Classification of Parkinson’s Disease using MultiPass Lvq,Logistic Model Tree,K-Star for Audio Data set : Classification of Parkinson Disease using Audio Dataset

Parkinson's disease (PD) is a degenerative illness whose cardinal symptoms include rigidity, tremor, and slowness of movement. In addition to its widely recognized effects PD can have a profound effect on speech and voice.The speech symptoms most commonly demonstrated by patients with PD are reduced vocal loudness, monopitch, disruptions of voice quality, and abnormally fast rate of speech. This cluster of speech symptoms is often termed Hypokinetic Dysarthria.The disease can be difficult to diagnose accurately, especially in its early stages, due to this reason, automatic techniques based on Artificial Intelligence should increase the diagnosing accuracy and to help the doctors make better decisions. The aim of the thesis work is to predict the PD based on the audio files collected from various patients.Audio files are preprocessed in order to attain the features.The preprocessed data contains 23 attributes and 195 instances. On an average there are six voice recordings per person, By using data compression technique such as Discrete Cosine Transform (DCT) number of instances can be minimized, after data compression, attribute selection is done using several WEKA build in methods such as ChiSquared, GainRatio, Infogain after identifying the important attributes, we evaluate attributes one by one by using stepwise regression.Based on the selected attributes we process in WEKA by using cost sensitive classifier with various algorithms like MultiPass LVQ, Logistic Model Tree(LMT), K-Star.The classified results shows on an average 80%.By using this features 95% approximate classification of PD is acheived.This shows that using the audio dataset, PD could be predicted with a higher level of accuracy.

A corpus approach to discursive constructions of a hip-hop identity

This chapter is an analysis of a 100,000-word corpus consisting of message-board postings on hip-hop websites. A discourse analysis of this corpus reveals three strategies employed by the posters to identify themselves as members of the hip-hop community in the otherwise anonymous setting of the internet: (1) defined openings and closings, (2) repeated use of slang and taboo terms, and (3) performance of verbal art. Each strategy is characterized by the codification of non-standard grammar and pronunciations characteristic of speech, as well as by the use of non-standard orthography. The purpose of the discourse is shown to be a performance of identity, whereby language is used and recognized as the discursive construction of one’s hip-hop identity.

Immigration, security and the public debate on US language policy : a critical discourse analysis of language attitudes in the United States of America

The narrative of the United States is of a "nation of immigrants" in which the language shift patterns of earlier ethnolinguistic groups have tended towards linguistic assimilation through English. In recent years, however, changes in the demographic landscape and language maintenance by non-English speaking immigrants, particularly Hispanics, have been perceived as threats and have led to calls for an official English language policy.This thesis aims to contribute to the study of language policy making from a societal security perspective as expressed in attitudes regarding language and identity originating in the daily interaction between language groups. The focus is on the role of language and American identity in relation to immigration. The study takes an interdisciplinary approach combining language policy studies, security theory, and critical discourse analysis. The material consists of articles collected from four newspapers, namely USA Today, The New York Times, Los Angeles Times, and San Francisco Chronicle between April 2006 and December 2007.Two discourse types are evident from the analysis namely Loyalty and Efficiency. The former is mainly marked by concerns of national identity and contains speech acts of security related to language shift, choice and English for unity. Immigrants are represented as dehumanised, and harmful. Immigration is given as sovereignty-related, racial, and as war. The discourse type of Efficiency is mainly instrumental and contains speech acts of security related to cost, provision of services, health and safety, and social mobility. Immigrants are further represented as a labour resource. These discourse types reflect how the construction of the linguistic 'we' is expected to be maintained. Loyalty is triggered by arguments that the collective identity is threatened and is itself used in reproducing the collective 'we' through hegemonic expressions of monolingualism in the public space and semi-public space. The denigration of immigrants is used as a tool for enhancing societal security through solidarity and as a possible justification for the denial of minority rights. Also, although language acquisition patterns still follow the historical trend of language shift, factors indicating cultural separateness such as the appearance of speech communities or the use of minority languages in the public space and semi-public space have led to manifestations of intolerance. Examples of discrimination and prejudice towards minority groups indicate that the perception of worth of a shared language differs from the actual worth of dominant language acquisition for integration purposes. The study further indicates that the efficient working of the free market by using minority languages to sell services or buy labour is perceived as conflicting with nation-building notions since it may create separately functioning sub-communities with a new cultural capital recognised as legitimate competence. The discourse types mainly represent securitising moves constructing existential threats. The perception of threat and ideas of national belonging are primarily based on a zero-sum notion favouring monolingualism. Further, the identity of the immigrant individual is seen as dynamic and adaptable to assimilationist measures whereas the identity of the state and its members are perceived as static. Also, the study shows that debates concerning language status are linked to extra-linguistic matters. To conclude, policy makers in the US need to consider the relationship between four factors, namely societal security based on collective identity, individual/human security, human rights, and a changing linguistic demography, for proposed language intervention measures to be successful.

