• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• 한국정보통신학회논문지
• /
• 제17권4호
• /
• pp.775-780
• /
• 2013

본 논문에서는 백색잡음 및 자동차잡음 환경 하에서 남녀 성별인식이 가능한 신경회로망에 의한 화자종속 음성인식 알고리즘을 제안한다. 본 논문에서 제안한 음성인식 알고리즘은 남성화자 및 여성화자를 인식하기 위하여 LPC 켑스트럼 계수를 사용하여 신경회로망에 의하여 학습된다. 본 실험에서는 백색잡음 및 자동차잡음에 대하여 총 6개의 신경회로망의 네크워크에 대한 인식결과를 나타낸다. 인식실험의 결과로부터 백색잡음에 대해서는 최대 96% 이상의 인식률, 자동차잡음에 대해서는 최대 88% 이상의 인식률을 구하였다. 마지막으로 본 실험에서는 제안하는 음성인식 알고리즘이 배경잡음 환경 하에서의 기존의 음성인식 알고리즘과 비교하여 본 방식의 알고리즘이 유효하다는 것을 실험으로 확인한다.

• 대한한방소아과학회지
• /
• 제24권3호
• /
• pp.138-149
• /
• 2010

Objectives: The purpose of this study is to estimate genetic and environmental factors which can effect growth, and predict final height using this factors. Methods: Correlation analysis and regression analysis were conducted between measurements of height and Genetic & environmental factors through survey from 1352 child & adolescent patients. Results: Factors which have correlation with height percentile are MPH(Mid-Parental Height), NBW(Neonatal body weight), anorexia, dyspepsia, atopic dermatitis, frequency of breakfast and quality of sleeping time. MPH has moderate relation, NBW and anorexia have fair relation, and other factors have linear but poor relation. Regression equation from factors which have correlation and height percentile has 26.9% of predictive power. Regression equation considering only genetic factor has 20.4%. MPH has the most effect on height percentile. Anorexia has more effect than NBW. Other factors also have small and similar effect. Conclusions: Height of parents has the most effect on growth, anorexia, dyspepsia, atopic dermatitis, frequency of breakfast and quality of sleeping time also has effect.

• 대한후두음성언어의학회지
• /
• 제13권1호
• /
• pp.52-58
• /
• 2002

The pitch range of the human voice is variable, extending from chest register to falsetto. Although numerous studies have investigated after laryngeal mechanism description of registers, systematic and objective studies were lack. The purpose of this study was to analyze and compare head register with chest register of singers acoustically. Fifteen healthy tenor major students were selected. Fifteen healthy untrained adults were the control group for this study. Long term average(LTA) power spectrum using the Fast Fourier transform(FFT) algorithm and Linear predictive coding (LPC) filter response were made during /a/ sustained in both head(G4, 392Hz) md chest registers (C3, 131Hz). Statistical analysis was performed using Mann-Whitney test. In the LTA power spectrum, head register of singer has increased level(energy gain) in the frequency band of 2.2-3.4kHz(p<0.01), and 7.5-8.4kHz(p<0.01, p<0.05). Chest register of singer has increased level in the frequency band of 2.2-3.1kHz(p<0.01), 7.8-8.4kHz(p<0.05) and around 9.6kHz(p<0.01). LTA power spectrum reveals a peak of acoustic energy around 2500Hz known as the singer's formant and another peak of acoustic energy around 8000Hz in singer's voice.

• 한국통신학회논문지
• /
• 제21권6호
• /
• pp.1430-1437
• /
• 1996

중간 주파수 대역(8kbps) 이하에서 적은 지연을 갖는 벡터여기 선형예측 음성 부호화기(LD-CELP)에 대하여 고려한다. 합성필터를 입력 프레임의 종류에 따라 변화시켜 음성 부호화기의 성능을 향상시키고자 한다. 먼저 프레임을 유성음과 무성음 그리고 개시 프레임으로 분류한다. 유성음과 무성음 프레임에서는 합성필터의 스펙트럼 포락을 음운의 특성에 적합하도록 변화시킨다. 개시 프레임에서는 합성필터의 성격을 바꾸어주기 위하여 바이어스 필터를 이용한다. 제안된 부호화기는 다른 적은 지연을 갖는 벡터여기 선형예측 음성 부호화기들에 비하여 비슷한 지연시간을 갖으면서 더 나은 음질을 제공하였다.

