• 한국물환경학회지
• /
• 제24권5호
• /
• pp.611-617
• /
• 2008

It is necessary to analysis the data characteristics of discharge and water quality for efficient water resources management, aggressive alternatives to inundation by flood and various water pollution accidents, the basic information to manage water quality in lakes and to make environmental policy. Therefore, the present study applied Self-Organizing Map (SOM) showing excellent performance in classifying patterns with weights estimated by self-organization. The result revealed five patterns and TOC versus rainfall-storage data according to the respective patterns were depicted in two-dimensional plots. The visualization presented better understanding of data distribution pattern. The result in the present study might be expected to contribute to the modeling procedure for data prediction in the future.

• 설비공학논문집
• /
• 제13권6호
• /
• pp.497-504
• /
• 2001

A study to improve the accuracy of a map-based compressor model with experiment was performed. Corrections on the effects of suction gas superheat and heat leakage from a compressor shell are required to apply the compressor amp model based on the empirical performance data(map) of compressor manufacturers to the actual system. So experiments to assess the effects of superheat and hat leakage were performed and the corrected equations were made. Compressors and refrigerant used in the experiment were the high pressure type rotary compressor and R-22, experiments were performed by compressor calorimeter. From the experiment, a volumetric efficiency correction factor$(F_ν)$ showed the value of 0.77, slightly higher than 0.75 proposed by Dabiri and Rice for low pressure type reciprocating compressor, and the heat leakage from the compressor shell turned out to be a factor that influenced the discharged mass flow rate. The relation between heat leakage of compressor shell and the variation of discharged mass flow rate from compressor was considered in compressor map modeling as an empirical function. With this function, the prediction accuracy of compressor model in system conditions was improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2381-2399
• /
• 2019

Traditional recommendation algorithms on Collaborative Filtering (CF) mainly focus on the rating prediction with explicit ratings, and cannot be applied to the top-N recommendation with implicit feedbacks. To tackle this problem, we propose a new collaborative filtering approach namely Maximize MAP with Matrix Factorization (MFMAP). In addition, in order to solve the problem of non-smoothing loss function in learning to rank (LTR) algorithm based on pairwise, we also propose a smooth MAP measure which can be easily implemented by standard optimization approaches. We perform experiments on three different datasets, and the experimental results show that the performance of MFMAP is significantly better than other recommendation approaches.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.777-783
• /
• 2022

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

• 전기학회논문지
• /
• 제56권9호
• /
• pp.1556-1560
• /
• 2007

Energized power transformers in substations make unwelcome noises which propagate to nearby residential areas. As the excessive noise level become a target of public grievance than ever, utilities are seeking solutions to it. This paper introduce a power transformer noise prediction program which can give utilities effective solutions. Once a noise source is given, the program calculates the propagated noise level at certain points. The estimated result is rendered as noise contour map. To validate the accuracy of the program, the predicted noises are compared to measured one in real substations and proven to be acceptable within a margin of 5 percent.

• 한국농공학회논문집
• /
• 제47권6호
• /
• pp.37-45
• /
• 2005

Almost every year, Korea has been suffered from serious damages of lives and properties, due to landslides that are triggered by heavy rains in monsoon season. In this paper, we systematized the physically based landslide prediction model which consisted of 3 parts, infinite slope stability analysis model, groundwater flow model and soil depth model. To evaluate its applicability to the prediction of landslides, the data of actual landslides were plotted on the predicted areas on the GIS map. The matching rate of this model to the actual data was $84.8\%$. And the relation between hydrological and land form factors and potential landslide were analyzed.