La confrontation de la laideur avec la beauté dans lesromans Mercure et Attentat. Une étude sur lareprésentation de la dualité thématique laideur-beautéchez Amélie Nothomb. : "Where there is Quasimodo, there is also Esmeralda." The confrontationbetween ugliness and beauty in the novels Mercure and Attentat. Astudy on the representation of the duality beauty-ugliness in the worksof Amélie Nothomb.

This paper studies one of the recurrent topics of writing found in Amélie Nothomb’snovels: beauty and ugliness. The novels Mercure and Attentat are analyzed in detail,with respect to figures of speech used to describe the extreme physical appearance ofthe protagonists and the role of the duality beauty-ugliness in the advancement of theplot.

First-principle data-driven models for assessment of motor disorders in Parkinson’s disease

Parkinson’s disease (PD) is an increasing neurological disorder in an aging society. The motor and non-motor symptoms of PD advance with the disease progression and occur in varying frequency and duration. In order to affirm the full extent of a patient’s condition, repeated assessments are necessary to adjust medical prescription. In clinical studies, symptoms are assessed using the unified Parkinson’s disease rating scale (UPDRS). On one hand, the subjective rating using UPDRS relies on clinical expertise. On the other hand, it requires the physical presence of patients in clinics which implies high logistical costs. Another limitation of clinical assessment is that the observation in hospital may not accurately represent a patient’s situation at home. For such reasons, the practical frequency of tracking PD symptoms may under-represent the true time scale of PD fluctuations and may result in an overall inaccurate assessment. Current technologies for at-home PD treatment are based on data-driven approaches for which the interpretation and reproduction of results are problematic.  The overall objective of this thesis is to develop and evaluate unobtrusive computer methods for enabling remote monitoring of patients with PD. It investigates first-principle data-driven model based novel signal and image processing techniques for extraction of clinically useful information from audio recordings of speech (in texts read aloud) and video recordings of gait and finger-tapping motor examinations. The aim is to map between PD symptoms severities estimated using novel computer methods and the clinical ratings based on UPDRS part-III (motor examination). A web-based test battery system consisting of self-assessment of symptoms and motor function tests was previously constructed for a touch screen mobile device. A comprehensive speech framework has been developed for this device to analyze text-dependent running speech by: (1) extracting novel signal features that are able to represent PD deficits in each individual component of the speech system, (2) mapping between clinical ratings and feature estimates of speech symptom severity, and (3) classifying between UPDRS part-III severity levels using speech features and statistical machine learning tools. A novel speech processing method called cepstral separation difference showed stronger ability to classify between speech symptom severities as compared to existing features of PD speech. In the case of finger tapping, the recorded videos of rapid finger tapping examination were processed using a novel computer-vision (CV) algorithm that extracts symptom information from video-based tapping signals using motion analysis of the index-finger which incorporates a face detection module for signal calibration. This algorithm was able to discriminate between UPDRS part III severity levels of finger tapping with high classification rates. Further analysis was performed on novel CV based gait features constructed using a standard human model to discriminate between a healthy gait and a Parkinsonian gait. The findings of this study suggest that the symptom severity levels in PD can be discriminated with high accuracies by involving a combination of first-principle (features) and data-driven (classification) approaches. The processing of audio and video recordings on one hand allows remote monitoring of speech, gait and finger-tapping examinations by the clinical staff. On the other hand, the first-principles approach eases the understanding of symptom estimates for clinicians. We have demonstrated that the selected features of speech, gait and finger tapping were able to discriminate between symptom severity levels, as well as, between healthy controls and PD patients with high classification rates. The findings support suitability of these methods to be used as decision support tools in the context of PD assessment.

