• The Journal of the Acoustical Society of Korea
• /
• 제17권2E호
• /
• pp.31-37
• /
• 1998

This paper proposes a feature extraction method using wavelet transform for speech recognition. Speech recognition system generally carries out the recognition task based on speech features which are usually obtained via time-frequency representations such as Short-Time Fourier Transform (STFT) and Linear Predictive Coding(LPC). In some respects these methods may not be suitable for representing highly complex speech characteristics. They map the speech features with same may not frequency resolutions at all frequencies. Wavelet transform overcomes some of these limitations. Wavelet transform captures signal with fine time resolutions at high frequencies and fine frequency resolutions at low frequencies, which may present a significant advantage when analyzing highly localized speech events. Based on this motivation, this paper investigates the effectiveness of wavelet transform for feature extraction of wavelet transform for feature extraction focused on enhancing speech recognition. The proposed method is implemented using Sampled Continuous Wavelet Transform (SCWT) and its performance is tested on a speaker-independent isolated word recognizer that discerns 50 Korean words. In particular, the effect of mother wavelet employed and number of voices per octave on the performance of proposed method is investigated. Also the influence on the size of mother wavelet on the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is compared with the most prevalent conventional method, MFCC (Mel0frequency Cepstral Coefficient). The experiments show that the recognition performance of the proposed method is better than that of MFCC. But the improvement is marginal while, due to the dimensionality increase, the computational loads of proposed method is substantially greater than that of MFCC.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.870-882
• /
• 2020

It is that failure of equipment at the factory site causes personal injury and property damage. We are required a real-time monitoring and risk forecasting techniques to prevent for equipment failure. In this paper, we proposed a 3-phase smart plug and real-time monitoring system that can be used in factories, and collected environmental information and power information using a smart plug to analyze the data. In order to analyze the correlation between the risk situation and the collected data, we predicted the risk situation using Linear Regression, SVM, and ANN algorithms. As a result, the SVM and ANN algorithms obtained high predictive accuracy and developed a mobile app that could use it to check the risk forecast results.

• Structural Monitoring and Maintenance
• /
• 제5권3호
• /
• pp.325-343
• /
• 2018

This study aims to propose a performance-based design method of a novel passive base isolation system, BIO isolation system, which is inspired by an energy dissipation mechanism called 'sacrificial bonds and hidden length'. Fragility functions utilized in this study are derived, indicating the probability that a component, element, or system will be damaged as a function of a single predictive demand parameter. Based on PEER framework methodology for Performance-Based Earthquake Engineering (PBEE), a systematic design procedure using performance and fragility objectives is presented. Base displacement, superstructure absolute acceleration and story drift ratio are selected as engineering demand parameters. The new design method is then performed on a general two degree-of-freedom (2DOF) structure model and the optimal design under different seismic intensities is obtained through numerical analysis. Seismic performances of the biologically inspired (BIO) isolation system are compared with that of the linear isolation system. To further demonstrate the feasibility and effectiveness of this method, the BIO isolation system of a 4-storey reinforced concrete building is designed and investigated. The newly designed BIO isolators effectively decrease the superstructure responses and base displacement under selected earthquake excitations, showing good seismic performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.310-312
• /
• 2004

The aim of this study was to analyze the characteristics of knee joint sound in frequency domain and classify the knee joint diseases. The spectral analysis of knee joint sounds was performed using LPC(Linear Predictive Coding) and Wigner-Ville distribution. Ten normal subjects and 5 patients with meniscal tearing were enrolled. Each subject was seated on a chair and underwent active knee flexion and extension for 60 seconds. Sampling frequency was 10kHz and electronic stethoscope and electro-goniometer were applied during the knee motion for data collection. The spectral analysis showed 3 peaks in both groups and the difference energy distribution in time-frequency domain. These results suggest that the diagnosis of knee joint pathology using the auscultation could be easier and more correct.

