• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1177-1183
• /
• 2018

Recent developments in machine learning have attracted a lot of attention for techniques such as machine learning and deep learning that implement artificial intelligence. In this paper, binary malicious code using deep learning based R-CNN is imaged and the feature is extracted from the image to classify the family. In this paper, two steps are used in deep learning to image malicious code using CNN. And classify the characteristics of the family of malicious codes using R-CNN. Generate malicious code as an image, extract features, classify the family, and automatically classify the evolution of malicious code. The detection rate of the proposed method is 93.4% and the accuracy is 98.6%. In addition, the CNN processing speed for image processing of malicious code is 23.3 ms, and the R-CNN processing speed is 4ms to classify one sample.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose a fusion model based on Long-Short Term Memory networks(LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.785-794
• /
• 2019

Recently Deep Learning technology, one of the fourth industrial revolution technologies, is used to identify the hidden meaning of network data that is difficult to detect in the security arena and to predict attacks. Property and quality analysis of data sources are required before selecting the deep learning algorithm to be used for intrusion detection. This is because it affects the detection method depending on the contamination of the data used for learning. Therefore, the characteristics of the data should be identified and the characteristics selected. In this paper, the characteristics of malware were analyzed using network data set and the effect of each feature on performance was analyzed when the deep learning model was applied. The traffic classification experiment was conducted on the comparison of characteristics according to network characteristics and 96.52% accuracy was classified based on the selected characteristics.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.668-673
• /
• 2021

As the fourth industrial revolution begins in earnest, related technologies are becoming a hot topic. Hardware development is accelerating to make the most of technologies such as high-speed wireless communication, and related companies are growing rapidly. Artificial intelligence often uses desktops in general for related research, but it is mainly used for the learning process of deep learning and often transplants the generated models into devices to be used by including them in programs, etc. However, it is difficult to produce results for devices that do not have sufficient power or performance due to excessive learning or lack of power due to the use of models built to the desktop's performance. In this paper, we analyze efficiency using boards with several Neural Process Units on sale before developing the performance of deep learning to match embedded boards, and deep learning accelerators that can increase deep learning performance with USB, and present a simple development direction possible using embedded boards.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.

• Journal of Advanced Navigation Technology
• /
• v.28 no.3
• /
• pp.262-271
• /
• 2024

In this paper, by applying deep learning, one of the A.I. techniques, through angle information, which is optical observation data generated when observing satellites at observatories, distance information from observatories is learned to predict range data, thereby increasing the precision of satellite's orbit determination. To this end, we generated observational data from GMAT, reduced the learning data error of deep learning through preprocessing of the generated observational data, and conducted deep learning through MATLAB. Based on the predicted distance information from learning, trajectory determination was performed using an extended Kalman filter, one of the filtering techniques for trajectory determination, through GMAT. The reliability of the model was verified by comparing and analyzing the orbital determination with angular information without distance information and the orbital determination result with predicted distance information from the model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.3
• /
• pp.59-71
• /
• 2018

Social media has immense popularity among all services today. Data from social network services (SNSs) can be used for various objectives, such as text prediction or sentiment analysis. There is a great deal of Korean and English data on social media that can be used for sentiment analysis, but handling such huge amounts of unstructured data presents a difficult task. Machine learning is needed to handle such huge amounts of data. This research focuses on predicting Korean and English sentiment using deep forward neural network with a deep learning architecture and compares it with other methods, such as LDA MLP and GENSIM, using logistic regression. The research findings indicate an approximately 75% accuracy rate when predicting sentiments using DNN, with a latent Dirichelet allocation (LDA) prediction accuracy rate of approximately 81%, with the corpus being approximately 64% accurate between English and Korean.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4214-4230
• /
• 2020

This paper introduces a pilot allocation scheme for massive MIMO systems based on deep convolutional neural network (CNN) learning. This work is an extension of a prior work on the basic deep learning framework of the pilot assignment problem, the application of which to a high-user density nature is difficult owing to the factorial increase in both input features and output layers. To solve this problem, by adopting the advantages of CNN in learning image data, we design input features that represent users' locations in all the cells as image data with a two-dimensional fixed-size matrix. Furthermore, using a sorting mechanism for applying proper rule, we construct output layers with a linear space complexity according to the number of users. We also develop a theoretical framework for the network capacity model of the massive MIMO systems and apply it to the training process. Finally, we implement the proposed deep CNN-based pilot assignment scheme using a commercial vanilla CNN, which takes into account shift invariant characteristics. Through extensive simulation, we demonstrate that the proposed work realizes about a 98% theoretical upper-bound performance and an elapsed time of 0.842 ms with low complexity in the case of a high-user-density condition.