• 한국산학기술학회논문지
• /
• 제7권6호
• /
• pp.1257-1263
• /
• 2006

다양한 의료진단 자동화 기기들이 개발되고 있으나 대부분 서양의학에 집중되어 있는 현실이고, 한의학의 진단시 자동화 및 정량화를 위한 장치 개발은 미미하다. 한편, 한의학에서의 네가지 진단 방법 중 하나인 망진은 환자의 관형과 찰색을 통해 질병의 유무와 경중을 진단한다. 망진을 시행할 때 얼굴에서 이목구비와 명당 부위의 상태가 특히 중요하다. 본 논문에서는 얼굴 영상으로부터 망진을 위한 얼굴 요소들을 추출하기 위한 방법을 제안하고, 남여 얼굴 영상에 대한 실험을 통해 제안한 방법의 유용성을 보이고자 한다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.338-345
• /
• 2013

Induction motors play an increasing importance in industrial manufacturing. Therefore, the state monitoring systems also have been considering as the key in dealing with their negative effect by absorbing faulty symptoms in motors. There are numerous proposed systems in literature, in which, several kinds of signals are utilized as the input. To solve the multiple faults problem of induction motors, like the proposed system, the vibration signals is good candidate. In this study, a new signal processing scheme was utilized, which transforms the time domain vibration signal into the spatial domain as an image. Then the spatial features of converted image then have been extracted by applying the dominant neighbourhood structure (DNS) algorithm. In addition, these feature vectors were evaluated to obtain the fruitful dimensions, which support to discriminate between states of motors. Because of reliability, the conventional one-against-all (OAA) multi-class support vector machines (MCSVM) have been utilized in the proposed system as classifier module. Even though examined in severity levels of signal-to-noise ratio (SNR), up to 15dB, the proposed system still reliable in term of two criteria: true positive (TF) and false positive (FP). Furthermore, it also offers better performance than five state-of-the-art systems.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권2호
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• 벤처창업연구
• /
• 제3권1호
• /
• pp.57-72
• /
• 2008

본 논문에서는 그동안 부분적으로 진행된 발달장애 진단 평가에 관련된 전산처리를 멀티미디어 기법을 응용하여 발달장애 진단 평가분야에 새로운 방법을 제시한다. 발달장애 진단 평가를 위한 멀티미디어 정보는 여러 가지 속성을 지니고 있기 때문에 모든 발달장애 진단 평가 정보에 대한 기술을 사람이 수행해야 할 때는 엄청난 작업량이 수반될 뿐 아니라 동일한 데이터에 대한 기술이 주관에 따라 달라질 수도 있다는 것을 알게 되였다. 특히 발달장애 시스템 구현은 현재의 컴퓨팅 환경에서의 동영상 데이터 처리에 대한 비중의 증가, 텍스트 위주의 데이터에서 시각적인 동영상으로의 데이터 활용의 전이 등 발달장애 데이터가 멀티미디어 환경에 적합한 데이터로의 전이가 필수적이며 사용자 역시 빠른 이해를 위해 시각적 데이터를 선호하기 때문에 본 논문에서는 GUI(Graphics User Interface) 기법을 도입하여 검사 중에 텍스트 명령어는 거의 사용하지 않고도 발달장애 진단 평가를 수행할 수 있게 했다. 특히 발달장애 진단 평가에서 필요한 각종 데이터는 그 속성이 영상, 이미지, 논리연산의 필요성 및 각종 연산이 요구된다. 그래서 본 논문에서는 문제점을 해결하기 위해 편집대상 데이터(Content)에 의해 관련 정보를 검색하는 내용 기반(Content-based)의 검색 기술에 대한 연구를 적용했다.

• 치과방사선
• /
• 제22권1호
• /
• pp.67-75
• /
• 1992

Transcranial radiograph is widely used in the diagnosis of craniomandibular disorder because it can be used by the dentist with relative ease in spite of image distortion. But correct information can be obtained only when one know the image change by projection angulation. The author compared the condyle position in the 3 groups of transcranial radiographs (horizontal angulation - 0°, 5°, individualized) with that in the individualized corrected lateral tomogram by objective and subjective evaluation methods. The results were as follows: 1. Among 3 transcranial groups, the condyle position in individualized group showed the highest concordance rate with that in the tomogram group in objective and subjective evaluation methods. 2. Correlation coefficient between individualized transcranial group and tomogram group in objective evaluation method was highest (P≤0.01). 3. Image clarity in individualized transcranial group was worse than that of the other two transcranial groups.

