• 한국통신학회논문지
• /
• 제30권6C호
• /
• pp.585-592
• /
• 2005

질병과 관련한 연구 중 가장 중요한 것은 질병이 발생치 알도록 하기 위해 치료보다는 예방과 보건 그리고 약품보다는 식품을 더 중요시해야 한다는 것이다. 따라서 일단 환자를 접할시 가장 중요한 것은 질환의 유무 그리고 만약 질환이 있다면 어떤 질환인지를 정확히 진단해 내는 것이 가장 중요하고 그 후에 용약(用藥) 과정을 거치게 된다. 본 논문에서는 한방에 있어 4대 질환 진단 방법중 가장 중요한 망진(望診)에 대해 기술하고자 한다. 망진은 관형(觀形)과 찰색(察色)이 주된 방법인데 지금까지는 이를 모두 의사의 직관에 의지 하였 왔던 것이 현 실정이었다. 이를 위해 본 연구에서는 의사에게 망진에 필요한 기초 자료를 자동으로 제공해 주는 시스템을 개발하고자 한다. 이때 시스템 개발시 개발 단계상 첫 번째 개발 단계이며 가장 중요한 작업은 관형이나 찰색에 상관없이 우선적으로 얼굴 영역을 자동으로 추출해 내는 작업이 수행되어야 한다. 또한 추출된 얼굴 영역에서 정면 얼굴인 경우는 중요한 얼굴내 요소인 눈, 눈썹, 코, 입등의 영역을 추출해 주고, 측면 얼굴의 경우는 코와 귀를 추출해 내는 작업이 전체 시스템 구축시 두 번째 작업 단계가 된다. 따라서 본 논문에서는 관형과 찰색을 위한 전체 시스템 개발 작업중 첫 번째와 두 번째 단계 작업인 정면 얼굴의 얼굴 영역 추출 방법, 그리고 추출된 정면얼굴 영역에서 눈, 눈썹, 코, 입등의 영역을 추출해 주는 방법에 대해 제안하고자 한다. 또한 제안한 방법의 유용성을 확인하기 위해 20명을 대상으로 실험을 수행한 결과 정면 얼굴의 영역 추출은 $100\%$ 성공하였다. 그리고 눈, 눈썹, 코, 입등과 같은 정면 얼굴내 주요 특징 영역 추출도 $100\%$ 성공하였으나 머리카락과 눈썹이 붙어 있는 경우에는 해당 눈썹 영역을 추출하지 못하는 결과도 있었다. 이는 차후 형태학적 연산등을 사용하여 추출해야 할 으로 사료된다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.456-460
• /
• 2012

개인정보보호법이 2012년 3월 30일 시행을 하였다. 일반적으로 개인정보를 관리하는 DB서버는 보안을 강화하기 위한 보안시스템을 갖추고 있으나, PC에서는 개인정보보호를 위한 취약점 분석과 보안성 자가진단에 대한 연구가 필요하다. 본 논문에서는 PC에서 개인정보보호 관련 정보를 검색하고, 암호화하여 보안성을 강화하고 삭제대상 파일은 복구 불가능하게 삭제한다. PC에서 검색된 취약성 분석은 사용자계정점검, 공유폴더점검, 서비스 방화벽 점검, 화면보호기, 자동패치업데이트를 점검한다. 점검 후에 취약점에 관한 정량화 분석과 표현을 통해, 보안성 강화를 위한 점검리스트을 작성해서 보여주고, PC보안 관리를 반자동화하여 서버에서 관리하여 작동시킨다. 본 논문을 통해 PC개인정보보호와 PC보안강화로 국민의 경제적 피해와 고충을 줄이는데 기여할 것이다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.940-952
• /
• 2020

The Alzheimer's disease (AD) is a neurodegenerative disease commonly found in the elderly individuals. It is one of the most common forms of dementia; patients with AD suffer from a degradation of cognitive abilities over time. To correctly diagnose AD, compuated-aided system equipped with automatic classification algorithm is of great importance. In this paper, we propose a novel deep learning based classification algorithm that takes advantage of MRI biomarker images including brain areas of hippocampus and cerebrospinal fluid for the purpose of improving the AD classification performance. In particular, we develop a new approach that effectively applies MRI biomarker patch images as input to 3D Deep Convolution Neural Network. To integrate multiple classification results from multiple biomarker patch images, we proposed the effective confidence score fusion that combine classification scores generated from soft-max layer. Experimental results show that AD classification performance can be considerably enhanced by using our proposed approach. Compared to the conventional AD classification approach relying on entire MRI input, our proposed method can improve AD classification performance of up to 10.57% thanks to using biomarker patch images. Moreover, the proposed method can attain better or comparable AD classification performances, compared to state-of-the-art methods.

