• 한국통신학회논문지
• /
• 제38A권2호
• /
• pp.174-182
• /
• 2013

Most methods for fusion-based finger vein recognition were to fuse different features or matching scores from more than one trait to improve performance. To overcome the shortcomings of "the curse of dimensionality" and additional running time in feature extraction, in this paper, we propose a finger vein recognition technology based on matching score-level fusion of a single trait. To enhance the quality of finger vein image, the contrast-limited adaptive histogram equalization (CLAHE) method is utilized and it improves the local contrast of normalized image after ROI detection. Gabor features are then extracted from eight channels based on a bank of Gabor filters. Instead of using the features for the recognition directly, we analyze the contributions of Gabor feature from each channel and apply a weighted matching score-level fusion rule to get the final matching score, which will be used for the last recognition. Experimental results demonstrate the CLAHE method is effective to enhance the finger vein image quality and the proposed matching score-level fusion shows better recognition performance.

• Journal of Information Science Theory and Practice
• /
• 제6권3호
• /
• pp.45-60
• /
• 2018

Research performance evaluation in Korean universities follows strict guidelines that specify scoring systems for publication venue categories and formulas for co-authorship credit allocation. To find out how the standards differ across universities and how they differ from bibliometric research evaluation measures, this study analyzed 25 standards from major Korean universities and rankings produced by applying standards and bibliometric measures such as publication and citation counts, normalized impact score, and h-index to the publication data of 195 tenure-track professors of library and information science departments in 35 Korean universities. The study also introduced a novel impact score normalization method to refine the methodology from prior studies. The results showed the university standards to be mostly similar to one another but quite different from citation-driven measures, which suggests the standards are not quite successful in quantifying the quality of research as originally intended.

• Journal of Trauma and Injury
• /
• 제28권3호
• /
• pp.134-143
• /
• 2015

Purpose: Many patients are injured by trauma. And some of them expire due to severity of trauma. Various scoring systems have been introduced in grading severity and predicting mortality of trauma patients. This study is to evaluation the usefulness of factors for determining the severity and predicting the prognosis of the trauma victims. Methods: Data on the patients who visited our Emergency departments from January 2010 to December 2011 were retrospectively reviewed using electronic medical records. The patients were activated severe trauma team calling system. The patients were categorized as survivors and non-survivors. Univariated associations were calculated, and a multiple logistic regression analysis was used to determine variables associated with hospital mortality. Results: Two hundred sixty two(262) patients were enrolled, and the mortality rate was 25.6%. By multivariate analysis, lower respiration rate, lower Glasgow Coma Score, higher International Normalized Ratio and emergency transfusion within 6 hours were expected as severity and prognosis predict factors (each of odds ratio were 24.907, 14.282, 2.667 and 16.144). Conclusion: As predict factors, respiration rate, Glasgow Coma Score, International Normalized Ratio and emergency transfusion, are useful determining the severity and predicting prognosis of trauma victims.

• 정보처리학회논문지D
• /
• 제18D권5호
• /
• pp.329-338
• /
• 2011

문헌에서의 전문용어 인식 연구는 정보검색, 정보추출, 시맨틱 웹, 질의응답 분야 등의 연구를 위한 선행 연구로서, 지금까지 대부분 특정 분야, 특히 생의학 분야에서 집중되어 연구되어 왔다. 그러나 기존 연구들이 특정 도메인 또는 문헌 내부 통계 정보를 활용함으로써 범용적인 전문용어 인식에 한계점을 보여 왔기 때문에, 본 연구에서는 웹 검색 결과와 사전, 후보용어의 문형 특징 등을 활용하는 기계 학습 기반 범용 전문용어 인식 방법을 제안하였다. 제안한 방법을 문헌의 지역 통계 정보를 사용하는 방법(C-value)과 비교 실험하여 80.8%의 F-값으로 6.5%의 성능향상을 보였다. 다양한 응집도 자질들을 접목한 두 번째 실험에서는 Normalized Google Distance 방법과 접목한 방식이 F-값 81.8%의 성능으로 최고의 성능을 나타냈다. 기계 학습 방법으로는 로지스틱 회귀분석, C4.5, SVMs 등을 적용하였는데, 일반적으로 이진 분류에 좋은 성능을 보이는 SVMs과 로지스틱 회귀분석 방법보다 결정 트리 방식의 C4.5가 전반적으로 좋은 성능을 보였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• 시스템엔지니어링학술지
• /
• 제17권2호
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.