• 대한토목학회논문집
• /
• 제42권1호
• /
• pp.35-44
• /
• 2022

V_S30지도는 부지증폭을 나타내는 주요 변수로 임의의 부지에서 지반운동을 예측하는 ShakeMap의 핵심 변수로 사용된다. 하지만, 한반도의 지질특성과 지형특성을 고려하는 V_S30지도는 아직 제시된 적이 없다. 이번 연구에서는 지질과 지형을 고려하는 V_S30지도를 작성하기 위해 전단파 속도 주상도로부터 계산 또는 추정된 1,101개의 V_S30과 한반도 광범위 지질, 지형정보 레이어를 수집하였다. 이러한 데이터와 일반선형회귀분석 방법을 사용하여 V_S30 추정 모델을 개발하였다. 모델은 지질분류에 따라 매립지, 신생대 제4기 퇴적층, 중생대 그룹, 선캄브리아기와 해양층으로 구분된 후 지형정보의 함수로 제안되었다. 지도의 해상도는 기상청에서 기존에 진도추정을 위한 ShakeMap 구동에 사용하는 미국지질조사국(USGS)의 지도의 2배로 하였다. 그 결과, 프락시 기반 V_S30지도의 대수로그 잔차의 표준편차는 0.233으로 USGS의 V_S30 지도의 표준편차인 0.387보다 낮은 수치를 보인다. 본 연구에서 개발한 V_S30지도를 사용한다면 ShakeMap의 불확실성이 줄어들 것으로 기대된다.

• 한국소음진동공학회논문집
• /
• 제20권6호
• /
• pp.555-561
• /
• 2010

Predicted noise level has been used to assess the annoyance response since noise map was generalized and being the normal method to assess the environmental noise. Unfortunately using predicted noise level to derive the annoyance prediction curve caused some problems. The data have to be grouped manually to use the annoyance prediction curve. The aim of this paper is to propose the method to handle the predicted noise level and the survey data for annoyance prediction curve. This paper used the percentage of persons annoyed(%A) and the percentage of persons highly annoyed as the descriptor of noise annoyance in a population. The logistic regression method was used for deriving annoyance prediction curve. It is concluded that the method of dichotomizing data and logistic regression was suitable to handle the predicted noise level and survey data.

• 풍력에너지저널
• /
• 제9권4호
• /
• pp.32-39
• /
• 2018

In this study, the annual power production of a wind farm according to obstacles and wind data was predicted for the Garyeok-do wind farm in the Saemangeum area. The Saemangeum Garyeok-do wind farm was built in December 2014 by the Korea Rural Community Corporation. Currently, two 1.5 MW wind turbines manufactured by Hyundai Heavy Industries are installed and operated. Automatic weather station data from 2015 to 2017 was used as wind data to predict the annual power production of the wind farm for three consecutive years. For prediction, a commercial computational fluid dynamics tool known to be suitable for wind energy prediction in complex terrain was used. Predictions were made for three cases with or without considering obstacles and wind direction errors. The study found that by considering both obstacles and wind direction errors, prediction errors could be substantially reduced. The prediction errors were within 2.5 % or less for all three years.

• Geomechanics and Engineering
• /
• 제36권5호
• /
• pp.441-453
• /
• 2024

Sinkhole subsidence and collapse is a common geohazard often formed in karst areas such as the state of Florida, United States of America. To predict the sinkhole occurrence, we need to understand the formation mechanism of sinkhole and its karst hydrogeology. For this purpose, investigating the factors affecting sinkholes is an essential and important step. The main objectives of the presenting study are (1) the development of a machine learning (ML)-based model, namely C5.0 decision tree (C5.0 DT), for the prediction of sinkhole susceptibility, which accounts for sinkhole/subsidence inventory and sinkhole contributing factors (e.g., geological/hydrogeological) and (2) the construction of a regional-scale sinkhole susceptibility map. The study area is east central Florida (ECF) where a cover-collapse type is commonly reported. The C5.0 DT algorithm was used to account for twelve (12) identified hydrogeological factors. In this study, a total of 1,113 sinkholes in ECF were identified and the dataset was then randomly divided into 70% and 30% subsets for training and testing, respectively. The performance of the sinkhole susceptibility model was evaluated using a receiver operating characteristic (ROC) curve, particularly the area under the curve (AUC). The C5.0 model showed a high prediction accuracy of 83.52%. It is concluded that a decision tree is a promising tool and classifier for spatial prediction of karst sinkholes and subsidence in the ECF area.