The relative perceptual weight of two Swedish prosodic contrasts

Abstract. In addition to 9 vowel and 18 consonant phonemes, Swedish has three prosodic phonemic contrasts: word stress, quantity and tonal word accent. There are also examples of distinctive phrase or sentence stress, where a verb can be followed by either an unstressed preposition or a stressed particle. This study focuses on word level and more specifically on word stress and tonal word accent in disyllabic words. When making curriculums for second language learners, teachers are helped by knowing which phonetic or phonological features are more or less crucial for the intelligibility of speech and there are some structural and anecdotal evidence that word stress should play a more important role for intelligibility of Swedish, than the tonal word accent. The Swedish word stress is about prominence contrasts between syllables, mainly signaled by syllable duration, while the tonal word accent is signaled mainly by pitch contour. The word stress contrast, as in armen [´arːmən] ‘the arm’ - armén [ar´meːn] ‘the army’, the first word trochaic and the second iambic, is present in all regional varieties of Swedish, and realized with roughly the same acoustic cues, while the tonal word accent, as in anden [´anːdən] ‘the duck’ - anden [`anːdən] ‘the spirit’ is absent in some dialects (as well as in singing), and also signaled with a variety of tonal patterns depending on region. The present study aims at comparing the respective perceptual weight of the two mentioned contrasts. Two lexical decision tests were carried out where in total 34 native Swedish listeners should decide whether a stimulus was a real word or a non-word. Real words of all mentioned categories were mixed with nonsense words and words that were mispronounced with opposite stress pattern or opposite tonal word accent category. The results show that distorted word stress caused more non-word judgments and more loss, than distorted word accent. Our conclusion is that intelligibility of Swedish is more sensitive to distorted word stress pattern than to distorted tonal word accent pattern. This is in compliance with the structural arguments presented above, and also with our own intuition.

O hate speech e suas limitações

O objetivo deste trabalho de conclusão de curso é externar a relevância do direito à liberdade de expressão, especialmente em casos de discursos ofensivos e de incitação ao ódio, além de investigar se em algumas situações ele pode ser limitado para ceder a outros valores e de que forma. Por exemplo, através da técnica da ponderação ou de outros parâmetros pré-estabelecidos, os quais têm a função facilitar a resolução de casos difíceis, isto é, situações em que há a colisão entre direitos e deve-se chegar à conclusão de qual deles deve preponderar.

Identification of a Microdeletion at the 7q33-q35 Disrupting the CNTNAP2 Gene in a Brazilian Stuttering Case

Speech and language disorders are some of the most common referral reasons to child development centers accounting for approximately 40% of cases. Stuttering is a disorder in which involuntary repetition, prolongation, or cessation of the sound precludes the flow of speech. About 5% of individuals in the general population have a stuttering problem, and about 80% of the affected children recover naturally. The causal factors of stuttering remain uncertain in most cases; studies suggest that genetic factors are responsible for 70% of the variance in liability for stuttering, whereas the remaining 30% is due to environmental effects supporting a complex cause of the disorder. The use of high-resolution genome wide array comparative genomic hybridization has proven to be a powerful strategy to narrow down candidate regions for complex disorders. We report on a case with a complex set of speech and language difficulties including stuttering who presented with a 10Mb deletion of chromosome region 7q33-35 causing the deletion of several genes and the disruption of CNTNAP2 by deleting the first three exons of the gene. CNTNAP2 is known to be involved in the cause of language and speech disorders and autism spectrum disorder and is in the same pathway as FOXP2, another important language gene, which makes it a candidate gene for causal studies speech and language disorders such as stuttering. (C) 2010 Wiley-Liss, Inc.

