• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1182-1194
• /
• 2018

The Dynamic Adaptive Streaming over HTTP(DASH) is envisioned to evolve to meet an increasing demand on providing seamless video streaming services in the near future. The DASH performance heavily depends on the client's adaptive quality selection algorithm that is not included in the standard. The existing conventional algorithms are basically based on a procedural algorithm that is not easy to capture and reflect all variations of dynamic network and traffic conditions in a variety of network environments. To solve this problem, this paper proposes a novel quality selection mechanism based on the Deep Q-Network(DQN) model, the DQN-based DASH Adaptive Bitrate(ABR) mechanism. The proposed mechanism adopts a new reward calculation method based on five major performance metrics to reflect the current conditions of networks and devices in real time. In addition, the size of the consecutive video segment to be downloaded is also considered as a major learning metric to reflect a variety of video encodings. Experimental results show that the proposed mechanism quickly selects a suitable video quality even in high error rate environments, significantly reducing frequency of quality changes compared to the existing algorithm and simultaneously improving average video quality during video playback.

• Journal of Fashion Business
• /
• v.4 no.2
• /
• pp.95-111
• /
• 2000

The purpose of this research is to investigate the concept of the photomontage technique, one of the various photographic techniques, and to analyze the photomontage image through the patterns that appeared in 1990's fashions. Moreover, by making clothes using the photomontage image, the intention of this study to apply the technique in real life is achieved. The results of this thesis for making clothes utilizing image of the photomontage are as followings. First, the photomontage expands the variety of materials that can be used, because the clothes using the photomontage image are able to take any photo images. Second, two different eras can co-exist in a piece of work since a photomontage work can uses two images from different eras. Third, it allows greater adaptability by expressing variety and utility in the making of the casual styles using conventional photo materials. The conclusion of this study is that the clothes appearing in the late 20th century using the photomontage image have been developed corresponding to the accelerated development of photography, machinery, and technical skill in civilization. Trends break away from the conventional expressions of art. This is a new trend and direction in art that will effect culture in the 21st century. The photo montage image would show the possibility of a good unification between human being and machines.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.2
• /
• pp.214-224
• /
• 2016

This paper proposes an algorithm to effectively detect the traffic lights and recognize the traffic signals using a monocular camera mounted on the front windshield glass of a vehicle in day time. The algorithm consists of three main parts. The first part is to generate the candidates of a traffic light. After conversion of RGB color model into HSI and YCbCr color spaces, the regions considered as a traffic light are detected. For these regions, edge processing is applied to extract the borders of the traffic light. The second part is to divide the candidates into traffic lights and non-traffic lights using Haar-like features and Adaboost algorithm. The third part is to recognize the signals of the traffic light using a template matching. Experimental results show that the proposed algorithm successfully detects the traffic lights and recognizes the traffic signals in real time in a variety of environments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.1
• /
• pp.26-34
• /
• 1996

One of the challenging tasks in visual inspection using CCD camera is to identify surface defects in an image with complex textured backgeound. In microscopic view, the surface of real objects shows regular or random textured patterns. In this paper, we present a visual inspection algorithm to extract abnormal surface defects in an image with textured background. The algorithm uses the space and frequency information at the same time by introducing the Dominant Frequency Map(DFM) which can describe the frequency characteristics of every small local region of an input image. We demonstrate the feasibility and effectiveness of the method through a series of real experiments for a 14" TV CRT mold. The method successfully identifies a variety of infinitesimal defects, whose size is larger than $50\mu\textrm{m}$, of the mold. The experimental results show that the DFM based method is less sensitive to the environmental changes, such as illumination and defocusing, than conventional vision techniques.ques.

