• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• 분석과학
• /
• 제32권6호
• /
• pp.233-242
• /
• 2019

Substance identification is the first step of the REACH registration. It is essential in terms of Classification, Labelling and Packaging (CLP) regulation and because even trace amounts of impurities or additives can affect the classification. In this study, a scheme for the screening, quantification, and interpretation of trace amounts of hazardous inorganic substances is proposed to detect the presence of more than 0.1% hazardous inorganic substances that have been affecting the hazard classification. An exemplary list of hazardous inorganic substances was created from the substances of very high concern (SVHCs) in REACH. Among 201 SVHCs, there were 67 inorganic SVHCs containing at least one or ~2-3 heavy metals, such as As, Cd, Co, Cr, Pb, Sb, and Sn, in their molecular formula. The inorganic SVHCs are listed in excel format with a search function for these heavy metals so that the hazardous inorganic substances, including each heavy metal and the calculated ratio of its atomic weight to molecular weight of the hazardous inorganic substance containing it, can be searched. The case study was conducted to confirm the validity of the established scheme with zinc oxide (ZnO). In a substance that is made of ZnO, Pb was screened by XRF analysis and measured to be 0.04% (w/w) by ICP-OES analysis. After referring to the list, the presence of Pb was interpreted just as an impurity, but not as an impurity relevant for the classification. Future studies are needed to expand on this exemplary list of hazardous inorganic substances using proper regulatory data sources.

• ETRI Journal
• /
• 제42권3호
• /
• pp.311-323
• /
• 2020

Encrypted traffic classification plays a vital role in cybersecurity as network traffic encryption becomes prevalent. First, we briefly introduce three traffic encryption mechanisms: IPsec, SSL/TLS, and SRTP. After evaluating the performances of support vector machine, random forest, naïve Bayes, and logistic regression for traffic classification, we propose the combined approach of entropy estimation and artificial neural networks. First, network traffic is classified as encrypted or plaintext with entropy estimation. Encrypted traffic is then further classified using neural networks. We propose using traffic packet's sizes, packet's inter-arrival time, and direction as the neural network's input. Our combined approach was evaluated with the dataset obtained from the Canadian Institute for Cybersecurity. Results show an improved precision (from 1 to 7 percentage points), and some application classification metrics improved nearly by 30 percentage points.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2005년도 추계 종합학술대회 논문집
• /
• pp.66-71
• /
• 2005

인터넷 정보를 검색하고 활용하는 것은 쉽고도 어려운 일이다. 많은 정보 중에서 원하는 정보를 얻기 위한 노력은 단순히 검색뿐만 아니라 정보의 수집에서 분류 및 가공, 활용에까지 각 분야별로 그 범위와 용도에서 다양한 기술의 발전이 급속히 진행되고 있다. 특히, 이러한 발전은 다양한 용도의 에이전트와 분류, 변환 등의 가공 기술에서 더욱 두드러지게 나타나고 있다. 또한, 시스템의 자동화를 통한 편리성을 제공한 다면 더욱 효과적인 정보관리가 이루어 질 것이다. 본 논문에서는 이러한 배경에서 인터넷 정보의 수집에서 자동 분류, 검색 서비스까지를 하나의 시스템에서 처리 할 수 있는 인터넷 문서 자동분류 서비스 시스템을 소개한다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(C)
• /
• pp.195-197
• /
• 2011

This research deals with an issue of preventive medicine in bioinformatics. We can diagnose liver conditions reasonably well to prevent Liver Cirrhosis by classifying liver disorder patients into fatty liver and high risk groups. The classification proceeds in two steps. Classification rules are first built by clustering five attributes (MCV, ALP, ALT, ASP, and GGT) of blood test dataset provided by the UCI Repository. The clusters can be formed by the K-mean method that analyzes multi dimensional attributes. We analyze the properties of each cluster divided into fatty liver, high risk and normal classes. The classification rules are generated by the analysis. In this paper, we suggest a method to diagnosis and predict liver condition to alcoholic patient according to risk levels using the classification rule from the new results of blood test. The K-mean classifier has been found to be more accurate for the result of blood test and provides the risk of fatty liver to normal liver conditions.

