• 산업경영시스템학회지
• /
• 제32권4호
• /
• pp.215-222
• /
• 2009

Human voice reacts very sensitively to human's minute physical condition. For instance, human voice disorders affect patients profoundly especially in the case of Parkinson's disease. Acoustic tools such as MDVP, can function as an equipment that measures various voice in different objects. Many different approaches have been applied for analyzing the voice disorders for diagnosis of Parkinson's disease. According to the voice data of suspected Parkinson's patients from UCI Machine Learning Repository, it is reported to have 23 people with Parkinson's disease and 8 healthy people. Applying Mahalanobis Taguchi System (MTS) for diagnosis of Parkinson's disease, the correct diagnosis performance is compared to previous research results.

• 음성과학
• /
• 제12권3호
• /
• pp.19-33
• /
• 2005

Tremor is a main factor of parkinsonism. Voice tremor may be the first, later or the only symptom of a neurological disease and its frequency, amplitude, and regularity may differ among the diseases of different neural subsystems. Differential diagnosis between idiopathic Parkinson's disease (IPD) and multiple system atrophy (MSA) has been difficult. This study included three groups: (1) 6 IPD patients; (2) 6 MSA patients; and (3) 20 ageand sex-matched normal controls. The MDVP (Multidimensional Voice Program) was used to analyze the sustained /a/phonation. The results were as follows: (1) frequency perturbation parameters (jitter, sPPQ, Vf0) and FTRI of tremor parameter of two patient groups were statistically different from those of the controls (p < .01); (2) measures were higher in short-term and long-term f0 and amplitude perturbation in MSA than IPD; (3) however, any acoustic parameters between IPD and MSA were not statistically different; except for the rate of frequency tremor, 4$\sim$5 Hz in IPD, 5$\sim$11 Hz in MSA and (4) the pattern of regularity for voice tremor through histogram indicated that amplitude of IPD was irregular while both f0 and amplitude of MSA were irregular. In conclusion, F0, rate of frequency tremor, and pattern of f0 regularity may be predictors for differential diagnosis. These findings might signify that voice tremor of parkinsonism was resulted from modulation of f0.

• 대한후두음성언어의학회지
• /
• 제28권2호
• /
• pp.71-78
• /
• 2017

Voice disorder is classified into three categories, structural, neurogenic and functional dysphonia. Neurogenic dysphonia refers to a disruption in the nerves controlling the larynx. Common examples of this include complete or partial vocal cord paralysis, spasmodic dysphonia. Also it occurs as part of an underlying neurologic condition such as Parkinson's disease, myasthenia gravis, Lou Gehrig's disease or disorder of the central nervous system that causes involuntary movement of the vocal folds during voice production. Functional dysphonia is a voice disorder in the absence of structual or neurogenic laryngeal characteristics. A near consensus exist that Muscle tension dysphonia (MTD) is functional voice disorder wherein hyperfunctional laryngeal muscle activity whereas Spasmodic dysphonia (SD) is neurogenic, action-induced focal laryngeal dystonia including several subtype. Both Adductor type spasmodic dysphonia (AdSD) and MTD may be associated with excessive supraglottic contraction and compensation, resulting in a strained voice quality with spastic voice breaks. It makes these two disorders extremely difficult to differentiate based on clinical interpretation alone. Because treatment for AdSD and MTD are quite different, correct diagnosis is important. Clinician should be aware of the specific vocal characteristics of each disease to improve therapeutic outcome.

• 사상체질의학회지
• /
• 제28권4호
• /
• pp.309-319
• /
• 2016

Objectives This study was aimed to analyze the reliability of vocal features and probabilities for being in Sasang constitutional types calculated from Sasang constitutional voice diagnosis system according to operator presence. Methods We acquired 96 voice recordings from one male and one female for 4 days. For the first 2 days, the subjects recorded their voice by themselves. For the last 2 days, they recorded according to the instruction of an operator following the standard operating procedure. We analyze the standard deviations of vocal features, probabilities for being three constitutional types, Tae-Eum (TE), So-Yang (SY), and So-Eum (SE) Results In the case of the female, coefficients of variations of the voice variables and the probabilities for being each constitutional type were all within 20%. In the case of the male, coefficients of variations were all within 20% except one variable. Even if there was no instruction from the operator, standard deviations of the probability did not increase for both genders. When recorded without the operator, for male, the probability for being SE decreased by 3.2%. For female, the probability for being TE increased by 5.438%, and that of SE decreased by 3.057%, and that of SY decreased by 2.394%. Conclusions When recorded without operators, for men, there was a significant difference in the probability for being SE. And for women, there were significant differences in the probabilities for all constitutional types.

