• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.117-122
• /
• 2021

Autonomous driving allows cars to drive without people and is being studied very actively thanks to the recent development of artificial intelligence technology. Among artificial intelligence technologies, deep reinforcement learning is used most effectively. Deep reinforcement learning requires us to build a neural network using an appropriate activation function. So far, many activation functions have been suggested, but different performances have been shown depending on the field of application. This paper compares and evaluates the performance of which activation function is effective when using deep reinforcement learning to learn autonomous driving on highways. To this end, the performance metrics to be used in the evaluation were defined and the values of the metrics according to each activation function were compared in graphs. As a result, when Mish was used, the reward was higher on average than other activation functions, and the difference from the activation function with the lowest reward was 9.8%.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.357-363
• /
• 2023

In underwater signal processing, separating individual signals from mixed signals has long been a challenge due to low signal quality. The common method using Short-time Fourier transform for spectrogram analysis has faced criticism for its complex parameter optimization and loss of phase data. We propose a Triple-path Recurrent Neural Network, based on the Dual-path Recurrent Neural Network's success in long time series signal processing, to handle three-dimensional tensors from multi-channel sensor input signals. By dividing input signals into short chunks and creating a 3D tensor, the method accounts for relationships within and between chunks and channels, enabling local and global feature learning. The proposed technique demonstrates improved Root Mean Square Error and Scale Invariant Signal to Noise Ratio compared to the existing method.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.139-148
• /
• 1999

오늘날 기술집약적인 벤처기업들에 대한 관심이 집중되고 있다. 소수의 진취적인 벤처기업들이 기술개발 및 신상품 개발 등 두드러진 활약을 보이고 있기 때문이다. 그러나 실제 이 벤처기업의 성공 가능성은 그렇게 높지 않다. 특히 벤처기업 환경이 아직 미약한 국내의 경우 위험부담이 훨씬 더 크다. 이러한 벤처기업 환경에서 투자대상 벤처기업을 선정하는 것은 매우 전략적인 의사결정이다. 일반적으로 일반 벤처투자가들은 관심이 있는 산업에 해당하는 기업의 사업계획서와 기초적인 관련 정보를 토대로 투자여부를 결정한다. 그렇지만 실제로는 이와 같은 분석에 필수적으로 요구되는 정보가 불확실할 뿐만 아니라 기술분야에 대한 전문적 지식도 부족하기 때문에 투자 여부를 결정하는 것은 매우 복잡하고 어려운 문제이다. 그러므로 투자대상 벤처기업의 선정을 효과적으로 지원해주는 체계적인 접근이 필요하다. 특히 벤처 사업과 관련된 기술 동향 및 수준 등에 관련된 전문 지식과 경험이 체계적으로 제공되어야 하고 또한 벤처 투자가의 개인적 경험과 판단이 평가 프로세스에 직접적으로 반영될 수 있어야 한다. 이에 본 연구에서는 전문가의 지식과 경험을 체계화하고 투자가의 개인적 판단을 효과적으로 수용할 수 있는 전문가시스템의 접근방법을 제시하고자 한다. 투자대상 벤처기업의 선정을 위한 전문가시스템을 구축하기 위해 본 연구에서는 다양한 정보수집 과정을 거쳤다. 우선 벤처 투자와 관련된 기존 문헌을 심층 분석하였으며 아울러 벤처 투자 업계에서 활약중인 전문 벤처캐피탈리스트들과의 수차례 인터뷰를 통해 벤처기업 평가의 주요 요인과 의사결정 과정을 파악할 수 있었다. 이러한 과정을 통하여 본 연구에서는 벤처 투자의 90%를 차지하는 정보통신분야에 속한 기법 중에서 투자대상 벤처기업의 선정을 위한 전문가시스템을 구축중이다.의 밀도를 비재무적 지표변수로 산정하여 로지스틱회귀 분석과 인공신경망 기법으로 검증하였다. 로지스틱회귀분석 결과에서는 재무적 지표변수 모형의 전체적 예측적중률이 87.50%인 반면에 재무/비재무적 지표모형은 90.18%로서 비재무적 지표변수 사용에 대한 개선의 효과가 나타났다. 표본기업들을 훈련과 시험용으로 구분하여 분석한 결과는 전체적으로 재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer algorithm could efficiently reject ISI of channel and in

• Electronics and Telecommunications Trends
• /
• v.37 no.1
• /
• pp.73-83
• /
• 2022

Visual object tracking can be utilized in various applications and has attracted considerable attention in the field of computer vision. Visual object tracking technology is classified in various ways based on the number of tracking objects and the methodologies employed for tracking algorithms. This report briefly introduces the visual object tracking challenge that contributes to the development of single object tracking technology. Furthermore, we review ten Siamese network-based algorithms that have attracted attention, owing to their high tracking speed (despite the use of neural networks). In addition, we discuss the prospects of the Siamese network-based object tracking algorithms.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.1004-1012
• /
• 2020

