• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.630-631
• /
• 2021

In this paper, we propose a high-resolution fringe pattern generation technique using deep learning networks. Generating a hologram using a computer requires a very large amount of computation. Therefore, in order to replace this, it was shown that it can be replaced through deep learning, but there was a limitation in the resolution of the output fringe pattern. To improve this, we propose an algorithm for generating a high-resolution fringe pattern.

• International Journal of Computer Science & Network Security
• /
• v.23 no.6
• /
• pp.140-146
• /
• 2023

A detailed survey, applications and challenges of video encoding-decoding systems is discussed in this paper. A novel architecture has also been set aside for future work in the same direction. The literature reviews span the years 1960 to the present, highlighting the benchmark methods proposed by notable academics in the field of video compression. The timeline used to illustrate the review is divided into three sections. Classical methods, conventional heuristic methods, and current deep learning algorithms are all used for video compression in these categories. The milestone contributions are discussed for each category. The methods are summarized in various tables, along with their benefits and drawbacks. The summary also includes some comments regarding specific approaches. Existing studies' shortcomings are thoroughly described, allowing potential researchers to plot a course for future research. Finally, a closing note is made, as well as future work in the same direction.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.40-44
• /
• 2023

The defect detection based on deep learning requires minimal loss and high accuracy to pinpoint product defects. In this paper, we confirm the loss rate of deep learning training based on disc-shaped artificial scaffold images. It is intended to compare the performance of Cross-Entropy functions used in object detection algorithms. The model was constructed using normal, defective artificial scaffold images and category cross entropy and sparse category cross entropy. The data was repeatedly learned five times using each loss function. The average loss rate, average accuracy, final loss rate, and final accuracy according to the loss function were confirmed.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.30-31
• /
• 2021

This study aims to build a deep learning model that can predict the value of concrete mixing properties according to a given concrete strength value. A model was created for a total of 1,291 concrete data, including 8 characteristics related to concrete mixing elements and environment, and the compressive strength of concrete. As the deep learning model, DNN-3L-256N, which showed the best performance on the prior study, was used. The average value for each characteristic of the data set was used as the initial input value. In results, in the case of 'curing temperature', which had a narrow range of values in the existing data set, showed the lowest error rate with less than 1% error based on MAE. The highest error rate with an error of 12 to 14% for fly and bfs.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.66.2-66.2
• /
• 2020

We propose a deep learning analysis technique with a convolutional neural network (CNN) to predict the evolutionary track of the Epoch of Reionization (EoR) from the 21-cm differential brightness temperature tomography images. We use 21cmFAST, a fast semi-numerical cosmological 21-cm signal simulator, to produce mock 21-cm maps between z = 6 ~ 13. We then apply two observational effects, such as instrumental noise and limit of (spatial and depth) resolution somewhat suitable for realistic choices of the Square Kilometre Array (SKA), into the 21-cm maps. We design our deep learning model with CNN to predict the sliced-averaged neutral hydrogen fraction from the given 21-cm map. The estimated neutral fraction from our CNN model has great agreement with the true value even after coarsely smoothing with broad beam size and frequency bandwidth and heavily covered by noise with narrow beam size and frequency bandwidth. Our results show that the deep learning analyzing method has the potential to reconstruct the EoR history efficiently from the 21-cm tomography surveys in future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.409-410
• /
• 2022

This paper proposes 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 Advanced Information Technology and Convergence
• /
• v.9 no.1
• /
• pp.127-134
• /
• 2019

In terms of deep Reinforcement Learning (RL), exploration can be worked stochastically in the action of a state space. On the other hands, exploitation can be done the proportion of well generalization behaviors. The balance of exploration and exploitation is extremely important for better results. The randomly selected action with ε-greedy for exploration has been regarded as a de facto method. There is an alternative method to add noise parameters into a neural network for richer exploration. However, it is not easy to predict or detect over-fitting with the stochastically exploration in the perturbed neural network. Moreover, the well-trained agents in RL do not necessarily prevent or detect over-fitting in the neural network. Therefore, we suggest a novel design of a deep RL by the balance of the exploration with drop-out to reduce over-fitting in the perturbed neural networks.

• Smart Structures and Systems
• /
• v.32 no.4
• /
• pp.219-233
• /
• 2023

Crack width is an important indicator to evaluate the health condition of the concrete structure. The crack width is measured by manual using crack width gauge commonly, which is time-consuming and laborious. In this paper, we have proposed a fast and simplified crack width quantification method via deep Q learning and geometric calculation. Firstly, the crack edge is extracted by using U-Net network and edge detection operator. Then, the intelligent decision of is made by the deep Q learning model. Further, the geometric calculation method based on endpoint and curvature extreme point detection is proposed. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method, achieving high precision in the real crack width quantification.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.90-99
• /
• 2023

This paper deals with studying strategy about impact of deep learning (DL) on the factor of Korean economic growth. To study classification of impact factors of Korean economic growth, we suggest dynamic equation of microeconomy and study methods on economic growth impact of deep learning. Next step is to suggest DL model to dynamic equation with Korean economy data with growth related factors to classify what factor is import and dominant factors to build policy and education. DL gives an influence in many areas because it can be implemented with ease as just normal editing works and speak including code development by using huge data. Currently, young generations will take a big impact on their job selection because generative AI can do well as much as humans can do it everywhere. Therefore, policy and education methods should be rearranged as new paradigm. However, government and officers do not understand well how it is serious in policy and education. This paper provides method of policy and education for AI education including generative AI through analysing many papers and reports, and experience.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.161-165
• /
• 2023

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.