• Radiation Oncology Journal
• /
• 제37권1호
• /
• pp.1-12
• /
• 2019

Despite recent innovation in treatment techniques and subsequently improved outcomes, the majority of glioblastoma (GBL) have relapses, especially in locoregional areas. Local re-irradiation (re-RT) has been established as a feasible option for recurrent GBL of all ages with safety, tolerability, and effectiveness both in survival and quality of life regardless of fractionation schedule. To keep adverse effects under acceptable range, cumulative dose limit in equivalent dose at 2 Gy fractions by the linear-quadratic model at α/β = 2 for normal brain tissue (EQD2) with narrow margin should be observed and single/hypofractionated re-RT should be undertaken very carefully to recurrent tumor with large volume or adjacent to the brainstem. Promising outcome of re-operation (re-Op) plus re-RT (re-Op/RT) need to be validated and result from re-RT with temozolomide/bevacizumab (TMZ/BV) or new strategy is expected. Development of new-concept prognostic scoring or risk group is required to select patients properly and make use of predictive biomarkers such as O(6)-methylguanine-DNA methyltransferase (MGMT) promotor methylation that influence outcomes of re-RT, re-Op/RT, or re-RT with TMZ/BV.

• 한국보건간호학회지
• /
• 제33권3호
• /
• pp.354-363
• /
• 2019

Purpose: This study was undertaken to identify factors related to quit-smoking intention based on the planned behavior theory among out-of-school youths. Methods: This study was a quantitative research, data were collected during Nov. 1. 2018 to Feb. 28, 2019, study subjects were 189 out-of-school youths in Youth support Center located in A, B, C area city. The data were analyzed using independent sample t-test and one-way ANOVA, Pearson's correlation coefficient, and multiple linear regression. Results: There was a significant differences of quit smoking intention according to age, weekly allowance, participate of antismoking program. There were positive correlations between quit smoking intention and attitude to non-smoking and perceived behavior control. In smoking cessation intention influenced by predictive variable, age, weekly allowance, attitude to non-smoking, and perceived behavior control explain 26.8% smoking cessation intention. Conclusion: We believe that findings from this study will help to develop the specific smoking cessation education program for out-of-school youth's health behaviors.

• 융합보안논문지
• /
• 제8권4호
• /
• pp.135-143
• /
• 2008

일반적인 HMI system은 원격 감시제어를 네트워크를 통하여 하고 있으나 기능이 제한 적이다. 본 논문에서는 산업용 HMI 시스템을 변형된 상태분할 알고리즘을 적용 하였다. 이 방법은, 미리 예상되는 질의어에 대한 데이터들을 갖고 모델링을 하였다. 그 결과, 모델링하는데 많은 시간이 절약되었고, 시스템을 안정적이고 정밀하게 구성하여 98.15%의 높은 인식률을 나타냈다. 음성 HMI 시스템을 산업용에 적용하여 인간이 직접적으로 활동할 수 없는 작업 환경에서도 산업용 기기들을 안정적으로 구동시킬 수 있다. HMI 시스템 엔진의 성능을 최적화하였다.

• 한국태양에너지학회 논문집
• /
• 제33권5호
• /
• pp.1-8
• /
• 2013

Wind resource data of short-term period has to be corrected a long-term period by using MCP method that Is a statistical method to predict the long-term wind resource at target site data with a reference site data. Because the field measurement for wind assessment is limited to a short period by various constraints. In this study, 2 different MCP methods such as Linear regression and Matrix method were chosen to compare the predictive accuracy between the methods. Finally long-term wind speed, wind power density and capacity factor at the target site for 20 years were estimated for the variability of wind and wind energy. As a result, for 20 years annual average wind speed, Yellow sea off shore wind farm was estimated to have 4.29% for coefficient of variation, CV, and -9.57%~9.53% for range of variation, RV. It was predicted that the annual wind speed at Yellow sea offshore wind farm varied within ${\pm}10%$.

• 대한전자공학회논문지TE
• /
• 제39권2호
• /
• pp.60-65
• /
• 2002

본 논문에서는, 음성 인식률 향상을 위하여 청각 특성을 기반으로 한 GFCC(gammatone filter frequency cepstrum coefficients) 파라미터를 음성 특징 파라미터로 제안한다. 그리고 전화망을 통해 얻은 고립단어를 대상으로 인식실험을 수행하였다. 성능비교를 위하여 MFCC(mel frequency cepstrum coefficients)와 LPCC(linear predictive cepstrum coefficient)를 사용하여 인식 실험을 하였다. 또한, 각 파라미터에 대하여 전화망의 채널 왜곡 보상기법으로 CMS(cepstral mean subtraction)를 도입한 방법과 적용시키지 않은 방법으로 인식실험을 하였다. 실험 결과로서, GFCC를 사용하여 인식을 수행한 방법이 다른 파라미터를 사용한 방법에 비해 향상된 결과를 얻었다.