• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.22-30
• /
• 2001

In this paper we propose three classification algorithms to classify breast tumors that occur in duct into Benign, DCIS(ductal carcinoma in situ) NOS(invasive ductal carcinoma) The general approach for a creating classifier is composed of 2 steps: feature extraction and classification Above all feature extraction for a good classifier is very significance, because the classification performance depends on the extracted features, Therefore in the feature extraction step, we extracted morphology features describing the size of nuclei and texture features The internal structures of the tumor are reflected from wavelet transformed images with 10$\times$ and 40$\times$ magnification. Pariticulary to find the correlation between correct classification rates and wavelet depths we applied 1, 2, 3 and 4-level wavelet transforms to the images and extracted texture feature from the transformed images The morphology features used are area, perimeter, width of X axis width of Y axis and circularity The texture features used are entropy energy contrast and homogeneity. In the classification step, we created three classifiers from each of extracted features using discriminant analysis The first classifier was made by morphology features. The second and the third classifiers were made by texture features of wavelet transformed images with 10$\times$ and 40$\times$ magnification. Finally we analyzed and compared the correct classification rate of the three classifiers. In this study, we found that the best classifier was made by texture features of 3-level wavelet transformed images.

• Nuclear Engineering and Technology
• /
• v.14 no.3
• /
• pp.122-137
• /
• 1982

Analyzed is the sensitivity of reactor transient behavior to various reactor parameters during the reactivity induced accidents (RIA) of the Kori Unit 1. Included in the analysis is a partial spectrum of RIAs with relatively fast transients such as uncontrolled rod cluster control assembly bank withdrawl from a subcritical or low power startup condition and rod ejection accidents. The analysis can be performed generally in three steps: calculation of an average core power change, hot spot heat transfer calculation and DNBR (departure from nucleate boiling ratio) calculation. The computer codes used for the analysis are either developed based on the codes relevent to it. These codes are evaluated to be highly reliable. An extensive sensitivity analysis is performed to study the effects of various reactor design and operating parameters on the reactor transient behavior during the accidents. The assumptions and initial conditions used for the RIA analysis in the Kori Unit 1 FSAR (Final Safety Analysis Report) are reexamined, and the corresponding analysis results are reassessed, based on the sensitivity analysis results, to be conservative and reliable.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.426-428
• /
• 2021

전 세계적으로 건강, 환경보호, 윤리적 소비를 추구하는 소비자들이 증가하면서 다양한 분야에서 동물성 제품을 섭취하거나 소비하지 않는 생활방식인 비거니즘(Veganism)을 지향하는 사람들이 증가하고 있다. 한국 또한 매년 채식에 대한 관심이 높아지고 있지만 외국에 비해 채식하기에 좋은 환경은 구축되어 있지 않으며 가공식품을 구매할 경우 성분 표를 일일이 확인해야 하는 어려움이 있다. 본 연구에서는 사용자가 섭취하고자 하는 가공식품의 성분을 분석하여 본인의 채식주의자 단계에 적합한 제품인지 쉽게 판별할 수 있는 모바일 앱을 제안한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.4
• /
• pp.42-53
• /
• 2012

In pattern recognition and machine learning society, classification has been a classical problem and the most widely researched area. Adaptive boosting also known as Adaboost has been successfully applied to binary classification problems. It is a kind of boosting algorithm capable of constructing a strong classifier through a weighted combination of weak classifiers. On the other hand, the PCA and LDA algorithms are the most popular linear feature extraction methods used mainly for dimensionality reduction. In this paper, the combination of Adaboost and feature extraction methods is proposed for efficient classification of two class data. Conventionally, in classification problems, the roles of feature extraction and classification have been distinct, i.e., a feature extraction method and a classifier are applied sequentially to classify input variable into several categories. In this paper, these two steps are combined into one resulting in a good classification performance. More specifically, each projection vector is treated as a weak classifier in Adaboost algorithm to constitute a strong classifier for binary classification problems. The proposed algorithm is applied to UCI dataset and FRGC dataset and showed better recognition rates than sequential application of feature extraction and classification methods.

