http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
머신러닝 기반 음성분석을 통한 체질량지수 분류 예측 - 한국 성인을 중심으로
김준호,박기현,김호석,이시우,김상혁,Kim, Junho,Park, Ki-Hyun,Kim, Ho-Seok,Lee, Siwoo,Kim, Sang-Hyuk 사상체질의학회 2021 사상체질의학회지 Vol.33 No.4
Objectives The purpose of this study was to check whether the classification of the individual's Body Mass Index (BMI) could be predicted by analyzing the voice data constructed at the Korean medicine data center (KDC) using machine learning. Methods In this study, we proposed a convolutional neural network (CNN)-based BMI classification model. The subjects of this study were Korean adults who had completed voice recording and BMI measurement in 2006-2015 among the data established at the Korean Medicine Data Center. Among them, 2,825 data were used for training to build the model, and 566 data were used to assess the performance of the model. As an input feature of CNN, Mel-frequency cepstral coefficient (MFCC) extracted from vowel utterances was used. A model was constructed to predict a total of four groups according to gender and BMI criteria: overweight male, normal male, overweight female, and normal female. Results & Conclusions Performance evaluation was conducted using F1-score and Accuracy. As a result of the prediction for four groups, The average accuracy was 0.6016, and the average F1-score was 0.5922. Although it showed good performance in gender discrimination, it is judged that performance improvement through follow-up studies is necessary for distinguishing BMI within gender. As research on deep learning is active, performance improvement is expected through future research.
단상 스위치드 릴럭턴스 모터에 설치된 영구자석 기동장치의 디텐트 토크
김준호,이승민,Kim, Jun-Ho,Lee, Seung-Min 한국전기전자재료학회 2010 전기전자재료학회논문지 Vol.23 No.5
The single-phase switched reluctance motor(SRM) generates the positive torque in the restricted section. So, it can not started by itself and the torque ripple is heavier than poly-phase. For self-starting and fixing rotating direction, the rotor should be placed at the rising inductance slope when stationary. The parking permanent magnet locates the rotor in the fixed position, which can be started by it-self. It is very simple and cost effective but has some drawbacks. It affects the rotor during the operation, so the characteristics of motor, such as a torque, speed, and ripple are changed to go bad. This paper presents the detent torque of parking magnet starting device through the finite element analysis and experiments. The finite element analysis is performed at incremental rotor positions over one detent torque cycle for any one pole. The prototype, fabricated in the previous research, is used for the experiments. The inductance, instant torque, and detent torque are calculated using the terminal voltage and phase current. Finally, the finite element analysis result and the experiment result are compared for analysis and validity.
김준호,김동현,이상근,홍성경,정석영,Kim, Joon Ho,Kim, Dong Hyawn,Lee, Sang Geun,Hong, Seong Kyeong,Jeong, Sek Young 한국강구조학회 2009 韓國鋼構造學會 論文集 Vol.21 No.3
가스배관이 매설된 지역에서 지면고에 변화가 발생하는 공사 수행시 가스배관의 안정성을 확보하기 위한 위치이동을 수행한다. 본 논문에서는 위치이동에 따른 배관의 구조해석을 위한 모델링 방법의 최적화와 함께 위치이동의 단계별 발생 응력을 실시간으로 예측하기 위한 방법을 제안하였다. 모델링 방법으로는 요소의 종류와 크기, 배관 매설부의 경계조건 처리 방법, 세장비에 의한 기하학적 비선형 특성 등의 영향에 관하여 분석하였으며 정확성을 확보하면서 해석 효율을 높일 수 있는 조건을 구하였다. 배관의 응력 예측을 위해서는 위치이동의 수 단계에 발생하는 배관위치 및 최대응력 정보를 이용하여 인공신경망을 학습시켰으며 학습 후 세부 이동단계별 배관의 위치와 최대응력을 예측할 수 있도록 하였다. 개발된 응력예측시스템은 윈도우 환경의 프로그램으로 개발하였다. If there are some construction works that affect the stability of buried pipelines, the pipelines should be moved to guarantee their safety. In this paper, modeling methods for analyzing the movement of pipelines were sought, and the step-by-step stress estimation method of moving pipelines was developed. Some factors affecting of pipeline response such as the element type, the element size, boundary modeling, and geometric non-linearity were quantitatively investigated. In addition, some conditions in which accuracy and effectiveness can be compromised in the analysis of long pipelines were identified. A neural network was used to estimate the pipeline stress. The inputs to the neural network included step-by-step displacements, and the output was the resulting stress at each movement step. After training the neural network, it can be used to estimate pipeline stresses at some sub-steps that are not included in the training. A Windows-based stress estimation program was developed.
