• 한국콘텐츠학회논문지
• /
• 제21권12호
• /
• pp.1-12
• /
• 2021

특정 연구 분야에 대한 전문성을 가진 연구자를 찾기 위해서는 객관적인 전문가 판별 방법이 필요하다. 기존에는 전문가 판별을 위해 인용 그래프 기반의 판별 기법과 수식 기반의 판별 기법이 존재한다. 본 논문에서는 기존 수식 기반 판별에서 고려하지 못하였던 다양한 특성들을 반영한 효율적인 전문가 판별 기법을 제안한다. 연구자의 전문성을 판별하기 위해 품질, 생산성, 기여도, 최신성, 정확성, 지속성을 고려한 전문성 지수를 제안한다. 또한, 학술 검색 사이트만의 특성을 반영하기 위해 소셜 인용 수를 추가로 고려한다. 다양한 학술 사이트 기반의 논문 수집 및 성능 평가 결과를 제시하고 제안하는 기법의 타당성과 실현성을 입증한다.

• 한국한의학연구원논문집
• /
• 제14권2호
• /
• pp.41-46
• /
• 2008

The study was to investigate the agreement rate between the statistical diagnosis of pattern identification by discriminant analysis and the clinical diagnosis of pattern identification by medical specialist in obese patients with BMI$\geqq$23. The agreement rate of deficiency of the spleen, phlegm-retention, deficiency of Yang, retention of undigested food, stagnation of liver Gi, and blood stagnation are 0.40, 0.33, 0.52, 0.76, 0.71, and 0.66, respectively and accuracy rate and prediction rate using linear discriminant function are 0.59 and 0.61, respectively. Therefore, the complementary management in CRF questionnaires and/or consultation from experts will improve the accuracy and prediction rate, which will be helpful for pattern identification of obesity by clinical experts.

• Journal of Biosystems Engineering
• /
• 제38권4호
• /
• pp.318-326
• /
• 2013

Purpose: We developed a viability evaluation method for cucumber (Cucumis sativus) seed using hyperspectral reflectance imaging. Methods: Reflectance spectra of cucumber seeds in the 400 to 1000 nm range were collected from hyperspectral reflectance images obtained using blue, green, and red LED illumination. A partial least squares-discriminant analysis (PLS-DA) was developed to predict viable and non-viable seeds. Various ranges of spectra induced by four types of LEDs (Blue, Green, Red, and RGB) were investigated to develop the classification models. Results: PLS-DA models for spectra in the 600 to 700 nm range showed 98.5% discrimination accuracy for both viable and non-viable seeds. Using images based on the PLS-DA model, the discrimination accuracy for viable and non-viable seeds was 100% and 99%, respectively Conclusions: Hyperspectral reflectance images made using LED light can be used to select high quality cucumber seeds.

• Nuclear Engineering and Technology
• /
• 제55권11호
• /
• pp.3925-3934
• /
• 2023

The importance of fast neutron detection for nuclear safeguards purposes has increased due to its potential advantages such as reasonable cost and higher precision for larger sample masses of nuclear materials. Pulse-shape discrimination (PSD) is inevitably used to discriminate neutron- and gamma-ray- induced signals from organic scintillators of very high gamma sensitivity. The light output (LO) threshold corresponding to several MeV of recoiled proton energy could be necessary to achieve fine PSD performance. However, this leads to neutron count losses and possible distortion of results obtained by neutron multiplicity counting (NMC)-based nuclear material accountancy (NMA). Moreover, conventional PSD techniques are not effective for counting of neutrons in a high-gamma-ray environment, even under a sufficiently high LO threshold. In the present work, PSD performance (figure-of-merit, FOM) according to LO bands was confirmed using a conventional charge comparison method (CCM) and compared with results obtained by convolution neural network (CNN)-based PSD algorithms. Also, it was attempted, for the first time ever, to reject fake neutron signals from distorted PSD regions where neutron-induced signals are normally detected. The overall results indicated that higher neutron detection efficiency with better accuracy could be achieved via CNN-based PSD algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권3호
• /
• pp.263-267
• /
• 2005

Building classifiers for financial real-world classification problems is often plagued by severely overlapping and highly skewed class distribution. New performance measures such as receiver operating characteristic (ROC) curve and area under ROC curve (AUC) have been recently introduced in evaluating and building classifiers for those kind of problems. They are, however, in-effective to evaluation of classifier's discrimination performance in a particular class of the classification problems that interests lie in only a local operating range of the classifier, In this paper, a new method is proposed that enables us to directly improve classifier's discrimination performance at a desired local operating range by defining and optimizing a partial area under ROC curve or domain-specific curve, which is difficult to achieve with conventional classification accuracy based learning methods. The effectiveness of the proposed approach is demonstrated in terms of fraud detection capability in a real-world fraud detection problem compared with the MSE-based approach.

