보증데이터를 이용한 텍스트 마이닝 기반 고장 현상 예측 연구

정진형(Jin Hyeong Jung),김용수(Yong Soo Kim) 한국신뢰성학회 2020 신뢰성응용연구 Vol.20 No.4

Purpose: This paper uses unstructured warranty data, such as customer complaints and repair information, extracted through text mining and proposes a methodology for identifying and predicting automotive failure. Methods: The Word2Vec and CountVectorizer algorithms were used to determine the similarity between and frequency of the vectorized meanings of the words. A word embedding model was constructed on the bases of these distinct features of the words, and multimodal-deep neural network (DNN) modeling was performed to derive the prediction results of the failure phenomenon. A comparative analysis of the performance metrics of different combinations of the models was performed. Results: The model using both the CountVectorizer algorithm for extracting features within similar text clusters and the multimodal-DNN for training the data exhibited the best performance. Conclusion: This study shows the effects of different data structures and feature extraction algorithms on failure prediction performance. The developed model improves the prediction accuracy by applying the relevant feature extraction algorithm and text classification learning model.

한방신경정신과 영역의 수면장애 관련 연구현황

정진형 ( Jin Hyeong Jung ),하지원 ( Ji Won Ha ),김보경 ( Bo Kyung Kim ) 대한한방신경정신과학회 2012 동의신경정신과학회지 Vol.23 No.4

대자석의 중의 신경정신과 임상연구 현황

정진형 ( Jin Hyeong Jung ),최윤희 ( Yun Hee Choi ),김태헌 ( Tae Heon Kim ),김보경 ( Bo Kyung Kim ) 대한한방신경정신과학회 2014 동의신경정신과학회지 Vol.25 No.4

Objectives: This study was intended to review the research trends of treating neuropsychiatric diseases and symptoms with Traditional Chinese Medicine containing Haematitum. Methods: Articles were obtained through the CNKI (China National Knowledge Infrastructure) by searching with ‘Haematitum`` as the main key word, and supportive words related with neuropsychiatric diseases and symptoms were selected. There were 61 articles related to clinical fields, which were then classified according to study design. Results: The 61 articles were categorized into the following types of study design: 3 randomized controlled trials, 1 quasi-randomized trial, 3 simple-designed clinical trials, and 54 case studies. Decoctions containing Haematitum were used to treat diseases and symptoms such as vertigo, headache, stroke, epilepsy, neurosis, globus hystericus, fishbilepoisoning, insomnia, mania, post-traumatic brain syndrome, and kinesia. All articles reported a good rate of effectiveness. There was no poor responsiveness regarding the effects of Haematitum in 9 studies, but it was not mentioned in the other 52 studies. Decoctions self-prepared by the authors were used in 28 studies. Modified Seonbokdeja-tang, modified Banhabeakchulcheonma-tang, modified Ondam-tang were used in that order of frequency. The daily dosage of Haematitum provided was 0.2¡­6 g in powder, and 9¡­60 g in decoction. Conclusions: Decoctions containing Haematitum are used restrictively in the neuropsychiatric clinical scene. While there were no reports of poor responsiveness of the effects of Haematitum, more research is needed to confirm its clinical stability.

인공지능 기반 장비의 자동탐지 성능인증을 위한 시험법 설계

김기연(Ki-Yeon Kim),정진형(Jin Hyeong Jung),윤연아(Yeon Ah Yoon),김용수(Yong Soo Kim) 한국신뢰성학회 2020 신뢰성응용연구 Vol.20 No.1

Purpose: This paper examined the design of a standard test method for certifying the performance of automatic detection equipment using artificial intelligence (AI). Methods: First, indicators for measuring the detection performance were determined and the terms were redefined. Then, the number of iterations required to give a criterion value at a given confidence level for data following the binomial distribution was calculated. As a case study, an aviation security x-ray scanner was tested. Results: If failures occur before the number of allowable times during the trial, the minimum probability of occurrence of true positive (TP) can be demonstrated. This means that F2-Score is satisfied, and the performance can be certified. Conclusion: This method can be used in industries that operate automatic detectors based on AI technology. The method should contribute to the development of a national certification system and improve product quality control.

캐비닛 엑스선 검색장비 이미지품질평가 고도화 방안 연구

윤연아 ( Yeon Ah Yoon ),정진형 ( Jin Hyeong Jung ),김용수 ( Yong Soo Kim ) 한국품질경영학회 2021 품질경영학회지 Vol.49 No.1

Purpose: This study proposes methods and procedures for evaluating imaging security systems quality of cabinet x-ray screening system to enhance performance certification technology. Also, conducted a comparative analysis of the literature of test-kit for imaging security quality evaluation. Methods: Comparative analysis of the test-kits and related documents for image quality assessment of cabinet x-ray screening equipment. This allows assessment items were selected and the methods for each assessment item were proposed. In addition, the configuration method of the assessment team was established by applying the technology readiness assessment(TRA). Results: Four of the assessment items were selected when estimate image quality by a comparative analysis of literature. For each assessment item, the evaluation method and minimum level of availability were determined. Finally, this paper proposes an imaging quality assessment of cabinet X-ray imaging security systems. Conclusion: Development of imaging security systems evaluation procedures for cabinet X-ray screening systems can be help improve performance certification of aviation security equipment.

