• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.3
• /
• pp.91-102
• /
• 2012

As the basis of the environmental ecological river management, this research developed a method of habitat classification using imagery information to understand a distribution characteristics of fish living in a natural river. First, topographic survey and investigation of discharge and water temperature were carried out to analyze hydraulic characteristics of fish habitat, and the unmanned aerial photography was applied to acquire river imagery at the observation time. Riffle, pool, and glide regions were selected as river habitat to analyze fish distribution characteristics. Analysis showed that the standard deviation of RGB on the riffle is higher than pool and glide because of fast stream flow. From the classification accuracy estimation on riffle region according to resolution and kernel size using the characteristics of standard deviation of RGB, the highest classification accuracy was 77.17% for resolution with 30cm and kernel size with 11. As the result of water temperature observation on pool and glide using infrared camera, they were $19.6{\sim}21.3^{\circ}C$ and $15.5{\sim}16.5^{\circ}C$ respectively with the differences of $4{\sim}5^{\circ}C$. Therefore it is possible to classify pool and glide region using the infrared photography information. The habitat classification to figure out fish distribution can be carried out more efficiently, if unmanned aerial photography system with RGB and infrared band is applied.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.2
• /
• pp.37-42
• /
• 2017

In this study, we were carried out the classification of Korea's climate zone. $K{\ddot{o}}ppen$ climate classification and Warmth Index were used for classification of climate zone and we have predicted how the climate zone will be changed during the 21st century. Especially, $K{\ddot{o}}ppen$ climate classification is one of the most widely used method in the world. The climate data used monthly climate normal data (1981-2010) and future climate data (2051-2060 and 2091-2100) by considering RCP 8.5 scenarios, which was made from geospatial climate models at 1km grid cell estimated. In conclusion, the temperature will rise steadily and the climate zone will be simplified in the future as a result.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11b
• /
• pp.878-881
• /
• 2010

For better diagnosis and prescription in Korean traditional medicine, Lee Je-Ma (1837-1900) created Sasang Constitution classification which was divided into four groups of Taeyangin, Soyangin, Taeumin and Soumin based on both body shape and natural disposition. The purpose of this study was to investigate the characteristics of facial skin parameters (hydration, lipid and pH) on forehead and cheek according to Sasang Constitution classifications of Taeumin, Soyangin and Soumin in Korean. Eighty-nine Korean female subjects were recruited for this study and the average age of them was 19.9${\pm}$0.84 years. The four groups by the Sasang Constitution were classified by questionnaire for the Sasang Constitution classification proposed by Kyung-Hee Oriental Medicine Hospital. Consequently, thirty-eight (42.7%) among the subjects were grouped into Soumin, twenty-nine (32.6%) into Taeumin, twenty (22.5%) into Soyangin and two (2%) into Taeyangin. Taeyangin group was excluded from statistical analysis due to small subjects. Hydration, lipid and pH parameters on forehead and cheek were measured by using non-invasive instruments of Corneometer (CM 825, Schwarzhaup, Germany), Sebumeter (SM 815, Schwarzhaup, Germany) and Skin-pH-meter (pH 905, Schwarzhaup, Germany), respectively. The measurements by the same investigator were performed under standardized condition with a room temperature of $21^{\circ}C$ and a humidity level of 40% to 50%. As a result, hydration (F=25.481, p=.000), lipid (F=5.753, p=.005) and pH (F=5.010, p=.009) of the forehead skin showed significant differences in the order of Taeumin, Soyangin and Soumin. Hydration (F=23.216, p=.000), lipid (F=6.898 p=.002) and pH (F=5.070, p=.008) of the cheek skin showed significant differences in the order of Taeumin, Soyangin and Soumin. In conclusion, facial skin surface seemed to be dependent on Sasang Constitution classification in Korean. These findings indicated that Sasang Constitution classification might be an useful esthetic treatment for caring facial skin in the future.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.30 no.6
• /
• pp.128-140
• /
• 2003

The purpose of this research was to present characteristics for the classification of biotopes and classification method of biotopes as basic data for ecological landscape planning in Metropolitan Daegu. The results of this study were as follows. 1) The study identified fifteen characteristics for classification of biotopes. Ecological landscape characteristics were divided into structural and functional factors. There are six structural factors such an inclination, and nine functional factors such as temperature. 2) The study area was separated into sixty eight biotope types. For example, an industrial district was divided into two biotope types: a biotope type of an industrial district with abundant green space, and a biotope type of an industrial district with scarce green space. 3) In the result of cluster analysis using the average linkage method between groups, biotope groups were divided into fifteen clusters and biotope groups were divided into seven clusters. Each cluster was named according to the features of a descriptive statistics analysis. For example, cluster 8 was identified as a biotope type with an impermeable pavement rate of more than 90 percent and an afforestation rate under 10 percent. 4) Fifteen biotope groups were converted to land use patterns for remote application and utilization of urban biotope in city planning. Biotope groups of a building area beyond an intermediate floor with an afforestation rate under 20-30 percent was converted to a land use pattern such as a tall apartment complex or commercial district. When examining the characteristics that were established in this research, there was a limit to achieve the objective of grade-classification because of a lack of related basic data. The research of landscape ecological characteristics for the classification of biotopes could not be completed due to a lack of time and resources, thus the study of ecological landscape characteristics will be accomplished over time.

