파킨슨병 환자에서 낙상군과 비낙상군에 대한 버그균형검사의 타당도

조규행,우영근,황수진,Cho, Gyu-Hang,Woo, Young-Keun,Hwang, Su-Jin 대한고유수용성신경근촉진법학회 2011 PNF and Movement Vol.9 No.3

Purpose : The purpose of this study was to evaluate the criterion-related validity of the Berg balance test between fallers and non-fallers in individuals with Parkinson's disease. Methods : Thirty-one patients were recruited for this study. Their initial diagnosis had been made on average $30.1{\pm}10.1$ years earlier. Score of Berg balance test showed significant correlations with indicators of motor functioning and daily living capacity. Berg balance test score was inversely associated with the unified Parkinson's disease rating scale-motor score, and Schwab and England activities of daily living rating scale. Results : In all 3 correlations, lower scores on the Berg balance test correlated with higher unified Parkinson's disease rating scale-motor scores. Results support the criterion-related validity of the Berg balance test. Conclusion : Our research results agree with other published research in suggesting that the Berg balance test may be used as a screening tool and ongoing assessment tool for patients with Parkinson's disease.

노인의 청력장애지수와 한국판 버그균형검사의 상관관계

조규행,황수진,Cho, Gyu-Hang,Hwang, Su-Jin 대한고유수용성신경근촉진법학회 2010 PNF and Movement Vol.8 No.1

Presbycusis or related-age hearing loss is approximately 30 percent for people aged over 65 years. The purpose of this study was to compare the relationship between the Hearing Handicap Inventory for the Elderly and the Berg Balance Scale for predicting and screening risk of falls in people over 65 years with diagnosed presbycusis. Thirty-five subjects all lived at the nursing home in Wonju. Disability caused presbycusis was measured using the Hearing Handicap Inventory for the Elderly, and static and dynamic balance was measured using Berg Balance Scale. Data were analyzed using Spearman correlation. Statistically significant differences were noted between two clinical meausres (r=.862, p<0.001). In conclusion, the results suggest that presbycusis may be able to predict dangerous falls in older persons.

효과적인 특징 벡터를 도입한 Support Vector Machine기반 음성 검출기

조규행,박윤식,이계환,장준혁 에스케이텔레콤 (주) 2008 Telecommunications Review Vol.18 No.2

본 논문에서는 support vector machine (SVM)을 이용하여 잡음 환경에서의 음성 검출기 (voice activity detection) 성능 향상을 위한 효과적인 특징 벡터를 제안한다. SVM은 통계적 학습 이론으로 훈련 데이터 사이의 최적 분류 초평면을 찾아내 최적화된 이진 분류를 보여준다. 음성 검출을 위한 SVM의 특징 벡터는 음성의 통계 모델에 기반한 음성 검출기에서 주요 파라미터로 사용된 세 가지 특징 벡터인 a posteriori SNR, a priori SNR과 predicted SNR을 결합하여 제시하였다. 도입된 특징 벡터를 적용한 SVM을 이용하여 구현된 음성 검출기의 성능 평가를 위해 G.729B의 음성 검출기와 기존에 제안된 SVM 기반의 음성 검출기와 비교하였으며, 전반적으로 제안된 특징 벡터를 사용했을 때 다양한 잡음 구간에서 향상된 성능을 보였다.

우도비 특징 벡터를 이용한 SVM 기반의 음성 검출기

조규행,강상기,장준혁,Jo, Q-Haing,Kang, Sang-Ki,Chang, Joon-Hyuk 한국음향학회 2007 韓國音響學會誌 Vol.26 No.8

