• 대한전기학회논문지:전력기술부문A
• /
• 제48권12호
• /
• pp.1544-1553
• /
• 1999

Recently, ultrasonic testing techniques have been widely used in the evaluation of the quality of metal. In this experiment, six heat-treated temperature of specimen have been considered : 0, 1200, 1250, 1300, 1350 and 1387$^{\circ}C$. As heat-treated temperature increases, the grain size of stainless steel also increases and then, eventually make it destroy. In this paper, a pattern recognition method is proposed to identify the heat-treated temperature of metals by evidence accumulation based on artificial intelligence with multiple feature parameters; difference absolute mean value(DAMV), variance(VAR), mean frequency(MEANF), auto regressive model coefficient(ARC), linear cepstrum coefficient(LCC) and adaptive cepstrum vector(ACV). The grain signal pattern recognition is carried out through the evidence accumulation procedure using the distances measured with reference parameters. Especially ACV is superior to the other parameters. The results (96% successful pattern classification) are presented to support the feasibility of the suggested approach for ultrasonic grain signal pattern recognition.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.393-396
• /
• 1995

In this syudy, the researches classifying the artificial and natural flaws in welding parts are performed using the smart pattern recognition technology. For this purpose the smart signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing,feature extraction , feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear disciminant function classifier, the empirical Bayesian classifier. Also, the smart pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack,lack of penetration,lack of fusion,porosity,and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately learned the neural network classifier is better than ststistical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

• 한국안전학회지
• /
• 제24권3호
• /
• pp.65-70
• /
• 2009

In-vehicle route guidance information(RGI) systems have been developed with the advancement of the information and communication technologies. However, the RGI is provided by a pre-determined option, drivers occasionally pass the target intersection owing to non- or late- recognizing it. The purpose of this experiment is to examine the position of driver's tum signal operation and intersection recognition approaching at the target intersection which is difficult to identify as a preliminary research on developing the additional RGI connecting with the tum signal control. The field experiment was conducted to measure distances of the turn signal operation and intersection recognition from the target intersection according to driving lanes and landmarks at adjacent intersection. And, glance behavior to the car navigation display was evaluated by using an eye camera. The results indicate that drivers operate the turn signal after confirming a landmark in the case of the intersection with it. However, most case of driving, drivers operate the tum signal at 40 to 50m before coming to the target. To provide the additional RGI, when drivers do not operate the tum signal approaching at the target intersection based on the results, is expected to improve the traffic safety and the comfort for drivers.

• Journal of Communications and Networks
• /
• 제17권5호
• /
• pp.491-498
• /
• 2015

Recognition of radar emitter signals is one of core elements in radar reconnaissance systems. A novel method based on singular value decomposition (SVD) and the main ridge slice of ambiguity function (AF) is presented for attaining a higher correct recognition rate of radar emitter signals in case of low signal-to-noise ratio. This method calculates the AF of the sorted signal and ascertains the main ridge slice envelope. To improve the recognition performance, SVD is employed to eliminate the influence of noise on the main ridge slice envelope. The rotation angle and symmetric Holder coefficients of the main ridge slice envelope are extracted as the elements of the feature vector. And kernel fuzzy c-means clustering is adopted to analyze the feature vector and classify different types of radar signals. Simulation results indicate that the feature vector extracted by the proposed method has satisfactory aggregation within class, separability between classes, and stability. Compared to existing methods, the proposed feature recognition method can achieve a higher correct recognition rate.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• 말소리와 음성과학
• /
• 제3권1호
• /
• pp.117-123
• /
• 2011

Most individuals with hearing impairment have difficulty in understanding speech in noisy situations. This study was conducted to investigate sentence recognition ability using the Korean Standard-Sentence Lists for Preschoolers (KS-SL-P2) in pre-school age children with cochlear implants and hearing aids. The subjects of this study were 10 pre-school age children with hearing aids, 12 pre-school age children with cochlear implants, and 10 pre-school age children with normal hearing. Three kinds of signal-to-noise (SNR) conditions (+10 dB, +5 dB, 0 dB) were applied. The results for all pre-school age children with cochlear implants and hearing aids presented a significant increase in the score for sentence recognition as SNR increased. The sentence recognition score in speech noise were obtained with the SNR +10 dB. Significant differences existed between groups in terms of their sentence recognition ability, with the cochlear implant group performing better than the hearing aid group. These findings suggest the presence of a sentence recognition test using speech noise is useful for evaluating pre-school age children's listening skill.

• 제어로봇시스템학회논문지
• /
• 제12권3호
• /
• pp.284-288
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 춘계학술대회 학술발표 논문집 제16권 제1호
• /
• pp.347-350
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

• 한국음향학회지
• /
• 제18권7호
• /
• pp.112-117
• /
• 1999

잡음에 강한 음성인식시스템을 위하여 주파수 차감법을 사용할 경우 음성 신호마저 차감하여 신호를 더욱 부식시키는 경우가 존재한다. 본 연구에서는 이러한 경우를 위해서 프레임 마다 추정 잡음과 차감 신호의 SNR(Signal to Noise Ratio) 함수로부터 반연속 HMM(Hidden Markov Model)의 가우시안 함수를 변형 및 결정하는 방법을 제안한다. 이 방법의 타당성을 위해 프레임마다 추정 잡음의 오류 정도가 추정 잡음의 크기와 관계함을 신호 파형 형태로써 보였으며, 이러한 이유에서 SNR을 기준으로 가우시안 함수를 변형 및 결정하게 된다. 실험에서 80㎞/h 이상의 속도로 달리는 차량 내에서 배경 잡음과 음성이 혼합되었을 때의 음성 인식율을 평가하였다. 그 결과 주파수 차감한 경우와 차감하지 않은 경우에 비해 본 논문에서 제안한 SNR에 의한 가우시안 결정 방법이 더욱 향상된 인식율을 보였다.

• 한국융합학회논문지
• /
• 제8권5호
• /
• pp.13-17
• /
• 2017

음성 인식에서 기존의 음성 특징 추출 방법은 명확하지 않은 스레숄드 값으로 인해 부정확한 음성 인식률을 가진다. 본 연구에서는 음성과 비음성에 대한 특징 추출을 묵음 특징 정규화를 융합한 음성 인식 성능 향상을 위한 방법을 모델링 한다. 제안한 방법에서는 잡음의 영향을 최소화하여 모델을 구성하였고, 각 음성 프레임에 대해 음성 신호 특징을 추출하여 음성 인식 모델을 구성하였고, 이를 묵음 특징 정규화를 융합하여 에너지 스펙트럼을 엔트로피와 유사하게 표현하여 원래의 음성 신호를 생성하고 음성의 특징이 잡음을 적게 받도록 하였다. 셉스트럼에서 음성과 비음성 분류의 기준 값을 정하여 신호 대 잡음 비율이 낮은 신호에서 묵음 특징 정규화로 성능을 향상하였다. 논문에서 제시하는 방법의 성능 분석은 HMM과 CHMM을 비교하여 결과를 보였으며, 기존의 HMM과 CHMM을 비교한 결과 음성 종속 단계에서는 2.1%p의 인식률 향상이 있었으며, 음성 독립 단계에서는 0.7%p 만큼의 인식률 향상이 있었다.