• 대한자기공명의과학회:학술대회논문집
• /
• 대한자기공명의과학회 2002년도 제7차 학술대회 초록집
• /
• pp.138-138
• /
• 2002

To determine the accuracy of magnetic resonance (MR) imaging for discrimination between intervertebral disk extrusion versus protrusion. MR images of 80 patients who had MR imaging of the spine and confirmed as intervertebral disk extrusion or protrusion were retrospectively reviewed by an experienced musculoskeletal radiologist. A 1.5-T scanner was used. After review of medical records, MR findings of disk extrusion and protrusion were compared using the chi-square test. Intraobserver agreement for differentiation of disk extrusion from protrusion was calculated by using coefficient.

• 대한음성학회지:말소리
• /
• 제61호
• /
• pp.113-123
• /
• 2007

The environmental differences between training and testing mode are generally considered to be the critical factor for the performance degradation in speaker recognition systems. Especially, general speaker recognition systems try to get as clean speech as possible to train the speaker model, but it's not true in real testing phase due to environmental and channel noise. So in this paper, the new method of weighting the frame-based likelihood according to frame SNR is proposed in order to cope with that problem. That is to make use of the deep correlation between speech SNR and speaker discrimination rate. To verify the usefulness of this proposed method, it is applied to the context dependent speaker identification system. And the experimental results with the cellular phone speech DB which is designed by ETRI for Koran speaker recognition show that the proposed method is effective and increase the identification accuracy by 11% at maximum.

• 사상체질의학회지
• /
• 제25권4호
• /
• pp.289-296
• /
• 2013

Objectives This study was aimed to validate Sasang Constitution Questionnaire for Japanese (SSCQ-J). Methods Sasang Constitution Questionnaire for Patients (SSCQ-P) was developed by joint researches between the Society of Sasang Constitutional Medicine and Korea Institute of Oriental Medicine. We translated SSCQ-P into Japanese and modified some items of that for Japanese. By getting approval from the Institutional Review Board（IRB）of School of Medicine, Keio University, we conducted a questionnaire survey of patients who visited Oriental Medicine Center from early January until mid-February 2011. The total of 364 patients filled out that Questionnaire and gave an interview with a Sasang constitution specialist. Using this Questionnaire data, we made Sasang constitutional classification functions and calculated diagnostic accuracy rate of SSCQ-J using discrimination analysis. Results 1. Male group's diagnostic accuracy rate of SSCQ-J was 77.01% and female was 78.10%. 2. Diagnostic accuracy of SSCQ-J was a little higher than SSCQ-P Conclusions 1. SSCQ-J can be considered to have good discriminant power compared with SSCQ-P 2. Further research with SSCQ-J will be helpful in the comparison study on the usual symptoms between Korean and Japanese as well as development of good discriminant function.

• 감성과학
• /
• 제16권3호
• /
• pp.409-416
• /
• 2013

집중은 관련된 사건을 선택적으로 주의하고, 관련 없는 사건을 무시하는 인간의 중요한 인지 기능중의 하나이다. 인간의 집중 능력을 관리 이용하는 컴퓨터 기반 장치에 있어서 집중과 비집중 상태를 구분하는 것은 필수적으로 요구되는 조건이다. 본 논문에서는, 뇌파신호로부터 분류기의 입력으로 사용되는 특징을 효율적으로 추출하기 위하여 비선형 반복 패턴 분석기법과 스펙트럼 분석 기법을 새로이 결합하였고(13개 특징 추출), 서포트벡터머신, 역전파 알고리즘, 선형분리, 로지스틱 회귀 분류 기반 분류기들을 포함하는 집중-비집중 분류기들의 성능을 분석하였다. 그중에서 81 %의 정확도를 보이는 서포트벡터머신 분류기가 가장 좋은 성능을 보였다. 또한 스펙트럼 분석으로 추출한 특징만을 사용하였을 경우(76 % 정확도)가 비선형 분석 방법으로 추출한 특징만을 사용했을 경우(67 % 정확도)보다 좀 더 우수한 성능을 보였다. 비선형-스펙트럼 분석법을 복합 적용한 서포트벡터머신 분류기가 추후 집중 관련 장비 설계에 있어서 효율적으로 적용될 수 있을 것이다.

• 대한공간정보학회지
• /
• 제17권2호
• /
• pp.55-60
• /
• 2009

본 연구에서는 경주시 내남면을 대상으로 KOMPSAT-2 MSC(Multi Spectral Camera) 영상(2007.06.12)을 기반으로 NDVI(Normalized Difference Vegetation Index)와 TCT(Tasseled-Cap Transformation) 영상 알고리즘을 적용하여 DN 분포도를 작성 하였다. NDVI 및 TCT DN 분포도와 산림 현장 조사 결과와의 비교 분석을 통하여 임상 분류 정확도 향상을 위한 영상 알고리즘 변별력 분석을 수행하고 마지막으로 현장조사 자료와의 중첩 분석을 통하여 임상분류 정확성을 검증 하였다. 본 연구를 통하여 KOMPSAT-2 MSC 영상을 이용하여 임상 분류 자동화 실용성에 대한 검토와 정밀 산림 임상도 제작과정에서 저비용 고효율성을 기대할 수 있으리라 사료된다.