We present a novel content-preserving seam estimation algorithm for real-time high-resolution video stitching. Seam estimation is one of the fundamental steps in image/video stitching. It is to minimize visual artifacts in the transition areas between images. Typical seam estimation algorithms are based on optimization methods that demand intensive computations and large memory. The algorithms, however, often fail to avoid objects and results in cropped or duplicated objects. They also lack temporal consistency and induce flickering between frames. Hence, we propose an efficient and temporarily-consistent seam estimation algorithm that utilizes a straight line. The proposed method also uses convolutional neural network-based instance segmentation to locate seam at out-of-objects. Experimental results demonstrate that the proposed method produces visually plausible stitched videos with minimal visual artifacts in real-time.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.104-105
• /
• 2023

해양 관측과 위성 원격탐사를 이용하여 시공간적으로 다양하게 변하는 생태 어장 환경 및 선박 관련 자료를 획득할 수 있다. 이번 연구의 주요 목적은 야간 불빛 위성 자료를 이용하여 광범위한 해역에 대한 어선의 위치 분포를 파악하는 딥러닝 기반 모델을 제안하는 것이다. 제안한 모델의 정확성을 평가하기 위해 야간 조업 어선의 위치를 포함하고 있는 AIS(Automatic Identification System) 정보와 상호 비교 평가 하였다. 이를 위해, 먼저 AIS 자료를 획득 및 분석하는 방법을 소개한다. 해양안전종합시스템(General Information Center on Maritime Safety & Security, GICOMS)으로부터 제공받은 AIS 자료는 동적정보와 정적정보로 나뉜다. 동적 정보는 일별 자료로 구분되어있으며, 이 정보에는 해상이동업무식별번호(Maritime Mobile Service Identity, MMSI), 선박의 시간, 위도, 경도, 속력(Speed over Ground, SOG), 실침로(Course over Ground, COG), 선수방향(Heading) 등이 포함되어 있다. 정적정보는 1개의 파일로 구성되어 있으며, 선박명, 선종 코드, IMO Number, 호출부호, 제원(DimA, DimB, DimC, Dim D), 홀수, 추정 톤수 등이 포함되어 있다. 이번 연구에서는 선박의 정보에서 어선의 정보를 추출하여 비교 자료로 사용하였으며, 위성 자료는 구름의 영향이 없는 깨끗한 날짜의 영상 자료를 선별하여 사용하였다. 야간 불빛 위성 자료, 구름 정보 등을 이용하여 야간 조업 어선의 불빛을 감지하는 심층신경망(Deep Neural Network; DNN) 기반 모델을 제안하였다. 본 연구의결과는 야간 어선의 분포를 감시하고 한반도 인근 어장을 보호하는데 기여할 것으로 기대된다.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.6
• /
• pp.34-43
• /
• 2019

The maintenance cost for road pavement is gradually increasing due to the continuous increase in road extension as well as increase in the number of old routes that have passed the public period. As a result, there is a need for a method of minimizing costs through preventative grievance preventive maintenance requires the establishment of a strategic plan through accurate prediction of road pavement. Hence, In this study, the deep neural network(DNN) and the recurrent neural network(RNN) were used in order to develop the expressway pavement damage prediction model. A superior model among these two network models was then suggested by comparing and analyzing their performance. In order to solve the RNN's vanishing gradient problem, the LSTM (Long short-term memory) circuits which are a more complicated form of the RNN structure were used. The learning result showed that the RMSE value of the RNN-LSTM model was 0.102 which was lower than the RMSE value of the DNN model, indicating that the performance of the RNN-LSTM model was superior. In addition, high accuracy of the RNN-LSTM model was verified through the comparison between the estimated average road pavement condition and the actually measured road pavement condition of the target section over time.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.167-177
• /
• 2022

In order to obtain satellite image products using the image transmitted to the ground station after capturing the satellite images, many image pre/post-processing steps are involved. During the pre/post-processing, when converting from level 1R images to level 1G images, geometric correction is essential. An interpolation method necessary for geometric correction is inevitably used, and the quality of the level 1G images is determined according to the accuracy of the interpolation method. Also, it is crucial to speed up the interpolation algorithm by the level processor. In this paper, we proposed a lightweight CNN-based interpolation method required for geometric correction when converting from level 1R to level 1G. The proposed method doubles the resolution of satellite images and constructs a deep learning network with a lightweight deep convolutional neural network for fast processing speed. In addition, a feature map fusion method capable of improving the image quality of multispectral (MS) bands using panchromatic (PAN) band information was proposed. The images obtained through the proposed interpolation method improved by about 0.4 dB for the PAN image and about 4.9 dB for the MS image in the quantitative peak signal-to-noise ratio (PSNR) index compared to the existing deep learning-based interpolation methods. In addition, it was confirmed that the time required to acquire an image that is twice the resolution of the 36,500×36,500 input image based on the PAN image size is improved by about 1.6 times compared to the existing deep learning-based interpolation method.