• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.693-696
• /
• 2021

There are various algorithms in reinforcement learning, and the algorithm used differs depending on the field. Even in games, specific algorithms are used when developing AI (artificial intelligence) using reinforcement learning. Different algorithms have different learning methods, so artificial intelligence is created differently. Therefore, the developer has to choose the appropriate algorithm to implement the AI for the purpose. To do that, the developer needs to know the algorithm's learning method and which algorithms are effective for which AI. Therefore, this paper compares the learning methods of three algorithms, SAC, PPO, and POCA, which are algorithms used to implement game AI. These algorithms are practical to apply to which types of AI implementations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.3
• /
• pp.170-177
• /
• 2010

Poker is a game of imperfect information where competing players must deal with multiple risk factors stemming from unknown information while making the best decision to win, and this makes it an interesting test-bed for artificial intelligence research. This paper introduces a new learning AI algorithm with embedded opponent modeling that can be used for these types of situations and we use this AI and apply it to a poker program. The new AI will be based on several graphs with each of its nodes representing inputs, and the algorithm will learn the optimal decision to make by updating the weight of the edges connecting these nodes and returning a probability for each action the graphs represent.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.1989-2001
• /
• 2024

Artificial intelligence (AI) techniques are now being considered in the nuclear field, but application faces with the lack of actual plant data. For this reason, most previous studies on AI applications in nuclear power plants (NPPs) have relied on simulators or thermal-hydraulic codes to mimic the plants. However, it remains uncertain whether an AI model trained using a simulator can properly work in an actual NPP. To address this issue, this study suggests the use of metadata, which can give information about parameter trends. Referred to here as robust AI, this concept started with the idea that although the absolute value of a plant parameter differs between a simulator and actual NPP, the parameter trend is identical under the same scenario. Based on the proposed robust AI, this study designs an event diagnosis algorithm to classify abnormal and emergency scenarios in NPPs using prototypical learning. The algorithm was trained using a simulator referencing a Westinghouse 990 MWe reactor and then tested in different environments in Advanced Power Reactor 1400 MWe simulators. The algorithm demonstrated robustness with 100 % diagnostic accuracy (117 out of 117 scenarios). This indicates the potential of the robust AI-based algorithm to be used in actual plants.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of The Korean Association of Information Education
• /
• v.24 no.5
• /
• pp.495-509
• /
• 2020

This study is a theoretical research to explore ways to effectively learn AI in the age of intelligent information driven by artificial intelligence (hereinafter referred to as AI). The emphasis is on presenting a teaching method to make AI education accessible not only to students majoring in mathematics, statistics, or computer science, but also to other majors such as humanities and social sciences and the general public. Given the need for 'Explainable AI(XAI: eXplainable AI)' and 'the importance of storytelling for a sensible and intelligent machine(AI)' by Patrick Winston at the MIT AI Institute [33], we can find the significance of research on AI storytelling learning model. To this end, we discuss the possibility through a pilot study targeting general students of an university in Daegu. First, we introduce the AI storytelling(AI+ST) learning method[30], and review the educational goals, the system of contents, the learning methodology and the use of new AI tools in the method. Then, the results of the learners are compared and analyzed, focusing on research questions: 1) Can the AI+ST learning method complement algorithm-driven or developer-centered learning methods? 2) Whether the AI+ST learning method is effective for students and thus help them to develop their AI comprehension, interest and application skills.

• Clinical Endoscopy
• /
• v.55 no.5
• /
• pp.594-604
• /
• 2022

Over the past decade, technological advances in deep learning have led to the introduction of artificial intelligence (AI) in medical imaging. The most commonly used structure in image recognition is the convolutional neural network, which mimics the action of the human visual cortex. The applications of AI in gastrointestinal endoscopy are diverse. Computer-aided diagnosis has achieved remarkable outcomes with recent improvements in machine-learning techniques and advances in computer performance. Despite some hurdles, the implementation of AI-assisted clinical practice is expected to aid endoscopists in real-time decision-making. In this summary, we reviewed state-of-the-art AI in the field of gastrointestinal endoscopy and offered a practical guide for building a learning image dataset for algorithm development.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.1-14
• /
• 2022

The proof-of-work consensus algorithm used by most blockchains is causing a massive waste of computing resources in the form of mining. A useful proof-of-work consensus algorithm has been studied to reduce the waste of computing resources in proof-of-work, but there are still resource waste and mining centralization problems when creating blocks. In this paper, the problem of resource waste in block generation was solved by replacing the relatively inefficient computation process for block generation with distributed artificial intelligence model learning. In addition, by providing fair rewards to nodes participating in the learning process, nodes with weak computing power were motivated to participate, and performance similar to the existing centralized AI learning method was maintained. To show the validity of the proposed methodology, we implemented a blockchain network capable of distributed AI learning and experimented with reward distribution through resource verification, and compared the results of the existing centralized learning method and the blockchain distributed AI learning method. In addition, as a future study, the thesis was concluded by suggesting problems and development directions that may occur when expanding the blockchain main network and artificial intelligence model.

• Journal of Drive and Control
• /
• v.18 no.1
• /
• pp.24-30
• /
• 2021

There is an increasing interest in condition-based maintenance for the prevention of economic loss due to failure. Moreover, immense research is being carried out in related technologies in the field of construction machinery. In particular, data-based failure diagnosis methods that employ AI (machine & deep learning) algorithms are in the spotlight. In this study, we have focused on the failure diagnosis and mode classification of reduction gear of excavator's travel device by using the AI algorithm. In addition, a remote monitoring system has been developed that can monitor the status of the reduction gear by using the developed diagnosis algorithm. The failure diagnosis algorithm was performed in the process of data acquisition of normal and abnormal under various operating conditions, data processing and analysis by the wavelet transformation, and learning. The developed algorithm was verified based on three-evaluation conditions. Finally, we have built a system that can check the status of the reduction gear of travel devices on the web using the Edge platform, which is embedded with the failure diagnosis algorithm and cloud.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.223-224
• /
• 2021

The process before the model learning stage in AI R&D can be subdivided into data collection/cleansing-data purification-data labeling. After that, according to the purpose of development, it goes through a stage of verifying the model by performing learning by using the algorithm of the artificial intelligence model. Several studies describe an important part of AI research as the learning stage, and try to increase the accuracy by changing the structure and layer of the AI model. However, if the refinement and labeling process of the learning data is tailored only to the model format and is not made for the purpose of development, the desired AI model cannot be obtained. The latest research reveals that most AI research failures are the failure of the learning data rather than the structure of the AI model. analyzed.