• 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.

• Nuclear Engineering and Technology
• /
• 제55권5호
• /
• pp.1814-1820
• /
• 2023

Safety classification of systems, structures, and components (SSC) is an essential activity for nuclear reactor design and operation. The current regulatory trend is to require risk-informed safety classification that considers first, the severity, but also the frequency of SSC failures. While safety classification for nuclear power plants is covered in many regulatory and scientific publications, research reactors received less attention. Research reactors are typically of lower power but, at the same time, are less standardized i.e., have more variability in the design, operational modes, and operating conditions. This makes them more challenging when considering safety classification. This work presents the Integrated Risk-Informed Safety Classification (IRISC) procedure which is a novel extension of the IAEA recommended process with dedicated probabilistic treatment of research reactor designs. The article provides the details of probabilistic analysis performed within safety classification process to a degree that is often missing in most literature on the topic. The article presents insight from the implementation of the procedure in the safety classification for the MARIA Research Reactor operated by the National Center for Nuclear Research in Poland.

• 한국환경복원기술학회지
• /
• 제2권1호
• /
• pp.29-37
• /
• 1999

Land cover classification is an essential basic information in natural environment management; however, land cover classification studies in Korea have not yet been proceeded to a sufficient level. At the present, only a limited number of the precedent studies that only cover definite city area has been conducted. Furthermore, there is almost no research conducted on the land cover classification schemes that could accurately classify the Korea's land cover conditions. This study primarily focuses on the land cover classification scheme which carries the most urgent priority in order to classify and to map out the Korean land cover conditions. In order to develop the most suitable land cover classification scheme, many foreign land cover classification cases and projects that are being carried out were reviewed in depth. The land cover classification scheme this study proposes comprises 3 levels : The first level consists of 7 different classes; the second level consists of 22 different classes; and the third level is made up of 50 classes. The land cover classification map will serve many important roles in natural environment management, such as the conjecture of natural habitats and estimation of oxygen production or carbon dioxide absorption capability of a forest. In water pollution modelling, the land cover classification data can be used to estimate and locate non-point sources of water pollution. If applied to a watershed, modelling it will allow to estimate the total amount of pollution from non-point sources of pollution in the water shed. The land cover classification data will also be good as a barometer data that determines defusion of air pollutants in air pollution modelling.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1997년도 봄 학술발표회 논문집
• /
• pp.169-178
• /
• 1997

• 한국토양비료학회지
• /
• 제50권6호
• /
• pp.520-529
• /
• 2017

In Korea, the largest agricultural lands are paddy fields which have poor infiltration and drainage properties. Recently, Korean government pursuits cultivating upland crops in paddy fields to reduce overproduced rice in Korea. In order to succeed this policy, it is critical to set criteria suitability classification for upland crops cultivating in paddy field soils. The objective of this study was developing guideline of suitability classification for sesame cultivation in paddy field soils. Yields of sesame cultivated in paddy field soils and soil properties were investigated at 40 locations at nationwide scale. Soil properties such as topography, soil texture, soil moisture contents, slope, and drainage level were investigated. The guideline of suitability classification for sesame was determined by multi-regression method. As a result, sesame yields had the greatest correlation with topography, soil moisture content, and slope. Since sesame is sensitive to excessive soil moisture content, paddy fields with well drained, slope of 7-15% and mountain foot or hill were best suit for cultivating sesame. Sesame yields were greater with less soil moisture contents. Based on these results, area of best suitable paddy field land for sesame was 161,400 ha, suitable land was 62,600 ha, possible land was 331,600 ha, and low productive land was 1,075,500 ha. Compared to existing suitability classification, the new guideline of classification recommended smaller area of best or suitable areas to cultivate sesame. This result may suggest that sesame cultivation in paddy field can be very susceptible to soil moisture contents.