본 논문에서는 기존의 통계적 모델 기반의 음성 검출기의 성능 향상을 위해 이진 분류에 우수한 support vector machine(SVM)을 도입한다. 기존의 통계적 모델 기반 음성 검출기의 경우 음성의 존재와 부재에 대한 가설로부터 각각의 통계적 모델을 세워 입력 데이타에 의해 결정된 각 주파수 채널별 우도비(likelihood ratio)를 단순히 기하 평균을 취하여 문턱값과 비교, 음성 검출 여부를 판단한다. 제안된 음성 검출기는 기존의 기하 평균을 이용한 결정식을 대신하여 분류 오류 확률이 최소화되도록 각 주파수 채널별 우도비를 SVM의 특징 벡터로 적용한다. 제안된 SVM 기반의 통계적 모델 음성 검출기는 기존의 LRT를 이용한 음성 검출기 및 SVM 기반의 음성 검출기들과 비교하여 다양한 잡음 환경에서 우수한 성능을 나타낸다. In this paper, we apply a support vector machine(SVM) that incorporates an optimized nonlinear decision rule over different sets of feature vectors to improve the performance of statistical model-based voice activity detection(VAD). Conventional method performs VAD through setting up statistical models for each case of speech absence and presence assumption and comparing the geometric mean of the likelihood ratio (LR) for the individual frequency band extracted from input signal with the given threshold. We propose a novel VAD technique based on SVM by treating the LRs computed in each frequency bin as the elements of feature vector to minimize classification error probability instead of the conventional decision rule using geometric mean. As a result of experiments, the performance of SVM-based VAD using the proposed feature has shown better results compared with those of reported VADs in various noise environments.

SVM의 확률 출력을 이용한 새로운 Global Soft Decision 기반의 음성 향상 기법

조규행,장준혁,Jo, Q-Haing,Chang, Joon-Hyuk 한국음향학회 2008 韓國音響學會誌 Vol.27 No.2

본 논문에서는 support vector machine (SVM) 기반의 global soft decison (GSD)을 이용한 새로운 음성 향상 기법을 제시한다. 일반적으로 soft decision (SD) 이득 수정 및 잡음 전력 추정에 근거한 음성 향상 기법이 hard decision을 이용한 음성향상 기법 보다 우수한 성능을 보이는 것으로 알려져 있다. 특히, 각 프레임에서의 음성 부재에 대한 효과적인 척도인 전역음성 부재확률 (global speech absence probability, GSAP)을 SD 기반의 음성 향상 기법에 적용한 여러 연구가 진행되었다. 본 논문에서는 sigmoid 함수를 이용하여 얻어진 SVM의 확률 출력에 의해 추정된 새로운 GSAP를 음성 향상 기법에 적용한다. 제안된 알고리즘의 성능은 다양한 잡음 환경에 적용하여 PESQ 및 MOS 평가 방법을 바탕으로 기존의 GSD 기반의 스펙트럼 향상 기법과 비교하여 향상된 결과를 나타내었다. In this paper, we propose a novel speech enhancement technique using global soft decision (GSD) based on the probabilistic outputs of support vector machine (SVM). Generally, speech enhancement algorithms applied soft decision gain modification and noise power estimation have bettor performance than those employing hard decision. Especially, global speech absence probability (GSAP), which is known as an effective measure of the speech absence in each frame, has been adopted to SD-based speech enhancement methods. For this reason, we introduce a new GSAP estimated from the probabilistic output of SVM using sigmoid function. The performance of the proposed algorithm is evaluated by the PESQ and MOS test under various noise environments and yields better results compared with the conventional GSD scheme.

Smoothed Global Soft Decision에 근거한 음성 향상 기법

조규행(Q-Haing Jo),박윤식(Yun-Sik Park),장준혁(Joon-Hyuk Chang) 대한전자공학회 2007 電子工學會論文誌-SP (Signal processing) Vol.44 No.6

본 논문에서는 잡음 환경에서의 음성 향상을 위해 향상된 Global Soft Decision (GSD) 기법을 제안한다. 통계적 모델을 바탕으로 한 음성 향상과 관련한 연구에서 GSD는 음성의 꼬리 부분에서 취약하다고 알려져 있으며, 이를 개선하기 위해 Smoothed Global Likelihood Ratio (SGLR)를 바탕으로 한 새로운 음성 향상 기법을 GSD에 적용한다. 제안된 방법은 다양한 잡음 환경에서 MOS 실험을 바탕으로 기존의 연구와 비교하였으며 우수한 성능을 보여주었다. In this paper, we propose an improved global soft decision for speech enhancement in noise environments. From an examination of statistical model-based speech enhancement, it is shown that the global soft decision has a fundamental drawback at the offset region of speech signals. To overcome the drawback, we apply a new speech enhancement method based on a smoothed Global likelihood ratio to the global soft decision. Performances of the proposed method are evaluated by subjective tests under various environments and yield better results compared with the reported speech enhancement method.