Are Working Memory Measures Free of Socioeconomic Influence?

Purpose: This study evaluated the impact of socioeconomic factors on children's performance on tests of working memory and vocabulary.Method: Twenty Brazilian children, aged 6 and 7 years, from low-income families, completed tests of working memory ( verbal short-term memory and verbal complex span) and vocabulary ( expressive and receptive). A further group of Brazilian children from families of higher socioeconomic status matched for age, gender, and nonverbal ability also participated in the study.Results: Children from the low socioeconomic group obtained significantly lower scores on measures of expressive and receptive vocabulary than their higher income peers but no significant group differences were found on the working memory measures.Conclusion: Measures of working memory provide assessments of cognitive abilities that appear to be impervious to substantial differences in socioeconomic background. As these measures are highly sensitive to language ability and learning in general, they appear to provide useful methods for diagnosing specific learning difficulties that are independent of environmental opportunity.

Secretion of middle ear in infants - Occurrence, recurrence and related factors

Objective: The present study aimed at evaluating the occurrence and recurrence of middle ear effusion and possible associated factors in the first two years of life of 190 newborns and infants, participants in the interdisciplinary prevention, detection, and intervention program at the Clínica de Educação para Saúde of Universidade do Sagrado Coração, Methods: Newborns and infants were monthly submitted to anamneses, otoscopy, behavioral hearing assessment using sound instruments and pure tones (pediatric audiometry) and tympanometry. Results: The results revealed that 68.4% of infants presented one or more episodes of middle ear effusion during their two first years, with more recurrence among males. Peak occurrence was between four and 12 months of age and, the earlier the first episode, the higher the probability of recurrence. Greatest incidence was during May and August. It was found that, of the variables investigated, the period of exclusive breastfeeding actuated as a protector factor. With respect of risk factors, it was observed that passive smoking, gastro-esophageal reflux and respiratory allergy were related with the recurrences of effusion. Conclusion: Findings revealed the importance of periodic auditory follow-up for infants during their first two years of life, considered to be the critical period of auditory system maturation, during which sensory deprivation can be responsible for damage to the development of speech, language and other auditory abilities. Copyright © 2005 by Sociedade Brasileira de Pediatria.

Wavelets in a problem of signal processing

In this work a new method is proposed for noise reduction in speech signals in the wavelet domain. The method for signal processing makes use of a transfer function, obtained as a polynomial combination of three processings, denominated operators. The proposed method has the objective of overcoming the deficiencies of the thresholding methods and the effective processing of speech corrupted by real noises. Using the method, two speech signals are processed, contaminated by white noise and colored noises. To verify the quality of the processed signals, two evaluation measures are used: signal to noise ratio (SNR) and perceptual evaluation of speech quality (PESQ).

Cephalometric evaluation of hyoid bone position in a patient with Down syndrome: Case report

The hyoid bone contributes to the maintenance of the airway, chewing and swallowing, given to its anatomical and functional relations to the craniocervical complex. Cephalometric analysis has great importance for orthopedics, orthodontics and oral maxillary surgery. For the treatment of patients with special care needs, the cephalometric evaluation of the position of the hyoid bone should also contribute as a complementary element for dental diagnosis and the selection of the adequate treatment. The aim of this paper is to demonstrate the alteration of the hyoid position after carrying out the functional orthopedic maxillary treatment in a 9 year-old patient with Down Syndrome. Initial cephalometric analysis revealed inadequate position of hyoid bone. The association of speech therapy to dynamic functional rehabilitation of jaws showed a positive effect in occlusal relation and facial expression. After treatment, all dimensions obtained from the hyoid triangle were higher than initial ones, except the anterior-posterior value of C3-H, which suggested function improvement of stomatognathic system. Once considered its anatomical and physiological relationship with the others structures of the stomatognathic system, cephalometric analysis of hyoid bone position was helpful to the comprehension of the craniofacial abnormalities related to chromosomal anomaly, and thus is essential to the interdisciplinary dialogue.