• 한국식품저장유통학회지
• /
• 제6권1호
• /
• pp.29-36
• /
• 1999

Using Fuji apple fruits cultivated in Kyungpook prefecture, the calibration model for firmness evaluation of fruits by near infrared(NIR) reflectance spectroscopy was developed, and the various influence factors such as instrument variety, measuring method, sample group, apple peel and selection of firmness point were investigated. Spectra of sample were recorded in wavelength range of 1100∼2500nm using NIR spectrometer (InfraAlyzer 500), and data were analyzed by stepwise multiple linear regression of IDAS program. The accuracy of calibration model was the highest when using sample group with wide range, and the firmness mean values obtained in graph by texture analyser(TA) were used as standard data. Chemometrics models were developed using a calibration set of 324 samples and an independent validation set of 216 samples to evaluate the predictive ability of the models. The correlation coefficients and standard error of prediction were 0.84 and 0.094kg, respectively. Using developed calibration model, it was possible to monitor the firmness change of fruits during storage frequently. Time, which was reached to firmness high value in graph by TA, is possible to use as new parameter for freshness of fruit surface during storage.

• Journal of Electrical Engineering and Technology
• /
• 제8권5호
• /
• pp.975-983
• /
• 2013

This study proposes a low order dynamic model of a building system in order to predict thermal behavior within a building and its energy consumption. The building system includes a thermally well-insulated room and an electric heater. It is modeled by a second order lumped RC thermal network based on the thermal-electrical analogy. In order to identify unknown parameters of the model, an experimental procedure is firstly detailed. Then, the different linear parametric models (ARMA, ARX, ARMAX, BJ, and OE models) are recalled. The parameters of the parametric models are obtained by the least square approach. The obtained parameters are interpreted to the parameters of the physically based model in accordance with their relationship. Afterwards, the obtained models are implemented in Matlab/Simulink(R) and are evaluated by the mean of the sum of absolute error (MAE) and the mean of the sum of square error (MSE) with the variable of indoor temperature of the room. Quantities of electrical energy and converted thermal energy are also compared. This study will permit a further study on Model Predictive Control adapting to the proposed model in order to reduce energy consumption of the building.

• 한국소음진동공학회논문집
• /
• 제21권11호
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• 기술혁신학회지
• /
• 제9권2호
• /
• pp.304-324
• /
• 2006

재무분석가들은 기업의 파산에 양향을 미치는 예측변수를 탐색하기 위해서 상당한 연구가 수행되어 왔다. 그러나 기술지향적 중소벤처기업은 일반적으로 역사적 재무자료가 부족하고, 기술경쟁력 수준에 따라 잠재적인 고성장과 고위험이 존재한다. 본 논문에서는 재무자료 대신에 기술력평가 자료를 이용하여 파산을 예측하기 위해서 파산예측 판별모형을 제안하였고, 모형의 정분류율을 통해서 예측력을 검증하기 위해서 교차타당성방법, 최대사후확률방법 등을 사용하였다. 분석결과 중소 벤처기업의 파산예측모형으로 선형판별모형이 로지스틱판별모형보다 적합한 모형이고, 표본자료에 대한 정분류율 추정은 약 69% 이고 정분류율 예측은 약 67% 가 될 것으로 기대된다.

• 한국음향학회지
• /
• 제20권7호
• /
• pp.69-75
• /
• 2001

화자확인에서 화자내 변이, 잡음환경, 그리고 학습환경과 인식 환경의 불일치는 화자확인 시스템이 실용화될 수 없는 가장 큰 원인이다. 본 연구에서는, 실제 환경에 강인한 화자 확인 시스템의 구현에 초점을 맞추어 음성 전처리 과정인 잡음환경에 강인한 끝점추출 알고리즘, 잡음제거 및 마이크특성 보상기법, LPG(Linear Predictive Coefficient)켑스트럼 가중치에 의한 화자간 변별력 향상 기법을 제안한다. 실험 결과, LPC잔차신호(residue)를 이용한 끝점추출 알고리즘을 사용한 경우 약 17.65% 가량의 끝점 추출 에러율을 향상시켰으며, 제안한 잡음제거 및 마이크특성 보상기법을 사용한 경우 다른 마이크 환경에서 화자 오인식율이 약 36.93% 가량 개선되었다. 또한, 제안한 LPC켑스트럼 가중치에 의한 화자간 변별력 향상 기법은 평균 화자 오인식율을 약 6.515% 향상시켰다.