• Journal of the Korean Mathematical Society
• /
• v.59 no.2
• /
• pp.311-335
• /
• 2022

This paper treats Merton's classical portfolio optimization problem for a market participant who invests in safe assets and risky assets to maximize the expected utility. When the state process is a d-dimensional Markov diffusion, this problem is transformed into a problem of solving a Hamilton-Jacobi-Bellman (HJB) equation. The main purpose of this paper is to solve this HJB equation by a deep learning algorithm: the deep Galerkin method, first suggested by J. Sirignano and K. Spiliopoulos. We then apply the algorithm to get the solution to the HJB equation and compare with the result from the finite difference method.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.991-998
• /
• 2022

Recently, object recognition using image/video signals is rapidly spreading on autonomous driving and mobile phones. However, the actual input image/video signals are easily exposed to a poor illuminance environment. A recent researches for improving illumination enable to estimate and compensate the illumination parameters. In this study, we propose VE-DCE (video enhancement zero-reference deep curve estimation) to improve the illumination of low-light images. The proposed VE-DCE uses unsupervised learning-based zero-reference deep curve, which is one of the latest among learning based estimation techniques. Experimental results show that the proposed method can achieve the quality of low-light video as well as images compared to the previous method. In addition, it can reduce the computational complexity with respect to the existing method.

• Journal of The Korean Association For Science Education
• /
• v.25 no.5
• /
• pp.563-570
• /
• 2005

This study investigated the relationships among middle school students' understanding about the nature of scientific knowledge, conceptual understanding, and learning strategies. Grade 7 students (N=162) in Incheon completed the nature of scientific knowledge scales (NSKS) and a learning strategy questionnaire. After learning density by way of a CAl program, a conception test was administered. Results indicated that students' conceptual understanding and both deep and surface learning strategies were significantly correlated to their understanding about the nature of scientific knowledge. A cluster analysis was used to classify students on the basis of their deep and surface learning strategies. Three clusters of students with distinctive learning strategy patterns were found; high deep-low surface strategy (cluster 1), low deep-high surface strategy (cluster 2), and high deep-high surface strategy (cluster 3). One-way ANOVA results revealed that the scores of cluster 3 were significantly higher than those of the others in the NSKS and the conception test. Additionally, cluster 1 also performed better than cluster 2 in the conception test. Lastly, educational implications were discussed.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.511-518
• /
• 2022

Supervised learning based on deep learning has made a leap forward in various application fields. However, many supervised learning methods work under the common assumption that training and test data are extracted from the same distribution. If it deviates from this constraint, the deep learning network trained in the training domain is highly likely to deteriorate rapidly in the test domain due to the distribution difference between domains. Domain adaptation is a methodology of transfer learning that trains a deep learning network to make successful inferences in a label-poor test domain (i.e., target domain) based on learned knowledge of a labeled-rich training domain (i.e., source domain). In particular, the unsupervised domain adaptation technique deals with the domain adaptation problem by assuming that only image data without labels in the target domain can be accessed. In this paper, we explore the unsupervised domain adaptation techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.55-65
• /
• 2023

In this paper, we apply KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) algorithm-driven topic extraction and topic frequency analysis to deep learning and reinforcement learning research to discover the rapidly changing trends in them. First, we crawled abstracts of research papers on deep learning and reinforcement learning, and temporally divided them into two groups. After pre-processing the crawled data, we extracted topics using KeyBERT algorithm, and then analyzed the extracted topics in terms of topic occurrence frequency. This analysis reveals that there are distinct trends in research work of all analyzed algorithms and applications, and we can clearly tell which topics are gaining more interest. The analysis also proves the effectiveness of the utilized topic extraction and topic frequency analysis in research trend analysis, and this trend analysis scheme is expected to be used for research trend analysis in other research fields. In addition, the analysis can provide insight into how deep learning will evolve in the near future, and provide guidance for select research topics and methodologies by informing researchers of research topics and methodologies which are recently attracting attention.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.119-124
• /
• 2023

Deep learning has recently demonstrated conspicuous efficacy across diverse domains than traditional machine learning techniques, as the most popular approach for pattern recognition. The classification problems for tabular data, however, are remain for the area of traditional machine learning. This paper introduces a novel network module designed to tabular data into high-dimensional tensors. The module is integrated into conventional deep learning networks and subsequently applied to the classification of structured data. The proposed method undergoes training and validation on four datasets, culminating in an average accuracy of 90.22%. Notably, this performance surpasses that of the contemporary deep learning model, TabNet, by 2.55%p. The proposed approach acquires significance by virtue of its capacity to harness diverse network architectures, renowned for their superior performance in the domain of computer vision, for the analysis of tabular data.

• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.864-875
• /
• 2018

In this paper, we propose a measurement method for height of white light scanning interferometer using deep learning. In order to measure the fine surface shape, a three-dimensional surface shape measurement technique is required. A typical example is a white light scanning interferometer. In order to calculate the surface shape from the measurement image of the white light scanning interferometer, the height of each pixel must be calculated. In this paper, we propose a neural network for height calculation and use virtual data generation method to train this neural network. The accuracy was measured by inputting 57 actual data to the neural network which had completed the learning. We propose two new functions for accuracy measurement. We have analyzed the cases where there are many errors among the accuracy calculation values, and it is confirmed that there are many errors when there is no interference fringe or outside the learned range. We confirmed that the proposed neural network works correctly in most cases. We expect better results if we improve the way we generate learning data.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.929-937
• /
• 2020

In this manuscript, the UNet++ model, which is one of the representative deep learning techniques for semantic segmentation, was used to detect changes in temporal satellite images. To analyze the learning results according to various loss functions, we evaluated the change detection results using trained UNet++ models by binary cross entropy and the Jaccard coefficient. In addition, the learning results of the deep learning model were analyzed compared to existing pixel-based change detection algorithms by using WorldView-3 images. In the experiment, it was confirmed that the performance of the deep learning model could be determined depending on the characteristics of the loss function, but it showed better results compared to the existing techniques.