• Journal of the Korean earth science society
• /
• v.22 no.2
• /
• pp.138-146
• /
• 2001

The land cover over Korean peninsula was classified using a multi-temporal NOAA/AVHRR (Advanced Very High Resolution Radiometer) data. Four types of phenological data derived from the 10-day composited NDVI (Normalized Differences Vegetation Index), maximum and annual mean land surface temperature, and topographical data were used not only reducing the data volume but also increasing the accuracy of classification. Self organizing feature map (SOFM), a kind of neural network technique, was used for the clustering of satellite data. We used a decision tree for the classification of the clusters. When we compared the classification results with the time series of NDVI and some other available ground truth data, the urban, agricultural area, deciduous tree and evergreen tree were clearly classified.

• ETRI Journal
• /
• v.39 no.1
• /
• pp.87-96
• /
• 2017

Ultrasonic surgical devices are routinely used for surgical procedures. The incision and coagulation of tissue generate a temperature of $40^{\circ}C-150^{\circ}C$ and depend on the controllable output power level of the surgical device. Recently, research on the classification of grasped tissues to automatically control the power level was published. However, this research did not consider the specific characteristics of the surgical device, tissue denaturalization, and so on. Therefore, this research proposes a robust algorithm that simulates noise to resemble real situations and classifies tissue using conventional classifier algorithms. In this research, the bioimpedance spectrum for six tissues (liver, large intestine, kidney, lung, muscle, and fat) is measured, and five classifier algorithms are used. A signal-to-noise ratio of additive white Gaussian noise diversifies the testing sets, and as a result, each classifier's performance exhibits a difference. The k-nearest neighbors algorithm shows the highest classification rate of 92.09% (p < 0.01) and a standard deviation of 1.92%, which confirms high reproducibility.

• Journal of Environmental Health Sciences
• /
• v.14 no.1
• /
• pp.33-38
• /
• 1988

Natural mineral water is generally quite different from ordinary drinking water due to its original nature and various properties. The complexity of natural mineral water requires, therefore, not only to identify its nature and proper characteristics, but also to classify them by a reasonable scientific basis of comparison. The study was concentrated on a possible classification technique to natural mineral waters by their constitutions and physico-ehemical properties. The classification was carried out by the computation of such numerical parameters as ionic equivalent percentage, electrolytic conductance or mobility, ionic molecular weight, molecular concentration, equivalent conductivity and degree of ionization in consideration of the determinative criteria as follows -particular single element or molecule -major components of natural waters as bicarbonate, sulphate, chloride,caloride, calcium, magnesium, and sodium -moleculat concentration related to blood osmotic pressure -water temperature at emergence from spring -contents of free carbon dioxide (CO2) -pH value of water -total dissolved solids or salts (NaCl) The results obtained proved out to be clearly distinguhhable from ordinary drinking water as far as concern natural mineral water as an example on the subject -simple water -bicarbonate-predominating water -cold spring -carbonated-non gaseous water -weak alkaline water -non saline water Putting these various results together, the sample turned out to be a kind of natural mineral water that can be used as a drinking water if microbiologically safe.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.80-89
• /
• 2020

Out - of - distribution (OOD) samples are frequently encountered when deploying a classification model in plenty of real-world machine learning-based applications. Those samples are normally sampling far away from the training distribution, but many classifiers still assign them high reliability to belong to one of the training categories. In this study, we address the problem of removing OOD examples by estimating marginal density estimation using variational autoencoder (VAE). We also investigate other proper methods, such as temperature scaling, Gaussian discrimination analysis, and label smoothing. We use Chonnam National University (CNU) weeds dataset as the in - distribution dataset and CIFAR-10, CalTeach as the OOD datasets. Quantitative results show that the proposed framework can reject the OOD test samples with a suitable threshold.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.21-29
• /
• 2018

In many companies handling flammable liquids, explosion-proof electrical equipment have been installed according to the Korean Industrial Standards (KS C IEC 60079-10-1). In these standards, hazardous area for explosive gas atmospheres has to be classified by the evaluation of the evaporation rate of flammable liquid leakage. The evaporation rate is an important factor to determine the zones classification and hazardous area distance. However, there is no systematic method or rule for the estimation of evaporation rate in these standards and the first principle equations of a evaporation rate are very difficult. Thus, it is really hard for industrial workplaces to employ these equations. Thus, this problem can trigger inaccurate results for evaluating evaporation range. In this study, empirical models for estimating an evaporation rate of flammable liquid have been developed to tackle this problem. Throughout the sensitivity analysis of the first principle equations, it can be found that main factors for the evaporation rate are wind speed and temperature and empirical models have to be nonlinear. Polynomial regression is employed to build empirical models. Methanol, benzene, para-xylene and toluene are selected as case studies to verify the accuracy of empirical models.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2014.11a
• /
• pp.214-215
• /
• 2014

Recently, Russia decided to export an annual 7.5 million tons of natural gas to Korea over 30 years from 2015, as also deal with China, planed to build a pipeline connecting Siberia to Shandong Peninsula about 4000km. Risk management is required depending on the project in extreme cold weather, because it is concerned about the behavior of the seasonal changes in soil temperature and the strain of pipe according to the long-distance pipeline construction. The plan of data management shall be prepared in parallel for a sophisticated risk management, because a data is massive scale and it is generated/accumulated in real time. Therefore, this research is aimed to classify a data items in engineering stage of pipeline by previous studies for managing a generated data depending on the detail works in extreme cold weather. We expect to be provided the foundation of an efficient classification system of a generated data from the pipeline project life cycle.