• 한국소음진동공학회논문집
• /
• 제26권6_spc호
• /
• pp.714-720
• /
• 2016

Rubbing and misalignment are the most usual faults that occurs in rotating machinery and with them severe effect on power plant availability. Especially blade rubbing is hard to detect on FFT spectrum using the vibration signal. In this paper, the possibility of feature analysis of vibration signal is confirmed under blade rubbing and misalignment condition. And the lab-scale rotor test device provides the blade rubbing and shaft misalignment modes. Feature selection based on GA (genetic algorithm) is processed by the extracted feature of the time domain. Then, classification of the features is analyzed by using SVM (support vector machine) which is one of the machine learning algorithm. The results of features selection based on GA compared with those based on PCA (principal component analysis). According to the results, the possibility of feature analysis is confirmed. Therefore, blade rubbing and shaft misalignment can be diagnosed by feature of vibration signal.

• 한국기계가공학회지
• /
• 제20권9호
• /
• pp.28-34
• /
• 2021

The Fourth Industrial Revolution has led to the development of drones for commercial and private applications. Therefore, the malfunction of drones has become a prominent problem. Failure mode and effect analysis was used in this study to analyze the primary cause of drone failure, and blade breakage was observed to have the highest frequency of failure. This was tested using a vibration sensor placed on drones along the breakage length of the blades. The data exhibited a significant increase in vibration within the drone body for blade fracture length. Principal component analysis was used to reduce the data dimension and classify the state with machine learning algorithms such as support vector machine, k-nearest neighbor, Gaussian naive Bayes, and random forest. The performance of machine learning was higher than 0.95 for the four algorithms in terms of accuracy, precision, recall, and f1-score. A follow-up study on failure prediction will be conducted based on the results of fault diagnosis.

• 한국기계가공학회지
• /
• 제20권9호
• /
• pp.35-41
• /
• 2021

A rotor is a crucial component in various mechanical assemblies. Additionally, high-speed and high-efficiency components are required in the automotive industry, manufacturing industry, and turbine systems. In particular, the failure of high-speed rotating bearings has catastrophic effects on auxiliary systems. Therefore, bearing reliability and fault diagnosis are essential for bearing maintenance. In this work, we performed failure mode and effect analysis on bearing rotors and determined that corrosion is the most critical failure type. Furthermore, we conducted experiments to extract vibration characteristic data and preprocess the vibration data through principle component analysis. Finally, we applied a machine learning algorithm called support vector machine to diagnose the failure and observed a classification performance of 98%.

• 대한방사선기술학회지:방사선기술과학
• /
• 제42권2호
• /
• pp.119-130
• /
• 2019

Positron emission tomography (PET) is widely used imaging modality for effective and accurate functional testing and medical diagnosis using radioactive isotopes. However, PET has difficulties in acquiring images with high image quality due to constraints such as the amount of radioactive isotopes injected into the patient, the detection time, the characteristics of the detector, and the patient's motion. In order to overcome this problem, we have succeeded to improve the image quality by using the dynamic image reconstruction method based on singular value decomposition. However, there is still some question about the characteristics of the proposed technique. In this study, the characteristics of reconstruction method based on singular value decomposition was estimated over computational simulation. As a result, we confirmed that the singular value decomposition based reconstruction technique distinguishes the images well when the signal - to - noise ratio of the input image is more than 20 decibels and the feature vector angle is more than 60 degrees. In addition, the proposed methode to estimate the characteristics of reconstruction technique can be applied to other spatio-temporal feature based dynamic image reconstruction techniques. The deduced conclusion of this study can be useful guideline to apply medical image into SVD based dynamic image reconstruction technique to improve the accuracy of medical diagnosis.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• 전력전자학회논문지
• /
• 제26권6호
• /
• pp.381-389
• /
• 2021

Most diagnosis approaches rely on historical failure data that might not be feasible in real operating conditions because the battery voltage and internal parameters are nonlinear according to various operating conditions, such as cell-to-cell configuration and initial condition. To overcome this issue, the estimator and the predictor require integrated approaches that consider comprehensive data, with the degradation process and measured data taken into account. In this paper, vector autoregressive models (VAR) with various parameters that affect overdischarge to the cell in the battery pack were constructed, and the cell-to-cell parameters were identified using an adaptive model to analyze the influence of failure prognosis. The theoretical analysis is validated using experimental results in terms of the feasibility and advantages of fault prognosis.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.144-146
• /
• 2021

