• 한국지능시스템학회논문지
• /
• 제23권3호
• /
• pp.262-267
• /
• 2013

The recognition of human emotional state is one of the most important components for efficient human-human and human- computer interaction. In this paper, four emotions such as fear, disgust, joy, and neutral was a main problem of classifying emotion recognition and an approach of visual-stimuli for eliciting emotion based on physiological signals of skin conductance (SC), skin temperature (SKT), and blood volume pulse (BVP) was used to design the experiment. In order to reach the goal of solving this problem, half-against-half (HAH) multi-class support vector machine (SVM) with Gaussian radial basis function (RBF) kernel was proposed showing the effective techniques to improve the accuracy rate of emotion classification. The experimental results proved that the proposed was an efficient method for solving the emotion recognition problems with the accuracy rate of 90% of neutral, 86.67% of joy, 85% of disgust, and 80% of fear.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• pp.1934-1935
• /
• 2011

In order for a service robot to perform several tasks, basically autonomous navigation technique such as localization, mapping, and path planning is required. The localization (estimation robot's pose) is fundamental ability for service robot to navigate autonomously. In this paper, we propose a new system for point pattern matching based visual global localization using spot lightings in ceiling. The proposed algorithm us suitable for system that demands high accuracy and fast update rate such a guide robot in the exhibition. A single camera looking upward direction (called ceiling vision system) is mounted on the head of the mobile robot and image features such as lightings are detected and tracked through the image sequence. For detecting more spot lightings, we choose wide FOV lens, and inevitably there is serious image distortion. But by applying correction calculation only for the position of spot lightings not whole image pixels, we can decrease the processing time. And then using point pattern matching and least square estimation, finally we can get the precise position and orientation of the mobile robot. Experimental results demonstrate the accuracy and update rate of the proposed algorithm in real environments.

• Journal of Electrical Engineering and Technology
• /
• 제12권6호
• /
• pp.2118-2126
• /
• 2017

The large-scale power system blackouts have indicated that conventional protection relays that based on local signals cannot fit for modern power grids with complicated setting or heavily loaded-flow transfer. In order to accurately detect various faulted lines and improve the fault-tolerance of wide-area protection, a novel multi-section weighed fault matching and detecting algorithm is proposed. The real protection vector (RPV) and expected section protection vectors (ESPVs) for five fault sections are constructed respectively. The function of multi-section weighed fault matching is established to calculate the section fault matching degrees between RPV and five ESPVs. Then the fault degree of protected line based on five section fault degrees can be obtained. Two fault detecting criterions are given to support the higher accuracy rate of detecting fault. With the enumerating method, the simulation tests illustrate the correctness and fault-tolerance of proposed algorithm. It can reach the target of 100% accuracy rate under 5 bits error of wide-area protections. The influence factors of fault-tolerance are analyzed, which include the choosing of wide-area protections, as well as the topological structures of power grid and fault threshold.

• 한국콘텐츠학회논문지
• /
• 제11권4호
• /
• pp.27-32
• /
• 2011

본 논문은 수면 2기의 EEG 신호와 주성분 분석(principle component analysis)을 이용하여 수면 장애를 분류하는 방안을 제안하고 있다. 초기 특징을 추출하기 위해서 첫 번째 단계에서는 수면 2기의 EEG 신호가 고속 푸리에 변환(fast Fourier transforms)에 의해서 잡음을 제거하는 과정이 수행되었다. 잡음이 제거된 EEG 신호를 두 번째 단계에서는 주성분 분석을 이용하여 5개의 차원으로 축소하였다. 마지막 단계에서는 축소된 5개의 차원을 가중 퍼지소속함수 기반 신경망(neural network with weighted fuzzy membership functions, NEWFM)의 입력으로 사용하여 분류성능을 측정하였다. 분류성능에 있어서 정확도(accuracy), 특이도(specificity), 민감도(sensitivity)가 모두 100%로 나타났다.

• 한국산업정보학회논문지
• /
• 제23권3호
• /
• pp.59-71
• /
• 2018

Social media has immense popularity among all services today. Data from social network services (SNSs) can be used for various objectives, such as text prediction or sentiment analysis. There is a great deal of Korean and English data on social media that can be used for sentiment analysis, but handling such huge amounts of unstructured data presents a difficult task. Machine learning is needed to handle such huge amounts of data. This research focuses on predicting Korean and English sentiment using deep forward neural network with a deep learning architecture and compares it with other methods, such as LDA MLP and GENSIM, using logistic regression. The research findings indicate an approximately 75% accuracy rate when predicting sentiments using DNN, with a latent Dirichelet allocation (LDA) prediction accuracy rate of approximately 81%, with the corpus being approximately 64% accurate between English and Korean.

