• Journal of KIISE:Software and Applications
• /
• v.34 no.11
• /
• pp.1001-1010
• /
• 2007

HMM tends to output high probability for not only the proper class data but confusable class data, since the modeling power increases as the number of parameters increases. Thus it may not be helpful for discrimination to simply increase the number of parameters of HMM. We proposed two methods in this paper. One is a CMC(Confusion Likelihood Model Selection Criterion) using confusion class data probability, the other is a new recognition method, RCM(Recognition Using Confusion Models). In the proposed recognition method, confusion models are constructed using confusable class data, then confusion models are used to depress misrecognition by confusion likelihood is subtracted from the corresponding standard model probability. We found that CMC showed better results using fewer number of parameters compared with ML, ALC2, and BIC. RCM recorded 93.08% recognition rate, which is 1.5% higher result by reducing 17.4% of errors than using standard model only.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.999-1009
• /
• 2019

The importance of high-resolution sea ice maps of the Arctic Ocean is increasing due to the possibility of pioneering North Pole Routes and the necessity of precise climate prediction models. In this study,sea ice classification algorithms for two deep learning models were examined using Sentinel-1 A/B SAR data to generate high-resolution sea ice classification maps. Based on current ice charts, three classes (Open Water, First Year Ice, Multi Year Ice) of training data sets were generated by Arctic sea ice and remote sensing experts. Ten sea ice classification algorithms were generated by combing two deep learning models (i.e. Simple CNN and Resnet50) and five cases of input bands including incident angles and thermal noise corrected HV bands. For the ten algorithms, analyses were performed by comparing classification results with ground truth points. A confusion matrix and Cohen's kappa coefficient were produced for the case that showed best result. Furthermore, the classification result with the Maximum Likelihood Classifier that has been traditionally employed to classify sea ice. In conclusion, the Convolutional Neural Network case, which has two convolution layers and two max pooling layers, with HV and incident angle input bands shows classification accuracy of 96.66%, and Cohen's kappa coefficient of 0.9499. All deep learning cases shows better classification accuracy than the classification result of the Maximum Likelihood Classifier.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.74.3-74.3
• /
• 2019

SCUBA-2 North Ecliptic Pole survey, one of the ongoing JCMT large programs, is designed to obtain 850 ㎛ imaging data over ~4 deg² around the NEP based on the AKARI NEP-Wide survey. By August 2019, the program is 50 % complete in terms of observing time, increasing the submillimeter coverage by a factor of 2 with the comparable depth. The rms measured in the deepest center is 0.92 mJy/beam, slightly above the 850 ㎛ confusion limit. With 4 σ detection, the source count is 50 % complete at 9 mJy. The surface density of submillimeter galaxies at this flux limit is 200 deg^-2. Multi-wavelength identification of the 850 ㎛ sources was done through the likelihood analysis based on the far-infrared (250-500 ㎛), mid-infrared (18 ㎛), near-infrared (2-4 ㎛), and optical (i-band) source catalog. We are going to present morphologies and physical properties of 850 ㎛ selected submillimeter galaxies with the help of ancillary multi-wavelength datasets over the NEP area.

• Safety and Health at Work
• /
• v.8 no.4
• /
• pp.327-328
• /
• 2017

Despite provision of drinking water as the most common method of occupational heat stress prevention, there remains confusion in hydration messaging to workers. During work site interactions in a hot and humid climate, workers commonly report being informed to consume tepid fluids to accelerate rehydration. When questioned on the evidence supporting such advice, workers typically cite that fluid absorption is delayed by ingestion of chilled beverages. Presumably, delayed absorption would be a product of fluid delivery from the gut to the intestines, otherwise known as gastric emptying. Regulation of gastric emptying is multifactorial, with gastric volume and beverage energy density the primary factors. If gastric emptying is temperature dependent, the impact of cooling is modest in both magnitude and duration (${\leq}5$ minutes) due to the warming of fluids upon ingestion, particularly where workers have elevated core temperature. Given that chilled beverages are most preferred by workers, and result in greater consumption than warm fluids during and following physical activity, the resultant increased consumption of chilled fluids would promote gastric emptying through superior gastric volume. Hence, advising workers to avoid cool/cold fluids during rehydration appears to be a misinterpretation of the research. More appropriate messaging to workers would include the thermal benefits of cool/cold fluid consumption in hot and humid conditions, thereby promoting autonomy to trial chilled beverages and determine personal preference. In doing so, temperature-based palatability would be maximized and increase the likelihood of workers maintaining or restoring hydration status during and after their work shift.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.16 no.2
• /
• pp.114-124
• /
• 2014

