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.

김준호의 독서일기-청소년

김준호,Kim, Jun-Ho 대한출판문화협회 2006 출판저널 Vol.367 No.-

점수를 통한 발굽과 보행의 상태

김준호,Kim, Jun-Ho 한국종축개량협회 2006 種畜改良 Vol.11 No.4

본 글은 Veeppro dairy management 11월호의 내용을 발췌하여 정리한 내용입니다.

헬기 MRO 비즈니스의 잠재력

김준호,황창전,Kim, Joune ho,Hwang, Chang jeon 항공우주시스템공학회 2014 항공우주시스템공학회지 Vol.8 No.3

Since the global economic crisis in year 2008, the world civil helicopter market has been growing recently. According to the market outlook in the next decade, the demand of civil helicopter will be driven by the demand of Private & Corporate, Oil & Gas, Off-shore and EMS(Emergency Medical Service) usages. On the other side, the demand of military market will be driven by the modification and upgrading for life extension or performance enhancement than the new helicopter development for replacing old models. To summarize these situations, the demand of MRO(Maintenance, Repair & Overhaul) market has also been on the rise because of the demand due to above several usages in civil side and the life-extension in military side. Through the MRO market analysis for characteristics, developmental trends and a supply chain, this paper describes that the potential of MRO business is considerably large as a propulsive power of domestic helicopter industry. And also, it proposes the construction direction of MRO network because the domestic industry must make the developmental awareness and reliability a stepping-stone towards own helicopter.

Ti base alloy 의 플라즈마 질화

김준호,이창희,윤의박 ( Joon Ho Kim,Chang Hee Lee,Eui Pak Yoon ) 대한금속재료학회 1997 大韓金屬學會會報 Vol.10 No.1

우레탄기를 포함하는 벤조퀴논 / 디아민 중합체의 합성과 특성분석

김준호,노시태,김동국,이치규 ( Jun Ho Kim,Si Tae Noh,Dong Kook Kim,Chi Gyu Lee ) 한국공업화학회 1993 공업화학 Vol.4 No.4

용해성과 접착력을 향상하기 위하여 우레탄 그룹을 함유하는 디아민-퀴논 중합체를 합성하고 특성분석을 행하였다. 디이소시아네이트와 저분자량의 디올을 반응시켜 NCO말단 프리폴리머를 합성한 다음 NCO그룹을 아민으로 변화시켜 우레탄기를 함유하는 디아민을 제조하였다. 이때 NC0/0H몰 비율을 1.2에서 2.1까지 변화시켜 디아민 분자량을 변화시켰다. 이러한 디아민기를 함유하는 프리폴리머를 p-벤조퀴논과 반응시켜 디아민-벤조퀴논 중합체를 제조하였다. 중합체의 분석에는 분광분석기와 크로마토그래피를 이용하여 분자구조 분석과 분자량을 측정하였으며, 용해도와 열적 거동도 측정·검토하였다. To improve the solubility and adhesion strength of diamine-quinone polymers, urethane group was introduced into the polymer backbone. Urethane group containing polymeric diamines(UDA) were prepared firstly by the decarboxylation of the NCO group in NCO terminated prepolymer obtained from the reaction of MDI and 1.6-hexandiol. The reaction mole ratio of NC0/0H was changed from 1.2 to 2.1 to increase the molecular weight of diamine. From the addition reaction of UDA and p-benzoquinone in THF or DMSO solvent, five kinds of urethane group containing diamine/quinone polymers(PUAQ) were prepared according to the diamine used. IR, NMR, UV-visible spectroscopy and GPC were used to characterize the molecular structure and molecular weight of UDAs and PUAQs. Thermal analysis of polymer by DSC and TGA were carried out according to the molecular weight differency. Also solubility test of UDA and PUAQ with 10 different solvents were carried out to predict the coating property of the polymers.

김준호의 독서일기

김준호,Kim, Jun-Ho 대한출판문화협회 2006 출판저널 Vol.369 No.-

가스배관 위치이동 해석 및 응력 예측 기법 개발

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.

Solvent-Free Preparation of Fluorinated Polythiophene Nano-Particles by Supercritical CO₂ RESOLV Process

김준호,( Hullathy Subban Ganapathy ),( Seung Ho Kim ),임권택 한국공업화학회 2006 한국공업화학회 연구논문 초록집 Vol.2006 No.1

식물의 대사에 미치는 요소질소의 영향 (2) 대맥근에 (大麥根) 흡수된 후의 질소대사

김준호 (Joon Ho Kim) 한국식물학회 1962 Journal of Plant Biology Vol.5 No.2

KIM. Joon Ho (Dept. of Biology, Kongju Teacher`s College): The effects of urea nitrogen on the metabolism of plants. Ⅱ. The response of some nitrogen components of barley to urea and other nitrogen in water culture. Kor. Jour. Bot. V(2), 6-12. 1962. For the comparison with the previous paper (4) the present report deals with the absorption and metabolism of urea and other nitrogen ions in barley seedling absorbed through root. 1. The amount of nitrate in barley treated with urea reach it pcak on the 8 th day, NO_3 on the 4 th, NH_4 on the 6 th or 8th. respectively. 2. The ammonia content in urea group reaches its peak on the 6 th day but other groups on the 4 th day. The present data in the urea group show to shorten 4 days compared with that of the previous paper (4). 3. The content of total amide from the present data are gradually increased on all of the groups during this experiment. These are agreement with the result of the previous paper (4). 4. The alcohol soluble nitrogen in the urea group shows the similar tendency to the NaNO_3 group but reaches its peak 2 days later than in the (NH4)_2SO_4 group. 5. The content of total nitroaen in the urea series has the lowest amount at the beginning while the richest from the 4th day after. These would be explained on that the absorption of urea is delayed and the PH in the urea solution does not change, so called physiological neutralily. The author should like to express his sincere thanks to Prof. M. J. Lee of Seoul National University for his valuable advices.