• 전기학회논문지
• /
• 제66권2호
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• 한국인터넷방송통신학회논문지
• /
• 제14권5호
• /
• pp.87-93
• /
• 2014

n/m=qm+r에서 에서 m=7인 단순한 경우에도 주어진 수 n이 m의 배수 판정법은 간단하지가 않다. 만약, m이 두 자리 수 이상이 되면 더욱 복잡해진다. 일반적인 배수 판정법으로 둔켈스 (Dunkels)법이 있지만 n이 컴퓨터로 처리하지 못하는 매우 큰 자리수인 경우 이 방법도 처리할 수 없다. 본 논문은 n과 m의 자리수와 무관하게 n(modm)=0 여부로 n이 m의 배수인지 여부를 검증하는 간단하면서도 정확한 방법을 제안한다. 제안된 방법은 $n=n_1n_2n_3{\cdots}n_k$, $m=m_1m_2{\cdots}m_l$에 대해 $r_1=n_1n_2{\cdots}n_l(mod m)$으로 설정하고, $r_i=r_{i-1}{\times}10+n_i(mod m)$, $i=2,3,{\cdots},k-1+1$로 n의 자리수를 1자리씩 감소시키는 방법을 적용하였다. 제안된 방법을 다양한 n,m 데이터에 적용한 결과 쉽고, 빠르며 정확한 몫과 나머지 값을 구할 수 있음을 보였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권4호
• /
• pp.125-132
• /
• 2021

인공신경망의 계층의 깊이가 깊어지고 입력으로 사용되는 데이터 차원이 증가됨에 신경망의 학습 및 인식에 있어서 많은 연산을 고속으로 요구하는 고연산의 문제가 발생한다. 따라서 본 논문에서는 신경망 입력 데이터의 차원을 감소시키기 위한 데이터 차원 감소 방법을 제안한다. 제안하는 선분 특징 분석(Line-segment Feature Analysis; LFA) 알고리즘은 한 영상 내에 존재하는 객체의 선분(Line-segment) 특징을 분석하기 위하여 메디안 필터(median filter)를 사용한 기울기 기반의 윤곽선 검출 알고리즘을 적용한다. 추출된 윤곽 영상은 [0, 1, 2, 4, 8, 16, 32, 64, 128]의 계수 값으로 구성된 3×3 또는 5×5 크기의 검출 필터를 이용하여 8가지 선분의 종류에 상응하는 고유값을 계산한다. 각각의 검출필터로 계산된 고유값으로부터 동일한 반응값을 누적하여 두 개의 1차원의 256 크기의 데이터를 생성하고 두 가지 데이터 요소를 합산하여 LFA256 데이터를, 두 데이터를 합병하여 512 크기의 LAF512 데이터를 생성한다. 제안한 LFA 알고리즘의 성능평가는 필기체 숫자 인식을 위한 데이터 차원 감소를 목적으로 PCA 기법과 AlexNet 모델을 이용하여 비교 실험한 결과 LFA256과 LFA512가 각각 98.7%와 99%의 인식 성능을 보였다.

• Clinics in Shoulder and Elbow
• /
• 제8권2호
• /
• pp.181-186
• /
• 2005

An anterior dislocation of the elbow without a fracture of the olecranon is an extremely rare injury. This paper reports a 36-year-old male who stumbled and fell on his outstretched hand during a soccer game. The anteroposterior and lateral radiographs indicated a simple anterior dislocation of the elbow, which was reduced using a closed method. The elbow joint was stable in the range of motion, but the sensation of the two ulnar digits was still reduced. MRI was useful for the identification of the pathoanatomy. At the follow-up examination three months after the initial trauma, the hypesthesia has fully recovered and the patient regained the full range of the elbow and forearm motion without pain and instability. After 18 months, the patient had a normal elbow function, and could play various sports. If an anterior elbow dislocation is detected early, a closed reduction with careful pathoanatomical considerations would be successful.

