• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.49.2-49
• /
• 2002

This paper describes the configuration of a multi-agent system that can recognize human intentions. This system constructs ontologies of human intentions and enables knowledge acquisition and sharing between intelligent agents operating in different environments. This is achieved by using a bi-directional associative memory network. The process of intention recognition is based on fuzzy association inferences. This paper shows the process of information sharing by using ontologies. The purpose of this research is to create human-centered systems that can provide a natural interface in their interaction with people.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.306-311
• /
• 2009

We initially obtained human diseases-related proteins dataset from the OMIM and the SWISS PROT and then constructed disease-related protein-protein interaction network. The protein network contains 40 hub proteins such as CALM1, ACTB and ABL2. The protein network can be derived the map of the relationship between different disease proteins, denoted disease interaction network. We demonstrate that the associations between diseases are directly correlated to their underlying protein-protein interaction networks. From constructed the disease-protein bipartite network, we derived 38 diseasomal proteins, including APP, ABL1 and STAT1. We previously demonstrated that hub proteins in the network tend to be diseasomal proteins in the disease-related protein sub-networks. However, we found that 18% hubs are only diseasomal proteins in the whole disease network. At this point, we could not elucidate difference in the hub-diseasomal proteins tendency between sub0network and whole network. In spite of we still have unsolved problems, our results elucidate that the discovery of protein interaction networks assigned by diseases will provide insight into the underlying molecular mechanisms and biological processes in complex human disease system.

• Genomics & Informatics
• /
• v.2 no.4
• /
• pp.167-173
• /
• 2004

The main mechanism of evolution is that biological entities change, are selected, and reproduce. We propose a different concept in terms of the main agent or atom of evolution: in the biological world, not an individual object, but its interactive network is the fundamental unit of evolution. The interaction network is composed of interaction pairs of information objects that have order information. This indicates a paradigm shift from 3D biological objects to an abstract network of information entities as the primary agent of evolution. It forces us to change our views about how organisms evolve and therefore the methods we use to analyze evolution.

• Genomics & Informatics
• /
• v.18 no.4
• /
• pp.39.1-39.8
• /
• 2020

Alzheimer's disease (AD) is a chronic, progressive brain disorder that slowly destroys affected individuals' memory and reasoning faculties, and consequently, their ability to perform the simplest tasks. This study investigated the hub genes of AD. Proteins interact with other proteins and non-protein molecules, and these interactions play an important role in understanding protein function. Computational methods are useful for understanding biological problems, in particular, network analyses of protein-protein interactions. Through a protein network analysis, we identified the following top 10 hub genes associated with AD: PTGER3, C3AR1, NPY, ADCY2, CXCL12, CCR5, MTNR1A, CNR2, GRM2, and CXCL8. Through gene enrichment, it was identified that most gene functions could be classified as integral to the plasma membrane, G-protein coupled receptor activity, and cell communication under gene ontology, as well as involvement in signal transduction pathways. Based on the convergent functional genomics ranking, the prioritized genes were NPY, CXCL12, CCR5, and CNR2.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.489-490
• /
• 2023

기계 학습에서 데이터 및 기능은 기계 학습의 상한을 결정한다.이러한 기능은 산업 생산에서 과도한 데이터 양과 유형으로 인해 상당한 추가 비용이 발생할 수 있다. 따라서 적절한 특징 처리 방법이 매우 중요해졌다. 대부분의 기존 특징 처리 방법은 특징 엔지니어링을 기능 검색 문제, 즉 모델 성능을 최적화할 수 있는 기능 변환 작업을 검색하는 것으로 추상화한다. 그러나 자동 특징 엔지니어링의 경우 검색량과 변환 조합의 수가 매우 많기 때문에 요인 분해 기반 모델을 사용하여 벡터 곱셈을 통해 상호 작용을 측정하면 조합 특징의 패턴을 자동으로 학습하는 방법이 특히 효율적이다. xDeepFM 은 명확한 방식으로 특징적인 상호작용을 생성하도록 설계된 새로운 Compressed Interaction Network (CIN)를 제안한다. 여기에 제시된 Low-rank Compressed Interaction Network(LRCIN )은 xDeepFM 접근 방식에서 CIN 네트워크의 단순화된 개선을 기반으로 하며 xDeepFM 에 주의 메커니즘을 추가하여 보다 정확하게 예측된다. 실험 결과에 따르면 모델은 계산 복잡성을 단순화할 뿐만 아니라 예측 정확도도 다른 모델보다 훨씬 우수한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.252-255
• /
• 2010

