• Journal of Korean Society of Rural Planning
• /
• v.23 no.3
• /
• pp.37-51
• /
• 2017

There has been a growing concern on ontology especially in recent knowledge-based industry and defining a field-customized semantic word network is essential for building it. In this paper, a word network for ontology is established with 785 publications of Korean Society of Rural Planning(KSRP), from 1995 to 2017. Semantic relationships between words in the publications were quantitatively measured with the 'normalized pointwise mutual information' based on the information theory. Appearance and co-appearance frequencies of nouns and adjectives in phrases are analyzed based on the assumption that a 'noun phrase' represents a single 'concept'. The word network of KSRP was compared with that of $WordNet^{TM}$, a world-wide thesaurus network, for the verification. It is proved that the KSRP's word network, established in this paper, provides words' semantic relationships based on the common concepts of Korean rural planning research field. With the results, it is expecting that the established word network can present more opportunity for preparation of the fourth industrial revolution to the field of the Korean rural planning.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.1-6
• /
• 2009

We propose an intensity-based image registration method for medical images. The proposed registration is performed by the use of a new measure based on the entropy of conditional probabilities. To achieve the registration, we define a modified conditional entropy (MCE) computed from the joint histograms for the area intensities of two given images. And we conduct experiments with our method as well as existing methods based on the sum of squared differences (SSD), normalized correlation coefficient (NCC), normalized mutual information (NMI) criteria. We evaluate the precision of SSD-, NCC-, MI- and MCE-based measurements by comparing the registration obtained from the same modality magnetic resonance (MR) images and the different modality transformed MR/transformed CT images. The experimental results show that the proposed method is faster and more accurate than other optimization methods.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.5
• /
• pp.311-317
• /
• 2015

The aim of this study is to develop a 3D registration algorithm for positron emission tomography/computed tomography (PET/CT) and magnetic resonance (MR) images acquired from independent PET/CT and MR imaging systems. Combined PET/CT images provide anatomic and functional information, and MR images have high resolution for soft tissue. With the registration technique, the strengths of each modality image can be combined to achieve higher performance in diagnosis and radiotherapy planning. The proposed method consists of two stages: normalized mutual information (NMI)-based global matching and independent component analysis (ICA)-based refinement. In global matching, the field of view of the CT and MR images are adjusted to the same size in the preprocessing step. Then, the target image is geometrically transformed, and the similarities between the two images are measured with NMI. The optimization step updates the transformation parameters to efficiently find the best matched parameter set. In the refinement stage, ICA planes from the windowed image slices are extracted and the similarity between the images is measured to determine the transformation parameters of the control points. B-spline. based freeform deformation is performed for the geometric transformation. The results show good agreement between PET/CT and MR images.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.37-48
• /
• 2012

Image registration is a process to establish the spatial correspondence between the images of same scene, which are acquired at different view points, at different times, or by different sensors. In this paper, we propose an effective registration method for images acquired by multi-sensors, such as EO (electro-optic) and IR (infrared) sensors. Image registration is achieved by extracting features and finding the correspondence between features in each input images. In the recent research, the multi-sensor image registration method that finds corresponding features by exploiting NMI (Normalized Mutual Information) was proposed. Conventional NMI-based image registration methods assume that the statistical correlation between two images should be global, however images from EO and IR sensors often cannot satisfy this assumption. Therefore the registration performance of conventional method may not be sufficient for some practical applications because of the low accuracy of corresponding feature points. The proposed method improves the accuracy of corresponding feature points by combining the gradient orientation as spatial information along with NMI attributes and provides more accurate and robust registration performance. Representative experimental results prove the effectiveness of the proposed method.

• Journal of Korea Multimedia Society
• /
• v.23 no.1
• /
• pp.1-7
• /
• 2020

Clustering methods essentially take a two-step approach; extracting feature vectors for dimensionality reduction and then employing clustering algorithm on the extracted feature vectors. However, for clustering images, the traditional clustering methods such as stacked auto-encoder based k-means are not effective since they tend to ignore the local information. In this paper, we propose a method first to effectively reduce data dimensionality using convolutional auto-encoder to capture and reflect the local information and then to accurately cluster similar data samples by using a hierarchical clustering approach. The experimental results confirm that the clustering results are improved by using the proposed model in terms of clustering accuracy and normalized mutual information.

• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2697-2700
• /
• 2003

이 논문에서는 3 차원 CT/CTA 영상 데이터에 대하여 고속 자동 정합 기법을 제안한다. 제안하는 기법은 다해상도 (multi-resolution) 구조의 정규 상호 정보량(normalized mutual information) 을 최대화하는 정합 방식에서, 정합 유사도를 계산하는 볼륨 영역을 효율적으로 줄여 정합 속도를 증가시키는 방법이다. 제안된 정합방식을 CT/CTA (CT angiography) 팬텀 데이터와 7 세트의 실제 CT/CTA 임상 데이터에 적용하여 테스트하였다. 이로부터 제안하는 방식이, 정합 정확도를 유지하는 동시에 정합 속도를 10 ∼ 60％ 로 감소시킴을 확인 할 수 있었다. 또한 제안된 정합 방식을 DS-CTA (digital subtraction CT angiography) 에 적용하여, CT/CTA 영상으로부터 혈관 영상을 성공적으로 추출하였다.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.769-779
• /
• 2022

Spectral clustering has become a typical and efficient clustering method used in a variety of applications. The critical step of spectral clustering is the similarity measurement, which largely determines the performance of the spectral clustering method. In this paper, we propose a novel spectral clustering algorithm based on the local similarity measure of shared neighbors. This similarity measurement exploits the local density information between data points based on the weight of the shared neighbors in a directed k-nearest neighbor graph with only one parameter k, that is, the number of nearest neighbors. Numerical experiments on synthetic and real-world datasets demonstrate that our proposed algorithm outperforms other existing spectral clustering algorithms in terms of the clustering performance measured via the normalized mutual information, clustering accuracy, and F-measure. As an example, the proposed method can provide an improvement of 15.82% in the clustering performance for the Soybean dataset.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.161-164
• /
• 2019

본 논문은 BERT 모델을 이용하여 동형이의어의 단어 표현(Word Representation) 차이에 대한 실험을 한다. BERT 모델은 Transformer 모델의 인코더 부분을 사용하여 양방향을 고려한 단어 예측과 문장 수준의 이해를 얻을 수 있는 모델이다. 실험은 동형이의어에 해당되는 단어의 임베딩으로 군집화를 수행하고 이를 Purity와 NMI 점수로 계산하였다. 또한 각 단어 임베딩 사이를 코사인거리(Cosine Distance)로 계산하고 t-SNE를 통해 계층에 따른 변화를 시각화하였다. 군집된 결과는 모델의 중간 계층에서 점수가 가장 높았으며, 코사인거리는 8계층까지는 증가하고 11계층에서 급격히 값이 변하는 것을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2587-2605
• /
• 2022

In order to efficiently detect community structure in complex networks, community detection algorithms can be designed from the perspective of node similarity. However, the appropriate parameters should be chosen to achieve community division, furthermore, these existing algorithms based on the similarity of common neighbors have low discrimination between node pairs. To solve the above problems, a noval community detection algorithm using closeness similarity based on common neighbor node clustering entropy is proposed, shorted as CSCDA. Firstly, to improve detection accuracy, common neighbors and clustering coefficient are combined in the form of entropy, then a new closeness similarity measure is proposed. Through the designed similarity measure, the closeness similar node set of each node can be further accurately identified. Secondly, to reduce the randomness of the community detection result, based on the closeness similar node set, the node leadership is used to determine the most closeness similar first-order neighbor node for merging to create the initial communities. Thirdly, for the difficult problem of parameter selection in existing algorithms, the merging of two levels is used to iteratively detect the final communities with the idea of modularity optimization. Finally, experiments show that the normalized mutual information values are increased by an average of 8.06% and 5.94% on two scales of synthetic networks and real-world networks with real communities, and modularity is increased by an average of 0.80% on the real-world networks without real communities.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3874-3884
• /
• 2000

An information retrieval system has to retrieve all and only documents which are relevant to a user query, even if index terms and query terms are not matched exactly. However, term mismatches between index terms and qucry terms have been a serious obstacle to the enhancement of retrieval performance. In this paper, we discuss automatic term normalization between words in text corpora and their application to a Korean information retrieval system. We perform two types of term normalizations to alleviate semantic term mismatches: equivalence class and co-occurrence cluster. First, transliterations, spelling errors, and synonyms are normalized into equivalence classes bv using contextual similarity. Second, context-based terms are normalized by using a combination of mutual information and word context to establish word similarities. Next, unsupervised clustering is done by using K-means algorithm and co-occurrence clusters are identified. In this paper, these normalized term products are used in the query expansion to alleviate semantic tem1 mismatches. In other words, we utilize two kinds of tcrm normalizations, equivalence class and co-occurrence cluster, to expand user's queries with new tcrms, in an attempt to make user's queries more comprehensive (adding transliterations) or more specific (adding spc'Cializationsl. For query expansion, we employ two complementary methods: term suggestion and term relevance feedback. The experimental results show that our proposed system can alleviatl' semantic term mismatches and can also provide the appropriate similarity measurements. As a result, we know that our system can improve the rctrieval efficiency of the information retrieval system.