• The Journal of the Acoustical Society of Korea
• /
• 제13권1E호
• /
• pp.64-70
• /
• 1994

예측신경회로망 모델은 패턴 예측에 의한 매우 효과적인 음성인식 모델이다. 그러나, 그러한 모델은 유사한 어휘간에서 변별력이 떨어지는 단점이 있다. 이 논문에서는 그러한 단점을 극복하기 위한 변별력있는 학습 알고리즘을 제안한다. 이 알고리즘은 최소 분류 오차 수식화와 GPD 알고리즘으로부터 유도외면 그에 따라서 인식 오차의 수를 직접 최소화하는 것이 가능하다. 한국어 숫자음에 대한 인식 실험결과, 기존의 알고리즘에서 발생하는 오인식의 30%를 줄일 수 있었다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.997-1002
• /
• 1994

Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. Those models can effectively normalize the temporal and spatial variability of speech signals. But those models suffer from poor discrimination between acoustically similar words. In this paper, we propose a discriminative training algorithm for predictive neural network models based on a generalized probabilistic descent (GPD) algorithm and minimum classification error formulation (MCEF). The Evaluation of our training algorithm on ten Korean digits shows its effectiveness by 40% reduction of recognition error.

• 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.

• 전자공학회논문지C
• /
• 제34C권2호
• /
• pp.71-79
• /
• 1997

In this paper, we propose a new nearest-neighbor classifier with reduced computational complexity in search process. In the proposed classifier, the classes are divided into two sets: reference and non-reference sets. It reduces computational requriement by approximating the distance between the input and a class iwth the information of distances among the calsses. It calculates only the distance between the input and the reference classes. We convert a given classifier into RCC (reduced computational complexity but smal lincrease in misclassification probability of its corresponding RCC classifier. We designed RCC classifiers for the recognition of digits from the NIST database. We obtained an RCC classifier with 60% reduction in the computational complexity with the cost of 0.5% increase in misclassification probability.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권11호
• /
• pp.491-494
• /
• 2006

In the adder design, reduction of the delay of the carry propagation or ripple is the most important consideration. Previously, it was introduced that, if a redundant number system is adopted, the carry propagation is completely eliminated, with which addition can be done in a constant time, without regarding to the count of the digits of numbers involved in addition. In this paper, a RBCD(Redundant Binary Coded Decimal) is adopted to code 0 to 11, and an efficient and economic carry-free BCD adder is designed.

• Archives of Plastic Surgery
• /
• 제48권1호
• /
• pp.98-106
• /
• 2021

Background Hand fractures can be treated using various operative or nonoperative methods. When an operative technique utilizing fixation is performed, early postoperative mobilization has been advocated. We implemented a protocol involving controlled active exercise in the early postoperative period and analyzed the outcomes. Methods Patients who were diagnosed with proximal phalangeal or metacarpal fractures of the second to fifth digits were included (n=37). Minimally invasive open reduction and internal fixation procedures were performed. At 3 weeks postoperatively, controlled active exercise was initiated, with stress applied against the direction of axial loading. The exercise involved pain-free active traction in three positions (supination, neutral, and pronation) between 3 and 5 weeks postoperatively. Postoperative radiographs and range of motion (ROM) in the interphalangeal and metacarpophalangeal joints were analyzed. Results Significant improvements in ROM were found between 6 and 12 weeks for both proximal phalangeal and metacarpal fractures (P<0.05). At 12 weeks, 26 patients achieved a total ROM of more than 230° in the affected finger. Postoperative radiographic images demonstrated union of the affected proximal phalangeal and metacarpal bones at a 20-week postoperative follow-up. Conclusions Minimally invasive open reduction and internal fixation minimized periosteal and peritendinous dissection in hand fractures. Controlled active exercise utilizing pain-free active traction in three different positions resulted in early functional exercise with an acceptable ROM.