• Journal of Biomedical Engineering Research
• /
• v.38 no.6
• /
• pp.321-329
• /
• 2017

This paper presents a bone metastasis Detection algorithm on abdominal computed tomography images for early detection using fully convolutional neural networks. The images were taken from patients with various cancers (such as lung cancer, breast cancer, colorectal cancer, etc), and thus the locations of those lesions were varied. To overcome the lack of data, we augmented the data by adjusting the brightness of the images or flipping the images. Before the augmentation, when 70% of the whole data were used in the pre-test, we could obtain the pixel-wise sensitivity of 18.75%, the specificity of 99.97% on the average of test dataset. With the augmentation, we could obtain the sensitivity of 30.65%, the specificity of 99.96%. The increase in sensitivity shows that the augmentation was effective. In the result obtained by using the whole data, the sensitivity of 38.62%, the specificity of 99.94% and the accuracy of 99.81% in the pixel-wise. lesion-wise sensitivity is 88.89% while the false alarm per case is 0.5. The results of this study did not reach the level that could substitute for the clinician. However, it may be helpful for radiologists when it can be used as a screening tool.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.5
• /
• pp.338-344
• /
• 2017

In this paper, an interpolation method of HRTF (Head-Related Transfer Function) is proposed for small-sized measurement data set, especially. The proposed algorithm is based on acoustic modeling of HRTFs, and the algorithm tries to interpolate the HRTFs via estimation the model coefficients. However, the estimation of the model coefficients is hard if there is lack of measurement points, so the algorithm solves the problem by a data augmentation using the VBAP (Vector Based Amplitude Panning). Therefore, the proposed algorithm consists of two steps, which are data augmentation step based on VBAP and model coefficients estimation step by least squares method. The proposed algorithm was evaluated by a simulation with a measured data from CIPIC (Center for Image Processing and Integrated Computing) HRTF database, and the simulation results show that the proposed algorithm reduces mean-squared error by 1.5 dB ~ 4 dB than the conventional algorithms.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.495-502
• /
• 2018

The advent of deep learning technology has made rapid progress in handwritten letter recognition in many languages. Handwritten Chinese recognition has improved to 97.2% accuracy while handwritten Japanese recognition approached 99.53% percent accuracy. Hanguel handwritten letters have many similar characters due to the characteristics of Hangeul, so it was difficult to recognize the letters because the number of data was small. In the handwritten Hanguel recognition using Hybrid Learning, it used a low layer model based on lenet and showed 96.34% accuracy in handwritten Hanguel database PE92. In this paper, 98.64% accuracy was obtained by organizing deep CNN (Convolution Neural Network) in handwritten Hangeul recognition. We designed a new network for handwritten Hangeul data based on GoogLenet without using the data augmentation or the multitasking techniques used in Hybrid learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.10
• /
• pp.1909-1916
• /
• 2017

Recently, deep learning algorithms have good performance in various fields, but they are not actively applied to sonar systems. In this study, we carried out experiments to classify active sonar returns into a metal object such as a mine and a rock using a convolutional neural network which is one of the deep learning algorithms. Data augmentation is applied on this paper to avoid overfitting and increase performance. And we analyzed performance variation depending on hyperparameter value and change of the number of training data through data augmentation. The experiments are performed with two training data; an aspect-angle independent and an aspect-angle dependent. As a result, the performances are 88.9% and 94.9% in aspect-angle independent and dependent, respectively. These are up to 4.5% point higher than the performance obtained by applying artificial neural network and support vector machine algorithm in the previous study.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.5
• /
• pp.493-504
• /
• 2008

Space-Based Augmentation System (SBAS), which is one of the GPS augmentation systems, is a Wide-Area Differential GPS that provides differential GPS corrections and integrity data. In this study, we did performance analysis of kinematic SBAS surveying by conducting Real-Time Kinematic (RTK), DGPS, standalone, and SBAS surveys. Considering static survey results as truth, 2-D Root Mean Square (RMS) error and 3-D RMS error were computed to evaluate the positioning accuracy of each survey method. As a result, the 3-D positioning error of RTK was 13.1cm, DGPS 126.0cm, standalone (L1/L2) 135.7cm, standalone (C/A) 428.9cm, and SBAS 109.2cm. The results showed that the positioning accuracy of SBAS was comparable to that of DGPS.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.34 no.5
• /
• pp.740-753
• /
• 2010

