• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제49권4호
• /
• pp.246-255
• /
• 2000

This paper deals with a novel full digital control method of the three-phase PWM inverter for UPS. The voltage and current of output filter capacitor as state variables are the feedback control input. In addition, a double deadbeat control consisting of a d-q current minor loop and a d-q voltage major loop, both with precise decoupling, have been developed. The switching pulse width modulation based on SVM is adopted so that the capacitor current should be exactly equal to its reference current. In order to compensate the calculation time delay, the predictive control is achieved by the current·voltage observer. The load prediction is used to compensate the load disturbance by disturbance observer with deadbeat response. The experimental results show that the proposed system offers an output voltage with THD less than 2% at a full nonlinear load.

• Korean Chemical Engineering Research
• /
• 제61권4호
• /
• pp.523-541
• /
• 2023

3D 프린터의 활용이 높아짐에 따라 발생하는 화학물질에 대한 노출 빈도가 증가하고 있다. 그러나 3D 프린팅 발생 화학물질의 독성 및 유해성에 대한 연구는 미비하며, 분자 구조 데이터의 결측치로 인해 in silico 기법을 사용한 독성예측 연구는 저조한 실정이다. 본 연구에서는 화학물질의 분자구조 정보를 나타내는 주요 분자표현자의 결측치를 보간하여 3D 프린팅의 독성 및 유해성을 예측한 Data-centric QSAR 모델을 개발하였다. 먼저 MissForest 알고리즘을 사용해 3D 프린팅으로 발생되는 유해물질의 분자표현자 결측치를 보완하였으며, 서로 다른 4가지 기계학습 모델(결정트리, 랜덤포레스트, XGBoost, SVM)을 기반으로 Data-centric QSAR 모델을 개발하여 생물 농축 계수(Log BCF)와 옥탄올-공기분배계수(Log Koa), 분배계수(Log P)를 예측하였다. 또한, 설명 가능한 인공지능(XAI) 방법론 중 TreeSHAP (SHapley Additive exPlanations) 기법을 활용하여 Data-centric QSAR 모델의 신뢰성을 입증하였다. MissForest 알고리즘 기반 결측지 보간 기법은, 기존 분자구조 데이터에 비하여 약 2.5배 많은 분자구조 데이터를 확보할 수 있었다. 이를 바탕으로 개발된 Data-centric QSAR 모델의 성능은 Log BCF, Log Koa와 Log P를 각각 73%, 76%, 92% 의 예측 성능으로 예측할 수 있었다. 마지막으로 Tree-SHAP 분석결과 개발된 Data-centric QSAR 모델은 각 독성치와 물리적으로 상관성이 높은 분자표현자를 통하여 선택함을 설명할 수 있었고 독성 정보에 대한 높은 예측 성능을 확보할 수 있었다. 본 연구에서 개발한 방법론은 다른 프린팅 소재나 화학공정, 그리고 반도체/디스플레이 공정에서 발생 가능한 오염물질의 독성 및 인체 위해성 평가에 활용될 수 있을 것으로 사료된다.

• 제어로봇시스템학회논문지
• /
• 제20권12호
• /
• pp.1259-1266
• /
• 2014

Road signs provide important safety information about road and traffic conditions to drivers. Road signs include not only common traffic signs but also warning information regarding unexpected obstacles and road constructions. Therefore, accurate detection and identification of road signs is one of the most important research topics related to safe driving. In this paper, we propose a 3-D vision technique to automatically detect and track road signs in a video sequence which is acquired from a stereo vision camera mounted on a vehicle. First, color information is used to initially detect the sign candidates. Second, the SVM (Support Vector Machine) is employed to determine true signs from the candidates. Once a road sign is detected in a video frame, it is continuously tracked from the next frame until it is disappeared. The 2-D position of a detected sign in the next frame is predicted by the 3-D motion of the vehicle. Here, the 3-D vehicle motion is acquired by using the 3-D pose information of the detected sign. Finally, the predicted 2-D position is corrected by template-matching of the scaled template of the detected sign within a window area around the predicted position. Experimental results show that the proposed method can detect and track many types of road signs successfully. Tracking comparisons with two different methods are shown.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권12호
• /
• pp.7473-7482
• /
• 2013

The G-protein coupled receptor 87 (GPR87) is a recently discovered orphan GPCR which means that the search of their endogenous ligands has been a novel challenge. GPR87 has been shown to be overexpressed in squamous cell carcinomas (SCCs) or adenocarcinomas in lungs and bladder. The 3D structure of GPR87 was here modeled using two templates (2VT4 and 2ZIY) by a threading method. Functional assignment of GPR87 by SVM revealed that along with transporter activity, various novel functions were predicted. The 3D structure was further validated by comparison with structural features of the templates through Verify-3D, ProSA and ERRAT for determining correct stereochemical parameters. The resulting model was evaluated by Ramachandran plot and good 3D structure compatibility was evidenced by DOPE score. Molecular dynamics simulation and solvation of protein were studied through explicit spherical boundaries with a harmonic restraint membrane water system. A DRY-motif (Asp-Arg-Tyr sequence) was found at the end of transmembrane helix3, where GPCR binds and thus activation of signals is transduced. In a search for better inhibitors of GPR87, in silico modification of some substrate ligands was carried out to form polar interactions with Arg115 and Lys296. Thus, this study provides early insights into the structure of a major drug target for SCCs.