• 한국정보통신학회논문지
• /
• 제17권5호
• /
• pp.1064-1069
• /
• 2013

본 논문에서는 SOM과 개선된 ART-1을 이용하여 악보를 인식하는 방법을 제안한다. 악보 인식을 위해 스캔된 악보 이미지를 호프 변환, Otsu's 이진화를 원본 이미지에 적용하고, 히스토그램 분석을 통해 구분된 작은악절에서 오선을 제거하여 악보의 음표 성분을 추출할 수 있는 이미지 전처리 단계를 수행한다. 오선이 제거된 작은악절은 레이블링을 이용하여 음표 성분을 분리한다. 추출된 음표들은 SOM 알고리즘을 적용하여 일정한 크기로 정규화하고, 정규화된 음표 정보들을 개선된 ART-I 알고리즘을 적용하여 학습과 인식한다. 제안된 방법을 적용하여 음표 인식 실험을 한 결과, 제안된 방법이 음표 인식에 효율적임을 확인하였다.

• 대한영상의학회지
• /
• 제81권3호
• /
• pp.632-643
• /
• 2020

목적 자기공명영상 근거 영상표현형과 생체분자학적 아형, 유전자 발현 프로파일 근거 위험도 등 유방암 유전체 특징의 관계를 분석하고자 하였다. 대상과 방법 The Cancer Genome Atlas와 and the Cancer Imaging Archive에 공개된 자료를 이용하였다. 122개의 유방암의 자기공명영상에서 영상표현형이 추출되었다. 유전자 발현 프로파일에 따라 PAM50아형을 분류하고 위험도를 지정하였다. 영상표현형과 생체분자학적 특징의 관계를 분석하였다. 예측모델을 알아보기 위해 penalized generalized regression analysis를 이용하였다. 결과 PAM50아형은 maximum 2D diameter (p = 0.0189), degree of correlation (p = 0.0386), 그리고 inverse difference moment normalized (p = 0.0337)와 유의하게 관련이 있었다. 위험도 시스템 중에 GGI와 GENE70이 통계적으로 유의하게 8개의 영상표현형 특징을 서로 공유하였다(p = 0.0008~0.0492). Maximum 2D diameter가 두 위험도 시스템에서 가장 유의하게 관련있는 특징이었으나(p = 0.0139, p = 0.0008) 예측모델의 전반적인 연관 정도는 약했고 가장 높은 연관계수는 GENE70이 0.2171이었다. 결론 영상표현형 중에 maximum 2D diameter, degree of correlation, 그리고 inverse difference moment normalized가 PAM50 아형 그리고 GENE70과 같은 유전자 발현 프로파일 근거 위험도와 그 연관도는 약하였으나 유의한 관련을 보였다.

• Journal of information and communication convergence engineering
• /
• 제10권2호
• /
• pp.135-140
• /
• 2012

Massive numbers of users of social networks share various types of information such as opinions, news, and ideas in real time. As a new form of social network, Twitter is a particularly useful information source. Studying influence can help us better understand the role of social networks. The popularity of social networks like Twitter is primarily measured by the number of followers. The number of followers in Twitter and the number of users exposed to news media are important factors in measuring influence. We chose Twitter and the New York Times as representative media to analyze the influence and present an empirical analysis of these datasets. When the correlation between the number of followers in Twitter and the number of users exposed to the New York Times is computed, the result is moderately high. The correlation between the number of users exposed to the New York Times and the number of sections including the users on it, was found to be very high. We measure the normalized influence score using our proposed expression based on the two correlation coefficients.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.427-430
• /
• 1992

In this paper, we proposed an algorithm for the musical note recognition. Firstly, a given bit-mapped music score image is converted to a set of individual note pattern images via vertical projection. Then, the pitch of a note is determinal by comparison in the note-head position with the reference five-lines. Also, the length of a note is found via leader clustering with a set of normalized note patterns. Finally, a datafile to play the music is obtained using the pitch and length of musical notes. Experimental results with a simple musical score image show that the proposed scheme is performed well.