• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.460-468
• /
• 2023

Developmental Dysplasia of the Hip (DDH) is a pathological condition commonly occurring during the growth phase of infants. It acts as one of the factors that can disrupt an infant's growth and trigger potential complications. Therefore, it is critically important to detect and treat this condition early. The traditional diagnostic methods for DDH involve palpation techniques and diagnosis methods based on the detection of keypoints in the hip joint using X-ray or ultrasound imaging. However, there exist limitations in objectivity and productivity during keypoint detection in the hip joint. This study proposes a deep learning model-based keypoint detection method using X-ray and ultrasound imaging and analyzes the performance of keypoint detection using various deep learning models. Additionally, the study introduces and evaluates various data augmentation techniques to compensate the lack of medical data. This research demonstrated the highest keypoint detection performance when applying the residual network 152 (ResNet152) model with simple & complex augmentation techniques, with average Object Keypoint Similarity (OKS) of approximately 95.33 % and 81.21 % in X-ray and ultrasound images, respectively. These results demonstrate that the application of deep learning models to ultrasound and X-ray images to detect the keypoints in the hip joint could enhance the objectivity and productivity in DDH diagnosis.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.3
• /
• pp.19-27
• /
• 2016

Advance in Information and Communication Technology (ICT) is intensely influenced to increase importance of Software on global ICT industries. The trend of technological development has been transformed from hardware-oriented environment to software-oriented environment. This industrial transformation brought novel trend to Software market. Open Source Software (OSS) has been widely distributed for private uses. At the same time, many governmental offices are planning to expand the use of OSS. In this paper, we analyze the strength and weaknesses of OSSs for both Web and WAS servers based on 4 types of testing environments which are created by the combination of 5 selected OSSs. We anticipated to learn the optimal system architecture design for the next generation of V-World through this research.

• KNOM Review
• /
• v.22 no.2
• /
• pp.12-21
• /
• 2019

There is a rapid development of experimental equipment and ICT technology in data-intensive scientific areas, thus, big data of more than exabyte size is being generated. However, the big data transmission technology does not satisfy the needs of the application researchers who utilize it. Various high-performance transmission technologies have been developed based on QoS(Quality of Service), but they also require changes in the clean slate method. On the other hand, ScienceDMZ technologies improve the performance of scientific big data transmission by bypassing the firewall that causes a big problem in transmission performance. In addition, it is possible to implement without changing the existing network. In this paper, we built ScienceDMZ in an international long-distance environment based on KREONET(Korea Research Environment Open NETwork), and we verified the performance. We also introduced how GPU platform could be linked in a distributed ScienceDMZ environment.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.4
• /
• pp.410-416
• /
• 2013

In this paper, we propose a chaotic correlation delay shift keying(CDSK) using digital retrodirective array antenna (RDA) for improving security and receive performance. Chaotic signals provide improved security due to non-periodic and non-predictable performance of chaotic signals. However, the receive performance of these chaotic signals is degraded due to self-interference and interference signals. Therefore, this paper, we analyze the receive BER performance of chaos communication system which has digital RDA based on CDSK modulation schemes for improving security without receive performance degradation. Simulation results show that the proposed system can get the same receiving performance compared to BPSK modulation schemes when array elements of RDA are 5.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.10-13
• /
• 2016

정부는 K-ICT 클라우드 활성화를 위해 정부 3.0 클라우드 추진 계획을 발표하고 관련 제도와 법률을 제정하여 클라우드 서비스 도입을 위한 정책을 추진하고 있다. 그러나 공공 분야의 클라우드 컴퓨팅 도입은 기존의 법률, 제도, 관행의 통제로 인해 미미한 실정이다. 공공 기관의 클라우드 컴퓨팅 도입 활성화를 위해 중요한 부분은 클라우드 컴퓨팅의 성능과 품질 등에 대한 특성을 파악하는 것이다. 클라우드 컴퓨팅의 특성을 알아야만 적격의 클라우드 컴퓨팅 사업자 선정이 가능하게 된다. 유럽 연합(European Commission)에서는 클라우드 컴퓨팅의 특성을 서비스 성능과 품질에 대한 일반특성, 기술성, 경제성으로 분류하고 있다. 그러나 클라우드 도입을 위한 설계 시 공공 기관 담당자는 클라우드 특성의 각 부문별 하위 항목에 대한 상세한 내용과 수준까지 객관적으로 평가하기 어렵다. 이러한 문제를 해결하고자 본 연구는 클라우드 컴퓨팅의 성능과 품질 및 기술 특성을 파악하여 각 특성에 대한 가중치를 구하고 우선순위 측정을 통해 사업자 선정을 위한 평가 기준으로 적용하는 기법을 제안한다.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.55-63
• /
• 2020

