• Journal of Integrative Natural Science
• /
• v.7 no.1
• /
• pp.57-61
• /
• 2014

This study measured the stream data from the several sensors, and stores the database in MapReduce framework environment, and it aims to design system with the small performance and cluster analysis error rate through the KMSVM algorithm. Through the KM-SVM algorithm, the cluster analysis effective data was used for U-health system. In the results of experiment by using 2003 data sets obtained from 52 test subjects, the k-NN algorithm showed 79.29% cluster analysis accuracy, K-means algorithm showed 87.15 cluster analysis accuracy, and SVM algorithm showed 83.72%, KM-SVM showed 90.72%. As a result, the process speed and cluster analysis effective ratio of KM-SVM algorithm was better.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.103-111
• /
• 2011

The research has increased the role of physical activity in promoting health and preventing chronic disease. Estimating algorithm of physical activity energy expenditure was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). COUNT method has been proven through experiments of validity Freedson, Hendelman, Leenders, Yngve was implemented by applying the SVM method. A total of 10 participants(5 males and 5 females aged between 20 and 30 years). The activity protocol consisted of three types on treadmill; participants performed three treadmill activity at three speeds(3, 5, 8 km/h). These activities were repeated four weeks. Customized estimating algorithm for energy expenditure of physical activities were implemented with COUNT and SVM correlation between the data.

• Journal of Korea Water Resources Association
• /
• v.47 no.11
• /
• pp.1095-1105
• /
• 2014

A spatial downscaling method using the Support Vector Machine (SVM) Regression for 25 km Tropical Rainfall Measuring Mission (TRMM) Monthly precipitation is proposed. The nonlinear relationship among hydrometeorological variables and precipitation was effectively depicted by the SVM for predicting downscaled grid precipitation. The accuracy of spatially downscaled precipitation was estimated by comparing with rain gauge data from sixty-four stations and found to be improved than the original TRMM data in overall. Especially the positive bias of the original TRMM data was effectively removed after the downscaling procedure. The spatial distributions of 25 km and 1 km grid precipitation were generally similar, while the local spatial trend was better detected by 1 km grid precipitation. The downscaled grid data derived from the proposed method can be applied in hydrological modelling for higher accuracy and further be studied for developing optimized downscaling method incorporation other regression methods.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.1-8
• /
• 2012

Estimating algorithm of physical activity energy expenditure was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). A total of 33 participants(15 males and 18 females) that performed walking and running on treadmill at 2 ~ 11 km/h speeds(each stage increase 1km/h). Algorithm for energy expenditure of physical activities were implemented with $VO_2$ consumption and SVM correlation between the data. Algorithm consists of three kinds and hip, wrist, waist and hip can be used to apply.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.5 no.1
• /
• pp.27-33
• /
• 2011

Estimating algorithm of physical activity energy expenditure and physical activity intensity was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). A total of 10 participants(5 males and 5 females aged between 20 and 30 years). The ActiGraph(LLC, USA) and Fitmeter(Fit.life, korea) was positioned anterior superior iliac spine on the body. The activity protocol consisted of three types on treadmill; participants performed three treadmill activity at three speeds(3, 5, 8 km/h). Each activity was performed for 7 minutes with 4 minutes rest between each activity for the steady state. These activities were repeated four weeks. Algorithm for METs, kcal and intensity of activities were implemented with ActiGraph and Fitmeter correlation between the data.

• Journal of Wetlands Research
• /
• v.25 no.4
• /
• pp.306-314
• /
• 2023

Stream sediments are an important component of water quality management because they are receptors of various pollutants such as heavy metals and organic matters emitted from upland sources and can be secondary pollution sources, adversely affecting water environment. To effectively manage the stream sediments, identification of primary sources of sediment contamination and source-associated control strategies will be required. We evaluated the performance of machine learning models in identifying primary sources of sediment contamination based on the physico-chemical properties of stream sediments. A total of 356 stream sediment data sets of 18 quality parameters including 10 heavy metal species(Cd, Cu, Pb, Ni, As, Zn, Cr, Hg, Li, and Al), 3 soil parameters(clay, silt, and sand fractions), and 5 water quality parameters(water content, loss on ignition, total organic carbon, total nitrogen, and total phosphorous) were collected near abandoned metal mines and industrial complexes across the four major river basins in Korea. Two machine learning algorithms, linear discriminant analysis (LDA) and support vector machine (SVM) classifiers were used to classify the sediments into four cases of different combinations of the sampling period and locations (i.e., mine in dry season, mine in wet season, industrial complex in dry season, and　industrial complex in wet season). Both models showed good performance in the classification, with SVM outperformed LDA; the accuracy values of LDA and SVM were 79.5% and 88.1%, respectively. An SVM ensemble model was used for multi-label classification of the multiple contamination sources inlcuding landuses in the upland areas within 1 km radius from the sampling sites. The results showed that the multi-label classifier was comparable performance with sinlgle-label SVM in classifying mines and industrial complexes, but was less accurate in classifying dominant land uses (50~60%). The poor performance of the multi-label SVM is likely due to the overfitting caused by small data sets compared to the complexity of the model. A larger data set might increase the performance of the machine learning models in identifying contamination sources.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.1
• /
• pp.87-93
• /
• 2012

The purpose of this study suggests a personalized algorithm of physical activity energy expenditure prediction through comparison and analysis of individual physical activity. The research for a 3-axial accelerometer sensor has increased the role of physical activity in promoting health and preventing chronic disease has long been established. Estimating algorithm of physical activity energy expenditure was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). A total of 10 participants(5 males and 5 females aged between 20 and 30 years). The activities protocol consisted of three types on treadmill; participants performed three treadmill activity at three speeds(3, 5, 8 km/h). These activities were repeated four weeks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.5-5
• /
• 2015

