• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.927-930
• /
• 2000

본 논문은 문서 영상에 대해 투영을 사용하여 영역을 나누었고 각 영역에 대해 고주파 밴드의 웨이블렛 계수의 통계적 분산과 히스토그램을 기반으로 한 두 가지 특징을 사용하여 문자와 그림으로 분류하였다. 투영으로 나누어진 영역들에 대해 일정 크기의 블록으로 나누고 두 가지 특징에 따라 문자와 그림으로 분류하였다. 따라서 투영에 의해 나뉜 영역 중 문자와 그림이 혼합되어 의미가 모호한 영역에 대해 잘못 분류되는 가능성을 줄일 수 있었다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6D
• /
• pp.759-766
• /
• 2008

Road classification system is the first step for determining the road function and design standards. Currently, roads are classified by various indices such as road location and function. In this study, we classify road using various traffic indices as well as to identify traffic characteristics for each type of road. To accomplish the objectives, mixture model was applied for classifying road and analyzing traffic characteristics using traffic data that observed at permanent traffic count stations. A total of 8 variables were applied: annual average daily traffic(AADT), $K_{30}$ coefficient, heavy vehicle proportion, day volume proportion, peak hour volume proportion, sunday coefficient, vacation coefficient, and coefficient of variation(COV). A total of 350 permanent traffic count points were categorized into three groups : Group I (Urban road), Group II (Rural road), and Group III (Recreational road). AADT were 30,000 for urban, 16,000 for rural, and 5,000 for recreational road. Group III was typical recreational road showing higher average daily traffic volume during Sunday and vacational periods. Group I showed AM peak and PM peak, while group II and group III did not show AM peak and PM peak.

• International Commerce and Information Review
• /
• v.18 no.4
• /
• pp.55-78
• /
• 2016

In this study, service quality attributes of uTradeHub were classified based on the Kano model, and quality attributes that should be managed in priority to improve the service quality of uTradeHub were investigated using Timko's customer satisfaction coefficient(CSC) and average satisfaction coefficient(ASC). The results of the study are summarized as follows. First, as a result of classifying service quality attributes based on Kano model, 12 one dimensional qualities, 5 must-be qualities, 2 indifferent qualities were deducted, and many quality attributes of uTradeHub service were confirmed to be one dimensional quality to which is needed to be paid attention and paid more detailed attention to enhance service quality. Second, in the analysis result using Timko's customer satisfaction coefficient, "post processing for problems and complaints", "cost reduction", "efficiency of business processing" were ranked in the top of satisfaction coefficient, and they found to be quality attributes that customer satisfaction increases when service quality was satisfied. While, "post processing for problems and complaints", "interaction", "ability to respond promptly when problems occur" were ranked in the top of unsatisfaction coefficient, and they were analysed to be quality attributes that customer complaints increase when service quality was unsatisfied. Third, in the result of analyzing the quality attributes that should be managed in priority to improve the service quality of uTradeHub based on the average satisfaction coefficient(ASC), "post processing for problems and complaints", "cost reduction", "useful information" were ranked in the top 3, and they were classified as quality attributes that the satisfaction level increases more when they are improved than now, but the satisfaction level decreases when they are worsen.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.37-39
• /
• 2006

지지 벡터 기계(Support Vector Machine; SVM)는 기본적으로 이진분류를 위해 고안되었지만, 최근 다양한 분류기 생성전략과 결합전략이 고안되어 다중부류 분류에도 적용되고 있다. 본 논문에서는 OVR(One-Vs-Rest) 전략으로 생성된 SVM을 NB(Naive Bayes) 분류기를 이용하여 동적으로 구성함으로써, OVR SVM을 이용한 다중부류 분류 시스템에서 자주 발생하는 동점을 효과적으로 해결하는 방법은 제안한다. 이 방법을 유전발현 데이터를 이용한 다중부류 암 분류에 적용하였는데, 고차원의 데이터로부터 NB 분류기 구축에 유용한 유전자를 선택하기 위해 Pearson 상관계수를 사용하였다. 14개의 암 유형과 16,063개의 유전발현 수준을 가지는 대표적인 다중부류 암 분류 데이터인 GCM 암 데이터에 적용하여 제안하는 방법의 유용성을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.16-22
• /
• 2010

Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1243-1248
• /
• 2008

As development in technology of bioinformatics recently mates it possible to operate micro-level experiments, we can observe the expression pattern of total genome through on chip and analyze the interactions of thousands of genes at the same time. In this thesis, we used CDNA microarrays of 3840 genes obtained from neuronal differentiation experiment of cortical stem cells on white mouse with cancer. It analyzed and compared performance of each of the experiment result using existing DT, NB, SVM and multi-perceptron neural network classifier combined the similar scale combination method after constructing class classification model by extracting significant gene list with a similar scale combination method proposed in this paper through normalization. Result classifying in Multi-Perceptron neural network classifier for selected 200 genes using combination of PC(Pearson correlation coefficient) and ED(Euclidean distance coefficient) represented the accuracy of 98.84%, which show that it improve classification performance than case to experiment using other classifier.

