• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.883-888
• /
• 2023

Since data centers are places that provide IT services 24 hours a day, 365 days a year, data center power consumption is expected to increase to approximately 10% by 2030, and the introduction of high-density IT equipment will gradually increase. In order to ensure the stable operation of IT equipment, various types of research are required to conserve energy in cooling and improve energy management. This study proposes the following process for energy saving in data centers. We conducted CFD modeling of the data center, proposed an artificial intelligence-based thermal environment prediction model, compared actual measured data, the predicted model, and the CFD results, and finally evaluated the data center's thermal management performance. It can be seen that the predicted values of RCI, RTI, and PUE are also similar according to the normalization used in the normalization method. Therefore, it is judged that the algorithm proposed in this study can be applied and provided as a thermal environment prediction model applied to data centers.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.1
• /
• pp.15-26
• /
• 2003

Ultrasonic inspection methods are widely used for detecting flaws in materials. The signal analysis step plays a crucial part in the data interpretation process. A number of signal processing methods have been proposed to classify ultrasonic flaw signals. One of the more popular methods involves the extraction of an appropriate set of features followed by the use of a neural network for the classification of the signals in the feature space. This paper describes an alternative approach which uses the least mean square (LMS) method and expectation maximization (EM) algorithm with the model based deconvolution which is employed for classifying nondestructive evaluation (NDE) signals from steam generator tubes in a nuclear power plant. The signals due to cracks and deposits are not significantly different. These signals must be discriminated to prevent from happening a huge disaster such as contamination of water or explosion. A model based deconvolution has been described to facilitate comparison of classification results. The method uses the space alternating generalized expectation maximization (SAGE) algorithm In conjunction with the Newton-Raphson method which uses the Hessian parameter resulting in fast convergence to estimate the time of flight and the distance between the tube wall and the ultrasonic sensor Results using these schemes for the classification of ultrasonic signals from cracks and deposits within steam generator tubes are presented and showed a reasonable performances.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.37-45
• /
• 2006

In this paper, we propose the development of MHLA(Modulatory Hippocampus Learning Algorithm) which remodel a principle of brain of hippocampus. Hippocampus takes charge auto-associative memory and controlling functions of long-term or short-term memory strengthening. We organize auto-associative memory based 3 steps system(DG, CA3, CAl) and improve speed of learning by addition of modulator to long-term memory learning. In hippocampal system, according to the 3 steps order, information applies statistical deviation on Dentate Gyrus region and is labelled to responsive pattern by adjustment of a good impression. In CA3 region, pattern is reorganized by auto-associative memory. In CAI region, convergence of connection weight which is used long-term memory is learned fast by neural networks which is applied modulator. To measure performance of MHLA, PCA(Principal Component Analysis) is applied to face images which are classified by pose, expression and picture quality. Next, we calculate feature vectors and learn by MHLA. Finally, we confirm cognitive rate. The results of experiments, we can compare a proposed method of other methods, and we can confirm that the proposed method is superior to the existing method.

• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.393-413
• /
• 2021

Digital humanities, which creates new and innovative knowledge through the combination of digital information technology and humanities research problems, can be seen as a representative multidisciplinary field of study. To investigate the intellectual structure of the digital humanities field, a network analysis of authors and keywords co-word was performed on a total of 441 papers in the last two years (2019, 2020) at the Digital Humanities Conference. As the results of the author and keyword analysis show, we can find out the active activities of Europe, North America, and Japanese and Chinese authors in East Asia. Through the co-author network, 11 dis-connected sub-networks are identified, which can be seen as a result of closed co-authoring activities. Through keyword analysis, 16 sub-subject areas are identified, which are machine learning, pedagogy, metadata, topic modeling, stylometry, cultural heritage, network, digital archive, natural language processing, digital library, twitter, drama, big data, neural network, virtual reality, and ethics. This results imply that a diver variety of digital information technologies are playing a major role in the digital humanities. In addition, keywords with high frequency can be classified into humanities-based keywords, digital information technology-based keywords, and convergence keywords. The dynamics of the growth and development of digital humanities can represented in these combinations of keywords.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2001.11a
• /
• pp.20-20
• /
• 2001