현재 우리나라에서 지상관측장비인 AWS(Automatic Weather System)와 ASOS(Automated Synoptic Observing System)기구가 한반도내 668개 지점에서 운영되고 있다. 이러한 장비는 지상관측장비로 하나의 지점에서 측정된 기상변량들이 특정 영역의 대푯값으로 사용되어지고 있다. 기존의 다양한 지점 단위의 수문 모형에서는 지상관측소를 통한 관측값을 적용하기에 어려움 없이 적절한 결과를 도출할 수 있었다. 컴퓨터의 발달로 인하여 복잡한 물리적 현상을 공간적으로 분석할 수 있는 모형의 구동이 가능해짐에 따라서 수문 분야에서도 다양한 분포형 해석 모형이 활발하게 개발 및 적용되고 있다. 지점 관측 자료는 공간적인 연속성을 반영하지 못하는 한계로 인하여 지점 관측자료를 이용한 공간자료의 생성 기법들이 사용되어지고 있지만 자연계에서 나타나는 정확한 공간적 현상을 재현해주지 못하는 문제점이 존재한다. 이러한 지점 관측의 한계를 해결하기 위하여 공간적인 관측이 가능한 레이더와 위성관측과 같은 원격 관측 장비들이 개발되어 공간적으로 연속성을 갖는 기상변량의 취득이 가능하여졌다. TRMM 강우자료는 지구 전체를 0.25도 약 25km 공간해상도를 갖으며 3시간 간격으로 제공되고 있다. 유역단위의 수문모형에 적용하기에 TRMM 강수자료의 공간해상도는 너무 커서 직접적인 적용에 어려움이 있다. 이러한 점에서 TRMM 자료의 상세화 기법을 통하여 수문모형에 적용이 가능한 1km 이하의 고해상도 자료를 생산하는 연구들이 진행되고 있다. 이러한 상세화 방법은 최종적으로 도출하고자 하는 공간해상도를 갖는 대체 변량(지표면 온도, 고도, 식생, 해수면 기압, 상대 습도, 대기온도, 풍향 등)을 이용하여 회귀분석의 형태로 분석이 이루어지고 있다. 그러나 대체 변량을 통해 도출된 상세화된 TRMM 강우는 간접적인 추정으로 인하여 정확한 결과의 도출에는 한계가 있을 것으로 판단된다. 이러한 점에서 본 연구에서는 한반도내 지상 관측값을 공간적 자료로 변환하여 주는데 효과적으로 평가받는 PRISM 모형에 적용하여 기존 SVM 모형을 통한 TRMM 상세화 결과가 갖는 정확성을 평가해 보고 지점 관측자료의 보간 기법의 평가에 TRMM 자료를 활용하는 방안에 대해 평가해 보고자 한다.

• Atmosphere
• /
• v.20 no.4
• /
• pp.415-426
• /
• 2010

A Land cover map over East Asian region (Kongju national university Land Cover map: KLC) is classified by using support vector machine (SVM) and evaluated with ground truth data. The basic input data are the recent three years (2006-2008) of MODIS (MODerate Imaging Spectriradiometer) NDVI (normalized difference vegetation index) data. The spatial resolution and temporal frequency of MODIS NDVI are 1km and 16 days, respectively. To minimize the number of cloud contaminated pixels in the MODIS NDVI data, the maximum value composite is applied to the 16 days data. And correction of cloud contaminated pixels based on the spatiotemporal continuity assumption are applied to the monthly NDVI data. To reduce the dataset and improve the classification quality, 9 phenological data, such as, NDVI maximum, amplitude, average, and others, derived from the corrected monthly NDVI data. The 3 types of land cover maps (International Geosphere Biosphere Programme: IGBP, University of Maryland: UMd, and MODIS) were used to build up a "quasi" ground truth data set, which were composed of pixels where the three land cover maps classified as the same land cover type. The classification results show that the fractions of broadleaf trees and grasslands are greater, but those of the croplands and needleleaf trees are smaller compared to those of the IGBP or UMd. The validation results using in-situ observation database show that the percentages of pixels in agreement with the observations are 80%, 77%, 63%, 57% in MODIS, KLC, IGBP, UMd land cover data, respectively. The significant differences in land cover types among the MODIS, IGBP, UMd and KLC are mainly occurred at the southern China and Manchuria, where most of pixels are contaminated by cloud and snow during summer and winter, respectively. It shows that the quality of raw data is one of the most important factors in land cover classification.

• Journal of Astronomy and Space Sciences
• /
• v.40 no.4
• /
• pp.199-215
• /
• 2023

The Korea Pathfinder Lunar Orbiter (KPLO), the first South Korea lunar exploration probe, successfully arrived at the Moon on December, 2022 (UTC), following a 4.5-month ballistic lunar transfer (BLT) trajectory. Since the launch (4 August, 2022), the KPLO magnetometer (KMAG) has carried out various observations during the trans-lunar cruise phase and a 100 km altitude lunar polar orbit. KMAG consists of three fluxgate magnetometers capable of measuring magnetic fields within a ± 1,000 nT range with a resolution of 0.2 nT. The sampling rate is 10 Hz. During the originally planned lifetime of one year, KMAG has been operating successfully while performing observations of lunar crustal magnetic fields, magnetic fields induced in the lunar interior, and various solar wind events. The calibration and offset processes were performed during the TLC phase. In addition, reliabilities of the KMAG lunar magnetic field observations have been verified by comparing them with the surface vector mapping (SVM) data. If the KPLO's mission orbit during the extended mission phase is close enough to the lunar surface, KMAG will contribute to updating the lunar surface magnetic field map and will provide insights into the lunar interior structure and lunar space environment.