• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1407-1416
• /
• 2018

The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learning model for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice's similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice's similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.

• Wind and Structures
• /
• v.29 no.3
• /
• pp.149-161
• /
• 2019

When a railway vehicle runs in crosswinds, the unsteady aerodynamic forces acting on the train induced by the vehicle speed, crosswind velocity and local landforms are a common problem. To investigate the dynamic performance of a railway vehicle due to the influence of unsteady aerodynamic forces caused by local landforms, a vehicle aerodynamic model and vehicle dynamic model were established. Then, a wind-loaded vehicle system model was presented and validated. Based on the wind-loaded vehicle system model, the dynamic response performance of the vehicle, including safety indexes and vibration characteristics, was examined in detail. Finally, the effects of the crosswind velocity and vehicle speed on the dynamic response performance of the vehicle system were analyzed and compared.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.81.2-81.2
• /
• 2019

We develop an image-to-image translation model, which is a popular deep learning method based on conditional Generative Adversarial Networks (cGANs), to generate solar magnetograms and EUV images from sunspot drawings. For this, we train the model using pairs of sunspot drawings from Mount Wilson Observatory (MWO) and their corresponding SDO/HMI magnetograms and SDO/AIA EUV images (512 by 512) from January 2012 to September 2014. We test the model by comparing pairs of actual SDO images (magnetogram and EUV images) and the corresponding AI-generated ones from October to December in 2014. Our results show that bipolar structures and coronal loop structures of AI-generated images are consistent with those of the original ones. We find that their unsigned magnetic fluxes well correlate with those of the original ones with a good correlation coefficient of 0.86. We also obtain pixel-to-pixel correlations EUV images and AI-generated ones. The average correlations of 92 test samples for several SDO lines are very good: 0.88 for AIA 211, 0.87 for AIA 1600 and 0.93 for AIA 1700. These facts imply that AI-generated EUV images quite similar to AIA ones. Applying this model to the Galileo sunspot drawings in 1612, we generate HMI-like magnetograms and AIA-like EUV images of the sunspots. This application will be used to generate solar images using historical sunspot drawings.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.81.3-81.3
• /
• 2019

In this study, we apply conditional Generative Adversarial Network, which is one of the deep learning method, to the image-to-image translation from solar magentograms to solar UV and EUV images. For this, we train a model using pairs of SDO/AIA 9 wavelength UV and EUV images and their corresponding SDO/HMI line-of-sight magnetograms from 2011 to 2017 except August and September each year. We evaluate the model by comparing pairs of SDO/AIA images and corresponding generated ones in August and September. Our results from this study are as follows. First, we successfully generate SDO/AIA like solar UV and EUV images from SDO/HMI magnetograms. Second, our model has pixel-to-pixel correlation coefficients (CC) higher than 0.8 except 171. Third, our model slightly underestimates the pixel values in the view of Relative Error (RE), but the values are quite small. Fourth, considering CC and RE together, 1600 and 1700 photospheric UV line images, which have quite similar structures to the corresponding magnetogram, have the best results compared to other lines. This methodology can be applicable to many scientific fields that use several different filter images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.29-36
• /
• 2022

In deep learning classification tasks, most models frequently assume that all labels are available for the training datasets. As such strategies to learn new concepts from unlabeled datasets are scarce. In fingerprint classification tasks, most of the fingerprint datasets are labelled using the subject/individual and fingerprint datasets labelled with finger type classes are scarce. In this paper, authors have developed approaches of classifying fingerprint images using the majorly known fingerprint classes. Our study provides a flexible method to learn new classes of fingerprints. Our classifier model combines both the clustering technique and use of deep learning to cluster and hence label the fingerprint images into appropriate classes. The K means clustering strategy explores the label uncertainty and high-density regions from unlabeled data to be clustered. Using similarity index, five clusters are created. Deep learning is then used to train a model using a publicly known fingerprint dataset with known finger class types. A prediction technique is then employed to predict the classes of the clusters from the trained model. Our proposed model is better and has less computational costs in learning new classes and hence significantly saving on labelling costs of fingerprint images.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.587-594
• /
• 2021

