• 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.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.137-153
• /
• 2024

This study introduces a new approach in Korean morphological analysis combining dictionary-based techniques with Transformer-based deep learning models. The key innovation is the use of a BERT-based reranking system, significantly enhancing the accuracy of traditional morphological analysis. The method generates multiple suboptimal paths, then employs BERT models for reranking, leveraging their advanced language comprehension. Results show remarkable performance improvements, with the first-stage reranking achieving over 20% improvement in error reduction rate compared with existing models. The second stage, using another BERT variant, further increases this improvement to over 30%. This indicates a significant leap in accuracy, validating the effectiveness of merging dictionary-based analysis with contemporary deep learning. The study suggests future exploration in refined integrations of dictionary and deep learning methods as well as using probabilistic models for enhanced morphological analysis. This hybrid approach sets a new benchmark in the field and offers insights for similar challenges in language processing applications.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.127-135
• /
• 2024

Recent studies have shown that inverse design using deep learning has the potential to rapidly generate the optimal design that satisfies the target performance without the need for iterative optimization processes. Unlike traditional methods, deep learning allows the network to rapidly generate a large number of solution candidates for the same objective after a single training, and enables the generation of diverse designs tailored to the objectives of inverse design. These inverse design techniques are expected to significantly enhance the efficiency and innovation of design processes in various fields such as aerospace, biology, medical, and engineering. We analyzes inverse design models that are mainly utilized in the nano and chemical fields, and proposes inverse design models based on supervised and unsupervised learning that can be applied to the engineering system. It is expected to present the possibility of effectively applying inverse design methodologies to the design optimization problem in the field of engineering according to each specific objective.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1005-1012
• /
• 2021

Recently, the use of various location-based services-based location information systems using maps on the web has been expanding, and there is a need for a monitoring system that can check power demand in real time as an alternative to energy saving. In this study, we developed a deep learning real-time virtual power demand prediction web system using open source-based mapping service to analyze and predict the characteristics of power demand data using deep learning. In particular, the proposed system uses the LSTM(Long Short-Term Memory) deep learning model to enable power demand and predictive analysis locally, and provides visualization of analyzed information. Future proposed systems will not only be utilized to identify and analyze the supply and demand and forecast status of energy by region, but also apply to other industrial energies.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.768-783
• /
• 2020

Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship's drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1115-1121
• /
• 2018

In this paper, we have studied a data analysis method by deep learning to predict learning achievements based on accumulated data in cyber university learning management system. By predicting learner's academic achievement, it can be used as a tool to enhance learner's learning and improve the quality of education. In order to improve the accuracy of prediction of learning achievements, the autoencoder based attendance prediction method is developed to improve the prediction performance and deep learning algorithm with ongoing evaluation metrics and predicted attendance are used to predict the final score. In order to verify the prediction results of the proposed method, the final grade was predicted by using the evaluation factor attendance data of the learning process. The experimental result showed that we can predict the learning achievements in the middle of semester.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.521-530
• /
• 2018

This paper proposes "The Agriculture Decision-making System(ADS) based on Deep Learning for improving crop productivity" that collects weather information based on location supporting precision agriculture, predicts current crop condition by using the collected information and real time crop data, and notifies a farmer of the result. The system works as follows. The ICM(Information Collection Module) collects weather information based on location supporting precision agriculture. The DRCM(Deep learning based Risk Calculation Module) predicts whether the C, H, N and moisture content of soil are appropriate to grow specific crops according to current weather. The RNM(Risk Notification Module) notifies a farmer of the prediction result based on the DRCM. The proposed system improves the stability because it reduces the accuracy reduction rate as the amount of data increases and is apply the unsupervised learning to the analysis stage compared to the existing system. As a result, the simulation result shows that the ADS improved the success rate of data analysis by about 6%. And the ADS predicts the current crop growth condition accurately, prevents in advance the crop diseases in various environments, and provides the optimized condition for growing crops.

• Journal of Drive and Control
• /
• v.18 no.4
• /
• pp.9-18
• /
• 2021

This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user's desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.5159-5178
• /
• 2018

Network Intrusion detection is a rapidly growing field of information security due to its importance for modern IT infrastructure. Many supervised and unsupervised learning techniques have been devised by researchers from discipline of machine learning and data mining to achieve reliable detection of anomalies. In this paper, a deep convolutional neural network (DCNN) based intrusion detection system (IDS) is proposed, implemented and analyzed. Deep CNN core of proposed IDS is fine-tuned using Randomized search over configuration space. Proposed system is trained and tested on NSLKDD training and testing datasets using GPU. Performance comparisons of proposed DCNN model are provided with other classifiers using well-known metrics including Receiver operating characteristics (RoC) curve, Area under RoC curve (AuC), accuracy, precision-recall curve and mean average precision (mAP). The experimental results of proposed DCNN based IDS shows promising results for real world application in anomaly detection systems.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.87-93
• /
• 2019

In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.