• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.132-137
• /
• 2004

Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.1981-1986
• /
• 2009

This paper presents new matting techniques. The matting is an alpha estimation technique of object in an image. We can extract the object in an image naturally using the matting technique. The proposed algorithms begin by segmenting an image into three regions: definitely foreground, definitely background, and unknown. Then we estimate foreground, background, and alpha for all pixels in the unknown region. The proposed algorithms learn the definitely foreground and definitely background using self-organizing map(SOM), and estimate an alpha value of each pixel in the unknown region using SOM learning result. SOM matting is distinguished between global SOM matting and local SOM matting by learning method. Experiment results show the proposed algorithms can extract the object in an image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.981-984
• /
• 2010

In this paper, we used Support Vector Machines(SVMs) as the learning method, one of Artificial Neural Network, to segregated from the continuous speech into phonemes, an initial, medial, and final sound, and then, performed continuous speech recognition from it. A Decision boundary of phoneme is determined by algorithm with maximum frequency in a short interval. Speech recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme segregated from the eye-measurement. From the simulation results, we confirmed that the method, SVMs, we proposed is more effective in an initial sound than Gaussian Mixture Models(GMMs).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.197-200
• /
• 2010

The development of service industries like more information on each individual's comments are provided only for wanting to receive services that do not like the prolonged waiting time. However, existing venues, theaters, libraries and seating management systems to suit the individual seating arrangements can not automatically provide information and give everyone the same. In this paper these issues to improve the fit of personal preference or personal inclination of the body in condition to meet intelligently deployed seats, and can provide information only preferred system is proposed. To verify the proposed system's performance using any of the theater seating chart for the experiments was to check to see better performance could be seen.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.189-192
• /
• 2010

본 논문에서는 개선된 Fuzzy ART 알고리즘을 이용하여 한의학을 기반으로 증상에 대한 질병을 진단하고 민간요법을 제시하는 한방 자가 검진 시스템을 제안한다. 제안된 방법은 신체 부위를 전신, 머리, 배, 다리 등 17부위로 분류하여 사용자가 증상을 선택하도록 제시하고, 사용자가 선택한 증상과 질병에 포함된 증상 그리고 결과로 도출될 질병간의 선택증상 비율에 대한 우선순위를 개선된 Fuzzy ART 알고리즘에 적용하여 증상을 분류한 후, 퍼지 추론 규칙을 적용하여 질병을 도출한다. 도출된 질병과 그 질병에 대한 원인 및 민간요법을 결과로 제시한다. 데이터베이스에 구축되어 있는 질병 데이터는 통계청에서 정리하여 배포한 한국표준질병 사인분류(K.C.D)를 토대로 표준 질병 정보를 얻어 각 질병의 증상과 원인, 민간요법을 정리한 후, 마지막으로 한의학 전문의의 검증을 거쳐 데이터베이스를 구축하였다. 제안된 한방 자가 검진 시스템에 대한 한의학 전문의의 분석 및 검증 결과, 본 시스템의 증상에 대한 질병 도출이 높은 정확도를 보임을 확인하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.141-148
• /
• 2003

Customer retention is a common concern for many industries and a critical issue for the survival in today's greatly compressed marketplace. Current customer retention models only focus on detection of potential defectors based on the likelihood of defection by using demographic and customer profile information. In this paper, we propose a dynamic procedure for defection detection and prevention using past and current customer behavior by utilizing SOM and Markov chain. The basic idea originates from the observation that a customer has a tendency to change his behavior (i.e. trim-out his usage volumes) before his eventual withdrawal. This gradual pulling out process offers the company the opportunity to detect the defection signals. With this approach, we have two significant benefits compared with existing defection detection studies. First, our procedure can predict when the potential defectors could withdraw and this feature helps to give marketing managers ample lead-time for preparing defection prevention plans. The second benefit is that our approach can provide a procedure for not only defection detection but also defection prevention, which could suggest the desirable behavior state for the next period so as to lower the likelihood of defection. We applied our dynamic procedure for defection detection and prevention to the online gaming industry. Our suggested procedure could predict potential defectors without deterioration of prediction accuracy compared to that of the MLP neural network and DT.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.703-715
• /
• 2017

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and gray-level co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.669-672
• /
• 2018

캡술내시경은 식도부터 항문까지 소화기관 전체를 한번에 촬영할 수 있는 의료기기로, 한번의 검사에 평균 8~12 시간 정도의 길이와 5만장 이상의 프레임으로 구성된 영상을 생성한다. 그러나 생성된 영상에 대한 분석은 수작업으로 진행되고 있어, 캡술내시경 영상 분석 자동화에 대한 기술적인 수요가 높아지고 있는 추세이다. 이를 위해, 캡슐내시경 영상 분석에 대한 많은 연구가 진행되고 있는데, 본 연구에서는 그 중에서도 폴립 영상에 대한 검출 자동화 연구에 주목하였다. 폴립이란 위장관 내에서 발견될 수 있는 융기성 병변으로, 많은 연구에서 기계학습 혹은 딥러닝 방식을 적용하여 이를 검출하기 위한 연구를 수행하였다. 그러나 캡슐내시경 영상의 특성상, 병번이 있는 영상이 굉장히 적기 때문에 일반적인 딥러닝 방식의 적용으로 좋은 성능을 내기 어렵다. 따라서 본 논문에서는 폴립 검출 컨볼루션 신경망 설계를 위한 멀티 스케일에 대한 원형 검출기법을 결합하여 폴립이 의심되는 영역을 추출해주는 특징 추출 기법으로, 수집한 데이터 150장에 대한 실험한 결과 약 82%의 성능을 보였다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.166-169
• /
• 2018

캐시 부채널 공격 중 하나인 FLUSH+RELOAD 공격은 높은 해상도와 적은 오류로 그 위험성이 높고, 여러가지 프로그램에서도 적용되어 개인정보의 유출에 대한 위험성까지 증명 되었다. 따라서 이 공격을 막기 위해 실시간으로 감지 할 수 있어야 할 필요성이 있다. 본 연구에서는 4가지 실험을 통하여 이 FLUSH+RELOAD 공격을 받을 때 PCM(Performance Counter Monitor)를 사용해 각각의 counter들의 값의 변화를 관찰하여 3가지 중요한 요인에 의해 공격 탐지를 할 수 있다는 것을 발견하였다. 이를 이용하여 머신 러닝의 logistic regression과 ANN(Artificial Neural Network)를 사용해 결과에 대한 각각 학습을 시킨 뒤, 실시간으로 공격에 대한 탐지를 할 수 있는 프로그램을 제작하였다. 일정한 시간동안 공격을 진행하여 모든 공격을 감지하는데 성공하였고, 상대적으로 적은 오탐률을 보여주었다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.543-551
• /
• 1999

The primary purposes in this paper are to analyze the class separation of features in handwritten numeral recognition and to make use of the results in feature selection. Using the Parzen window technique, we compute the class distributions and define the class separation to be the overlapping distance of two class distributions. The dimension of a feature vector is reduced by removing the void or redundant feature cells based on the class separation information. The experiments have been performed on the CENPARMI handwritten numeral database, and partial classification and full classification have been tested. The results show that the class separation is very effective for the feature selection in the 10-class handwritten numeral recognition problem since we could reduce the dimension of the original 256-dimensional feature vector by 22%.