• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Journal of Biosystems Engineering
• /
• v.25 no.2
• /
• pp.97-106
• /
• 2000

To develop the grain moisture meter using microwave free space transmission technique, a 10.5GHz microwave signal with the power of 11mW generated by an oscillar with a dielectric resonator is transmitted to an isolator and radiated from a transmitting $2{\times}2$ microstrip patch array antenna into the sample holder filled with the 12 to 26%w.b. of Korean Hwawung paddy rice. the microwave signal, attenuated through the grain with moisture, is collected by a receiving $2{\times}2$ microstrip patch array antenna and detected using a Shottky diode with excellent high frequency characteristic. A pair of light and simple microstrip patch array antenna for measurement of grain moisture content is designed and implemented on atenflon substrate with trleative dielectric constant of 2.6 and thickness of 0.54 by using Ensemble ver. 4.02 software. The aperture of microstrip patch arrays is 41 mm width and 24mm high. The characteristics of microstrip patch antenna such as grain. return loss, and bandwidth are 11.35dBi, -38dB and 0.35GHz($50^{\circ}$ at far-field pattern of E and H plane. The width of the sample holder is large enough to cover the signal between the antennas temperature and bulk density respectively. The calibration model for measurement of grain moisture content is proposed to reduce the effects of fluectuations in bulk density and temperature which give serious errors for the measurements . From the results of regression analysis using the statistically analysis method, the moisture content of grain samples (MC(%)) is expressed in terms of the output voltage(v), temperature (t), and bulk density of samples(${\rho}b$)as follows ;$$MC(%)\;=\;(-3.9838{\times}10^{-8}{\times}v^{3}+8.023{\times}10^{-6}{\times}v^{2}-0.0011{\times}v-0.0004{\times}t+0.1706){\frac{1}{{\rho}b}}{\times}100$ Its determination coefficient, standard error of prediction(SEP) and bias were found to be 0.9855, 0.479%w.b. and -0.0.369 %w.b. respectively between measured and predicted moisture contents of the grain samples.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.5
• /
• pp.944-958
• /
• 2011

Soil hydraulic properties such as hydraulic conductivity or water retention which are costly to measure can be indirectly generated by soil pedotransfer function (PTF) using easily obtainable soil data. The field soil structure description which is routinely recorded could also be used in PTF as an input to reduce the uncertainty. The purposes of this study were to use qualitative morphological soil structure descriptions and soil structural index into PTF and to evaluate their contribution in the prediction of soil hydraulic properties. We transformed categorical morphological descriptions of soil structure into quantitative values using categorical principal component analysis (CATPCA). This approach was tested with a large data set from the US National Pedon Characterization database with the aid of a categorical regression tree analysis. Six different PTFs were used to predict the saturated hydraulic conductivity and those results were averaged to quantify the uncertainty. Quantified morphological description was successively used in multiple linear regression approach to predict the averaged ensemble saturated conductivity. The selected stepwise regression model with only the transformed morphological variables and structural index as predictors predicted the $K_{sat}$ with $r^2$ = 0.48 (p = 0.018), indicating the feasibility of CATPCA approach. In a regression tree analysis, soil structure index and soil texture turned out to be important factors in the prediction of the hydraulic properties. Among structural descriptions size class turned out to be an important grouping parameter in the regression tree. Bulk density, clay content, W33 and structural index explained clusters selected by a two step clustering technique, implying the morphologically described soil structural features are closely related to soil physical as well as hydraulic properties. Although this study provided relatively new method which related soil structure description to soil structure index, the same approach should be tested using a datasets containing the actual measurement of hydraulic properties. More insight on the predictive power of soil structure index to estimate hydraulic properties would be achieved by considering measured the saturated hydraulic conductivity and the soil water retention.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.12 no.3
• /
• pp.170-177
• /
• 2007

In this study, the long-term predictability of El Nino and La Nina events of Pusan National University Coupled General Circulation Model(PNU/CME CGCM) developed from a Research and Development Grant funded by Korea Meteorology Administration(KMA) was examined in terms of the correlation coefficients of the sea surface temperature between the model and observation and skill scores at the tropical Pacific. For the purpose, long-term global climate was hindcasted using PNU/CME CGCM for 12 months starting from April, July, October and January(APR RUN, JUL RUN, OCT RUN and JAN RUN, respectively) of each and every years between 1979 and 2004. Each 12-month hindcast consisted of 5 ensemble members. Relatively high correlation was maintained throughout the 12-month lead hindcasts at the equatorial Pacific for the four RUNs starting at different months. It is found that the predictability of our CGCM in forecasting equatorial SST anomalies is more pronounced within 6-month of lead time, in particular. For the assessment of model capability in predicting El Nino and La Nina, various skill scores such as Hit rates and False Alarm rate are calculated. According to the results, PNU/CME CGCM has a good predictability in forecasting warm and cold events, in spite of relatively poor capability in predicting normal state of equatorial Pacific. The predictability of our CGCM was also compared with those of other CGCMs participating DEMETER project. The comparative analysis also illustrated that our CGCM has reasonable long-term predictability comparable to the DEMETER participating CGCMs. As a conclusion, PNU/CME CGCM can predict El Nino and La Nina events at least 12 months ahead in terms of NIino 3.4 SST anomaly, showing much better predictability within 6-month of leading time.

• 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.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.