• Journal of the Korean Society for Railway
• /
• v.19 no.2
• /
• pp.204-212
• /
• 2016

The soils used as trackbed in Korea are selected using USCS utilizing basic soil properties such as Grain Size Distribution(GSD), % passing of #200 sieve ($P_{200}$), % passing of #4 sieve ($P_4$), Coefficient of uniformity ($C_u$), and Coefficient of curvature ($C_c$). Degree of compaction of the soils adapted in the code by KR should be evaluated by maximum dry density (${\gamma}_{d-max}$) and deformation modulus $E_{v2}$. The most important influencing factor that is critical to stability and deformation of the compacted soils used as trackbed is stiffness. Thus, it is necessary to construct a correlation between the modulus and the basic soil properties of trackbed soil in order to redefine a new soil classification system adaptable only to railway construction. To construct the relationship, basic soil test data is collected as a database, including GSD, maximum dry unit weight (${\gamma}_{d-max}$), OMC, $P_{200}$, $P_4$, $C_u$, $C_c$, etc.; deformation modulus $E_{v2}$ and $E_{vd}$ are obtained independently by performing a Repeated Plated Bearing Test (RPBT) and Light Weight Deflectometer Test (LWDT) for ten different railway construction sites. A linear regression analysis is performed using SPSS to obtain the relationship between the basic soil properties and the deformation modulus $E_{v2}$ and $E_v$. Based on the constructed relationship and the various obtained mechanical test data, a new soil classification system will be proposed later as a guideline for the design and construction of trackbed foundation in Korea.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.4 no.2
• /
• pp.13-24
• /
• 2000

최근 국내에서 많이 건설되어지고 있는 주상복합 건축물은 하부의 골조형식과 상부의 벽식 구조가 결합된 구조형식을 가지고 있다 따라서 지진 발생시 동일한 형식을 가진 건축물과는 상이하고 복잡한 반응을 보이게 된다 이러한 건축물의 등가정적 해석시 국내 규준에서는 기타구조물로 분류하여 3.5 의 반응수정계수를 적용하고 있다 그러나 이 계수는 검증되어지지 않는 상태로 사용되어지고 있으므로 상당한 위험성을 내포하고 있다 본 연구에서는 단순화한 주상복합 건물의 해석 및 실제의 건물에 대한 3차원 비선형 해석을 통하여 반응수정계수를 유도하였다 유도된 반응수정계수는 ATC 기준과 우리나라 기준의 차이를 고려한 보정을 수행하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.3-5
• /
• 2007

본 논문에서는 새로운 내용기반 이미지 검색 기법으로 식물 잎의 윤곽선에 대하여 동적 시간 정합 기법을 이용하여 유사한 이미지를 효과적으로 검색하는 방법을 제안한다. 이를 위하여 우선 식물 잎의 기준점에 대하여 잎의 가장자리를 따라 가면서 구해지는 거리의 곡선을 통하여 잎의 외형 특성을 표현하였다. 추출된 곡선 정보의 효율적인 저장과 처리를 위하여 곡선의 특성을 표현할 수 있는 퓨리에 계수(Fourier Coefficients)를 계산하고 이를 바탕으로 유사한 이미지를 계산하였다. 이런 과정에서 생기는 문제점으로는 복잡한 형태의 곡선에 대해서는 퓨리에 계수를 통하여 저장하고 복원하는 과정에서 원본 곡선의 세부적인 형태 정보를 상실하게 된다. 이러한 문제를 해결하기 위해서는 복잡한 곡선 유형에 대해서는 복원시 상실되는 정보가 최소화될 수 있는 작은 단위의 구간으로 나누고 이에 대한 퓨리에 계수를 계산하는 방법으로 다수의 퓨리에 계수 세트를 추출하는 이진 구간 분할 (Binary Range Reduction) 알고리즘을 사용하였고 질의 이미지와 저장된 이미지들을 비교하는 과정에서 검색의 정확도를 향상시키기 위하여 동적 시간 정합(Dynamic Time Warping) 알고리즘을 사용하였다. 그리고 검색의 효율을 더욱 높이기 위하여 추출된 외형 정보를 기반으로 잎의 유형을 다양한 카테고리로 분류하는 외형 기형 기반의 잎 분류 기법을 제안하였다. 다양한 실험을 통하여 제안한 기법이 식물 잎 검색에 우수한 성능을 나타냄을 보인다.

• International Journal of Highway Engineering
• /
• v.5 no.1 s.15
• /
• pp.35-45
• /
• 2003

This paper presents a theoretical approach for estimation of CBR-value of subbase course and subgrade using a portable pavement dynamic cone penetrometer(PDCP). The PDCP used in this paper was based on a design from South Africa and extensive studies by Kleyn(1982) and more recently by Liveneh and Ishai(1987) and Chua(1988). To date, California Bearing Ratio[CBR] value was studied mainly for application of pavement structural design. This study was initiated to develop a method of obtaining the in situ CBR-values of subbase and subgrade for the structural evaluation of pavements in the swift and inexpensive manner. PDCP tests were implemented at 20 different kinds of soil samples in the lab and test results were analysed by a theoretical approach introduced. The procedure presented provides acceptable and promising results.