of tasks were trained and tested using the Markov Model. Data analysis focused on the reliability of the system and the integrity of the collected data. The sequence of tasks were successfully recognized for all subjects and the averaged data pattern of tasks sequences between the subjects had a high correlation. Analysis of the data collected indicates that sensors placed in different locations are capable of recognizing activities, with the movement detection sensor contributing the most to detection of tasks. The central top of the room with no obstruction of view was considered to be the best location to record data for activity detection. Wireless sensor systems show much promise as easily deployable to monitor and recognize activities of daily living.

Cost-effectiveness analysis of stereotactic body radiotherapy and radiofrequency ablation for medically inoperable liver metastases from colorectal cancer

This report describes the development of a Markov model for comparing percutaneous radiofrequency ablation (RFA) and stereotactic body radiation therapy (SBRT) in terms of their cost-utility in treating isolated liver metastases from colorectal cancer. The model is based on data from multiple retrospective and prospective studies, available data on different utility states associated with treatment and complications, as well as publicly available Medicare costs. The purpose of this report is to establish a well-justified model for clinical management decisions. In comparison with SBRT, RFA is the most cost-effective treatment for this patient population. From the societal perspective, SBRT may be an acceptable alternative with an ICER of $28,673/QALY. ^