• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1173-1183
• /
• 2006

Matrix-star, Pancake, and RFM graphs have such a good property of Star graph and a lower network cost than Hypercube. Matrix-star graph has Star graph as a basic module and the node symmetry, the maximum fault tolerance, and the hierarchical decomposition property. Also it is an interconnection network that improves the network cost against Star graph. In this paper, we propose a method to embed among Matrix-star Pancake, and RFM graphs using the edge definition of graphs. We prove that Matrix-star $MS_{2,n}$ can be embedded into Pancake $P_{2n}$ with dilation 4, expansion 1, and $RFM_{n}$ graphs can be embedded into Pancake $P_{n}$ with dilation 2. Also, we show that Matrix-star $MS_{2,n}$ can be embedded into the $RFM_{2n}$ with average dilation 3.

• KIISE Transactions on Computing Practices
• /
• v.23 no.12
• /
• pp.698-702
• /
• 2017

Since the introduction of Deep Neural Networks to the Natural Language Processing field, two major approaches have been considered for modeling text. One method involved learning embeddings, i.e. the distributed representations containing abstract semantics of words or sentences, with the textual context. The other strategy consisted of composing the embeddings trained by the above to get embeddings of longer texts. However, most studies of the composition methods just adopt word embeddings without consideration of the optimal embedding unit and the optimal method of composition. In this paper, we conducted experiments to analyze the optimal embedding unit and the optimal composition method for modeling longer texts, such as documents. In addition, we suggest a new discourse-based composition to overcome the limitation of the sequential composition method on composing sentence embeddings.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.257-263
• /
• 2002

A graph embedding problem has been studied for applications of resource allocation and mapping the underlying data structure of a parallel algorithm into the interconnection architecture of massively parallel processing systems. In this paper, we consider the embedding problem of the pyramid into the regular 2-dimensional mesh interconnection network topology. We propose a new embedding function which can embed the pyramid of height N into 2$^{N}$ x2$^{N}$ 2-dimensional mesh with dilation max{2$^{N1}$-2. [3.2$^{N4}$＋1)/2, 2$^{N3}$＋2. [3.2$^{N4}$＋1)/2]}. This means an improvement in the dilation measure from 2$^{N}$ $^1$in the previous result into about (5/8) . 2$^{N1}$ under the same condition.condition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.504-507
• /
• 2003

In this paper, we introduce a new hyper-chaos synchronization method called embedding synchronization using hyper-chaos consist of State-Controlled Cellular Neural Network (SC-CNN). We make a hyper-chaos circuit using SC-CNN with the n-double scroll. A hyper-chaos circuit is created by applying identical n-double scroll with weak coupled method to each cell. Hyper-chaos synchronization was achieved using embedding synchronization between the transmitter and receiver about each state variable in the SC-CNN.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.575-578
• /
• 2003

In this paper, we introduce a hyper-chaos secure communication method using Hyper-chaos consist of State-Controlled Cellular Neural Network (SC-CNN). A hyper-chaos circuit is created by applying identical n-double scroll with weak coupled method to each cell. Hyper-chaos synchronization was achieved using embedding synchronization between the transmitter and receiver about in SC CNN. And then, we accomplish secure communication by synthesizing the desired information with a hyper-chaos circuit by embedding the information signal to the only one state variable instead of all state variables in the driven-synchronization method. After transmitting the synthesized signal to the identical channel, we confirm secure communication by separating the information signal and the hyper-chaos signal in the receiver.

• Genomics & Informatics
• /
• v.19 no.4
• /
• pp.51.1-51.8
• /
• 2021

This study explored the trends of Genomics & Informatics during the period of 2003-2018 in comparison with 11 other scholarly journals: BMC Bioinformatics, Algorithms for Molecular Biology: AMB, BMC Systems Biology, Journal of Computational Biology, Briefings in Bioinformatics, BMC Genomics, Nucleic Acids Research, American Journal of Human Genetics, Oncogenesis, Disease Markers, and Microarrays. In total, 22,423 research articles were reviewed. Content analysis was the main method employed in the current research. The results were interpreted using descriptive analysis, a clustering analysis, word embedding, and deep learning techniques. Trends are discussed for the 12 journals, both individually and collectively. This is an extension of our previous study (PMCID: PMC6808643).

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.199-202
• /
• 2020

본 논문에서는 가짜뉴스 탐지 모델에 워드 임베딩 기법을 접목하여 성능을 향상시키는 방법을 제안한다. 기존의 한국어 가짜뉴스 탐지 연구는 희소 표현인 빈도-역문서 빈도(TF-IDF)를 활용한 탐지 모델들이 주를 이루었다. 하지만 이는 가짜뉴스 탐지의 관점에서 뉴스의 언어적 특성을 파악하는 데 한계가 존재하는데, 특히 문맥에서 드러나는 언어적 특성을 구조적으로 반영하지 못한다. 이에 밀집 표현 기반의 워드 임베딩 기법인 Word2vec을 활용한 텍스트 전처리를 통해 문맥 정보까지 반영한 가짜뉴스 탐지 모델을 본 연구의 제안 모델로 생성한 후 TF-IDF 기반의 가짜뉴스 탐지 모델을 비교 모델로 생성하여 두 모델 간의 비교를 통한 성능 검증을 수행하였다. 그 결과 Word2vec 기반의 제안모형이 더욱 우수하였음을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.543-545
• /
• 2019

본 논문은 최신 한국어 의존 구문 분석 모델(Korean dependency parsing model)들과 다양한 앙상블 모델(ensemble model)들을 결합하여 그 성능을 분석한다. 단어 표현은 미리 학습된 워드 임베딩 모델(word embedding model)과 ELMo(Embedding from Language Model), Bert(Bidirectional Encoder Representations from Transformer) 그리고 다양한 추가 자질들을 사용한다. 또한 사용된 의존 구문 분석 모델로는 Stack Pointer Network Model, Deep Biaffine Attention Parser와 Left to Right Pointer Parser를 이용한다. 최종적으로 각 모델의 분석 결과를 앙상블 모델인 Bagging 기법과 XGBoost(Extreme Gradient Boosting) 이용하여 최적의 모델을 제안한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.