뇌졸중 환자에서 순환식 과제지향 프로그램이 기능 증진에 미치는 효과

조규행 ( Gyu Hang Cho ),이석민 ( Suk Min Lee ),우영근 ( Young Keun Woo ) 한국전문물리치료학회 2004 한국전문물리치료학회지 Vol.11 No.3

편마비 환자의 건측에 적용한 고유수용성 신경근 촉진법이 환측 근 긴장도에 미치는 영향

우영근,조규행,유은영 한국전문물리치료학회 2002 한국전문물리치료학회지 Vol.9 No.2

The purpose of this study was to investigate the effect of proprioceptive neuromuscular facilitation (PNF) approach on the spasticity of affected side in patients with hemiplegia, Three subjects with hemiplegia participated in this study. In single-subject research design (a multiple baseline across individuals) was employed in this study. The intervention program including PNF to the unaffected side was introduced for 30 minutes each day during each intervention phase. Muscle tone of affected side was measured with Tone Assessment Scale, and active hip abduction distance of affected side was taken with the subject supine. And then the muscle tone and the hip abduction distance were measured again 30 minutes later following the intervention. The results showed that the PNF application had some beneficial effects on both muscle tone and active hip abduction. This results suggests that PNF application to non-paretic limb can be effective in reducing muscle tone and improving hip abduction range on paretic limb in persons with hemiplegia. However, further research is needed to prove the effect of PNF application on functional improvement.

통계적 모델 기반의 음성 검출기를 위한 변별적 가중치 학습

강상익,조규행,박승섭,장준혁,Kang, Sang-Ick,Jo, Q-Haing,Park, Seung-Seop,Chang, Joon-Hyuk 한국음향학회 2007 韓國音響學會誌 Vol.26 No.5

In this paper, we apply a discriminative weight training to a statistical model-based voice activity detection(VAD). In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratios(LRs) based on a minimum classification error(MCE) method which is different from the previous works in that different weights are assigned to each frequency bin which is considered more realistic. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LR test. 본 논문에서는 음성의 통계적 모델에 기반한 음성검출기의 성능향상을 위해 변별적 가중치 학습(discriminative weight training) 기반의 최적화된 우도비 테스트(Likelihood Ratio Test, LRT)를 제안한다. 먼저, 기존의 통계모델기반의 음성검출기를 분석하고, 이를 기반으로 MCE(minimum classification error)방법을 도입하여, 각 주파수 채널별로 다른 가중치를 가지는 우도비 기반의 음성검출 결정법(decision rule)을 제시한다. 제안된 알고리즘은 비정상(non-stationary)잡음환경에서 기존의 동일 가중치를 가지는 기하 평균 기반의 음성검출기와 비교하였으며, 우수한 성능을 보인다.

아급성기 뇌졸중 환자의 체간 조절과 기능적 수행능력과의 관계

안승헌,조규행,An, Seung-heon,Cho, Gyu-Haeng 대한고유수용성신경근촉진법학회 2012 PNF and Movement Vol.10 No.3

Purpose : This study was to compare the difference Trunk Control Test(TCT), Postural Assessment Scale for Stroke(PASS-TC), and Trunk Impairment Scale(TIS) and its subscales in relation to the difference MBI(Modified Barthel Index), BBS(Berg Balance Scale), and to establish the association between MBI, BBS, Fugl Meyer-motor function(FM-M), and to predict MBI-subscales from the variables. Methods : 58 stroke patients, attending a rehabilitation programme, participated in the study. Trunk control was measured with the use of the TCT, PASS-TC, TIS, and the performance of Activities daily living was obtained by MBI, and dynamic balance ability(by BBS). Trunk control scores from the difference MBI, BBS were compared using the 1-way ANOVA(Mann Whitney U test) and the data were analyzed using Pearson product correlation. Multiple stepwise regression analyses were performed to identify prognostic factors for ADL subscale. Results : Trunk control scores showed significant differences between MBI(F=2.139~13.737, p<.05~.001), BBS(t=3.491~7.705, p<.01~.001). It was significantly related with value of the MBI(r=.25~.50), BBS(r=.38~.68), FMM( r=.31~.48). Stepwise linear regression analysis showed an additional, significant contribution of the TCT, in addition to the PASS-TC, dynamic sitting balance subscale of the TIS for measures of MBI subscales. Conclusion : Measures of trunk control were significantly related with values of MBI, BBS score, so the management of trunk rehabilitation after stroke should be emphasized. The use of both quantitative and qualitative scales was shown to be a good measuring instrument for the classification of the general performance of the stroke patients. Further study about trunk control is needed using a longitudinal study design.