• 대한기관식도과학회지
• /
• 제7권2호
• /
• pp.161-167
• /
• 2001

Background and Objectives： Total laryngectomy is often required for advanced cases. But this operation induced the many inconvenience of basic daily life. Early diagnosis of laryngeal cancer is very important to prevent from this disastrous condition. In this point of view, mass screening test for early detection of laryngeal cancer is necessary. Screening test using voice has many advantages such as simple, less interventional. Voice collection by Automatic Response System(ARS) is comfortable and easy to got acoustic sample. Thus author tried to got the acoustic parameters which can differentiate normal, benign. and malignant laryngeal diseases and also checked the availability of parameters on neural network system. Materials and Methods: Author has evaluated the voice from 17 laryngeal cancer patients and 45 benign laryngeal disease patients who visited at Department of Otolaryngology, Pusan National University Hospital from May 1998 to April 2001, and 15 normal control. Author chose the sir Parameters (Jitt. vFo, Shim, vAm, NHR, SPI) that was thought to be related with voice collected by ARS among thirty-three parameters analysed by a Multi-Dimensional Voice Program (MDVP). Two-step neural network was used for the availability of six parameters. Results: The detection rate of normal voice by ARS voice analysis is 78.5% and detection rate of abnormal voice was 97.1 o/o. Among abnormal voice, the detection rate of benign laryngeal diseases and laryngeal cancers were 82.4 o/o, 70.6% respectively. Conclusion: Author concluded that six parameters and Matlab based neural network software may be effective in development of acoustic screening system for laryngeal cancer and further study should be necessary for development of new acoustic parameters.

• 한국통신학회논문지
• /
• 제34권10B호
• /
• pp.1062-1069
• /
• 2009

비만으로 인해 대사증후군을 많이 앓고 있는 상황에서 후유증으로 신장 질환이 커다란 사회문제가 되고 있는 실정이다. 따라서 자각증상이 없는 신장의 이상 유무를 조기에 판단하여 적절한 조치를 취하는 것이 무엇보다 중요하다. 이를 위해 본 논문에서는 음성 분석을 통해 신장 질환을 무자각, 무구속, 무통종의 방법으로 진단할 수 있는 방법을 제안하였다. 구성하고자 하는 전체 시스템은 크게 음성 분석과 얼굴색을 살피는 방법을 결합시키는 시스템이 개발되고 있으며 이 중 본 논문은 입술소리를 기반으로 신장 질환을 진단하는 방법에 설계하였다. 이를 위해 본 논문에서는 첫째, 신장 질환을 앓고 있는 환자와 정상인을 대상으로 피실험자 집단을 각각 구성하고 입술소리의 수치학적 분석을 실험으로 출력하고 그 결과값에 대한 비교 분석을 수행하였으며 둘째, 한의학적 청진 이론과 언어학, 음성학과의 상관성을 분석하고 이를 기반으로 음성에 대한 신장의 특징 요소를 추출하여 제1포먼트 주파수와의 연관성을 도출하였다. 실험 결과 신장 질환자 집단이 정상인 집단보다 제1포먼트 주파수 대역폭이 넓게 형성되는 결과를 추출하였으며 최종적으로 입술소리만으로 신장 질환을 진단할 때의 오진 확률에 대해 계산하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.355-357
• /
• 2019

고령화 사회로 진입하고 있는 지금, 시니어 세대에게는 새로운 디바이스나 IoT기술에 대한 사용자 접점은 매우 불편하다. 이를 개선하기 위하여 우리는 AI 기술 기반 지능형 시니어 도우미 음성인식 시스템을 제안한다. 제안 시스템은 Cloud platform기반 API를 구현하여 머신러닝 처리 활용을 위한 데이터를 축적하며, 치매진단, 치매예방활동을 위한 콘텐츠를 제공하며,시니어 세대를 위한 챗봇 콘텐츠를 제공한다. 우리가 제안한 개념모델을 이용한 서비스를 API로 제공함으로서 시니어 세대에 대한 IoT기반 등 새로운 디바이스의 접근성 및 편리성을 증대하는 계기가 될 것으로 기대한다.

