• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.515-518
• /
• 2017

I used Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA) to utilize biometric technology for security. I used 14 korean consonants(ㄱ to ㅎ). And It has both information of gestures for each consonants and identity of user. So this experiment is set for this two aspects. I used database including 20 people's images. Each person did 140 action for every consonant with 10 trials. PCA and LDA must be applied on self-collected database using MATLAB programming. Equal Error Rate (EER) is used for evaluate performance of this analysis.

• Journal of the KSME
• /
• v.28 no.4
• /
• pp.313-321
• /
• 1988

어떤 구조물이 반복하중을 받으면 피로파괴를 일으킨다. 만일 이 구조물이 부식환경 속에 앗 으면 불활성 분위기나 공기 중에서 보다 빨리 파괴에 이르게 된다. 이러한 현상을 흔히 부식 피로라고 한다. 부식피로에 크게 영향을 미치는 변수들을 대략 기계적 변수, 금속학적 변수, 환경 변수로서, 기계적 변수에는 최대응력 확대계수, 응력확대계수범위, 응력비, 반복하중 주파수, 반복하중파형, 응력상태, 잔류응력, 균열의 크기 및 모양 등이 있으며 금속학적 변수로는 합금 조성, 합금원소와 불순물의 분포, 미세조직과 결정구조, 열처리, 소성가공, 집합조직 등이며 환 경변수에는 온도, 환경의 형태(기체, 액체), 부식성분의 분압 또는 농도, 전기화학적 전위, pH, 수용성 환경의 점성, 피복, 부식억제제 등이 있다. 이와 같이 부식환경 속에 있는 구조물의 파 손을 이해하기 위하여는 응력부식과 부식피로를 공부하여야 한다. 이 현상은 매우 복잡한 문 제이기 때문에 아직도 완전히 이해되지 않은 상태이고 따라서 중요한 연구대상이 되고 있다. 여기서는 응력부식과 부식피로의 파괴역학적인 측면을 소개하고자 한다.

• Journal of Chest Surgery
• /
• v.37 no.5
• /
• pp.452-455
• /
• 2004

We report a case of a 40-year-old woman whose right ventricular out-flow tract was moderately obstructed by a heavily calcified pericardial ring. It was passing over the base of pulmonary artery and mid-portion of left ventricle but the other parts of the pericardium was mildly fibrotic. The pericardium and calcified ring were completely removed under cardiopulmonary bypass. The patient was recovered uneventfully and we could not find the specific cause of calcified pericardial ring.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.229-231
• /
• 2013

본 논문은 신경망 알고리즘을 사용하여 사람의 필기체 문자를 인식하였고, 이를 바탕으로 뇌졸중 환자의 재활치료를 돕는 시스템을 구현하였다. 뇌졸중 환자의 재활치료에서는 단기간에 환자에게 반복적인 행동 및 학습하는 것이 효율적이라고 알려져 있다. 본 연구에서는 뇌졸중 환자에게 문자 템플릿을 보여주었고, 환자는 문자 템플릿을 인지하고 문자 템플릿과 같은 형태의 문자를 쓰게 하는 방식을 사용하였다. 뇌졸중 환자가 쓴 필기체 문자를 신경망 알고리즘을 사용하여 인식하고, 자주 틀리는 문자에 대해 추천시스템 방식을 사용하여 틀린 문자와 모양이 비슷하거나 같은 문자를 추천해줌으로써 문자 쓰기학습의 반복을 유도하였다. 실험을 통해 제안한 시스템은 뇌졸중 환자의 인지장애와 손 기능장애에 대한 재활치료의 효과를 상승시켰다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.679-682
• /
• 2010

피부 영역 검출 기술은 생체 인식 기술의 하나로서 얼굴 자동 인식 혹은 손 모양 자동 인식 등을 위해 사용되고 있다. 일반적으로 색상을 이용하여 피부 영역을 검출하기 위해서는 다양한 피부색 샘플을 이용해 구해진 피부색 모델을 이용한다. 하지만 피부색은 사람마다 다르고, 조명과 같은 주변 환경의 영향도 받기 때문에 다양한 영상에 하나의 고정된 피부색 모델을 적용하여 피부 영역을 검출하기에는 한계가 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 영상 피드백 방법을 이용하여 영상에 적응적인 피부색 모델을 구한 뒤 이를 적용하여 피부 영역을 추출하는 방법을 제안한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.95-103
• /
• 1998

This paper deals with a problem occuring in recognition of tactile images due to the effects of imposed force at a me urement moment. Tactile image of a contact surface, used for recognition of the surface type, varies depending on the forces imposed so that a false recognition may result in. This paper fuzzifies two parameters of the contour of a tactile image with the membership function formed by considering the imposed force. Two fuzzifed paramenters are fused by the average Minkowski's dist; lnce. The proposed algorithm was implemented on the multisensor system cnmposed of an optical tact le sensor and a 6 axes forceltorque sensor. By the experiments, the proposed algorithm has shown average recognition ratio greater than 869% over all imposed force ranges and object models which is about 14% enhancement comparing to the case where only the contour information is used. The pro- ~oseda lgorithm can be used for end-effectors manipulating a deformable or fragile objects or for recognition of 3D objects by implementing on multi-fingered robot hand.

