• Journal of KIISE
• /
• v.43 no.1
• /
• pp.80-86
• /
• 2016

A speech-act is a behavior intended by users in an utterance. Speech-act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and transformation-based learning (TBL). The user's utterance is first classified by SVM that is preferentially applied to categories with a low utterance rate in training data. Next, when an utterance has negative scores throughout the whole of the categories, the utterance is applied to the correction phase by rules. The results from our method were higher performance over the baseline system long with error-reduction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.39-39
• /
• 2012

Data assimilation techniques have received growing attention due to their capability to improve prediction in various areas. Despite of their potentials, applicable software frameworks to probabilistic approaches and data assimilation are still limited because the most of hydrologic modelling software are based on a deterministic approach. In this study, we developed a hydrological modelling framework for sequential data assimilation, namely MPI-OHyMoS. MPI-OHyMoS allows user to develop his/her own element models and to easily build a total simulation system model for hydrological simulations. Unlike process-based modelling framework, this software framework benefits from its object-oriented feature to flexibly represent hydrological processes without any change of the main library. In this software framework, sequential data assimilation based on the particle filters is available for any hydrologic models considering various sources of uncertainty originated from input forcing, parameters and observations. The particle filters are a Bayesian learning process in which the propagation of all uncertainties is carried out by a suitable selection of randomly generated particles without any assumptions about the nature of the distributions. In MPI-OHyMoS, ensemble simulations are parallelized, which can take advantage of high performance computing (HPC) system. We applied this software framework for several catchments in Japan using a distributed hydrologic model. Uncertainty of model parameters and radar rainfall estimates is assessed simultaneously in sequential data assimilation.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.45-55
• /
• 2021

Information obtained through various sensors embedded in a smartphone can be used to identify and analyze user's movements and situations. In this paper, we propose two rule-based motion detection systems that can detect three alphabet motions, 'I', 'S', and 'Z' by analyzing data obtained by the acceleration and gyroscope sensors in a smartphone. First of all, the characteristics of acceleration and angular velocity for each motion are analyzed. Based on the analysis, two rule-based systems are proposed and implemented as an android application and it is used to verify the detection performance for each motion. Two rule-based systems show high recognition rate over 90% for each motion and the rule-based system using ensemble shows better performance than another one.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.67-77
• /
• 2023

This study represents an innovative research conducted in the smart farm environment, developing a deep learning-based disease and pest detection model and applying it to the Intelligent Internet of Things (IoT) platform to explore new possibilities in the implementation of digital agricultural environments. The core of the research was the integration of the latest ImageNet models such as Pseudo-Labeling, RegNet, EfficientNet, and preprocessing methods to detect various diseases and pests in complex agricultural environments with high accuracy. To this end, ensemble learning techniques were applied to maximize the accuracy and stability of the model, and the model was evaluated using various performance indicators such as mean Average Precision (mAP), precision, recall, accuracy, and box loss. Additionally, the SHAP framework was utilized to gain a deeper understanding of the model's prediction criteria, making the decision-making process more transparent. This analysis provided significant insights into how the model considers various variables to detect diseases and pests.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• 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 Satellite, Information and Communications
• /
• v.12 no.3
• /
• pp.22-34
• /
• 2017

The K-DRUM(K-water hydrologic & hydraulic Distributed RUnoff Model), a distributed rainfall-runoff model of K-water, calculates predicted runoff and water surface level of a dam using precipitation data. In order to obtain long-term hydrometeorological information, K-DRUM requires long-term weather forecast. In this study, we built a system providing long-term hydrometeorological information using predicted rainfall ensemble of GloSea5(Global Seasonal Forecast System version 5), which is the seasonal meteorological forecasting system of KMA introduced in 2014. This system produces K-DRUM input data by automatic pre-processing and bias-correcting GloSea5 data, then derives long-term inflow predictions via K-DRUM. Web-based UI was developed for users to monitor the hydrometeorological information such as rainfall, runoff, and water surface level of dams. Through this UI, users can also test various dam management scenarios by adjusting discharge amount for decision-making.

• Atmosphere
• /
• v.28 no.2
• /
• pp.113-121
• /
• 2018

In order to monitor greenhouse gases including $CO_2$, various types of surface-, aircraft-, and satellite-based measurement projects have been conducted. These data help understand the variations of greenhouse gases and are used in atmospheric inverse modeling systems to simulate surface fluxes for greenhouse gases. CarbonTracker is a system for estimating surface $CO_2$ flux, using an atmospheric inverse modeling method, based on only surface observation data. Because of the insufficient surface observation data available for accurate estimation of the surface $CO_2$ flux, additional observations would be required. In this study, a system that assimilates aircraft $CO_2$ measurement data in CarbonTracker (CT2013B) is developed, and the estimated results from this data assimilation system are evaluated. The aircraft $CO_2$ measurement data used are obtained from the Comprehensive Observation Network for Trace gases by the Airliner (CONTRAIL) project. The developed system includes the preprocessor of the raw observation data, the observation operator, and the ensemble Kalman filter (EnKF) data assimilation process. After preprocessing the raw data, the modeled value corresponding spatially and temporally to each observation is calculated using the observation operator. These modeled values and observations are then averaged in space and time, and used in the EnKF data assimilation process. The modeled values are much closer to the observations and show smaller biases and root-mean-square errors, after the assimilation of the aircraft $CO_2$ measurement data. This system could also be used to assimilate other aircraft $CO_2$ measurement data in CarbonTracker.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1229-1237
• /
• 2009

In the long-term care insurance(LTCI) system, the question of how to provide the most appropriate care has become a major issue for the elderly, their family, and for policy makers. To help beneficiaries use LTC services appropriately to their needs of care, National Health Insurance Corporation(NHIC) provide them with the individualized care plan, named the Long-term Care User Guide. It includes recommendations for beneficiaries' most appropriate type of care. The purpose of this study is to develop a recommending system for care plan(Res-CP) in LTCI system. We used data set for Long-term Care User Guide in the 3rd long-term care insurance pilot programs. To develop the model, we tested four models, including a decision-tree model in data-mining, a logistic regression model, and a boosting and boosting techniques in an ensemble model. A decision-tree model was selected to describe the Res-CP, because it may be easy to explain the algorithm of Res-CP to the working groups. Res-CP might be useful in an evidence-based care planning in LTCI system and may contribute to support use of LTC services efficiently.

• Proceedings of the KSME Conference
• /
• 2001.06e
• /
• pp.772-776
• /
• 2001

The flow structures of turbulent shear layer behind oil fences with different tip configurations were investigated experimentally using flow visualization and PIV velocity field measurement. An oil fence was installed in a circulating water channel and the flow structure around the fence tip was mainly analyzed in this experiment. The four tip configurations tested in this experiment are knife edge; semi-circle edge, circular edge and rectangular edge. The 300 instantaneous velocity fields were measured using the single-frame PIV system and they were ensemble averaged to give the mean velocity field and spatial distribution of turbulent statistics. Free stream velocity was fixed at 10ms/sec and the corresponding Reynolds number based on the fence height was Re=4000. As a result, for the oil fence with rectangular edge, the streamwise velocity component was decreased. On the other hand it was increased for the oil fence with circular edge. For all four fences tested in this study, general flow pattern of the lower shear layer is analogous but the upper layer shows difference depending on the tip configurations. The oil fence with circular edge has more diffusive upper shear layer than that of the others. The shear layer of the oil fence with rectangular edge has relatively thin thickness. The oil fence with circular edge was found to be proper shape for tandem fence.