• 사상체질의학회지
• /
• 제24권1호
• /
• pp.13-20
• /
• 2012

1. Objectives : It is very important to classify people into Sasang constitution correctly in SCM. There have been many researches for this and several tools have been developed for diagnosis of Sasang constitution. In our study, we introduce a new web application for Integrated Sasang Constitutional Diagnosis (ISCD) ${\beta}$-version and algorithm on the base of face, body shape, voice and questionnaire. 2. Development : The web application of ISCD ${\beta}$-version was designed to be used easily for subject, staffs, and oriental medical doctors. For this purpose, we developed a web-application of Integrated Sasang Constitutional Diagnosis ${\beta}$-version using mysql database, tomcat web system, JSP, JAVA, and C++ languages. 3. Current State : The ISCD ${\beta}$-version could be accessed at http://210.218.196.115/SDT/login.jsp. The ISCD ${\beta}$-version consisted of 3 parts, for staffs, subject and oriental medical doctors. The system has been managed since February 2011. Currently 7 oriental hospitals have used the system and 1,439 subjects have been diagnosed by the system. 4. Conclusion and future work : Although many researchers have tried to develop a system or an algorithm for diagnosis of subject's constitution, we could have not used the system based on objective information of human body type, characters, symptoms. In this study, we describe a web application of objective diagnosis algorithm as ISCD ${\beta}$-version. This system may help an oriental medical doctors to make a decision of Sasang constitutional diagnosis easily and correctly.

• 사상체질의학회지
• /
• 제24권3호
• /
• pp.34-41
• /
• 2012

Objectives In this study, we developed a mock-up of the system for Sasang Constitutional (SC) diagnosis. This system consists of 5 devices which are the face analyzer, the voice analyzer, the skin analyzer, the pulse analyzer, and the computer-based questionnaire. Our goal is to evaluate the repeatability of the system. Methods Each device is capable of classifying SC types. The classification probability of the integrated system for the SC types was obtained by summing the probability from each device. For evaluating the repeatability of the system, we collected data for 5 subjects, and repeated the measurement three times for each individual. The average and standard deviation were used for calculating the Coefficient of Variation. Results The results showed that the repeatability of the classification probability of the integrated system is about 8%, which implies the system is repeatable. Conclusions To increase usability of this system, it is desirable for the system to offer information on health condition of the user. The integrated constitutional diagnosis system will be upgraded to complement the convenience and to develop the diagnostic algorithm for the user's health condition.

• 한국산학기술학회논문지
• /
• 제9권5호
• /
• pp.1210-1217
• /
• 2008

사상의학은 개인별 체질의 분류에 따른 맞춤형 의학으로 우리나라 고유의 독특한 전통 의학이다. 이와 같은 사상의학에서 가장 중요하게 여겨지는 것이 사상체질의 정확한 분류이다. 따라서 사상체질 분류에 대한 객관적 요소의 확보 및 진단 지표 마련이 시급하게 해결되어야 할 과제이다. 이를 위해 본 논문에서는 사상체질 분류의 객관화, 정량화 및 시각화를 위해 얼굴 영상 신호와 음성 신호를 분석하여 결과값을 추출하고 체질별 집단군간의 차이점을 비교하여 사상체질 분류 시스템을 구현하고자 한다. 특히 영상 및 음성 신호는 성별, 연령별, 지역별 등의 구분에 따라 달라지기 때문에 본 논문에서는 40에서 50대 사이의 장년 여성을 대상으로 서울지역 거주자에 한해 사상체질 집단군을 구성하고 이들의 영상 및 음성 신호를 추출하여 체질간 비교, 분석을 수행하고자 한다. 최종적으로 실험을 통한 연구 결과의 유의성을 입증하고자 한다.