Prevalence of risk factors for stuttering among boys: analytical cross-sectional study

CONTEXTO E OBJETIVO:Há poucos estudos sobre os fatores de risco para os subgrupos de gagueira. O objetivo deste estudo foi caracterizar os fatores de risco para a gagueira desenvolvimental familial em meninos que gaguejam e que não gaguejam como tipologia das disfluências, fatores qualitativos e comunicativos associados, estresse físico e emocional, atitude familiar e reação pessoal.TIPO DE ESTUDO E LOCAL:Estudo transversal analítico com um grupo controle, realizado no Laboratório de Estudo da Fluência, que faz parte do Departamento de Fonoaudiologia de uma universidade pública.MÉTODOS:Pais de 40 meninos com e sem gagueira pareados por idade fizeram parte do estudo. Os participantes foram divididos em dois grupos: crianças com gagueira e crianças sem gagueira, com idades entre 6 anos 0 meses e 11 anos 11 meses Inicialmente todos os participantes foram submetidos a uma avaliação de fluência e depois os dados foram coletados por meio do Protocolo de Risco para a Gagueira do Desenvolvimento.RESULTADOS:Não foi observada diferença nos fatores de estresse físicos e reações pessoais entre os grupos. As atitudes inadequadas familiares foram apresentadas por 95% das crianças com gagueira e 30% das crianças sem gagueira. Quatro fatores de risco analisados não ocorreram nas crianças sem gagueira, a saber, disfluências gagas, fatores qualitativos, estresse físico e emocional.CONCLUSÕES:Os achados sugerem que a presença de disfluências gagas, fatores qualitativos e comunicativos associados, estresse emocional e atitude familiar inadequada são fatores de risco importantes para a gagueira desenvolvimental familial em meninos.

A study of the role of the FOXP2 and CNTNAP2 genes in persistent developmental stuttering

A number of speech disorders including stuttering have been shown to have important genetic contributions, as indicated by high heritability estimates from twin and other studies. We studied the potential contribution to stuttering from variants in the FOXP2 gene, which have previously been associated with developmental verbal dyspraxia, and from variants in the CNTNAP2 gene, which have been associated with specific language impairment (SLI). DNA sequence analysis of these two genes in a group of 602 unrelated cases, all with familial persistent developmental stuttering, revealed no excess of potentially deleterious coding sequence variants in the cases compared to a matched group of 487 well characterized neurologically normal controls. This was compared to the distribution of variants in the GNPTAB, GNPTG, and NAGPA genes which have previously been associated with persistent stuttering. Using an expanded subject data set, we again found that NAGPA showed significantly different mutation frequencies in North Americans of European descent (p = 0.0091) and a significant difference existed in the mutation frequency of GNPTAB in Brazilians (p = 0.00050). No significant differences in mutation frequency in the FOXP2 and CNTNAP2 genes were observed between cases and controls. To examine the pattern of expression of these five genes in the human brain, real time quantitative reverse transcription PCR was performed on RNA purified from 27 different human brain regions. The expression patterns of FOXP2 and CNTNAP2 were generally different from those of GNPTAB, GNPTG and NAPGA in terms of relatively lower expression in the cerebellum. This study provides an improved estimate of the contribution of mutations in GNPTAB, GNPTG and NAGPA to persistent stuttering, and suggests that variants in FOXP2 and CNTNAP2 are not involved in the genesis of familial persistent stuttering. This, together with the different brain expression patterns of GNPTAB, GNPTG, and NAGPA compared to that of FOXP2 and CNTNAP2, suggests that the genetic neuropathological origins of stuttering differ from those of verbal dyspraxia and SLI. Published by Elsevier Inc.

Dysarthria and quality of life in neurologically healthy elderly and patients with Parkinson's disease

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)