• Korean Journal of Environmental Biology
• /
• v.39 no.4
• /
• pp.581-589
• /
• 2021

Using visible-near infrared(Vis-NIR) spectra combined with machine learning methods, the feasibility of quick and non-destructive classification of Convolvulaceae species was studied. The main aim of this study is to classify six Convolvulaceae species in the field in different geographical regions of South Korea using a handheld spectrometer. Spectra were taken at 1.5 nm intervals from the adaxial side of the leaves in the Vis-NIR spectral region between 400 and 1,075 nm. The obtained spectra were preprocessed with three different preprocessing methods to find the best preprocessing approach with the highest classification accuracy. Preprocessed spectra of the six Convolvulaceae sp. were provided as input for the machine learning analysis. After cross-validation, the classification accuracy of various combinations of preprocessing and modeling ranged between 43.4% and 98.6%. The combination of Savitzky-Golay and Support vector machine methods showed the highest classification accuracy of 98.6% for the discrimination of Convolvulaceae sp. The growth stage of the plants, different measuring locations, and the scanning position of leaves on the plant were some of the crucial factors that affected the outcomes in this investigation. We conclude that Vis-NIR spectroscopy, coupled with suitable preprocessing and machine learning approaches, can be used in the field to effectively discriminate Convolvulaceae sp. for effective weed monitoring and management.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.12-18
• /
• 2010

Automatic Target Detection (ATD) systems that use forward-looking infrared (FLIR) consists of three stages. preprocessing, detection, and clutter rejection. All potential targets are extracted in preprocessing and detection stages. But, this results in a high false alarm rates. To reduce false alarm rates of ATD system, true targets are extracted in the clutter rejection stage. This paper focuses on clutter rejection stage. This paper presents a new clutter rejection technique using PCA features and stochastic features of clutters and targets. PCA features are obtained from Euclidian distances using which potential targets are projected to reduced eigenspace selected from target eigenvectors. CV is used for calculating stochastic features of edges in targets and clutters images. To distinguish between target and clutter, LDA (Linear Discriminant Analysis) is applied. The experimental results show that the proposed algorithm accurately classify clutters with a low false rate compared to PCA method or CV method

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.183-192
• /
• 2006

간세포암은 우리나라에서 전체 암사망자 중 17.2%로 3번째의 흔한 사망원인이며, 간암에 의한 사망률은 인구 10만 명당 약 21명에 이른다. 본 논문에서는 간 내부에서 발생하는 간세포암을 CT 영상에서 자동으로 추출하는 방법을 제안하여 간세포암의 보조진단으로서의 유용성에 대해 알아보고자 한다. 간 내부의 종양을 추출하기 위해 흉부의 윗부분에서 시작하여 2.5mm의 간격으로 약 45-50장 정도를 촬영한 CT 영상들을 대상으로 먼저 간 영역을 추출한다. 간 영역 추출은 먼저 관심이 없는 외부 영역을 갈비뼈를 중심으로 제거한 후 영상의 밝기 정보를 이용하여 각 기관의 영역을 분할 한다. 분할된 영역들은 위 아래로 인접한 영상에서의 분할 영역들과 밝기 값을 비교하여 적절하게 병합하는 3차원적 접근방법을 사용한다. 간 영역은 여러개의 영역들 중에서 간 영역의 구조 및 위치 등의 정보를 활용하여 추출한다. 추출된 간 영역에서 종양 판별과 추출을 위해 종양이 가지는 특징을 분석하여 종양을 추출한다. 전형적인 간세포암은 과혈관성 종양이므로 조영증강 CT 영상에서 주위보다 밝은 색으로 나타나며, 팽창 형성장을 보일 경우에는 구형으로 나타나는 특징이 있다. 이에, 주위 보다 밝은 색을 가지고 둥근형태를 가지는 영역을 종양의 후보영역으로 선정한 후, 그 영상의 위와 아래로 연결되는 영상에서도 같은 위치에서 같은 특징을 보이는 영역이 있으면 간 내부의 종양으로 판별하여 추출한다. 제안된 간 영역 및 간 종양 추출 방법의 정확성을 판별하기 위하여 CT 영상을 대상으로 실험하여 영상의학 전문의가 판단한 결과와 비교하였다. 간 영역 추출은 정확히 모두 추출되었으며, 간 종양 추출 및 판별은 전문의의 보조 진단도구로 활용할 수 있는 가능성이 매우 높다는 것을 확인할 수 있었다.emantic Similarity Measure 등을 단계적으로 수행하여 자동화되고 정확한 규칙식별을 하고자 한다. 이러한 방법들의 조합으로 인하여 규칙구성요소 추출이 되지 않을 후보 단어들의 수를 줄여서 보다 더 정확하고, 지능적인 규칙구성요소 추출 방법론을 제시하고 구현하여 지식관리자의 규칙습득에 대한 부담을 줄여 주고자 한다. 도움을 받을 수 있게 되었다.을 거치도록 되어있다. 교통주제도는 국가의 교통정책결정과 관련분야의 기초자료로서 다양하게 활용되고 있으며, 특히 ITS 노드/링크 기본지도로 활용되는 등 교통 분야의 중요한 지리정보로서 구축되고 있다..20{\pm}0.37L$, 72시간에 $1.33{\pm}0.33L$로 유의한 차이를 보였으므로(F=6.153, P=0.004), 술 후 폐환기능 회복에 효과가 있다. 4) 실험군과 대조군의 수술 후 노력성 폐활량은 수술 후 72시간에서 실험군이 $1.90{\pm}0.61L$, 대조군이 $1.51{\pm}0.38L$로 유의한 차이를 보였다(t=2.620, P=0.013). 5) 실험군과 대조군의 수술 후 일초 노력성 호기량은 수술 후 24시간에서 $1.33{\pm}0.56L,\;1.00{\ge}0.28L$로 유의한 차이를 보였고(t=2.530, P=0.017), 술 후 72시간에서 $1.72{\pm}0.65L,\;1.33{\pm}0.3L$로 유의한 차이를 보였다(t=2.540, P=0.016). 6) 대상자의 술 후 폐환기능에 영향을 미치는 요인은 성별로 나타났다. 이에 따른 폐환기능의 차이를 보면, 실험군의 술 후 노력성 폐활량이 48시간에 남자($1.78{\pm}0.61L$)가 여자(

