• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.2
• /
• pp.155-161
• /
• 2019

Currently, numerous companies and institutes provide services using the Internet, and establish and operate Information Systems to manage them efficiently and reliably. The Information System implies the possibility of losing the ability to provide normal services due to a disaster or disability. It is preparing for this by utilizing a disaster recovery system. However, existing disaster recovery systems cannot perform normal recovery if files for system recovery are corrupted. In this paper, we proposed a system that can verify the integrity of the system recovery file and proceed with recovery by utilizing hyper-ledger fabric blockchain. The PBFT consensus algorithm is used to generate the blocks and is performed by the leader node of the blockchain network. In the event of failure, verify the integrity of the recovery file by comparing the hash value of the recovery file with the hash value in the blockchain and proceed with recovery. For the evaluation of proposed techniques, a comparative analysis was conducted based on four items: existing system recovery techniques and data consistency, able to data retention, recovery file integrity, and using the proposed technique, the amount of traffic generated was analyzed to determine whether it was actually applicable.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.4
• /
• pp.466-475
• /
• 2024

Matched-Field Processing (MFP) is a model-based approach that requires accurate knowledge of the ocean environment and array geometry (e.g., array tilt) to localize underwater acoustic sources. Consequently, it is inherently sensitive to model mismatches. In contrast, the waveguide invariant-based approach (also known as array invariant) offers a simple and robust means for source-range estimation in shallow waters. This approach solely exploits the beam angles and travel times of multiple arrivals separated in the beam-time domain, requiring no modeling of the acoustic fields, unlike MFP. This paper extends the waveguide invariant-based approach to shallow water environments featuring a shallow pit, where the waveguide invariant is not defined due to the complex bathymetry. An in-depth performance analysis is conducted using experimental data and numerical simulations.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.3
• /
• pp.45-55
• /
• 2022

BIM models allow building spaces to be instantiated and recognized as unique objects independently of model elements. These instantiated spaces provide the required semantics that can be leveraged for building code checking, energy analysis, and evacuation route analysis. However, theses spaces or rooms need to be designated manually, which in practice, lead to errors and omissions. Thus, most BIM models today does not guarantee the semantic integrity of space designations, limiting their potential applicability. Recent studies have explored ways to automate space allocation in BIM models using artificial intelligence algorithms, but they are limited in their scope and relatively low classification accuracy. This study explored the use of Graph Convolutional Networks, an algorithm exclusively tailored for graph data structures. The goal was to utilize not only geometry information but also the semantic relational data between spaces and elements in the BIM model. Results of the study confirmed that the accuracy was improved by about 8% compared to algorithms that only used geometric distinctions of the individual spaces.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06d
• /
• pp.58-60
• /
• 2012

스마트 TV 및 스마트 셋톱박스와 같은 가정내의 고정형 스마트 기기에 대한 관심이 증가하고 있으며, 이러한 기기는 가정의 미디어 서비스를 제어하는 콘텐츠 허브로 발전하고 있으며, 홈 플랫폼의 포괄적 개념으로 정의할 수 있다. 이러한 홈 플랫폼은 IPTV, 지상파, 케이블, 및 위성 등의 다양한 방송 콘텐츠를 수용할 수 있으며, 모바일 단말 등의 외부 기기와의 연동을 통해 다양한 형태의 콘텐츠에 대해서 접근이 가능하다. 이와 관련하여 실제 서비스 제공이 가능한 기술은 방송 콘텐츠와 시간적으로 연계된 부가정보를 사용자의 모바일 단말에서 제공해 주는 서비스 기술이다. 또, 가정내의 홈 플랫폼을 통해 접근 가능한 다양한 방송 및 콘텐츠 부가정보를 통합적으로 취합하여 하나의 콘텐츠 가이드를 생성하고, 이를 개인 모바일 단말로 전송하여 사용자의 콘텐츠 소비 만족도를 보다 향상할 수 있는 기술에 대한 관심 역시 증가하고 있다. 본 논문에서는 홈 플랫폼에서 방송 수신 정보, 로컬 콘텐츠 및 모바일 단말의 저장 콘텐츠 정보를 기반으로 부가정보를 정합하여 ECG를 생성하고, 이를 모바일 단말에 전송하여 콘텐츠 서비스를 제공하는 플랫폼을 설계하고, 구현하였다. 통합 ECG 생성을 위한 콘텐츠의 메타데이터는 TV-Anytime 표준을 기반으로 적용되어 플랫폼간 상호 연동성이 확보되도록 하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.13-20
• /
• 2010