• The Journal of Korean Physical Therapy
• /
• v.14 no.3
• /
• pp.92-105
• /
• 2002

This research described dynamic scapulohumeral rhythm though the measurement of inter relationship between humorous and scapular movement during elevation of the arm in the scapular plane. In the previous studies static plane film X-ray has usually been used, but the limitation of such method was that it did not show the real· movement. In this study, we investigated real movement of humorous and scapular bones by Digital fluoroscopy system. 1. In resting position, humorous was taken to lie at the average $5.97^{\circ}$ in abduction, and scapular at the average $3.66^{\circ}$ in internal rotation. 2. At the maximal abduction, humorous was abducted to the average of 181.25", and scapular was rotated externally to $51.43^{\circ}$. 3. This research has shown that there is a variety of scapulohumeral rhythm from resting position to $60^{\circ}$ abduction in elevation of humorous. This case study demonstrated that the ratio n of scapulohumeral rhythm is 3.46 to 1, but there was individual difference.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.18 no.2
• /
• pp.181-192
• /
• 2014

In this paper, we propose a robust real-time myocardial border tracking algorithm for echocardiography. Commonly, after an initial contour of LV border is traced at one or two frame from the entire cardiac cycle, LV contour tracking is performed over the remaining frames. Among a variety of tracking techniques, optical flow method is the most widely used for motion estimation of moving objects. However, when echocardiography data is heavily corrupted in some local regions, the errors bring the tracking point out of the endocardial border, resulting in distorted LV contours. This shape distortion often occurs in practice since the data acquisition is affected by ultrasound artifacts, dropout or shadowing phenomena of cardiac walls. The proposed method deals with this shape distortion problem and reflects the motion realistic LV shape by applying global deformation modeled as affine transform partitively to the contour. We partition the tracking points on the contour into a few groups and determine each affine transform governing the motion of the partitioned contour points. To compute the coefficients of each affine transform, we use the least squares method with equality constraints that are given by the relationship between the coefficients and a few contour points showing good tracking results. Many real experiments show that the proposed method supports better performance than existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.103-107
• /
• 2013

In this paper, A real-time lane tracking algorithm is proposed for lane departure warning system. To eliminate perspective effect, input image is converted into Bird's View by inverse perspective mapping. Next, suitable features are extracted for lane detection. Lane feature that correspond to area of interest and RANSAC are used to detect lane candidates. And driving lane is decided by clustering of lane candidates. Finally, detected lane is tracked using the Kalman filter. Experimental results show that the proposed algorithm can be processed within 30ms and its detection rate is approximately 90% on the highway in a variety of environments such as day and night.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4072-4079
• /
• 2021

This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.

• The Research Journal of the Costume Culture
• /
• v.30 no.1
• /
• pp.121-144
• /
• 2022

This study analyzed the effects of fashion creators' innovativeness and attractiveness on consumer response and orientation toward a sustainable relationship in personal media. A survey was conducted with consumers aged in their 20s and 30s who had experience in sharing video content or writing comments and participating in fashion creators' real-time broadcasting of personal media. The results show that the innovativeness of fashion creators was classified into originality, opinion leadership, variety, and adventurous spirit, while attractiveness was classified into physical, social, and professional attractiveness. Consumer responses were classified into either emotional or cognitive responses, and sustainable relationship orientation was classified into communication, sharing, and relationship sustainability. The originality and variety of the fashion creators positively affected the emotional and cognitive responses of consumers. Adventurous spirit positively affected emotional response, whereas opinion leadership positively affected cognitive response. In addition, the social and professional attractiveness of fashion creators positively affected consumers' emotional and cognitive responses. Emotional and cognitive responses positively affected consumers' sustainable relationship orientation. The originality and opinion leadership of the fashion creators positively affected the three factors of sustainable relationship orientation, while variety positively affected communication and relationship sustainability. Fashion creators' social and professional attractiveness positively affected the three factors of sustainable relationship orientation, and physical attractiveness positively affected relationship sustainability. The results of this study are expected to provide useful data on the direction of fashion startups using personal media and marketing as well as distribution strategies in the fashion industry.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2003.03a
• /
• pp.309-314
• /
• 2003

Impact Echo method has been successful in detecting a variety of defects in concrete structure. This study has the objectives to show important aspects of applying the Discrete Wavelet Transform(DWT) to signal processing of Modified Impact Echo(ModIE) Measurement systems and to the understanding of the seismic wave propagation. The data of ModIE were processed by DWT and compared with the results of conventional ModIE Analysis. Although it is inconsistent in the evaluated thickness of concrete lining, the DWT provides the features of separation, synthesis and de-noising in the original signal. The application of technique by wavelet was explained numerically with ABAQUS and performed experimentally with a real scale model in this work. Further works on the possible ways for creating new mother wavelet are specially needed for the enhancement of seismic signal analysis.