• Korean Journal of Environmental Biology
• /
• v.33 no.1
• /
• pp.34-44
• /
• 2015

Fish fauna, difference of stable isotope ratio between freshwater and seawater, and trophic guilds of freshwater fishes were investigated in the lower Geum River. The study was conducted in 2011, and total study area was about 30 km of 20 km upstream and 10 km downstream from the Geum River estuary barrage. Only freshwater fishes were used for analyzing trophic guilds, and discriminant function analysis (DFA) was utilized to reclassify trophic guilds based on stable isotope ratio. Fish fauna in freshwater and seawater areas were entirely different each other, but small number of migratory species such as Coilia nasus and Chelon haematocheilus occurred both areas. Other species were not collected in the different areas because they did not have physiological ability to adapt different salinity concentrations. Stable isotope ration of two areas were different considerably due to food sources. Estuary and seawater fishes uptake food sources originated from marine, and freshwater fishes were from freshwater and terrestrial. Some migratory species showed reverse stable isotope ratio. Even though they collected in freshwater, they showed stable isotope ratio of seawater. This is because ecological characteristics of each species. Trophic guilds of freshwater fishes were reclassified by DFA, and showed slight difference with literatures. However, because this result is related with ontogenetic shift of species, more studies are needed to explain exact and correct trophic guilds. Stable isotope ratio can be changed among regions, seasons and ontogenetic stage, thus we always consider these aspects when analyzing results to get a right answer.

• Journal of The Korean Association of Information Education
• /
• v.12 no.4
• /
• pp.427-436
• /
• 2008

It is more than 10 years since ICT training learning was introduced to educational curriculum, and it is now time for overall consideration about the result of the education. The most important difficulties that the teachers have are that there are big differences in the level of learning ability. The characteristics of ICT curriculum are its tool and stepwise progress. The main problem of a curriculum with such characteristics is with underachivers. To distinguish ICT underachivers, the present study was developed a distinction tool for investigation: The objects were the students in the 6th grade of the 4 elementary schools in Gyeonggi-do, and inquires were made to find out characteristics. Inquires were also made to the elementary school teachers in Goyang-city to find out the actual instructional situation. A teaching-learning system will be suggested to prevent the occurring of ICT underachivers by analyzing their characteristics. The system consists of a distinction examination module, a teaching-learning module and a feedback module, which are web-based, as well as an off-line actual class module. The purpose of the system is to prevent underachivers in ICT classes, so that the students' ability to utilize computer will be improved to a higher level.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.207-216
• /
• 2013

The aim of this study is to design a classifier for sleep stage analysis and select important feature set which shows sleep stage well based on physiological signals during sleep. Sleep has a significant effect on the quality of human life. When people undergo lack of sleep or sleep-related disease, they are likely to reduced concentration and cognitive impairment affects, etc. Therefore, there are a lot of research to analyze sleep stage. In this study, after acquisition physiological signals during sleep, we do pre-processing such as filtering for extracting features. The features are used input for the new combination algorithm using genetic algorithm(GA) and neural networks(NN). The algorithm selects features which have high weights to classify sleep stage. As the result of this study, accuracy of the algorithm is up to 90.26% with electroencephalography(EEG) signal and electrocardiography(ECG) signal, and selecting features are alpha and delta frequency band power of EEG signal and standard deviation of all normal RR intervals(SDNN) of ECG signal. We checked the selected features are well shown that they have important information to classify sleep stage as doing repeating the algorithm. This research could use for not only diagnose disease related to sleep but also make a guideline of sleep stage analysis.