Idiopathic pulmonary fibrosis (IPF) is one of the most dreadful lung diseases which effects the performance of the lung unpredictably. There is no any authentic natural history discovered yet pertaining to this disease and it has been very difficult for the physicians to diagnosis this disease. With the advent of Artificial intelligent and its related technologies this task has become a little bit easier. The aim of this paper is to develop and to explore the machine learning models for the prediction and diagnosis of this mysterious disease. For our study, we got IPF dataset from Haeundae Paik hospital consisting of 2425 patients. This dataset consists of 502 features. We applied different data preprocessing techniques for data cleaning while making the data fit for the machine learning implementation. After the preprocessing of the data, 18 features were selected for the experiment. In our experiment, we used different machine learning classifiers i.e., Multilayer perceptron (MLP), Support vector machine (SVM), and Random forest (RF). we compared the performance of each classifier. The experimental results showed that MLP outperformed all other compared models with 91.24% accuracy.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.289-290
• /
• 2022

동맥경화증은 경동맥 혈관 벽이 두꺼워지는 질병으로 진단을 위해 혈관 벽의 두께를 모니터링하는 것이 중요하다. 본 연구에서는 경동맥 MRI 영상에서 324개의 라디오믹스 특징을 추출하고 머신러닝 기법을 이용하여 동맥경화증을 진단하는 모델을 제안한다. 라디오믹스 특징을 통해 로지스틱 회귀, 서포트 벡터 머신, 랜덤 포레스트, XGBoost의 총 4가지 분류 모델을 학습하였다. 5-fold 교차 검증에서 가장 높은 성능의 모델인 XGBoost는 정확도 0.9023, 민감도 0.9517, 특이도 0.8035, AUC 0.8776의 결과값을 보여준다.

• Journal of Plant Biotechnology
• /
• 제31권4호
• /
• pp.285-293
• /
• 2004

FMDV는 동물에서 구제역을 일으키는 병원체이며, VP1은 이 바이러스의 주요 capsid단백질이므로 구제역의 진단과 단백질 백신의 개발에 가장 많이 사용되는 재료 중 하나이다. 본 연구는 FMDV taiwan O형과 베트남에서 분리된 FMDV의 VP1 sequence를 기반으로 식물에서 VP1 유전자의 발현을 위하여 633 bp의 VP1유전자로 재편집하였으며, 이를 long-nucleotide를 사용한 multiple fragment extension 방법을 사용하여 인공적인 DNA 단편을 합성하였다. 또한 새로운 식물 형질전환 벡터로 pBI121 과 pCAMBIA1390의 장점을 수용하여, hygromycin 저항성과 CaMV 35S promoter를 포함하는 pCAMBIA II를 제작하였다. 제작된 벡터와 VP1 유전자 및 GFP유전자를 사용하여 담배를 형질 전환시켰고, 각각의 형질전환식물체내에서 전체길이의 target gene(VPl)의 성공적인 삽입을 확인하였다. 각 유전자의 발현은 RT-PCR과 Real-Time PCR의 결과로 측정하였으며, VP1 유전자의 전사가 담배 내에서 이루어졌음과 고효율의 전사체를 만드는 형질전환체 VP1-4를 선별하였다.

• 전자공학회논문지
• /
• 제50권8호
• /
• pp.196-202
• /
• 2013

기저 세포암은 가장 일반적인 피부암이고 그 발병이 급속도로 증가하고 있다. 본 연구에서는 피부 조직에서 측정한 라만 스펙트럼에서 기저 세포암 진단을 위해 NMF(non-negative matrix factorization) 알고리즘을 사용하는 방법을 제안하였다. 측정된 라만 스펙트럼은 영역 선택과 정규화 등의 몇 가지 전처리 과정을 거쳐 분류 실험에 사용한다. 전처리 과정을 수행한 라만 스펙트럼은 NMF 알고리즘을 이용하여 분해된 행렬의 열벡터를 기저로 사용한다. 이 기저들을 선형 결합하여 각 클래스의 평균 스펙트럼에 근사하기 위한 가중치는 행렬 연산으로 결정한다. 분류 실험은 스펙트럼과 NMF에 의한 기저와 가중치의 선형 결합 스펙트럼의 차에 대한 제곱평균제곱근을 최소로 하는 클래스를 선택하는 것으로 수행한다. 기저 세포암의 진단을 위한 분류 실험에서 제안한 방법을 사용하는 경우가 약 99.1%의 평균 분류율로 이전의 BCC 진단에 사용한 방법보다 약 2-3% 정도의 향상된 성능을 보였다.