In this thesis, it suggests large scale interactive display system which is able to various touch interaction and bases on infrared LED BAR and using 3D. Interaction layer formed on space from screen which is able to feel 3D using suggested IR LED BAR. It gets the image in real time what is composed in interaction section using infrared camera with band pass filter. The image finds touch interaction coordinate through image processing module and saves as packet. It send packet to server through network data communication. It analyze packet by metaphor analysis module and save as metaphor event and send it to contents. On contents, it practices to metaphor event result in real time so it makes use touch interaction in stereopsis. According to this process, it does not need touch the screen at firsthand but it is possible system and touch interaction so touch interaction is possible while use 3D.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.527-530
• /
• 2011

This Paper studied out prototype and the structure of comic expression on Social Network Game and started with issues based on SNS(Social Network Service) in Culture Communication. Interaction with the platform have the information that aims to develop relationships with SNG. In a world where the paradigm is changing the game People of all ages, transcending national borders in the mediator role of interaction could have been important. Today SNG is a major topic in Game Contents and this issue has influenced the game design and Story Telling. Under this Situation, this study has a significant meaning because it proves that the factors Comic Expression in game is analyzed by SNG.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.418-421
• /
• 2009

This paper presents a human-machine interaction based on a realtime upper limb motion prediction method using surface electromyography (sEMG). The motions were predicted using an artificial neural network algorithm and sEMG signals which are acquired from five muscles, and then a manipulator was controlled to follow after the predicted motions. Upper limb motions were restricted to 2D vertical plane with the contact condition between a user and an end-effector of manipulator. In order to demonstrate the feasibility of the proposed method, experiments using developed method and using a goniometer were performed. The results showed that the proposed real-time motion prediction method can be implemented a human-machine interaction system.

• Journal of Information Science Theory and Practice
• /
• v.5 no.4
• /
• pp.26-38
• /
• 2017

Even through many professional organizations increasingly use Q&A sites in their online communities for information sharing, there are few studies which examine what is really going on in the Q&A activities in professional online communities (POC). This study aims to examine the interaction patterns and contents posted in the Q&A site of a POC, KOSEN, a science and technology online community in South Korea, focusing on how actively scientific information and knowledge are shared. The interaction patterns among the participants were identified through social network analysis (SNA) and the contents in the Q&As were examined by content analysis. The results show that the overall network indicated a moderate level of participation and connection and answerers especially tended to be active. Also, there are different interaction patterns depending on academic fields. Relatively few participants were posting leaders who seemed to steer the overall interactions. Furthermore, some content related to manipulation and explanation for experiments, which are in urgent need, seem to be posted in the sites more frequently with more amounts. Combining both SNA and content analysis, this study demonstrated how actively information and knowledge is shared and what types of contents are exchanged. The findings have practical implications for POC managers and practitioners.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1673-1681
• /
• 2021

Item cold start is a well studied problem in the research field of recommender systems. Still, many existing collaborative filters cannot recommend items accurately when only a few user-item interaction data are available for newly introduced items (Cold items). We propose a interaction feature prediction method to mitigate item cold start problem. The proposed method predicts the interaction features that collaborative filters can calculate for the cold items. For prediction, in addition to content features of the cold-items used by state-of-the-art methods, our method exploits the interaction features of k-nearest content neighbors of the cold-items. An attention network is adopted to extract appropriate information from the interaction features of the neighbors by examining the contents feature similarity between the cold-item and its neighbors. Our evaluation on a real dataset CiteULike shows that the proposed method outperforms state-of-the-art methods 0.027 in Recall@20 metric and 0.023 in NDCG@20 metric.