• 대한환경공학회지
• /
• 제30권2호
• /
• pp.168-174
• /
• 2008

본 논문에서는 하수처리장의 자동 계측 제어 시스템을 구축함에 있어 제한 요소로 작용되는 2차 침전조의 침전 상태를 자동으로 진단하기 위해 이미지 분석 기법을 적용한 On-line SVI(Sludge Volume Index) analyzer를 이용하였다. 침전 상태를 알아보기 위해 카메라로 촬영한 디지털 이미지로부터 RGB(Red-Green-Blue) 프로파일을 얻었으며, 이를 통해 상등수와 슬러지층의 경계를 자동으로 감지할 수 있는 SV30 감지 알고리즘을 제안하였다. 개발된 SV30 감지 알고리즘은 벌킹, 핀플럭과 같은 침전 문제 발생 시에도 신뢰성 있는 감지능을 보여주었다. 또한 본 논문에서는 상등수 부분의 RGB 값과 실제 운전자에 의해 측정된 탁도 값 사이의 상관관계를 통하여, 탁도 추정 모델을 제안하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권11호
• /
• pp.680-688
• /
• 2005

The electrical current generated by heart creates not only electric potential but also a magnetic field. We have observed electrophysiological phenomena of the heart by measuring components of magnetocardiogram(MCG) using 61 channel superconducting quantum interference device(SQUD) system. We have analyzed the possibility and characteristics of MCG parameters for diagnosis of ischemic heart disease. A technique for automatic analysis of MCG signals in time domain was developed. The methods for detecting the position, the interval, the amplitude ratio, and the direction of single current dipole were examined in the MCG wave. The position and interval parameters were obtained by calculating the gradients of a envelope curve which could be formed by the difference between the maximum and minimum envelope of multi-channel MCG signals. We show some differences of the frequency contour map between the normal MCG and the abnormal (ischemic heart disease) MCG. The direction of single current dipole can be defined by rotating the magnetic field according to Biot-Savart's law at each point of MCG signals. In this study, we have examined the direction of single current dipole from searching for the centroids of positive and negative magnetic fields. The amplitude ratio parameters for measuring 57 deviation consisted of A$_{T}$/A$_{R}$ and other ratios. and We developed a new analysis method, which is based on the frequency contour map of electromagnetic field. Using theses parameters, we founded significant differences between normal subjects and ischemic patients in some parameters.

• 대한임상검사과학회지
• /
• 제41권4호
• /
• pp.173-179
• /
• 2009

The analysis of serum free light chains (sFLCs) can improve the diagnosis and monitoring of multiple myeloma and other plasma cell dyscrasias. As with other immunoassays, sFLCstests are subject to potential antigen excess and heterophilic antibody interference. We describe 9 cases of sFLCs antigen excess in patients with multiple myeloma using the FreeliteTM Human Kappa and Lambda Free Kits (The Binding Site ltd., Birmingham, UK) and the Hitachi7600 P module turbidimetric system. A total of 1,247 consecutive samples from 250 patients with multiple myeloma were assayed for sFLCs from April to September, 2009. The samples were assayed using an initial dilution of 1 :5and subsequent dilutions of 1 :50 and 1: 100. The same samples were analyzed for the presence of monoclonal gammopathies using serum protein electrophoresis (SPE) and immunofixation electrophoresis (IFE). There were 9 samples (0.72%) of antigen excess with 3 cases of kappa (0.24%) and 6 cases of lambda (0.48%). These cases represents an example of antigen excess or "hook effect" using the serum free light chain assays and mandates high level of attention to falsely low sFLC levels due to antigen excess, especially when it is disaccordant to other assay results or clinical manifestations.

• 대한한의학회지
• /
• 제40권2호
• /
• pp.133-141
• /
• 2019

Objectives: The condition of the skin is greatly influenced by seasonal changes. We wanted to know the seasonal change of skin condition and to find out the difference in the efficacy of Seoshiokyongsan (SSOOS) CP soap in spring and autumn. We are to help people who use soap to make a wise choice in choosing a cleanser according to the season. Methods: To investigate the seasonal skin condition, this experiment was conducted to examine the skin condition of spring and autumn in 20 students at A university. To compare the seasonal efficacy of Seosiokyongsan (SSOOS) CP soap, we had skin test 10 students in spring and autumn. We made herbal fermented soaps using SSOOS and distributed them to experiment participants. We let them wash their face in the morning and evening for 6 weeks using herbal fermented soap. Prior to the experiment, their skin condition was checked and assessed using A-ONE Smart One-Click Automatic Facial Diagnosis System three times at 3-week intervals. After the experiment, the changes of skin were measured and analyzed through facial analysis test. Results: In spring and autumn, the oil of T zone and U zone was significantly less and the water content was significantly higher in autumn than in spring. In the case of using the SSOOS CP soap, water content increased and oil content decreased in spring, oil content and elasticity increased in autumn. Conclusion: There is a difference in the skin condition according to the season and SSOOS CP soap showed difference in efficacy in spring and autumn. So we should pay attention to seasonal soap selection.