This study analyzes the motives of Korean women for choosing breast augmentation in a cultural and relational context; in addition, it investigates their evaluations after surgery. Data was collected through in-depth interviews with 10 Korean women in their 20s and 30s who have received cosmetic breast augmentation. Enlarged and made-up breasts are a form of clothing that symbolizes the socio-economic status of women. In the vertical and individualized Korean society, the desire of women for a fashionable body invigorated the appearance management market. Fashion consumers have passively internalized the ideal body trends as the concept of the ideal body-image, which has been constructed by the social structure, markets, and the media. The analysis was rooted in post-modern feminist perspectives on the female body. The ideal body-image internalization process through the social interactions of participants was the main cultural factor to choose breast surgery. The self-image and conformity/individuality of participant were categorized as relational factors for the motivation to undergo breast surgery. The result showed that after surgery the participants achieved positive feedback from their social relationships. They expressed or hid their socio-economic statuses through their purchased fashion bodies. They also showed higher self-esteem and feelings of satisfaction by pursuing individuality and conformity as a member of society. Moreover, they achieved wider fashion options and greater controls over their public/private/secret clothing choices for certain occasions. Cosmetic breast surgery positively empowered individual women while reinforcing the socially manipulated body ideals that oppress women at the same time. Participants internalized socially constructed values and justified their surgery choices.

• Archives of Plastic Surgery
• /
• v.46 no.2
• /
• pp.160-166
• /
• 2019

Background Implant-related deformities in aesthetic rhinoplasty are a major problem for rhinoplasty surgeons. Capsular contracture is believed to be the pathological cause of delayed contour deformities, comparable to breast implant-related contracture. This study investigated the prevalence of bacterial biofilms and other epidemiological factors related to capsular contracture in cases of silicone augmentation rhinoplasty. Methods Thirty-three patients who underwent corrective rhinoplasty due to a delayed contour deformity or aesthetic revision after implant rhinoplasty were studied from December 2014 to December 2016. All recruited patients received surgical correction by the authors. The patients were categorized by clinical severity into four grades. Demographic data and related confounding factors were recorded. Samples of capsular tissue and silicone removed from each patient were analyzed for the presence of a biofilm by ultrasonication with bacterial culture and scanning electron microscopy. Results Thirty-three paired samples of capsular tissue and silicone implants from the study group were analyzed. Biofilms were detected in one of 10 subjects (10%) with grade 1 contracture, two of four (50%) with grade 2 contracture, 10 of 14 (71.40%) with grade 3 contracture, and four of five (80%) with grade 4 contracture (P<0.05). The organisms found were Staphylococcus epidermidis (47.10%), coagulase-negative staphylococci (35.30%), and Staphylococcus aureus (17.60%). Conclusions As with breast implant-related capsular contracture, silicone nasal augmentation deformities likely result from bacterial biofilms. We demonstrated the prevalence of biofilms in patients with various degrees of contracture. Implant type and operative technique seemed to have only vague correlations with biofilm presence.

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.396-409
• /
• 2023

In the field of autonomous vehicles, where high accuracy and reliability are critical, various satellite navigation augmentation systems have been developed to improve system performance. These systems generate correction and integrity information based on measurements and navigation data collected from ground reference stations, enhancing user positioning accuracy. Thus, the performance of the system heavily relies on the deployment and spacing of reference stations. To construct an effective satellite navigation augmentation system, careful consideration must be given to the installation points of reference stations. This paper presents a user positioning performance modeling formula and proposes a method for selecting the installation points of new reference stations. The proposed method involves selecting a candidate group area that can optimize the user's positioning performance. By utilizing this method, the system's performance can be improved, ensuring high accuracy and reliability for autonomous vehicle applications.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.