• 한국농공학회논문집
• /
• 제64권1호
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2014년도 전력전자학술대회 논문집
• /
• pp.291-292
• /
• 2014

The three-phase four-leg voltage source inverter (VSI) topology can be an interesting option for the three phase-four wire system. With an additional leg, this topology can achieve superior performance with unbalanced and/or nonlinear load. This paper proposes a new hybrid controller which combines PI controller and resonant controller in synchronous frame for three phase four leg inverter. The hybrid controller is simple in structure and easy to implement. The performance of proposed controller is verified by the experiments and compared with that of the conventional PI controller.

• 문화기술의 융합
• /
• 제9권3호
• /
• pp.727-730
• /
• 2023

전세계적으로 온실가스 및 미세먼지 저감을 위한 탄소중립 정책에 따라 전기차보급이 확대될 전망이다. 전기자동창의 운용은 열악한 환경에서 사용되고 충전과 방전 등을 거듭할수록 에너지밀도가 낮아지고 내부분리막의 손상등의 이유로 건전성이 떨어짐에 따라 차량의 주행거리가 줄고, 충전 속도가 느려지는 이유로 대략 5~10년 정도 사용한 배터리들은 폐배터리로 분류하며 이 같은 이유로 배터리 화재 및 폭발 등의 위험성이 높아 지게 됩에 따라 배터리의 진단 및 SOH의 추정이 필수적이라 할 수 있다. 배터리 SOH추정은 매우 중요한 요소로 현재는 배터리 충방전을 반복하면서 소요되는 시간, 온도, 전압을 측정하여 배터리의 상태를 평가하는데 정확도가 낮다. 불안정한 폐배터리를 다수의 반복적 충전과 방전을 통해 진단하는 과정에서 화재 및 폭발의 취약점을 보완하여 신뢰성이 높은 폐배터리의 상태데이터를 취득할 수 있는 기반을 마련하고 본 논문에서는 리튬이온 배터리의 SOH예측을 위해 테슬라 폐배터리를 이용한 방전 용량 측정을 바탕으로 획득한 데이터를 서포트 벡터 머신 기반으로 예측하고자 하였다.

• International Journal of Computer Science & Network Security
• /
• 제21권3호
• /
• pp.41-47
• /
• 2021

Detection of protein-protein interactions (PPIs) remains essential for the development of therapies against diseases. Experimental studies to detect PPI are longer and more expensive. Today, with the availability of PPI data, several computer models for predicting PPIs have been proposed. One of the big challenges in this task is feature extraction. The relevance of the information extracted by some extraction techniques remains limited. In this work, we first propose an extraction method based on correlation relationships between the physicochemical properties of amino acids. The proposed method uses a correlation matrix obtained from the hydrophobicity and hydrophilicity properties that it then integrates in the calculation of the bigram. Then, we use the SVM algorithm to detect the presence of an interaction between 2 given proteins. Experimental results show that the proposed method obtains better performances compared to the approaches in the literature. It obtains performances of 94.75% in accuracy, 95.12% in precision and 96% in sensitivity on human HPRD protein data.

• 천문학논총
• /
• 제27권4호
• /
• pp.223-224
• /
• 2012

Understanding the birth and evolution of galaxies, and the history of star formation in them, is one of the most important problems in astronomy. Using the data from the AKARI IRC survey of the Large Magellanic Cloud at 3.2, 7, 11, 15, and $24{\mu}m$, we have constructed a multi-wavelength catalog containing data from the cross-correlation with a number of other databases at different wavelengths. We present the first approach with a Support Vector Machine (SVM)-based method to separate different classes of stars in LMC in the color-color and color-magnitude diagrams.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2003년도 춘계전력전자학술대회 논문집(1)
• /
• pp.308-312
• /
• 2003

The objective of this paper is to investigate the power spectrum of a three-phase and a two-phase RCD (Random Pulse Centered Displacement) PWM scheme. The two-phase or three-phase pulses of RCD-PWM scheme are mutually center-aligned as in SVM(Space Vector Modulation), but the common pulse center is displaced randomly from the middle of the period. To verify the validity of the proposed two-phase RCD-PWM scheme, the power spectra of the output voltage, the d.c link current in the inverter drives and the radiated acoustic noise are experimentally investigated. And, the performance of the proposed two-phase RCD-PWM scheme was compared and discussed with the conventional three-phase RCD-PWM scheme.