• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.853-873
• /
• 2021

In recent years, deep reinforcement learning (DRL) models are enjoying great interest as their success in a variety of challenging tasks. Deep Q-Network (DQN) is a widely used deep reinforcement learning model, which trains an intelligent agent that executes optimal actions while interacting with an environment. This model is well known for its ability to surpass skilled human players across many Atari 2600 games. Although DQN has achieved excellent performance in practice, there lacks a clear understanding of why the model works. In this paper, we present a visual analytics system for understanding deep Q-network in a non-blind matter. Based on the stored data generated from the training and testing process, four coordinated views are designed to expose the internal execution mechanism of DQN from different perspectives. We report the system performance and demonstrate its effectiveness through two case studies. By using our system, users can learn the relationship between states and Q-values, the function of convolutional layers, the strategies learned by DQN and the rationality of decisions made by the agent.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.58 no.3
• /
• pp.272-280
• /
• 2022

The first step is to determine the principal dimensions of the design ship, such as length between perpendiculars, beam, draft and depth when accomplishing the design of a new vessel. To make this process easier, a database with a large amount of existing ship data and a regression analysis technique are needed. Recently, deep learning, a branch of artificial intelligence (AI) has been used in regression analysis. In this paper, deep learning neural networks are used for regression analysis to find the regression function between the input and output data. To find the neural network structure with the highest accuracy, the errors of neural network structures with varying the number of the layers and the nodes are compared. In this paper, Python TensorFlow Keras API and MATLAB Deep Learning Toolbox are used to build deep learning neural networks. Constructed DNN (deep neural networks) makes helpful in determining the principal dimension of the ship and saves much time in the ship design process.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.1
• /
• pp.55-62
• /
• 2023

In this study, a chest deflection is predicted by introducing a deep learning technique with the results of the frontal impact of the USNCAP conducted for 110 car models from MY2018 to MY2020. The 120 data are divided into training data and test data, and the training data is divided into training data and validation data to determine the hyperparameters. In this process, the deceleration data of each vehicle is averaged in units of 10 ms from crash pulses measured up to 100 ms. The performance of the deep learning model is measured by the indices of the mean squared error and the mean absolute error on the test data. A DNN (Deep Neural Network) model can give different predictions for the same hyperparameter values at every run. Considering this, the mean and standard deviation of the MSE (Mean Squared Error) and the MAE (Mean Absolute Error) are calculated. In addition, the deep learning model performance according to the inclusion of CVW (Curb Vehicle Weight) is also reviewed.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1119-1130
• /
• 2019

With the wide spread of Social Network Services (SNS), fake news-which is a way of disguising false information as legitimate media-has become a big social issue. This paper proposes a deep learning architecture for detecting fake news that is written in Korean. Previous works proposed appropriate fake news detection models for English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shorter sentences than English even with the same meaning; therefore, it is difficult to operate a deep neural network because of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-based deep learning architectures and "Fasttext" which is a word-embedding model learned by syllable unit. After training and testing its implementation, we could achieve meaningful accuracy for classification of the body and context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.

• Research in Mathematical Education
• /
• v.27 no.1
• /
• pp.1-24
• /
• 2024

In this paper, the author analyzed characteristics of deep mathematics learning in problem solving and problem-posing classroom teaching. Based on a simple wrong plane geometry problem, the author describes the classroom experience how one expert Chinese mathematics teacher guides students to modify geometry problems from solution to investigation, and guides the students to learn how to pose mathematics problems in inquiry-based deep learning classroom. This also demonstrates how expert mathematics teacher can effectively guide students to teach deep learning in regular classroom.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.27-32
• /
• 2020

In this paper, we propose an algorithm to measure the accumulated status of scrap boxes where metal scraps are accumulated. The accumulated status measuring is defined as a multi-class classification problem, and the method with deep learning classify the accumulated status using only the scrap box image. The learning was conducted by the Transfer Learning method, and the deep learning model was NASNet-A. In order to improve the accuracy of the model, we combined the Random Forest classifier with the trained NASNet-A and improved the model through post-processing. Testing with 4,195 data collected in the field showed 55% accuracy when only NASNet-A was applied, and the proposed method, NASNet with Random Forest, improved the accuracy by 88%.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.197-204
• /
• 2020

In this paper, we present a learning platform for robotic grasping in real world, in which actor-critic deep reinforcement learning is employed to directly learn the grasping skill from raw image pixels and rarely observed rewards. This is a challenging task because existing algorithms based on deep reinforcement learning require an extensive number of training data or massive computational cost so that they cannot be affordable in real world settings. To address this problems, the proposed learning platform basically consists of two training phases; a learning phase in simulator and subsequent learning in real world. Here, main processing blocks in the platform are extraction of latent vector based on state representation learning and disentanglement of a raw image, generation of adapted synthetic image using generative adversarial networks, and object detection and arm segmentation for the disentanglement. We demonstrate the effectiveness of this approach in a real environment.

• Journal of Technologic Dentistry
• /
• v.42 no.1
• /
• pp.1-8
• /
• 2020

Purpose: Among the virtual teeth generated by Deep Convolutional Generative Adversarial Networks (DCGAN), the optimal data was analyzed for the number of learning. Methods: We extracted 50 mandibular first molar occlusal surfaces and trained 4,000 epoch with DCGAN. The learning screen was saved every 50 times and evaluated on a Likert 5-point scale according to five classification criteria. Results were analyzed by one-way ANOVA and tukey HSD post hoc analysis (α = 0.05). Results: It was the highest with 83.90±6.32 in the number of group3 (2,050-3,000) learning and statistically significant in the group1 (50-1,000) and the group2 (1,050-2,000). Conclusion: Since there is a difference in the optimal virtual tooth generation according to the number of learning, it is necessary to analyze the learning frequency section in various ways.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.4
• /
• pp.257-267
• /
• 2017

Compressed Sensing(CS) deals with linear inverse problems. The theoretical results of CS have had an impact on inference problems and presented amazing research achievements in the related fields including signal processing and information theory. However, in order for CS to be applied in practical environments, there are two significant challenges to be solved. One is to guarantee in real time recovery of CS signals, and the other is that the signals have to be sparse. To this end, the latest researches using deep learning technology have emerged. In this paper, we consider CS problems based on deep learning and discuss the latest research results. And the approaches for CS signal reconstruction using deep learning show superior results in terms of recovery time and performance. It is expected that the approaches for CS reconstruction using deep learning shown in recent studies can not only raise the possibility of utilization of CS, but also be highly exploited in the fields of signal processing and communication areas.