We proposed a new technique to perform fast video stabilization using integral image in this article. In the proposed technique, it evaluate local and global motion by the block matching using the generated integral image for each frame and compensate the motion like jitter. We made the various experimental jitter patterns to evaluate the effectiveness of the proposed technique and evaluated stabilization capability and execution time with the existing ones. Through the experiment, we found that the execution time of proposed technique was faster than that of existing techniques and the compensation of jitter was well done.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.9A
• /
• pp.2141-2152
• /
• 1998

In this paper, we design and implement an indoor wireless modem using small signal of ISM band regulation, which can tranceive reliable data streams. We use direct sequence spead spectrum (DS-SS) signaling with synchronous BPSK and QPSK modulation, convolutional coding with viterbi decoding. The radio frequency module uses frequency devision duplexing in 900 MHz band, and the digital module is implemented with FPGAs for the purpose fo ASIC design. The perfomrance of our own acquistion and tracking circuit consisting digital matched filter and decision logic is proved by experiments, and the possibility of file transfer at indoor environment with the entrie system that the modem is connected the PC through RS-232C port is verified.

• The Korean Society of Law and Medicine
• /
• v.24 no.4
• /
• pp.67-101
• /
• 2023

The utilization of generative AI in the medical field is also being rapidly researched. Access to vast data sets reduces the time and energy spent in selecting information. However, as the effort put into content creation decreases, there is a greater likelihood of associated issues arising. For example, with generative AI, users must discern the accuracy of results themselves, as these AIs learn from data within a set period and generate outcomes. While the answers may appear plausible, their sources are often unclear, making it challenging to determine their veracity. Additionally, the possibility of presenting results from a biased or distorted perspective cannot be discounted at present on ethical grounds. Despite these concerns, the field of generative AI is continually advancing, with an increasing number of users leveraging it in various sectors, including biomedical and life sciences. This raises important legal considerations regarding who bears responsibility and to what extent for any damages caused by these high-performance AI algorithms. A general overview of issues with generative AI includes those discussed above, but another perspective arises from its fundamental nature as a large-scale language model ('LLM') AI. There is a civil law concern regarding "the memorization of training data within artificial neural networks and its subsequent reproduction". Medical data, by nature, often reflects personal characteristics of patients, potentially leading to issues such as the regeneration of personal information. The extensive application of generative AI in scenarios beyond traditional AI brings forth the possibility of legal challenges that cannot be ignored. Upon examining the technical characteristics of generative AI and focusing on legal issues, especially concerning the protection of personal information, it's evident that current laws regarding personal information protection, particularly in the context of health and medical data utilization, are inadequate. These laws provide processes for anonymizing and de-identification, specific personal information but fall short when generative AI is applied as software in medical devices. To address the functionalities of generative AI in clinical software, a reevaluation and adjustment of existing laws for the protection of personal information are imperative.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.3
• /
• pp.661-669
• /
• 2000

DS-CDMA downlink distinguishes actual user by orthogonal spreading codes ,but its orthogonality may be lost by the multiple access interference(MAI) caused by the multipath channel. Therefore in this paper, we proposed the single-user receiver, which use linear channel equalizer to eliminate the interference due to multipath channel and to recover orthogonality and then use code-matched filter to detect transmitted data. Unlike existing research, which mainly assumed ideal channel information, we use pilot channel assisted methods that is a kind of transmission of a parallel reference method to estimate the channel coefficients. Especially we use guard symbols which are inserted periodically to estimate channel coefficients exactly without interference from user signal. The results show that we accepted an approximately ideal channel information and achieved excellent performance improvement using proposed receiver compared with the conventional receiver especially user populations are high.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.5
• /
• pp.411-419
• /
• 2013

Research on developing algorithms for building modeling such as extracting outlines of the buildings and segmenting patches of the roofs using aerial images or LiDAR data are active. However, utilizing information from the building model is not well implemented yet. This study aims to propose a scheme for search identical or similar shape of buildings by utilizing graph topology pattern matching under the assumptions: (1) Buildings were modeled beforehand using imagery or LiDAR data, or (2) 3D building data from digital maps are available. Side walls, segmented roofs and footprints were represented as nodes, and relationships among the nodes were defined using graph topology. Topology graph database was generated and pattern matching was performed with buildings of various shapes. The results show that efficiency of the proposed method in terms of reliability of matching and database structure. In addition, flexibility in the search was achieved by altering conditions for the pattern matching. Furthermore, topology graph representation could be used as scale and rotation invariant shape descriptor.