• The Korean Journal of Zoology
• /
• v.38 no.3
• /
• pp.395-404
• /
• 1995

In order to study the process of spermiogenesis of the korean striped field mouse Apodemus agrorfus coreae, the cell differentiation of seminiferous epithelium and morphological features of mature sperm in cauda epididymis was examined and the results are as follows: Spermiogenesis was divided, according to the features of cell structure; Golgi, cap, acrosome and spermiation phases were further subdivided into two steps of early and late phases respectively, and maturation phase has only one step. Hence, the spermiogenesis consists of nine phases. in the changes of the chromatin in nucleus, the chromatin granules began to be condensed in the cap phase and the condensation proceeded to form a globular of nucleus at the acrsome phase. Finally, the chromatin regularization was completed and perfect nucleus of sperm was formed at the maturation phase. Sperm head had the falciform, and the outer dence fibers of middle piece were arranged in a horseshoe fashion. The outer dence fiber number 1, 5, 6 and 9 was larger than other fiber number 2, 3, 4, 7, 8.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.4
• /
• pp.19-26
• /
• 2015

This paper presents a method for optimizing a carrying pose of human body for a given object. The inputs are articulated human body model and and arbitrary-shaped object. We assume that the object is big and heavy, so that both arms should be used to carry it. Unlike small and light objects, big and heaby objects can be hold by only a small range of body poses while keeping a physical statbility. We first introduce an algorithm that evaluates a physical stability of a given human body pose and object state (position and orientation). Then, we define a configuration space and search the space for the most stable carrying pose by using the evaluation algorithm. Finally, to demonstrate the usability of our method, we present the results which each is experimented with different shaped objects and additional user conditions.

• Investigative Magnetic Resonance Imaging
• /
• v.4 no.1
• /
• pp.14-19
• /
• 2000

Purpose : This study was to present the functional brain mapping of both functional magnetic resonance imaging(MRI) and transcranial magnetic stimulation(TMS) in a case of schizencephaly. Materials and methods : A 28-year-old man, who had left hemiplegia and schizencephaly in right cerebral hemisphere, was exacted with both functional MRI and TMS. Motor function of left hand was decreased whereas right hand was within normal limit. For functional MRI, gradient-echo echo planar imaging($TR/TE/{\alpha}$=1.2 sec/90 msec/90) was employed. The paradigm of motor task consisted of repetitive self-paseo hand flexion-extension exercises with 1-2 Hz periods. An image set of 10 slices was repetitively acquired with 15 seconds alternating periods of task performance and rest and total 6 cycles (three ON periods and three OFF periods) were performed. In brain mapping, TMS was performed with the round magnetic stimulator (mean diameter; 90mm). The magnetic stimulation was done with 80% of maximal output. The latency and amplitude of motor evoked potential(MEP)s were obtained from both abductor pollicis brevis(APB) muscles. Results : Functional MRI revealed activation of the left primary motor cortex with flexion-extension exercises of healthy right hand. On the other hand, the left primary motor cortex, left supplementary motor cortex, and left promoter areas were activated with flexion-extension exercises of left hand. In TMS, magnetic evoked potentials were induced in no areas of right cerebral hemisphere, but in 5 areas of left corebral hemisphere from both abductor pollicis brevis. Latency, amplitude, and contour of response of the magnetic evoked potentials in both hands were similar. Conclusion : Functional MRI and TMS in a patient with schizencephaly were successfully used to localize cortical motor function. Ipsilateral motor pathway is thought to be secondary to reinforcement of the corticospinal tract of the ipsilateral motor cortex.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.411-417
• /
• 2021

The field that studies human-computer interaction is called HCI (Human-computer interaction). This field is an academic field that studies how humans and computers communicate with each other and recognize information. This study is a study on hand gesture recognition for human interaction. This study examines the problems of existing recognition methods and proposes an algorithm to improve the recognition rate. The hand region is extracted based on skin color information for the image containing the shape of the human hand, and the center of gravity profile is calculated using principal component analysis. I proposed a method to increase the recognition rate of hand gestures by comparing the obtained information with predefined shapes. We proposed a method to increase the recognition rate of hand gestures by comparing the obtained information with predefined shapes. The existing center of gravity profile has shown the result of incorrect hand gesture recognition for the deformation of the hand due to rotation, but in this study, the center of gravity profile is used and the point where the distance between the points of all contours and the center of gravity is the longest is the starting point. Thus, a robust algorithm was proposed by re-improving the center of gravity profile. No gloves or special markers attached to the sensor are used for hand gesture recognition, and a separate blue screen is not installed. For this result, find the feature vector at the nearest distance to solve the misrecognition, and obtain an appropriate threshold to distinguish between success and failure.