김명규 교수

The artificial neural network (ANN), one of the machine learning (ML) algorithms, inspired by the human brain system, was developed by connecting layers with artificial neurons. However, due to the low computing power and insufficient learnable data, ANN has suffered from overfitting and vanishing gradient problems for training deep networks. The advancement of computing power with graphics processing units and the availability of large data acquisition, deep neural network outperforms human or

USING GENERATIVE ADVERSARIAL NETWORK' and 'Image to Image Translation With Using GAN' as subsections '1) Image to Image Translation Without Using GAN' and '2) Image to Image Translation With Using GAN. ' At the time of submission, we checked this, but it missed at the publication. We forgot to check it at correction period.

Realistic image synthesis based on deep learning is an invaluable technique for developing high-performance computer aided diagnosis systems while protecting patient privacy. However, training a generative adversarial network (GAN) for image synthesis remains challenging because of the large amounts of data required for training various kinds of image features. This study aims to synthesize retinal images indistinguishable from real images and evaluate the efficacy of the synthesized images havi

In the field of HRI, to take advantage of people’s innate ability of communication, researchers have thus far concentrated on facial expression in facilitating human robot communication. However, for the robot to express emotional intensity, other modalities such as gestures, movement, sound, and color are also needed. This paper suggests that the intensity of emotion can be expressed with color and blinking, which are applicable on robots via LED. Although color and emotion have certain relatio

Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical verte

This paper presents the simplified welding distortion analysis method to predict the welding deformation of both plate and stiffener in fillet welds. Currently, the methods based on equivalent thermal strain like Strain as Direct Boundary (SDB) has been widely used due to effective prediction of welding deformation. Regarding the fillet welding, however, those methods cannot represent deformation of both members at once since the temperature degree of freedom is shared at the intersection nodes

The development process of the optical systems for various biomedical applications typically involve evaluations of technical performance. One popular evaluation method is to use a reference object such as a phantom that exhibits similar optical properties of tissue. Fabrication of a consistent phantom with known optical properties, such as scattering and absorption, is essential for accurate technical evaluation of the optical system. This paper presents a protocol for fabricating an agar-based

Abstract The computation of a navigation satellite position and clockis a general task in GPS positioning, and the data needed for this task can be obtained from navigation messagesand IGS precise ephemerides.This study analyzesbroadcast orbit and clock error variations by comparing them with IGS precise ephemerides. Orbit and clock errorsfrom 2001 to 2013 are computed for all GPS satellites as well as for the group of satellites visible inKorea. Orbit and clock errors versus GPS satellite types

Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmen

Space-based augmentation system (SBAS) provides correction information for improving the global navigation satellite system (GNSS) positioning accuracy in real-time, which includes satellite orbit/clock and ionospheric delay corrections. At SBAS service area boundaries, the correction is not fully available to GNSS users and only a partial correction is available, mostly satellite orbit/clock information. By using the geospatial correlation property of the ionosphere delay information, the ionos

Abstract. The coverage of regional ionosphere maps is determined by the distribution of ground-based monitoring stations, e.g., GNSS receivers. Since ionospheric delay has a high spatial correlation, ionosphere map coverage can be extended using spatial extrapolation methods. This paper proposes a support vector machine (SVM) to extrapolate the ionosphere map data with solar and geomagnetic parameters. One year of IGS ionospheric delay map data over South Korea is used to train the SVM algorithm