As the diagnosis using encephalography(EEG) has been expanded, various studies have been actively performed for classifying EEG automatically. This paper proposes a CNN model that can effectively classify EEG signals acquired from healthy persons and patients with epilepsy. We segment the EEG signals into sub-signals with smaller dimension to augment the EEG data that is necessary to train the CNN model. Then the sub-signals are segmented again with overlap and they are used for training the CNN model. We also propose ensemble strategy in order to improve the classification accuracy. Experimental result using public Bonn dataset shows that the CNN can detect the epileptic seizure with the accuracy above 99.0%. It also shows that the ensemble method improves the accuracy of 3-class and 5-class EEG classification.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.293-299
• /
• 2021

Purpose: To accelerate magnetic resonance fingerprinting (MRF) by developing a flexible deep learning reconstruction method. Materials and Methods: Synthetic data were used to train a deep learning model. The trained model was then applied to MRF for different organs and diseases. Iterative reconstruction was performed outside the deep learning model, allowing a changeable encoding matrix, i.e., with flexibility of choice for image resolution, radiofrequency coil, k-space trajectory, and undersampling mask. In vivo experiments were performed on normal brain and prostate cancer volunteers to demonstrate the model performance and generalizability. Results: In 400-dynamics brain MRF, direct nonuniform Fourier transform caused a slight increase of random fluctuations on the T2 map. These fluctuations were reduced with the proposed method. In prostate MRF, the proposed method suppressed fluctuations on both T1 and T2 maps. Conclusion: The deep learning and iterative MRF reconstruction method described in this study was flexible with different acquisition settings such as radiofrequency coils. It is generalizable for different in vivo applications.

• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.293-301
• /
• 2023

Scoliosis is a three-dimensional deformation of the spine that is a deformity induced by physical or disease-related causes as the spine is rotated abnormally. Early detection has a significant influence on the possibility of nonsurgical treatment. To train a deep learning model with preprocessed images and to evaluate the results with and without data augmentation to enable the diagnosis of scoliosis based only on a chest X-ray image. The preprocessed images in which only the spine, rib contours, and some hard tissues were left from the original chest image, were used for learning along with the original images, and three CNN(Convolutional Neural Networks) models (VGG16, ResNet152, and EfficientNet) were selected to proceed with training. The results obtained by training with the preprocessed images showed a superior accuracy to those obtained by training with the original image. When the scoliosis image was added through data augmentation, the accuracy was further improved, ultimately achieving a classification accuracy of 93.56% with the ResNet152 model using test data. Through supplementation with future research, the method proposed herein is expected to allow the early diagnosis of scoliosis as well as cost reduction by reducing the burden of additional radiographic imaging for disease detection.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.168-175
• /
• 2023

In the era of the 4th Industrial Revolution, Logistic 4.0 using data-based technologies such as IoT, Bigdata, and AI is a keystone to logistics intelligence. In particular, the AI technology such as prognostics and health management for the maintenance of logistics facilities is being in the spotlight. In order to ensure the reliability of the facilities, Time-Based Maintenance (TBM) can be performed in every certain period of time, but this causes excessive maintenance costs and has limitations in preventing sudden failures and accidents. On the other hand, the predictive maintenance using AI fault diagnosis model can do not only overcome the limitation of TBM by automatically detecting abnormalities in logistics facilities, but also offer more advantages by predicting future failures and allowing proactive measures to ensure stable and reliable system management. In order to train and predict with AI machine learning model, data needs to be collected, processed, and analyzed. In this study, we have develop a system that utilizes an AI detection model that can detect abnormalities of logistics rotational equipment and diagnose their fault types. In the discussion, we will explain the entire experimental processes : experimental design, data collection procedure, signal processing methods, feature analysis methods, and the model development.