• Investigative Magnetic Resonance Imaging
• /
• 제23권2호
• /
• pp.114-124
• /
• 2019

Purpose: We investigate biases in the assessments of left ventricular function (LVF), by compressed sensing (CS)-cine magnetic resonance imaging (MRI). Materials and Methods: Cardiovascular cine images with short axis view, were obtained for 8 volunteers without CS. LVFs were assessed with subsampled data, with compression factors (CF) of 2, 3, 4, and 8. A semi-automatic segmentation program was used, for the assessment. The assessments by 3 CS methods (ITSC, FOCUSS, and view sharing (VS)), were compared to those without CS. Bland-Altman analysis and paired t-test were used, for comparison. In addition, real-time CS-cine imaging was also performed, with CF of 2, 3, 4, and 8 for the same volunteers. Assessments of LVF were similarly made, for CS data. A fixed compensation technique is suggested, to reduce the bias. Results: The assessment of LVF by CS-cine, includes bias and random noise. Bias appeared much larger than random noise. Median of end-diastolic volume (EDV) with CS-cine (ITSC or FOCUSS) appeared -1.4% to -7.1% smaller, compared to that of standard cine, depending on CF from (2 to 8). End-systolic volume (ESV) appeared +1.6% to +14.3% larger, stroke volume (SV), -2.4% to -16.4% smaller, and ejection fraction (EF), -1.1% to -9.2% smaller, with P < 0.05. Bias was reduced from -5.6% to -1.8% for EF, by compensation applied to real-time CS-cine (CF = 8). Conclusion: Loss of temporal resolution by adopting missing data from nearby cardiac frames, causes an underestimation for EDV, and an overestimation for ESV, resulting in underestimations for SV and EF. The bias is not random. Thus it should be removed or reduced for better diagnosis. A fixed compensation is suggested, to reduce bias in the assessment of LVF.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.255-263
• /
• 2021

Smart grid is a fully-automated, bi-directional, power transmission network based on the physical grid system, which combines sensor measurement, computer, information communication, and automatic control technology. Blockchain technology, with its security features, can be integrated with Smart Grids to provide secure and efficient power management and transmission. This paper dicusses the deployment of Blockchain technology in Smart Grid. It presents application areas and protocols in which blockchain can be applied to in securing smart grid. One application of each area is explored in detail, such as efficient peer-to-peer transaction, lower platform costs, faster processes, greater flexibility in power generation to transmission, distribution and power consumption in different energy storage systems, current barriers obstructing the implementation of blockchain applications with some level of maturity in financial services but concepts only in energy and other sectors. Wide range of energy applications suggesting a suitable blockchain architecture in smart grid operations, a sample block structure and the potential blockchain technicalities employed in it. Also, added with efficient data aggregation schemes based on the blockchain technology to overcome the challenges related to privacy and security in the smart grid. Later on, consensus algorithms and protocols are discussed. Monitoring of the usage and statistics of energy distribution systems that can also be used to remotely control energy flow to a particular area. Further, the discussion on the blockchain-based frameworks that helps in the diagnosis and maintenance of smart grid equipment. We have also discussed several commercial implementations of blockchain in the smart grid. Finally, various challenges have been discussed for integrating these technologies. Overall, it can be said at the present point in time that blockchain technology certainly shows a lot of potentials from a customer perspective too and should be further developed by market participants. The approaches seen thus far may have a disruptive effect in the future and might require additional regulatory intervention in an already tightly regulated energy market. If blockchains are to deliver benefits for consumers (whether as consumers or prosumers of energy), a strong focus on consumer issues will be needed.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.19-28
• /
• 2021

위내시경 촬영은 조기에 위 병변을 진단하기 위해서 주로 사용한다. 하지만 위내시경을 했음에도 불구하고 위 내부를 자세히 관찰하지 못해서 10~20% 위 병변을 놓치는 경우가 생기는 것으로 보고되고 있다. 미국, 영국, 일본 등의 일부 국가와 세계내시경협회(Wold Endoscopy Organization)에서는 위내시경 시에 맹점 없는 관찰을 위해서 반드시 촬영해야 할 부위에 대한 촬영지침을 제안한 바 있다. 이에 본 논문에서는 수련의가 내시경을 하는 데 있어 위 내부를 자동으로 맹점 없이 관찰하는데 필요한 딥러닝 기술인 해부학적 분류모델을 제안한다. 제안한 모델은 위내시경 이미지에 적합한 전처리 모듈과 데이터 증강 기술들을 사용한다. 실험결과를 통해 최대 F1 점수 99.6% 분류 성능을 확인하였다. 또한, 실제 데이터를 통한 실험결과에서도 에러율이 4% 미만을 보였다. 이러한 성능을 바탕으로 설명 가능한 모델임을 보여 임상에서의 사용 가능성을 확인하였다.