우리나라 제지산업은 화학펼프의 80%를 수입에 의존하고 었으나 고지회수율 및 이용율이 세계적으로 볼 때 매우 높은 환경친화적 산업이다. 고지 재활용 공정 중에 서 가장 핵심적인 공정인 부유부상 공정은 고상계의 표면특성 차이를 이용하여 소수성 의 잉크업자를 기포에 부착시켜 부상을 통하여 제거하는 공정이다. 고지 사용의 고도화 를 위해서는 부유부상 공정의 효율 증대가 절실히 요구되고 있다. 또한 부유부상 공정 의 핵심적인 인자로 부유부상을 통하여 제거되는 고형물질의 표면 특성 특히 소수화도 가 중요하다는 것은 보고된 바 있으나 부유부상에 필요한 표면 특성의 존재 여부와 표 면 에너지와 부유부상 효율의 관계 등에 관한 기본적인 연구가 더욱 필요한 실정이다. 이에 본 연구에서는 부유부상 공정을 기초과학적 측면에서 규명하기 위해 마 이 크로 크리 스탈린 셀룰로오스(Microcrystalline cellulose: MCC)를 모델 물질로 사용하 고 이들의 표면특성을 접촉각 측정을 통하여 평가하였다. 친수성의 표면 특성을 지닌 M MCC의 표면 특성을 소수성으로 바꾸기 위하여 AKD(alkyl ketene dimer)의 함량별로 사이징 처리하여 소수성을 지닌 잉크를 모벨링 하고 친수성 MCC를 염색시약을 이용 하여 흑색으로 염색함으로써 소수화 된 MCC와의 색차를 두어 섬유를 모델링 하였다. 이렇게 제조된 MCC의 소수화 정도를 평가하기 위하여 분말상태인 MCC를 pellet으로 제조하여 각기 다른 표면장력과 표변특성을 지난 용액을 이용하여 Advancing Contact A Angle을 측정하고 다양한 방법으로 이를 분석하여 시료의 표면에너지를 평가하였다 그 리고 부유부상 셀내의 액상의 이온강도와 표면장력 등 화학적인 인자에 의한 부유부상 분리효과를 평가하였다.있었다 (그림 2). 칼렌다는 종이를 높은 전단력과 압축력으로 변형시키는데 비해 도침은 단순히 압축 압력만을 종이에 가하는 것이 다르다고 볼 수 있는데, 라 이너지와 백상지가 같은 조건하에서 왜 이러한 큰 차이를 보이는 이유를 아직 알수 없다.해 동일한 공정 데이터들올 이용하여 보편적으로 사용하는 통계기법 중의 하나인 주성분회귀분석을 실시하였다. 주성분 분석은 여러 개의 반응변수에 대하여 얻어진 다변량 자료의 다차원적인 변 수들을 축소, 요약하는 차원의 단순화와 더불어 서로 상관되어있는 반응변수들 상호간 의 복잡한 구조를 분석하는 기법이다. 본 발표에서는 공정 자료를 활용하여 인공신경망 과 주성분분석을 통해 공정 트러블의 발생에 영향 하는 인자들을 보다 현실적으로 추 정하고, 그 대책을 모색함으로써 이를 최소화할 수 있는 방안을 소개하고자 한다.금 빛 용사 둥과 같은 표면처리를 할 경우임의 소재 표면에 도금 및 용 사에 용이한 재료를 오버레이용접시킨 후 표면처리를 함으로써 보다 고품질의 표면층을 얻기위한 시도가 이루어지고 있다. 따라서 국내, 외의 오버레이 용접기술의 적용현황 및 대표적인 적용사례, 오버레이 용접기술 및 용접재료의 개발현황 둥을 중심으로 살펴봄으로서 아직 국내에서는 널리 알려지지 않은 본 기 술의 활용을 넓이고자 한다. within minimum time from beginning of the shutdown.및 12.36%, $101{\sim}200$일의 경우 12.78% 및 12.44%, 201일 이상의 경우 13.17% 및 11.30%로 201일 이상의 유기의 경우에만 대조구와 삭제 구간에 유의적인(p<0.05) 차이를 나타내었다.는 담수(淡水)에서 10%o의 해수(海水)로 이주된지 14일(日) 이후에 신장(腎臟)에서 수축된

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.168-177
• /
• 2020

Seabed multiple reflections (seabed multiples) are the main cause of misinterpretations of primary reflections in both shot gathers and stack sections. Accordingly, seabed multiples need to be suppressed throughout data processing. Conventional model-driven methods, such as prediction-error deconvolution, Radon filtering, and data-driven methods, such as the surface-related multiple elimination technique, have been used to attenuate multiple reflections. However, the vast majority of processing workflows require time-consuming steps when testing and selecting the processing parameters in addition to computational power and skilled data-processing techniques. To attenuate seabed multiples in seismic reflection data, input gathers with seabed multiples and label gathers without seabed multiples were generated via numerical modeling using the Marmousi2 velocity structure. The training data consisted of normal-moveout-corrected common midpoint gathers fed into a U-Net neural network. The well-trained model was found to effectively attenuate the seabed multiples according to the image similarity between the prediction result and the target data, and demonstrated good applicability to field data.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.1-11
• /
• 2006

Many research demonstrations and commercial applications have been tried to develop face detection and recognition systems. Human face detection plays an important role in applications such as access control and video surveillance, human computer interface, identity authentication, etc. There are some special problems such as a face connected with background, faces connected via the skin color, and a face divided into several small parts after skin region segmentation in generally. It can be allowed many face detection techniques to solve the first and second problems. However, it is not easy to detect a face divided into several parts of regions for reason of different illumination conditions in the third problem. Therefore, we propose an efficient modified skin segmentation algorithm to solve this problem because the typical region segmentation algorithm can not be used to. Our algorithm detects skin regions over the entire image, and then generates face candidate regions using our skin segmentation algorithm For each face candidate, we implement the procedure of region merging for divided regions in order to make a region using adjacency between homogeneous regions. We utilize various different searching window sizes to detect different size faces and a face detection classifier based on a back-propagation algorithm in order to verify whether the searching window contains a face or not.

• Geophysics and Geophysical Exploration
• /
• v.12 no.4
• /
• pp.347-354
• /
• 2009

Physical properties of rocks are strongly dependant on details of pore micro-structures, which can be used for quantifying relations between physical properties of rocks through pore-scale simulation techniques. Recently, high-resolution scan techniques, such as X-ray microtomography and high performance computers make it possible to calculate permeability from pore micro-structures of rocks. We try to extend this simulation methodology to velocity and electrical conductivity. However, the smoothing effect during tomographic inversion creates artifacts in pore micro-structures and causes inaccurate property estimation. To mitigate this artifact, we tried to use sharpening filter and neural network classification techniques. Both methods gave noticeable improvement in pore structure imaging and accurate estimation of permeability and electrical conductivity, which implies that our method effectively removes the smoothing effect in pore structures. However, the calculated velocities showed only incremental improvement. By comparison between thin section images and tomogram, we found that our resolution is not high enough, and it is mainly responsible for the inaccuracy in velocity despite the successful removal of the smoothing effect. In conclusion, our methods can be very useful for pore-scale modeling, since it can create accurate pore structure without the smoothing effect. For accurate velocity estimation, the resolution of pore structure should be at least three times higher than that for permeability simulation.