• International Journal of Control, Automation, and Systems
• /
• 제2권1호
• /
• pp.100-106
• /
• 2004

In this paper, we present a novel, rapid approach for the detection of brain tumors and deformity boundaries in medical images using a genetic algorithm with wavelet based preprocessing. The contour detection problem is formulated as an optimization process that seeks the contour of the object in a manner of minimizing an energy function based on an active contour model. The brain tumor segmentation contour, however, cannot be detected in case that a higher gradient intensity exists other than the interested brain tumor and deformities. Our method for discerning brain tumors and deformities from unwanted adjacent tissues is proposed. The proposed method can be used in medical image analysis because the exact contour of the brain tumor and deformities is followed by precise diagnosis of the deformities.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1998년도 춘계학술발표회논문집(2)
• /
• pp.705-710
• /
• 1998

We describe a multigrid wavelet-based natural pixel (WNP) method for image reconstruction in emission computed tomography (ECT). The ECT is used to identify the tagged radioactive material's position in the body for detection of abnormal tissue such as tumor or cancer, as in SPECT and PET. With ECT methodology in parallel beam mode, we formulate a matrix-based reconstruction method for radionuclide sources in the human body. The resulting matrix for a practical problem is very large and nearly singular. To overcome this ill-conditioning, wavelet transform is considered in this study. Wavelets have inherent de-noising and multiscale resolution properties. Therefore, the multigrid wavelet-based natural pixel (WNP) method is very efficient to reconstruct image from projection data that is noisy and incomplete. We test this multigrid wavelet natural pixel (WNP) reconstruction method with the MCNP generated projection data for diagnosis of the simulated cancerous tumor.

• 대한치과의사협회지
• /
• 제36권2호통권345호
• /
• pp.135-143
• /
• 1998

Cephalogram is one of the most important tool in researching growth and development of craniofacial area, orthodontic diagnosis and treatment planning. But its inherent distortion of actual length and angles during projecting three dimensional object to two dimensional plane might cause errors in quantitative analysis of shape and size. three dimensional high quality images can be obtained using computerized tomogram and have reported in literatures. Considering its expenses and amount of exposure to radiation, limitations still remain to be solved in its application to routine practice. construction of three dimensional image using principle of orientator can be obtained by biplanar stereoradiography. Theoretically two images, lateral and P-A can be used to construct three dimensional image provided that those are taken at same time by two different focal spots. As two images(lateral and P-A) obtained by conventional cephalogram have different head posture, those need compensation to construct three dimensional images. This study introduced principle of computerized head posture compensation and showed that conventional cephalogram could be used to construct three dimensional image and could be applied to routine orthodontic practice.

• 한국안광학회지
• /
• 제8권2호
• /
• pp.177-183
• /
• 2003

한의학, 진단학에서 사용되는 홍채 촬영용 광학계를 설계 제작해 보았다. 전체 구성은 광원부, 결상광학계, 촬상구동부, 진단 S/W로 되어있다. 결상광학계는 FD60, BACD5의 재질로 색수차를 제거한 0.58X배의 축소광학계로 설계하였다. 결상광학계의 국산화는 제품 전체의 원가절감에 큰 기여를 하게 되었다. 제작되어진 촬영장치는 외국제품과 비교해 볼 때 영상의 입체감에서 우수한 성능을 가직 가지게 되었다.

• Journal of Korean Neurosurgical Society
• /
• 제38권2호
• /
• pp.144-146
• /
• 2005

Herein, a case of missed upper lumbar disc herniation, diagnosed by thorough neurological examination, digital infrared thermographic imaging[DITI], and repeated magnetic resonance[MR] image study, is reported. A 36-year-old female presented with intractable leg pain on left anterior thigh. Although she underwent lumbar MR image at other hospital, she was misdiagnosed as acute sprain. Neurological examination suggested the possibility of upper lumbar disc herniation, which was confirmed by DITI, MRI, and selective root block. After operation, her leg pain was significantly improved. It should be considered that upper lumbar disc herniation might be misdiagnosed as an acute sprain, as in our case. A high index of suspicion based on thorough neurological examination is most important in such cases. Then, multi-access such as DITI, MR image, and selective block, base on thorough neurological examination, are warranted.