• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.145-146
• /
• 2017

본 논문에서는 남성의 하반신을 촬영한 MRI 영상으로부터 전립선을 분할하는 알고리즘을 제안한다. 우선 3 차원 입체 영상을 학습하기 위해 3D 컨볼루션 계층(convolutional layer) 및 3D 풀링 계층(pooling layer)에 기반한 네트워크를 제안한다. 다음으로 네트워크의 최후단에 해당하는 전연결 계층(fully connected layer)의 강인한 학습을 돕는 잡음 계층을 제안한다. 잡음 계층은 네트워크의 학습 파라미터 혹은 출력 영상에 가우시안 잡음를 더함으로써 드롭 아웃과 같이 훈련 영상에 대한 과적합(overfitting)을 막고 테스트 영상에 강인한 네트워크의 학습을 돕는다. 마지막으로 실험을 통해 제안하는 기법이 기존 기법에 비해 우수한 분할 성능을 보임을 확인한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.555-559
• /
• 2007

AMGA is a metadata catalogue service which offers access to metadata for files stored on the Grid. We evaluated the performance of AMGA and analyzed overhead in the current AMGA implementation. It had 700% poor throughput (read/insert per second) compared with the direct DB access. The biggest overhead was in managing GSI/SSL Connections, degrading throughput about 350%. We alsomeasured the throughput of load-balanced AMGA services, and it showed linear throughput improvement when we increased the number of AMGA server. In addition, we measured the throughputin the WAN environment, and it showed the number of the maximum connections that an AMGA server can handle is the most critical factor in the throughput.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.561-562
• /
• 2021

CNN (Convolutional Neural Network) is widely used to recognize various images. In this presentation, a single digit handwritten by humans was recognized by applying the CNN technique of deep learning. The deep learning network consists of a convolutional layer, a pooling layer, and a platen layer, and finally, we set an optimization method, learning rate and loss functions.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.992-1004
• /
• 2017

To assess image quality accurately, an image quality assessment (IQA) metric is required to reflect the human visual system (HVS) properly. In other words, the structure, color, and contrast ratio of the image should be evaluated in consideration of various factors. In addition, as mobile embedded devices such as smartphone become popular, a fast computing speed is important. In this paper, the proposed IQA metric combines color similarity, gradient similarity, and phase similarity synergistically to satisfy the HVS and is designed by using optimized pooling and quantization for fast computation. The proposed IQA metric is compared against existing 13 methods using 4 kinds of evaluation methods. The experimental results show that the proposed IQA metric ranks the first on 3 evaluation methods and the first on the remaining method, next to VSI which is the most remarkable IQA metric. Its computing speed is on average about 20% faster than VSI's. In addition, we find that the proposed IQA metric has a bigger amount of correlation with the HVS than existing IQA metrics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.141-147
• /
• 2021

In this paper, in order to improve the utilization of hyperspectral large-capacity data feature information by reducing complex computations by dimension reduction of neural network inputs in embedded systems, the band selection algorithm is applied in each subset. Among feature extraction and feature selection techniques, the feature selection aim to improve the optimal number of bands suitable for datasets, regardless of wavelength range, and the time and performance, more than others algorithms. Through this experiment, although the time required was reduced by 1/3 to 1/9 times compared to the others band selection technique, meaningful results were improved by more than 4% in terms of performance through the K-neighbor classifier. Although it is difficult to utilize real-time hyperspectral data analysis now, it has confirmed the possibility of improvement.

• Journal of Convergence for Information Technology
• /
• v.7 no.2
• /
• pp.31-36
• /
• 2017

In this paper, we try to search and reproduce the image part of a specific cast from a large number of images. The conventional method must manually set the offset value when searching for a scene or viewing a corner. However, in this paper, the proposed method learns the main character 's face, then finds the main character in the image recognition and moves to the scene where the main character appears to reproduce the image. Data for specific performers is extracted and collected using crawl techniques. Based on the collected data, we learn using convolutional neural network algorithm and perform performance evaluation using it. The performance evaluation measures the accuracy by extracting and judging a specific performer learned in the extracted key frame while playing the drama. The performance confirmation of how quickly and accurately the learned scene is searched has obtained about 93% accuracy. Based on the derived performance, it is applied to the image service such as viewing, searching for person and detailed information retrieval per corner

• Review of Culture and Economy
• /
• v.21 no.2
• /
• pp.3-28
• /
• 2018

This study focuses on analyzing the glass ceiling effect in arts and culture professionals through the quintile decomposition applied to the RIF unconditional quantile regression and Oaxaca-Blinder decomposition technique. From the industrial viewpoint, we divide arts and culture professionals into cultural contents professionals(large category J industry) and arts professionals(large category R industry). For our analysis, we employ the pooling data of 'Wage Structure Survey' from 2009 to 2016. Our results are summarized as follows. First, as OLS wage decomposition showed that the gender wage gap among the arts professionals was lower than cultural contents professionals, but the discrimination portion of total gender wage gap was larger. Second, from quintile regression decompositions, the glass ceiling effects of two types of professionals showed different results. Cultural contents sector was observed with the "steady glass ceiling effect" as the portion of the discrimination was continuously increased, while the arts sector was observed with the "limited glass ceiling effect" as the discrimination had drastically increased in the 80s and 90s.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.635-645
• /
• 2007

Component technology has been widely accepted as an effective way for building software systems with reusable components, and Microsoft (MS) .NET is one of the recent representative component technologies. Model Driven Architecture (MDA) is a new development paradigm which generates software by transforming design models automatically and incrementally. Transformation of structural models in MDA has been successfully applied. However, transformation of dynamic models and pervasive services, such as transaction service, security service, synchronization service and object pooling are largely remains as an area for further research. The recent enterprise system has multi tier distributed architecture, and the functionality of early mentioned pervasive services is essential for this architecture. .NET platform can implement Component Object Model+ (COM+) component for supporting pervasive services by specify Attribute code. In this paper, we specify the functionalities of the COM+ component offering pervasive services, and then those functionalities are defined by UML profile. By using the profile, the Platform Specific Model (PSM) for .NET/C# is specified, and .NET components are automatically generated through our tool. The development productivity, extensibility, portability, and maintenance of software can be dramatically improved by using of the proposed methods.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.544-551
• /
• 2023

Speech enhancement used to improve the perceptual quality and intelligibility of noise speech has been studied as a method using a complex-valued spectrum that can improve both magnitude and phase in a method using a magnitude spectrum. In this paper, a study was conducted on how to apply attention mechanism to complex-valued spectrum-based speech enhancement systems to further improve the intelligibility and quality of noise speech. The attention is performed based on additive attention and allows the attention weight to be calculated in consideration of the complex-valued spectrum. In addition, the global average pooling was used to consider the importance of the feature map. Complex-valued spectrum-based speech enhancement was performed based on the Deep Complex U-Net (DCUNET) model, and additive attention was conducted based on the proposed method in the Attention U-Net model. The results of the experiments on noise speech in a living room environment showed that the proposed method is improved performance over the baseline model according to evaluation metrics such as Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short Time Object Intelligence (STOI), and consistently improved performance across various background noise environments and low Signal-to-Noise Ratio (SNR) conditions. Through this, the proposed speech enhancement system demonstrated its effectiveness in improving the intelligibility and quality of noisy speech.