• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.73-78
• /
• 2021

Recently, as interest in deep learning has increased, many researches in various fields using deep learning techniques have been conducted. Studies on automatic generation of fonts using deep learning-based generation models are limited to several languages such as Roman or Chinese characters. Generating Korean font is a very time-consuming and expensive task, and can be easily created using deep learning. For research on generating Korean fonts, it is important to prepare a Korean font dataset from the viewpoint of process automation in order to keep pace with deep learning-based generation models. In this paper, we propose a Korean font dataset for deep learning-based Korean font research and describe a method of constructing the dataset. Based on the Korean font data set proposed in this paper, we show the usefulness of the proposed dataset configuration through the process of applying it to a deep learning Korean font generation application.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1589-1605
• /
• 2022

Phase unwrapping is an essential procedure for interferometric synthetic aperture radar techniques. Accordingly, a lot of phase unwrapping methods have been developed. Deep-learning-based unwrapping methods have recently been proposed. In this paper, we reviewed state-of-the-art deep-learning-based unwrapping approaches in terms of 1) the approaches to predicting unwrapped phases, 2) deep learning model structures for phase unwrapping, and 3) training data generation. The research trend of the approaches to predicting unwrapped phases was introduced by categorizing wrap count segmentation, phase jump classification, phase regression, and deep-learning-assisted method. We introduced the case studies of deep learning model structure for phase unwrapping, and model structure optimization to relate the overall phase information. In addition, we summarized the research trend of the training data generation approaches in the views of phase gradient and noise in the main. And the future direction in deep-learning-based phase unwrapping was presented. It is expected that this paper is used as guideline for exploring future direction of deep-learning-based phase unwrapping research in Korea.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.25-31
• /
• 2022

Deep learning-based image processing is essential for autonomous vehicles. To process road images in real-time in a System-on-Chip (SoC) environment, we need to execute deep learning models on a NPU (Neural Procesing Units) specialized for deep learning operations. In this study, we imported seven open-source image processing deep learning models, that were developed on GPU servers, to Texas Instrument Deep Learning (TIDL) NPU environment. We confirmed that the models imported in this study operate normally in the SoC virtual environment through performance evaluation and visualization. This paper introduces the problems that occurred during the migration process due to the limitations of NPU environment and how to solve them, and thereby, presents a reference case worth referring to for developers and researchers who want to port deep learning models to SoC environments.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.4
• /
• pp.283-292
• /
• 2020

Artificial intelligence, which is one of the representative images of the 4th industrial revolution, has been highly recognized since 2016. This paper analyzed domestic paper trends for 'Artificial Intelligence', 'Machine Learning', and 'Deep Learning' among the domestic papers provided by the Korea Academic Education and Information Service. There are approximately 10,000 searched papers, and word count analysis, topic modeling and semantic network is used to analyze paper's trends. As a result of analyzing the extracted papers, compared to 2015, in 2016, it increased 600% in the field of artificial intelligence, 176% in machine learning, and 316% in the field of deep learning. In machine learning, a support vector machine model has been studied, and in deep learning, convolutional neural networks using TensorFlow are widely used in deep learning. This paper can provide help in setting future research directions in the fields of 'artificial intelligence', 'machine learning', and 'deep learning'.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.3099-3120
• /
• 2023

The present fast-moving era brings a serious stress issue that affects elders and youngsters. Everyone has undergone stress factors at least once in their lifetime. Stress is more among youngsters as they are new to the working environment. whereas the stress factors for elders affect the individual and overall performance in an organization. Electroencephalogram (EEG) based stress level classification is one of the widely used methodologies for stress detection. However, the signal processing methods evolved so far have limitations as most of the stress classification models compute the stress level in a predefined environment to detect individual stress factors. Specifically, machine learning based stress classification models requires additional algorithm for feature extraction which increases the computation cost. Also due to the limited feature learning characteristics of machine learning algorithms, the classification performance reduces and inaccurate sometimes. It is evident from numerous research works that deep learning models outperforms machine learning techniques. Thus, to classify all the emotions based on stress level in this research work a hybrid deep learning algorithm is presented. Compared to conventional deep learning models, hybrid models outperforms in feature handing. Better feature extraction and selection can be made through deep learning models. Adding machine learning classifiers in deep learning architecture will enhance the classification performances. Thus, a hybrid convolutional neural network model was presented which extracts the features using CNN and classifies them through machine learning support vector machine. Simulation analysis of benchmark datasets demonstrates the proposed model performances. Finally, existing methods are comparatively analyzed to demonstrate the better performance of the proposed model as a result of the proposed hybrid combination.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1217-1227
• /
• 2017

Deep learning has been studied explosively and has achieved excellent performance in areas like image and speech recognition, the application areas in which computations have been challenges with ordinary machine learning techniques. The theoretical study of deep learning has also been researched toward improving the performance. In this paper, we try to find a key of the success of the deep learning in rich and efficient expressiveness of the deep learning function, and analyze the theoretical studies related to it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.283-289
• /
• 2023

AI is bringing about drastic changes not only in the aspect of technologies but also in society and culture. Medical AI based on deep learning have developed rapidly. Especially, the field of medical image analysis has been proven that AI can identify the characteristics of medical images more accurately and quickly than clinicians. Evaluating the latest results of the AI-based medical image processing is important for the implication for the development direction of medical AI. In this paper, we analyze and evaluate the latest trends in AI-based medical image analysis, which is showing great achievements in the field of medical AI in the healthcare industry. We analyze deep learning models for medical image analysis and AI-based medical image segmentation for quantitative analysis. Also, we evaluate the future development direction in terms of marketability as well as the size and characteristics of the medical AI market and the restrictions to market growth. For evaluating the latest trend in the deep learning-based medical image processing, we analyze the latest research results on the deep learning-based medical image processing and data of medical AI market. The analyzed trends provide the overall views and implication for the developing deep learning in the medical fields.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.203-208
• /
• 2024

The convergence of deep learning and smart factory is drawing a lot of attentions from not only industrial but also academic circles. The objective of this article is to quantitatively review on deep learning and smart factory from 2010 to 2023. This research analyzed the 138 articles, extracted from the Core Collection of Web of Science, in terms of four dimensions such as the main trend in article publications, the main trend in article citations, the distribution of article publications by research area, and the keywords representing the main contents of published articles. The quantitative review results reveal the following four points: First, the article publications drastically grew from 2019 to 2022 in its annual trend. Second, the article citations have rapidly grown since 2018. Third, Engineering, Computer Science, and Telecommunications are the top 3 research areas composing the 138 articles. Fourth, it is the top 10 keywords such as 'deep', 'learning', 'smart', 'detection', factory', 'data', 'system', 'manufacturing', 'neural', and 'network' that represent the main contents of the 138 articles published from 2010 to 2023 in deep learning and smart factory. These findings revealed by this quantitative review will be significantly useful for deepening and widening relevant future research on deep learning and smart factory.