• 전자공학회논문지B
• /
• 제31B권12호
• /
• pp.108-115
• /
• 1994

Most pattern classifiers have been designed based on the ML (Maximum Likelihood) training algorithm which is simple and relatively powerful. The ML training is an efficient algorithm to individually estimate the model parameters of each class under the assumption that all class models in a classifier are statistically independent. That assumption, however, is not valid in many real situations, which degrades the performance of the classifier. In this paper, we propose a minimum-error-rate training algorithm based on the MAP (Maximum a Posteriori) approach. The algorithm regards the normalized outputs of the classifier as estimates of the a posteriori probability, and tries to maximize those estimates. According to Bayes decision theory, the proposed algorithm satisfies the condition of minimum-error-rate classificatin. We apply this algorithm to NPM (Neural Prediction Model) for speech recognition, and derive new disrminative training algorithms. Experimental results on ten Korean digits recognition have shown the reduction of 37.5% of the number of recognition errors.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2932-2934
• /
• 1999

In this paper, a scheme for recognition of handwritten digits using a multilayer neural network trained with the back-propagation algorithm using generalized delta rule is proposed. The neural network is trained with hand written digit data of different writers and different styles. One of the purpose of the work with neural networks is the minimization of the mean square error(MSE) between actual output and desired one. The back-propagation algorithm is an efficient and very classical method. The back-propagation algorithm for training the weights in a multilayer net uses the steepest descent minimization procedure and the sigmoid threshold function. As an error rate is reduced, recognition rate is improved. Therefore we propose a method that is reduced an error rate.

• 한국전자통신학회논문지
• /
• 제5권4호
• /
• pp.363-371
• /
• 2010

특징벡터의 분류를 개선시켜 화자독립 음성인식의 오류율을 줄이려는 노력의 일환으로서, 우리는 MFCC의 추출에 있어서 푸리에 스펙트럼을 기울이는 방법이 미치는 효과를 연구한다. 음성신호에 FIR 필터링을 적용하는 효과의 조사도 병행된다. 제안된 방법은 두 가지 독립적인 방법에 의해 평가된다. 즉, 피셔의 차별함수에 의한 방법과 은닉 마코브 모델 및 퍼지 벡터양자화를 사용한 음성인식 오류율 조사 방법이다. 실험 결과, 적절한 파라미터의 선택에 의해 기존의 방법에 비해 10% 정도 낮은 인식 오류율이 얻어짐을 확인하였다.

• 전기학회논문지
• /
• 제58권1호
• /
• pp.126-131
• /
• 2009

This study was carried out for the reliability of PD(Partial Discharge) pattern recognition. For the pattern recognition, the database for PD was established by use of self-designed insulation defects which occur and were mostly critical in GIS(Gas Insulated Switchgear). The acquired database was analyzed to distinguish patterns by means of PRPD(Phase Resolved Partial Discharge) method and stored to the form with to unite the average amplitude of PD pulse and the number of PD pulse as the input data of neural network. In order to prove the performance of genetic algorithm combined with neural network, the neural networks with trial-and-error method and the neural network with genetic algorithm were trained by same training data and compared to the results of their pattern recognition rate. As a result, the recognition success rate of defects was 93.2% and the neural network train process by use of trial-and-error method was very time consuming. The recognition success rate of defects, on the other hand, was 100% by applying the genetic algorithm at neural network and it took a relatively short time to find the best solution of parameters for optimization. Especially, it could be possible that the scrupulous parameters were obtained by genetic algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• 한국정보통신학회논문지
• /
• 제21권12호
• /
• pp.2365-2370
• /
• 2017

본 논문에서는 체험형 VR 환경을 고려한 동작 및 위치 인식 기법을 제안한다. 동작 인식은 신체부위에 복수개의 AHRS 디바이스를 부착하고 이를 기준으로 좌표계를 정의한다. 각각의 AHRS 디바이스로부터 측정되는 9축 움직임 정보를 기반으로 사용자의 동작을 인식하고 신체 분절 간의 관절각을 추출하여 동작을 보정한다. 위치인식은 AHRS 디바이스의 관성센서를 통해 보행 정보를 추출하여 상대위치를 인식하고 BLE Fingerprint를 이용하여 누적오차를 보정한다. 제안하는 동작 및 위치인식 기법의 구현을 위해 AHRS기반의 위치인식과 관절각 추출 실험을 진행하였다. 위치 인식 실험의 평균 오차는 0.25m, 관절 각 추출 실험에서 관절 각 평균 오차는 $3.2^{\circ}$로 나타났다.

• 정보처리학회논문지D
• /
• 제14D권7호
• /
• pp.809-818
• /
• 2007

본 논문에서는 컬러정보를 이용하여 교통표지판 영역을 추출하고, 추출된 이미지의 인식을 위해 오류 역전파 학습알고리즘을 적용한 교통표지판 인식시스템을 제안한다. 제안된 방법은 교통표지판의 컬러를 분석하여 영상에서 교통표지판의 후보영역을 추출한다. 후보영역을 추출하는 방법은 RGB 컬러 공간으로부터 YUV, YIQ, CMYK 컬러 공간이 가지는 특성을 이용한다. 형태처리는 교통표지판의 기하학적 특성을 이용하여 영역을 분할하고, 교통표지판 인식은 학습이 가능한 오류역전파 학습알고리즘을 이용하여 인식한다. 실험결과 제안된 시스템은 다양한 크기의 입력영상과 조명의 차이에 영향을 받지 않고 후보영역 추출과 인식에 우수한 성능이 입증되었다.

• 한국산업융합학회 논문집
• /
• 제17권2호
• /
• pp.77-83
• /
• 2014

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.

• 한국산업융합학회 논문집
• /
• 제16권4호
• /
• pp.113-117
• /
• 2013

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.

• 한국콘텐츠학회논문지
• /
• 제5권6호
• /
• pp.57-64
• /
• 2005

다층 퍼셉트론의 학습을 빠르게 하기 위한 방법으로 층별 학습이 제안되었었다. 이 방법에서는 각 층별로 오차함수가 주어지고, 이렇게 층별로 주어진 오차함수를 최적화 방법을 사용하여 감소시키도록 학습이 이루어진다. 이 경우 중간층 오차함수가 학습의 성능에 큰 영향을 미치는 데, 이 논문에서는 층별 학습의 성능을 개선하기 위한 중간층 오차함수를 제안한다. 이 중간층 오차함수는 출력층 오차함수에서 중간층 가중치의 학습에 관계된 성분을 유도하는 형태로 제안된다. 제안한 방법은 필기체 숫자 인식과 고립단어인식 문제의 시뮬레이션으로 효용성을 확인하였다.