• 반도체디스플레이기술학회지
• /
• 제7권3호
• /
• pp.29-34
• /
• 2008

This paper describes the fabrication and characterization of a differential pressure type integrated mass-flow controller made of stainless steel for reactive and corrosive gases. The fabricated mass-flow controller is composed of a normally closed valve and differential pressure sensor. A stacked solenoid actuator mounted on a base-block is utilized for precise and rapid control of gas flow. The differential pressure flow sensor consisting of four diaphragms can detect a flow rate by deflection of diaphragm. By a feedback control from the flow sensor to the valve actuator, it is possible to keep the flow rate constant. This device shows a fast response less than 0.3 sec. Also, this device shows accuracy less than 0.1% of full scale. It is confirmed that this device is not attacked by toxic gas, so the integrated mass-flow controller can be applied to advanced semiconductor processes which need fine mass-flow control corrosive gases with fast response.

• 대한핵의학회지
• /
• 제36권1호
• /
• pp.34-38
• /
• 2002

Positron emission tomography(PET) is an imaging method that employs radionuclide and tomography techniques. Since 1995, we applied PET not only to the diagnosis of breast cancer but also to the detection of abnormalities in the augmented breast and to the detection of metastasis. Until 2001, we evaluated 242 breast cases by PET at PET center of Seoul National University Hospital. Our group has reported serially at the international journals. In the first report, PET showed high sensitivity for detecting breast cancer, both the primary and axillary node metastasis. A total of 27 patients underwent breast operations based on PET results at Seoul National University Hospital from 1995 to 1996. The diagnostic accuracy of PET were 97% for the primary tumor mass and 96% for axillary lymph node metastasis. In case of the breast augmented, PET also showed excellent diagnostic results for primary breast cancer and axillary lymph node metastasis where mammography and ultrasound could not diagnose properly. PET also had outstanding results in the detection of recurrent or metastatic breast cancer(sensitivity 94%, specificity 80%, accuracy 89%). In addition, our study gave some evidence that PET could be applied further to evaluate the growth rate of tumors by measuring SUV, and finally to prognosticated the disease. PET could also be applied to evaluate the response after chemotherapy to measure its metabolic rate and size. In conclsion, PET is a highly sensitive, accurate diagnostic tool for breast cancer of primary lesion in various conditions including metastasis.

• Structural Engineering and Mechanics
• /
• 제16권2호
• /
• pp.219-240
• /
• 2003

One of the most versatile approaches for analyzing the dynamic behavior of structural systems is direct time integration of semi-discrete equations of motion. However responses computed by time integration are generally inexact and hence the corresponding errors would rather be studied in advance. In spite of the various error estimation formulations that exist in the literature, it is accepted practice to repeat the analyses with smaller time steps, followed by a comparison between the results. In this paper, after a review of this simple method and disregarding the round-off errors, a more efficient, reliable and yet simple method for estimating errors and enhancing the accuracy is proposed. The main objectives of this research are more realistic error estimation based on the concept of convergence, approximately controlling the reliability by comparing the actual rate of convergence with the integration method's order of accuracy, and enhancement of reliability by applying Richardson's extrapolation. Starting from the errors at specific time instants, the study is then generalized to cases in which the errors should be estimated and decreased at specific events e.g. peak responses. Numerical study illustrates the efficacy of the proposed method.

• Ocean Systems Engineering
• /
• 제4권1호
• /
• pp.53-62
• /
• 2014

The detection of ship wakes image can demonstrate substantial information regarding on a ship, such as its tonnage, type, direction, and speed of movement. Consequently, the wake target recognition is a favorable way for ship identification. This paper proposes a Local Binary Pattern (LBP) approach to extract image features (wakes) for training an Improved Back Propagation Artificial Neural Network (IBPANN) to identify ship speed. This method is applied to sort and recognize the ship wakes of five different speeds images, the result shows that the detection accuracy is satisfied as expected, the average correctness rates of wakes target recognition at the five speeds may be achieved over 80%. Specifically, the lower ship's speed, the better accurate rate, sometimes it's accuracy could be close to 100%. In addition, one significant feature of this method is that it can receive a higher recognition rate than the nearest neighbor classification method.

• 한국광학회지
• /
• 제23권5호
• /
• pp.197-202
• /
• 2012

맴핑용 레이저 레이더 실험실 시제품의 성능시험과 분석 결과를 소개한다. 광섬유 레이저와 아발란치 광검출기 외 관련 구성모듈로 이루어진 레이저 레이더 시스템이 설계, 제작되었다. 레이저 레이더 시스템은 현재 실험실 환경에서의 성능 확인을 목적으로 하는 실험실 시제품으로서, 레이저 레이더 광원 특성, 거리 정확도, 소광율, 오경보율과 같은 시스템 성능변수가 실험적으로 측정되었다. 실험결과 분석을 통해 레이저 레이더 시제품이 양호한 성능수준을 제시하는 것으로 확인되었다.