• Journal of Biomedical Engineering Research
• /
• v.39 no.5
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.167-175
• /
• 2023

Chest PA is the basic examination of radiographic imaging. Moreover, Chest PA's demands are constantly increasing because of the Increase in respiratory diseases. However, it is not meeting the demand due to problems such as a shortage of radiological technologist, sexual shame caused by patient contact, and the spread of infectious diseases. There have been many cases of using artificial intelligence to solve this problem. Therefore, the purpose of this research is to build an artificial intelligence dataset of Chest PA and to find a posture evaluation method. To construct the posture dataset, the posture image is acquired during actual and simulated examination and classified correct and incorrect posture of the patient. And to evaluate the artificial intelligence posture method, a posture estimation algorithm is used to preprocess the dataset and an artificial intelligence classification algorithm is applied. As a result, Chest PA posture dataset is validated with in over 95% accuracy in all artificial intelligence classification and the accuracy is improved through the Top-Down posture estimation algorithm AlphaPose and the classification InceptionV3 algorithm. Based on this, it will be possible to build a non-face-to-face automatic Chest PA examination system using artificial intelligence.

• Physical Therapy Rehabilitation Science
• /
• v.5 no.2
• /
• pp.53-62
• /
• 2016

Objective: The aim of this systematic review was to investigate for effective strategies to improve home exercise program (HEP) adherence in vestibular rehabilitation (VR). Design: Systematic review. Methods: A systematic review was conducted to identify effective strategies used to improve HEP adherence of patients in VR. Six databases, Academic Search Premier, Cochrane Library, CINAHL, PUBMED, PsycINFO, and Web of Science were searched from their inception to December 31, 2015. The keywords used for search were 'home program', 'home intervention', 'compliance', 'adherence', 'vestibular rehabilitation', 'motion sickness', and 'motion sensitivity'. Results: A total of eight studies were selected to be included in the review. There was 95.2% agreement between the two reviewers who reviewed the studies using a quality assessment tool. The overall inter-rater agreement (${\kappa}$=0.73) showed good agreement between the reviewers. Strong evidence was identified for 3 major categories of effective HEP adherence strategies, 1) providing patient with written summary of HEP; 2) asking patient to maintain a record of HEP and symptoms; and 3) providing tele-rehabilitation in form of email and/or telephone support along with in person treatment sessions. Also, based on strong evidence, computerized technology was not found to be superior to other strategies for improving patients' HEP adherence in VR. Conclusions: The effective strategies for improving HEP in VR include written summary of exercise, maintenance of log of HEP and symptoms and tele-rehabilitation along with in person treatment sessions.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.83-86
• /
• 2019

도시화 과정에서 도시의 생활폐기물 문제가 빠르게 증가되고 있고, 효과적이지 못한 생활폐기물 관리는 도시의 오염을 악화시키고 물리적인 환경오염과 경제적인 부분에서 극심한 문제들을 야기시킬 수 있다. 게다가 부피가 커서 관리하기 힘든 대형 생활폐기물들이 증가하여 도시 발전에도 방해가 된다. 생활폐기물을 처리하는데 있어 대형 생활폐기물 품목에 대해서는 요금을 청구하여 처리한다. 다양한 유형의 대형 생활폐기물을 수동으로 분류하는 것은 시간과 비용이 많이 든다. 그 결과 대형 생활폐기물을 자동으로 분류하는 시스템을 도입하는 것이 중요하다. 본 논문에서는 대형 생활폐기물 분류를 위한 시스템을 제안하며, 이 논문의 4 가지로 분류된다. 1) 높은 정확도와 강 분류(roust classification) 수행에 적합한 Convolution Neural Network(CNN) 모델 중 VGG-19, Inception-V3, ResNet50 의 정확도와 속도를 비교한다. 제안된 20 개의 클래스의 대형 생활폐기물의 데이터 셋(data set)에 대해 가장 높은 분류의 정확도는 86.19%이다. 2) 불균형 데이터 문제를 처리하기 Class Weight VGG-19(CW-VGG-19)와 Extreme Gradient Boosting VGG-19 두 가지 방법을 사용하였다. 3) 20 개의 클래스를 포함하는 데이터 셋을 수동으로 수집 및 검증하였으며 각 클래스의 컬러 이미지 수는 500 개 이상이다. 4) 딥 러닝(Deep Learning) 기반 모바일 애플리케이션을 개발하였다.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.6
• /
• pp.959-964
• /
• 2012

Internal pressure of vacuum interrupter (VI) is one of the most important parameters in VI operation and may increase due to the outgassing from the materials inside VI or gas permeation through metal flange or ceramic vessel. The increase of the pressure above a certain level leads to the failures of switching or insulation. Therefore, an effective pressure check of VI is essential and an analysis of partial discharge (PD) characteristics is an effective monitoring method to identify the degree of the internal pressure of VI. This paper introduces a research work on monitoring the internal pressure of VI by analyzing PDs which were measured using a capacitive PD coupler. The authors have developed cost effective capacitive coupler based on the ceramic material that has an excellent insulation properties and the main component of the capacitive coupler is made by SrTiO3. Detectable internal pressure range and distinguishability of the internal pressure of VI were investigated. From the PD tests results, the internal pressure range, from $10^{-2}$ torr to 500 torr, can be monitored by PD measurements using the capacitive coupler and PD inception voltage (PDIV) follows the Paschen's law. In addition, rise time of PD pulse at 13.2kV decreases with the increase of the internal pressure of VI.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.167-174
• /
• 2021

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.337-345
• /
• 2023

Estimating the rice heading date is one of the most crucial agricultural tasks related to productivity. However, due to abnormal climates around the world, it is becoming increasingly challenging to estimate the rice heading date. Therefore, a more objective classification method for estimating the rice heading date is needed than the existing methods. This study, we aimed to classify the rice heading stage from various images using a CNN classification model. We collected top-view images taken from a drone and a phenotyping tower, as well as slanted-view images captured with a RGB camera. The collected images underwent preprocessing to prepare them as input data for the CNN model. The CNN architectures employed were ResNet50, InceptionV3, and VGG19, which are commonly used in image classification models. The accuracy of the models all showed an accuracy of 0.98 or higher regardless of each architecture and type of image. We also used Grad-CAM to visually check which features of the image the model looked at and classified. Then verified our model accurately measure the rice heading date in paddy fields. The rice heading date was estimated to be approximately one day apart on average in the four paddy fields. This method suggests that the water head can be estimated automatically and quantitatively when estimating the rice heading date from various paddy field monitoring images.