The IoT technology is a field that applies and converges the technologies in the existing industrial environment, instead of new technologies. The IoT technology is releasing various application services converged with other industries such as smart home, healthcare, construction, and automobile, and it is also possible to secure the work efficiency and convenience of users of IoT-based technologies. However, the security threats occurring in the IoT-based technology environment are succeeding to the vulnerability of the existing wireless network environment. And the occurrence of new and variant attacks in the combination with the ICT convergence environment, is causing damages. Thus, in the IoT technology-based environment, it would be necessary to have researches on the safe transmission of messages in the communication environment between user and device, and device and device. This thesis aims to design a safe communication protocol in the IoT-based technology environment. Regarding the suggested communication protocol, this thesis performed the safety analysis on the attack techniques occurring in the IoT technology-based environment. And through the performance evaluation of the existing PKI-based certificate issuance system and the suggested communication protocol, this thesis verified the high efficiency(about 23%) of communication procedure. Also, this thesis verified the reduced figure(about 65%) of the issued quantity of certificate compared to the existing issuance system and the certificate management technique.

• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.107-108
• /
• 2023

자율운항선박 (Maritime Autonomous Surface Ship, MASS) 관련 기술은 전 세계적으로 활발히 개발 중이다. 이와 더불어 선박정보 통신 기술(ICT)을 활용한 선박 관리에 대한 수요가 증가하면서 선박 데이터의 신뢰성 확보가 더욱 중요해지고 있다. 선박에서 사용하는 데이터는 점차 복잡해지고 용량이 증가함에 따라 체계적인 관리 방안이 필요하다. 본 연구에서는 주요 선급에서 발간한 기술자료와 표준동향 분석 및 전문가 논의를 통해 신규 표준 아이템을 도출하였다. 이를 기반으로 ISO 선박 및 해양기술 분과에 제안한 선박 데이터 신뢰성 확보를 위한 데이터 품질 관리 표준 제안한 결과를 소개하고자 한다. 신규 제안한 표준을 통해 국내 조선소 및 기업에서 개발한 선박 성능 분석 및 모니터링 시스템에 대한 품질 검증에 활용할 수 있을 것으로 예상된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.126-128
• /
• 2022

초고성능컴퓨터를 활용하여 전통적인 병렬처리 기반의 계산과학을 비롯하여 AI, 빅데이터 등의 ICT 기반 연구를 수행할 수 있어야 한다는 수요가 증가하고 있다. 계산과학 연구의 다양성에 맞춰 컴퓨팅 연구환경을 제공하기 위하여 한국과학기술정보연구원(KISTI)에서는 초고성능컴퓨터를 인프라로 활용하는 HPC 클라우드인 KI(KISTI Intelligent) Cloud를 개발하여 서비스하고 있다. 본 논문에서는 KI Cloud의 과금을 위한 기능의 설계 및 구현 현황을 기술하였다. 가상서버(VM) 기반의 서비스와 컨테이너 기반의 서비스의 사용량을 측정하기 위하여 Prometheus로 CPU의 사용량을 수집하여 과금 정책을 적용하고 있는 KI Cloud의 과금 기능에 대해서 살펴보도록 한다.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.625-634
• /
• 2002

In this paper, we conducted various experiments with Bayesian networks in order to analyze clinical data of infertility patients. With these experiments, we tried to find out inter-dependencies among important factors playing the key role in clinical pregnancy, and to compare 3 different kinds of Bayesian network classifiers (including NBN, BAN, GBN) in terms of classification performance. As a result of experiments, we found the fact that the most important features playing the key role in clinical pregnancy (Clin) are indication (IND), stimulation, age of female partner (FA), number of ova (ICT), and use of Wallace (ETM), and then discovered inter-dependencies among these features. And we made sure that BAN and GBN, which are more general Bayesian network classifiers permitting inter-dependencies among features, show higher performance than NBN. By comparing Bayesian classifiers based on probabilistic representation and reasoning with other classifiers such as decision trees and k-nearest neighbor methods, we found that the former show higher performance than the latter due to inherent characteristics of clinical domain. finally, we suggested a feature reduction method in which all features except only some ones within Markov blanket of the class node are removed, and investigated by experiments whether such feature reduction can increase the performance of Bayesian classifiers.