REM 수면 행동 장애의 치료에 대한 중의학 및 Kampo의 연구 경향

최윤희 ( Yoon Hee Choi ),정진형 ( Jin Hyeong Jung ),김보경 ( Bo Kyung Kim ) 대한한방신경정신과학회 2013 동의신경정신과학회지 Vol.24 No.4

Objectives: This study was performed to review the research trends in treatment for REM sleep behavior disorder (RBD) in Traditional Chinese Medicine (TCM) and Kampo in Japan. Methods: We searched articles in CNKI (China National Knowledge Infrastructure) under the key words, "RBD", and Chinese words related with it in Traditional Chinese Medicine, Traditional Chinese Medicinal Herbs and Combination of Traditional Chinese Medicine With Western Medicine`` field, and also in CiNii (Citation Information by NII); we also searched articles in Kampo Square in Japan under the key words, "RBD" and Japanese words related with it. We found 10 papers, and then selected 6 of them except the non-clinical and unrelated studies. We then analyzed their way of diagnosis, treatments, study type and etc. Results: 6 studies were divided into 4 case reports, one control study, and one literature review study. All of the studies reported that Herbal medicine for RBD was effective as much as Western medicine like clonazepam and paroxetine. However, the quality and the quantity of these clinical studies were not enough. Conclusions: It seems that the researches for RBD have gradually been performed in TCM and Kampo. We hope that our study can activate/push forward clinical research for this disorder in Korean traditional medicine.

다중 접속이 가능한 다계통 e-CNC 용 네트워크 HMI 기술

남성호(Sung Ho Nam),정진형(Jin Hyeong Jeong),김종태(Jong Tae Kim),성대중(Dae Jung Seong),이석우(Seok Woo Lee) Korean Society for Precision Engineering 2009 한국정밀공학회지 Vol.26 No.4

광업 데이터의 시계열 분석을 통해 실리카 농도를 예측하기 위한 머신러닝 모델

이승훈 ( Lee Seung Hoon ),윤연아 ( Yoon Yeon Ah ),정진형 ( Jung Jin Hyeong ),심현수 ( Sim Hyun Su ),장태우 ( Chang Tai-woo ),김용수 ( Kim Yong Soo ) 한국품질경영학회 2020 품질경영학회지 Vol.48 No.3

Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.

불면환자 350명의 동반증상과 심박변이도, 체성분 분석의 연관성에 관한 연구

하지원 ( Ji Won Ha ),김보경 ( Bo Kyung Kim ),정진형 ( Jin Hyeong Jung ) 대한한방신경정신과학회 2012 동의신경정신과학회지 Vol.23 No.3

Objectives : This study is to figure the relations of the heart rate variability, body component analysis and accompanying symptoms of 350 insomnia patients. Methods : For this study we evaluated Heart Rate Variability(HRV) and body component analysis on 350 insomnia patients who visited Dongeui oriental hospital of Dongeui university from January 2008 to March 2012. The accompanying symptoms was collected based on each patient`s progress note. Results : 1. There was no difference between PR, LF and VLF of male and female groups. HF was higher in the patients` of female group and LF/HF ratio was higher in the male group. The patients` group of age under 39 had higher HF, LF, VLF and LF/HF ratio than the group over 39. 2. The average of LF was the smallest, and the average of VLF was in the middle, while the average of HF was the largest. 3. Regarding patients` age and gender, as the patients` age increased, their HF, LF, VLF and LF/HF ratio decreased significantly. HF, LF, VLF, and LF/HF ratios were, however, independent on the patients` gender. As the patients` age increased, their BMI increased, while the patients` gender did not affect on their BMI. The amount of visceral fat increased with the patients` age, but wasn`t dependent on the patients` gender. 4. As the patients` BMI increased, PR and LF decreased. As the patients` amount of visceral fat increased, PR, HF, LF and VLF decreased. 5. The most frequent accompanying symptoms of the insomnia patients was headache. Neither HF nor LF/HF ratio was dependant on any of the accompanying symptoms. Patients with anxiety showed significantly higher LF than those without anxiety. Patients with fatigue and physical pain showed significantly higher VLF than those without either of them. Conclusions : The study showed that as the insomnia patients age increased, the HF, LF, VLF, LF/HF ratio significantly decreased, but the BMI and visceral fat increased. The HF, LF, VLF, LF/HF ratio BMI, or the visceral fat was independent on the gender. As BMI increased, PR and LF decreased. As visceral fat increased, PR HF, LF and VLF decreased. Patients presenting anxiety had higher LF. Patients either with fatigue or physical pain had higher VLF. Neither HF nor LF/HF ratio had any significant correlation with any of the accompanying symptoms.