구강작열감증후군과 구강 내 Helicobacter pylori의 상호관련성
김준호,유지원,윤창륙,안종모,Kim, Jun-Ho,Ryu, Ji-Won,Yoon, Chang-Lyuk,Ahn, Jong-Mo 대한안면통증구강내과학회 2011 Journal of Oral Medicine and Pain Vol.36 No.2
Helicobacter pylori (H. pylori) is bacterial infection, with more than half of the world population infected and relates to many oral disease such oral lichen planus, recurrent aphthous ulceration, periodontal disease and halitosis and so on. Burning mouth syndrome(BMS) is defined as a burning sensation of the oral mucosa, lips, and/or tongue, in the absence of specific oral lesions. The etiology of BMS is suggested local, systemic and psychological factors and researchs related BMS and to infection of H. pyloir in the oral cavity are few. The purpose of this study was to evaluate relationship between burning mouth syndrome and H. pylori in the oral cavity. We recruited 21 subjects with burning mouth syndrome and 21 subjects as control group. Samples in the oral cavity were taken area of buccal mucosa, dorsum of the tongue and saliva. We analysed samples by nested polymerase chain reaction(PCR). The results were as follows: 1. Among 21 patients with burning mouth sydrome and 21 subjects of control group, 6(29%) and 3(14%) were positive respectively(P>0.05). 2. In detection rate of H. pylori in area taken sample, 3(14%), 2(10%) and 4(19%) were positive in buccal mucosa, dorsum of the tongue and saliva of patient and 2(10%) and 1(5%) were positive in dorsum of the tongue and saliva of control group(P>0.05). Conclusively, we can guess that H. pylori in the oral cavity is not related with burning mouth syndrome.
SCL EM 반작용 휠의 시간응답 최적화를 위한 비례 이득 추정
김준호,이상욱,전동익,오화석,Kim, Joon-Ho,Lee, Sang-Wook,Cheon, Dong-Ik,Oh, Hwa-Suk 항공우주시스템공학회 2009 항공우주시스템공학회지 Vol.3 No.4
The driver's speed control to the satellite's mission is required. Therefore, optimal control over the value of benefits is required. Driver to control the characteristics of the driver and the driver was analyzed. Experimental results based on the estimated parameters using the equations of motion and was passed to save the function. Using optimization techniques applied to estimate the proportional term gain was the result of the analysis.
김준호,이성호,서만철,이병하,Kim, Jun-Ho,Lee, Seong-Ho,Suh, Man-Chul,Lee, Byung-Ha 한국세라믹학회 2007 한국세라믹학회지 Vol.44 No.11
Spinel pigments, developing black color in high temperature glazes at oxidation or reduction atmosphere, without CoO because of its high price were synthesized by solid solution method. Ten mixed compositions consisted of NiO, MnO, $Fe_2O_3 and $Mn_2O_3$ were fired at $1250^{\circ}C$ for 1h. The resulting pigments were characterized by using XRD, FT-IR, SEM and UV-vis spectrometer. Structure of the pigments are spinel and particles' shape are spherical or cubic. Glazed tiles containing 5 wt% pigments were fired at $1260^{\circ}C$ and $1240^{\circ}C$ in reduction atmosphere. Color in glazes were analyzed by UV-vis spectrometer. Colors of NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.4875{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0125 mole% and NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.3875{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.1125 mole% in lime glaze showed black in oxidation, in reduction NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.4875{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0125 mole% and NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.4375{\cdot}Cr_2O_3$ $0.55{\cdot}Mn_2O_3$ 0.0125 mole% showed black. In case of lime-barium glaze, NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.3875{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.1125 mole%, NiO 0.975 MnO $0.075{\cdot}Fe_2O_3$ $0.4375{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0625 mole% and NiO 0.925 MnO $0.075{\cdot}Fe_2O_3$ $0.4375{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0625 mole% showed black color in oxidation and NiO 0.875 MnO $0.125{\cdot}Fe_2O_3$ $0.3875{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.1125 mole%, NiO 0.925 MnO $0.075{\cdot}Fe_2O_3$ $0.4375{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0625 mole% and NiO 0.725 MnO $0.275{\cdot}Fe_2O_3$ $0.4375{\cdot}Cr_2O_3$ $0.50{\cdot}Mn_2O_3$ 0.0625 mole% showed black one in reduction.