• 한국식품과학회지
• /
• 제30권1호
• /
• pp.118-124
• /
• 1998

Dehulled cowpea was microparticulated and coarse fractions and fine fractions were collected by air classification at air classifying wheel speed (ACWS) of 15,000 rpm, 12,000 rpm and 9,000 rpm, respectively. Protein content in fine fraction after air classification was 2 times higher than that of microparticulated cowpea, emulsion capacity was about 3 times than coarse fraction. The coarse fraction of the highest viscosity on the gelatinization properties were detected by amylograph, was C-3 (9,000 rpm coarse)fraction. The majority of microparticulated cowpea particles were oval shaped starch and the rest of them were indeterminate minute particles which had some sharp corners. As an application test, microparticulated cowpea and coarse fraction (C-3) were used for mook (Korea traditional starch jelly) preparation and the wet milled cowpea starch was compared as a control. Some impurities induced discoloring was detected by sensory evaluation but after washing, it made no difference in sensory scores between washed starch and the control cowpea mook. And also syneresis of washed cowpea was less than control. At the above result, it can be to recovery about 85% of cowpea starch using microparticulation/air classification technology.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.198-201
• /
• 2000

We propose a method for analyzing the document structure. This method consists of two processes, segmentation and classification. The segmentation first divides a low resolution image, and then finely splits the original document image using projection profiles. The classification deterimines each segmented region as text, line, table or image. An experiment with 238 documents images shows that the segmentation accuracy is 99.1% and the classification accuracy is 97.3%.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.29-30
• /
• 2022

Curriculum learning은 딥러닝의 성능을 향상시키기 위해 사람의 학습 과정과 유사하게 일종의 'curriculum'을 도입해 모델을 학습시키는 방법이다. 대부분의 연구는 학습 데이터 중 개별 샘플의 난이도를 기반으로 점진적으로 모델을 학습시키는 방안에 중점을 두고 있다. 그러나, coarse-to-fine 메카니즘은 데이터의 난이도보다 학습에 사용되는 class의 유사도가 더욱 중요하다고 주장하며, 여러 난이도의 auxiliary task를 차례로 학습하는 방법을 제안했다. 그러나, 이 방법은 혼동행렬 기반으로 class의 유사성을 판단해 auxiliary task를 생성함으로 다중 레이블 분류에는 적용하기 어렵다는 한계점이 있다. 따라서, 본 논문에서는 multi-label 환경에서 multi-class와 binary task를 생성하는 방법을 제안해 coarse-to-fine 메카니즘 적용을 위한 방안을 제시하고, 그 결과를 분석한다.

• 한국토양비료학회지
• /
• 제48권5호
• /
• pp.535-541
• /
• 2015

Korean soil classification system is based on the US soil taxonomy. This study aimed to understand and inform the soil taxonomy of 2010 and 2014 US soil classification systems. Ingwan series belonged to anthropogenic soil was classified to coarse loamy over sandy, mixed, mesic family of Aquic Udorthents based on the soil taxonomy of 2010 and coarse loamy over sandy, mixed, mesic family of Anthroportic Udorthents based on the soil taxonomy of 2014. An anthropogenic soil is increasing in Korea. Considering the domestic relationship depending on US soil taxonomy, it is important to be well-informed of the taxonomy and apply the updated taxonomy system properly to the domestic soil classification. This study of defining the anthropogenic soil will provide useful information on soil management and its utilization.

• 응용통계연구
• /
• 제25권2호
• /
• pp.261-267
• /
• 2012

신용평점표(credit scorecard) 작성시 각 특성변수(characteristic variable)들을 몇 개의 속성(attribute)들로 나누고 각 속성에 적절한 가중치를 부여하게 된다. 이 과정을 성김화(coarse classi cation)라 한다. 특성변수들을 속성들로 나눌 때 그 기준이 되는 절단값(cutpoint)을 선택해야 한다. 본 논문에서는 벌점화(penalization) 기반의 절단값 선택법을 제안한다. 또한 여러가지 모의실험과 실제 신용자료의 분석을 통하여 제안된 방법과 기존의 절단값 선택법인 스플라인 분류 기계 (Koo 등, 2009)의 성능을 비교한다.

