• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.307-313
• /
• 2024

This study explores the integration of Explainable Artificial Intelligence (XAI) and network science in healthcare, focusing on enhancing healthcare data interpretation and improving diagnostic and treatment methods. Key methodologies like Graph Neural Networks, Community Detection, Overlapping Network Models, and Time-Series Network Analysis are examined in depth for their potential in patient health management. The research highlights the transformative role of XAI in making complex AI models transparent and interpretable, essential for accurate, data-driven decision-making in healthcare. Case studies demonstrate the practical application of these methodologies in predicting diseases, understanding drug interactions, and tracking patient health over time. The study concludes with the immense promise of these advancements in healthcare, despite existing challenges, and underscores the need for ongoing research to fully realize the potential of AI in this field.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.4 no.4
• /
• pp.258-262
• /
• 2004

Storage over Ethernet (SoE) is a network storage architecture that allows direct attachment of existing ATA/ATAPI devices to Ethernet without a separate server. Unlike SAN, no server computer intervenes between the storage and the client hosts. We propose a SoE disk controller (SoEDC) amenable to low-cost, single-chip implementation that processes a simplified L3/L4 protocol and converts commands between Ethernet and ATA/ATAPI, while the rest of the complex tasks are performed by the remote hosts. Thanks to simple architecture and protocol, the SoEDC implemented on a single $4mm{\times}4mm$ chip in 0.18um CMOS technology achieves maximum throughput of 55MB/s on Gigabit Ethernet, which is comparable to that of a high-performance disk storage locally attached to a host computer.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.928-931
• /
• 2017

네트워크 트래픽 데이터를 정제하여, Convolutional Neural Network Model 훈련에 적합한 데이터 세트로 변환하는데, 그 방법은 패킷 단위의 트래픽 데이터를 이미지 형태로 만드는 것이다. 완성된 데이터 세트를 훈련데이터로 하여 Convolutional Neural Network Model에 훈련하고, 훈련데이터의 이미지 크기를 변환해가며 훈련시킨 결과에 대해 비교 분석 및 평가를 진행한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.434-439
• /
• 1994

Recently neural networks leave been proposed as new computational tools for solving constrained optimization problems because of its computational power. In this paper, the shortest path finding algorithm is proposed by rising a Hopfield type neural network. In order to design a Hopfield type neural network, an energy function must be defined at first. To obtain this energy function, the concept of a vector-represented network is introduced to describe the connected path. Through computer simulations, it will be shown that the proposed algorithm works very well in many cases. The local minima problem of a Hopfield type neural network is discussed.

• Genomics & Informatics
• /
• v.14 no.1
• /
• pp.2-11
• /
• 2016

The advances in mass spectrometry-based proteomics technologies have enabled the generation of global proteome data from tissue or body fluid samples collected from a broad spectrum of human diseases. Comparative proteomic analysis of global proteome data identifies and prioritizes the proteins showing altered abundances, called differentially expressed proteins (DEPs), in disease samples, compared to control samples. Protein biomarker candidates that can serve as indicators of disease states are then selected as key molecules among these proteins. Recently, it has been addressed that cellular pathways can provide better indications of disease states than individual molecules and also network analysis of the DEPs enables effective identification of cellular pathways altered in disease conditions and key molecules representing the altered cellular pathways. Accordingly, a number of network-based approaches to identify disease-related pathways and representative molecules of such pathways have been developed. In this review, we summarize analytical platforms for network-based protein biomarker discovery and key components in the platforms.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.31-35
• /
• 2008

Social Network는 웹 환경에서 개인을 중심으로 뻗어 나가는 연결로서 사용자별 프로필을 탐색하고 새로운 연결 및 정보의 소통을 지원한다. 이러한 상호신뢰를 바탕으로 구축된 Social Network 환경 내 구성원들이 가지고 있는 속성(Feature)을 이용하여 사용자간 친밀도를 산정한다면 친구 및 동호회 추천 등 Social Network 내부의 효율 향상 뿐만 아니라 웹 검색 등 다양한 사용자간의 공통 활동에도 응용할 수 있다. 본 논문에서는 Social Network 사용자간 친밀도를 산정하기 위한 방법을 제시한다. 기존의 친밀도가 없이 구성되어 있는 사용자간의 관계를 사용자의 속성(Feature)에 내재된 정보를 이용하여 주제의 유사성과 접근성을 이용하여 산정하였으며, 이는 Social Network 성격의 규명과 사용자의 정보 요구에 대한 판단의 척도로 사용될 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3003-3017
• /
• 2013

In this paper, we investigate the outage performance of a cognitive relay network. We consider mutual interference in an independent, non-identically distributed Nakagmai-m fading environment. We first derive the close-form outage probability expression, which provides an efficient means to evaluate the effects of several parameters. This allows us to study the impact of several parameters on the network's performance. We then derive the asymptotic expression and reveal that the diversity order is strictly determined by the fading severity of the cognitive system. It is not affected by the primary network. Moreover, the primary network only affects the coding gain of the cognitive system. Finally, Monte Carlo simulations are provided, which corroborate the analytical results.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.59.2-59.2
• /
• 2011

We introduce an ongoing project for monitoring total flux density at 22 and 43GHz, linearly polarized flux, and polarization angle at 22GHz of Gamma-ray bright AGN (Active Galactic Nuclei) with KVN (Korean VLBI Network) 21-m radio telescopes. The project started in May, 2011 with an effective monitoring cycle of 4 days, observing four main objects (3C 454.3, BL Lac, 3C 273, and 3C 279). More objects were included in the source list when they had flared in Gamma-ray. In this paper, we report the current status of the project and preliminary results for the monitoring observations.

• Proceedings of the Korean Powder Metallurgy Institute Conference
• /
• 2006.09a
• /
• pp.462-463
• /
• 2006

Monodispersed and nano-sized Ni powders were synthesized from aqueous nickel sulfate hexahydrate $(NiSO_4{\cdot}6H_2O)$ inside nonionic polymer network by using wet chemical reduction process. The sucrose was used as a nonionic polymer network source. The effect of reaction conditions such as the amount of sucrose and a various reaction temperature, nickel sulfate hexahydrate molarity. The influence of a nonionic polymer network on the particle size of the prepared Ni powders was characterized by means of X-ray diffraction (XRD), scanning electron microscopy (SEM), and particle size analysis (PSA). The results showed that the obtained Ni powders were strong by dependent of the reaction conditions. In particular, the Ni powders prepared inside a nonionic polymer network had smooth spherical shape and narrow particle size distribution.

• Journal of Sensor Science and Technology
• /
• v.19 no.5
• /
• pp.369-374
• /
• 2010

It is important to efficiently elect the cluster header in Hierarchical Sensor Network, because it largely affects on the lifetime of the network. Therefore, recent research is focused on the lifetime extension of the whole network for efficient cluster header election. In this paper, we propose the new Cluster Header Election Scheme in which the cluster is divided into Group considering Distance from Upper Node, and a cluster header will be elected by node density of the Group. Also, we evaluate the performance of this scheme, and show that this proposed scheme improves network lifetime in Zigbee environment.