• Journal of the Korean Society for information Management
• /
• v.21 no.1
• /
• pp.93-117
• /
• 2004

This study is to develop a hierarchic clustering model fur document classification and browsing in OPAC systems. Two automatic indexing techniques (with and without controlled terms), two term weighting methods (based on term frequency and binary weight), five similarity coefficients (Dice, Jaccard, Pearson, Cosine, and Squared Euclidean). and three hierarchic clustering algorithms (Between Average Linkage, Within Average Linkage, and Complete Linkage method) were tested on the document collection of 175 books and theses on library and information science. The best document clusters resulted from the Between Average Linkage or Complete Linkage method with Jaccard or Dice coefficient on the automatic indexing with controlled terms in binary vector. The clusters from Between Average Linkage with Jaccard has more likely decimal classification structure.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.355-356
• /
• 2021

딥러닝 기술과 하드웨어의 발전으로 다양한 분야에서 인공신경망과 관련한 연구가 활발히 진행되고 있다. 비디오 코덱 부분에서도 딥러닝 기술을 적용하는 부호화 기술이 많이 연구되고 있다. 본 논문은 최근 완료된 VVC 에 채택된 신경망 기반의 기술인 MIP(Matrix Weighted Intra Prediction)를 확장하여 보다 깊은 계층의 모델로 학습된 새로운 화면내 예측 모델을 제안한다. 기존 VVC 의 MIP 의 성능과 비교하기 위하여 기존 MIP 모델과 제안하는 다중완전연결계층(Fully Connected Layer) 화면내 예측 모델을 HEVC(High Efficiency Video Coding)에 적용하여 그 성능을 비교하였다. 실험결과 제안기법은 VVC MIP 대비 0.08 BD-rate 성능 향상을 보였다.

• Journal of the Korean Society for information Management
• /
• v.18 no.2
• /
• pp.203-230
• /
• 2001

The purpose of this study is to develop a document clustering model for automatic classification of knowledge. Two test collections of newspaper article texts and journal article abstracts are built for the clustering experiment. Various feature reduction criteria as well as term weighting methods are applied to the term sets of the test collections, and cosine and Jaccard coefficients are used as similarity measures. The performances of complete linkage and K-means clustering algorithms are compared using different feature selection methods and various term weights. It was found that complete linkage clustering outperforms K-means algorithm and feature reduction up to almost 10% of the total feature sets does not lower the performance of document clustering to any significant extent.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.342-344
• /
• 2000

대부분 웹 검색엔진들의 검색결과로 수십 혹은 수백만건의 문서가 제시되어 사용자가 원하는 문서를 찾는데 어려움이 있다. 이러한 문제를 해결하기 위해 본 논문에서는 검색 결과의 브라우징을 위한 검색 결과 문서에 대한 자동 클러스터링 방법을 제안한다. 문서간 유사도를 계산하기 위해 공통 키워드 빈도를 이용하고, 클러스터링 방법은 계층적 클러스터링을 사용하고, 각 클러스터에 대한 디스트립터를 추출하기 위해 빈도를 이용한다. 실험 결과, 완전 연결 방법이 가장 나은 정확도를 보였지만 계산시간이 많이 소요되어 동적 환경에 부적합하다는 것을 보였다. 아울러 집단 평균 연결이 정확도나 계산 시간 측면에서 우수함을 알수 있었다.

• Journal of the Korean Society for Library and Information Science
• /
• v.38 no.1
• /
• pp.35-50
• /
• 2004

This study evaluated the applicability of the static hierarchic clustering model to clustering query results in OPAC. Two clustering methods(Between Average Linkage(BAL) and Complete Linkage(CL)) and two similarity coefficients(Dice and Jaccard) were tested on the query results retrieved from 16 title-based keyword searchings. The precision of optimal dusters was improved more than 100% compared with title-word searching. There was no difference between similarity coefficients but clustering methods in optimal cluster effectiveness. CL method is better in precision ratio but BAL is better in recall ratio at the optimal top-level and bottom-level clusters. However the differences are not significant except higher recall ratio of BAL at the top-level duster. Small number of clusters and long chain of hierarchy for optimal cluster resulted from BAL could not be desirable and efficient.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.758-765
• /
• 2021

Recently, various research on the application of deep learning to video encoding for enhancing coding efficiency are being actively studied. This paper proposes a deep learning based intra prediction which uses multiple models by extending Matrix-based Intra Prediction(MIP) that is a neural network-based technology adopted in VVC. It also presents an efficient learning method for the multi-model intra prediction. To evaluate the performance of the proposed method, we integrated the VVC MIP and the proposed fully connected layer based multi-model intra prediction into HEVC reference software, HM16.19 as an additional intra prediction mode. As a result of the experiments, the proposed method can obtain bit-saving coding gain up to 0.47% and 0.19% BD-rate, respectively, compared to HM16.19 and VVC MIP.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.37-44
• /
• 2021

Automatic classification of brain MRI images play an important role in early diagnosis of brain tumors. In this work, we present a deep learning-based brain tumor classification model in MRI images using ensemble of deep features. In our proposed framework, three different deep features from brain MR image are extracted using three different pre-trained models. After that, the extracted deep features are fed to the classification module. In the classification module, the three different deep features are first fed into the fully-connected layers individually to reduce the dimension of the features. After that, the output features from the fully-connected layers are concatenated and fed into the fully-connected layer to predict the final output. To evaluate our proposed model, we use openly accessible brain MRI dataset from web. Experimental results show that our proposed model outperforms other machine learning-based models.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.1-7
• /
• 2024

In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28×28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5×5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems. It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.

• Journal of KIISE:Information Networking
• /
• v.35 no.3
• /
• pp.183-191
• /
• 2008

In this paper, we propose Stream Control Transmission Protocol(SCTP) proxy which supports making an SCTP connection from a Corresponding Node(CN) to a Mobile Node(MN). Recently, mobility support in transport layer is proposed, which provides mobility in end-to-end way using the extension of SCTP. Mobile SCTP can provide handover to all applications that use SCTP as a transport protocol. However, current SCTP does not include independent location management service and can not make connection from a CN to a MN without assistance of other mobile protocols. To solve this problem, Proposed SCTP proxy interoperates with generic location management service and performs an address transformation to forward connection set up messages to the MN. Using the proposed proxy, SCTP can provide a complete mobility support including a connection setup to the MN and maintaining an existing connection.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2005.08a
• /
• pp.65-70
• /
• 2005

계층적 문서 클러스터링에 있어서 실험집단에 따라 응집식 기법과 분할식 기법의 성능이 다르며, 이를 좌우하는 요소는 분류의 깊이, 즉 분류수준이라고 가정하였다. 조금만 나누면 되는 대분류인 경우는 상대적으로 분할식 기법이 유리하고, 조금만 합치면 되는 소분류인 경우에는 응집식 기법이 유리할 것이라고 판단했기 때문이다. 그에 따라 분할식 클러스터링 기법인 양분(Bisecting) K-means기법과 응집식 기법인 완전연결, 평균연결, WARD기법의 성능을 실험집단이 대분류인 경우와 소분류인 경우의 유사계수를 적용하여 각 기법별 성능을 비교하여 실험집단의 특성에 따른 적합 클러스터링 기법을 찾고자 하였다. 실험결과 응집식 기법과 분할식 기법의 성능 우열에 영향을 미치는 것은 분류수준보다는 변이계수로 측정된 상대적인 군집의 크기 편차인 것으로 나타났다.