• 자원리싸이클링
• /
• 제10권6호
• /
• pp.29-34
• /
• 2001

석탄회 분말을 다중자연낙하법에 의한 공기분급에 의하여 미립 및 조립의 분말로 정제 및 분급한 후 각각의 분말을 사용하여 뮬라이트 및 제올라이트를 합성하였다 평균 입경이 $6.5mu$m인 미립 석탄회에$ A12$ $O_3$를 첨가한 후 145$0^{\circ}C$ 이상의 온도에서 소성하여 뮬라이트 상의 소결체를 얻었다. 평균 입경 $56.3\mu$m인 조립 석탄회를 사용하여 3.5 M NaOH수용액과 $120^{\circ}C$에서 수열 반응시켜 phillipsite형 제올라이트를 합성하였다. 이와 같은 방법으로 모든 입도의 석탄회 분말을 무기재료의 합성에 이용할 수 있었다.

• 한국지형학회지
• /
• 제26권4호
• /
• pp.47-65
• /
• 2019

A case study was conducted in Taean region to seek a more detailed macrotidal beach classification than existing beach classification models (Masselink and Short, 1993). Seepage and ridge & runnel were used for classification. On 20 beaches, 68 transects were surveyed 5 times using VRS-GPS. Cross-section area from the transect profiles, mean grain size from sediment analysis, significant wave height from Swan-wave modeling and beach embaymentization from aerial photograph analysis were used to identify the characteristics of the individual types. The transects were classified into 5 types in Taean region; Type 1: low tidal terrace, Type 2: low tidal terrace & ridge, Type 3: dissipative, Type 4: seasonal ridge, and Type 5: ridge & runnel. Generally, seepage was related to coarse sediment size and ridge & runnel was related to high significant wave height. Each type has different characteristics and there was a tendency between the types. The low tidal terrace type had coarse sediments, because this type is excluded from the littoral cell. In this study, the ridge and runnel type could be applied to the classification because the study area is limited only to the macrotidal environment in Taean region.

• 음성과학
• /
• 제11권2호
• /
• pp.193-210
• /
• 2004

In this paper, we develop a real time lip-synch system that activates 2-D avatar's lip motion in synch with an incoming speech utterance. To realize the 'real time' operation of the system, we contain the processing time by invoking merge and split procedures performing coarse-to-fine phoneme classification. At each stage of phoneme classification, we apply the support vector machine (SVM) to reduce the computational load while retraining the desired accuracy. The coarse-to-fine phoneme classification is accomplished via two stages of feature extraction: first, each speech frame is acoustically analyzed for 3 classes of lip opening using Mel Frequency Cepstral Coefficients (MFCC) as a feature; secondly, each frame is further refined in classification for detailed lip shape using formant information. We implemented the system with 2-D lip animation that shows the effectiveness of the proposed two-stage procedure in accomplishing a real-time lip-synch task. It was observed that the method of using phoneme merging and SVM achieved about twice faster speed in recognition than the method employing the Hidden Markov Model (HMM). A typical latency time per a single frame observed for our method was in the order of 18.22 milliseconds while an HMM method applied under identical conditions resulted about 30.67 milliseconds.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.433-438
• /
• 1999

The land use type of Korea is high-density. So, the image classification using coarse resolution satellite image may not provide land cover classification results as good as expected. The purpose of this paper is to compare the result of visual interpretation with that of digital image classification of 20 m resolution SPOT satellite image at Kwangju-eup, Kyunggi-do, Korea. Classes are forest, cultivated field, pasture, water and residential area, which are clearly discriminated in visual interpretation. Maximum likelihood classifier was used for digital image classification. Accuracy assessment was done by comparing each classification result with ground truth data obtained from field checking. The classification result from the visual interpretation presented an total accuracy 9.23 percent higher than that of the digital image classification. This proves the importance of visual interpretation for the area with high density land use like the study site in Korea.

• 대한원격탐사학회지
• /
• 제18권3호
• /
• pp.163-169
• /
• 2002

The land uses of Korean peninsula are very complicated and high-density. Therefore, the image classification using coarse resolution satellite images may not provide good results for the land cover classification. The purpose of this paper is to compare the classification accuracy of visual interpretation with that of digital image classification of satellite remote sensing data such as 20m SPOT and 30m TM. In this study, hybrid classification was used. Classification accuracy was assessed by comparing each classification result with reference data obtained from KOMPSAT-1 EOC imagery, air photos, and field surveys.