For classifying fire damaged areas and analyzing burn severity of two large-fire areas damaged over 100 ha in 2011, three methods were employed utilized supervised classification, unsupervised classification and Normalized Difference Vegetation Index (NDVI). In this paper, the post-fire imageries of SPOT were used to compute the Maximum Likelihood (MLC), Minimum Distance (MIN), ISODATA, K-means, NDVI and to evaluate large-scale patterns of burn severity from 1 m to 5 m spatial resolutions. The result of the accuracy verification on burn severity from satellite images showed that average overall accuracy was 88.38 % and the Kappa coefficient was 0.8147. To compare the accuracy between burn severity and field survey at Uljin and Youngduk, two large fire sites were selected as study areas, and forty-four sampling plots were assigned in each study area for field survey. The burn severities of the study areas were estimated by analyzing burn severity (BS) classes from SPOT images taken one month after the occurrence of the fire. The applicability of composite burn index (CBI) was validated with a correlation analysis between field survey data and burn severity classified by SPOT5, and by their confusion matrix. The result showed that correlation between field survey data and BS by SPOT5 were closely correlated in both Uljin (r = -0.544 and p<0.01) and Youngduk (r = -0.616 and p<0.01). Thus, this result supported that the proposed burn severity analysis is an adequate method to measure burn severity of large fire areas in Korea.

• Korean journal of applied entomology
• /
• v.59 no.2
• /
• pp.117-127
• /
• 2020

We monitored on the hitchhiker insect pests from a total of 112 foreign vessels entering into Korea during 109 days from 1. Jun. to 17. Sep. in 2018. As the results, a total of 336 samples of the hitchhiker insects were collected using simply collecting method by hands, one of interception method and identified as 159 species of 47 families under nine orders on the basis of integrative species identification. Among them, 14 species of nine families under three orders were detected as undistributed species in South Korea. We reported on the 14 undistributed species in South Korea with the data sheets for the risk assessments on invasive or invasive likelihood species. Also, we suggested and used the term 'not-distributed species' for avoiding confusion with 'unrecorded species', 'unreported species', or 'new reported species'.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.15
• /
• pp.6307-6313
• /
• 2014

The aim of this study was to examine the knowledge and awareness of women in Kuwait with regard to risk factors, symptoms and diagnostic procedures of breast cancer. A total of 521 questionnaires were distributed among women in Kuwait. Results showed that 72% of respondents linked breast cancer factors to family history, while 69.7% scored abnormal breast enlargement as the most detectable symptom of the disease. Some 84% of participants had heard about self-examination, but knowledge about mammograms was limited to 48.6% and only 22.2% were familiar with diagnostic procedures. Some 22.9% of respondents identified the age over 40 years as the reasonable age to start mammogram screening. Risk factor awareness was independent on age groups (p>0.05), but both high education and family history increased the likelihood of postivie answers; the majority knew about a few factors such as aging, pregnancy after age 30, breast feeding for short time, menopause after age of 50, early puberty, and poor personal hygiene. In conclusion, 43.1% of participants had an overall good knowledge of breast cancer with regards to symptoms, risk factors and breast examination. Very highly significant associations (p<0.005) were evident for all groups except for respondents distributed by nationality (p=0.444). Early campaigns for screening the breast should be recommended to eliminate the confusion of wrong perceptions about malignant mammary disease.

• Journal of Information Technology Services
• /
• v.13 no.3
• /
• pp.129-148
• /
• 2014

Generally, the Internet Address Resources Act is intended to protect the public from acts of Internet "cybersquatting", a term used to describe the bad faith, abusive registration of Internet domain names. In determining whether a person has a bad faith intent, a court may consider factors such as, (1) the trademark or other intellectual property rights of the person, if any, in the domain name, (2) the extent to which the domain name consists of the legal name of the person or a name that is otherwise commonly used to identify that person, (3) the person's prior use, if any, of the domain name in connection with the bona fide offering of any goods or services, (4) the person's bona fide noncommercial or fair use of the mark in a site accessible under the domain name, (5) the person's intent to divert consumers from the mark owner's online location to a site accessible under the domain name that could harm the goodwill represented by the mark, either for commercial gain or with the intent to tarnish or disparage the mark, by creating a likelihood of confusion as to the source, sponsorship, affiliation, or endorsement of the site, (6) the person's offer to transfer, sell, or otherwise assign the domain name to the mark owner or any third party for financial gain without having used, or having an intent to use, the domain name in the bona fide offering of any goods or services, or the person's prior conduct indicating a pattern of such conduct.

• Journal of Digital Convergence
• /
• v.12 no.10
• /
• pp.61-71
• /
• 2014

Global commerce is apparently here to bind Korean firms as well as Koreans. The advertising, buying and selling of goods and services recognizes no borders. As a result, enforcing territorially based trademark rights has become ever more challenging. Remote trademark owners who peacefully coexisted in a time before the internet and increasing globalism are now bumping heads. The internet also has made it easier for unscrupulous operators to deceive consumers and divert customers from established businesses by misappropriating trademarks on web-sites and in domain names. U.S. federal courts have been willing to help American businesses halt trademark infringements that reaches outside the United States. This is particularly true for e-business, via the internet, and the trend toward enforcement seems to be in favor of the trademark owner. This article discusses this trend as well as the extraterritorial enforcement of trademark rights by U.S. courts under the Lanham Act. It also offers suggestions for protecting valuable trademark rights worldwide. This paper will contribute to global Korean firms and Koreans who carefully read arguments in this valuable literature.