• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.230-231
• /
• 2023

This study proposes a deep reinforcement learning-based algorithm to automatically generate a ship's passage plan. First, Busan Port and Gwangyang Port were selected as target areas, and a container ship with a draft of 16m was designated as the target vessel. The experimental results showed that the ship's passage plan generated using deep reinforcement learning was more efficient than the Q-learning-based algorithm used in previous research. This algorithm presents a method to generate a ship's passage plan automatically and can contribute to improving maritime safety and efficiency.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.2
• /
• pp.126-134
• /
• 2023

Drones are emerging as a new security threat, and the world is working to reduce them. Detection and identification are the most difficult and important parts of the anti-drone systems. Existing detection and identification methods each have their strengths and weaknesses, so complementary operations are required. Detection and identification performance in anti-drone systems can be improved through the use of artificial intelligence. This is because artificial intelligence can quickly analyze differences smaller than humans. There are three ways to utilize artificial intelligence. Through reinforcement learning-based physical control, noise and blur generated when the optical camera tracks the drone may be reduced, and tracking stability may be improved. The latest NeRF algorithm can be used to solve the problem of lack of enemy drone data. It is necessary to build a data network to utilize artificial intelligence. Through this, data can be efficiently collected and managed. In addition, model performance can be improved by regularly generating artificial intelligence learning data.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.142-147
• /
• 2024

The emergence of programs like Midjourney, particularly known for its text-to-image capability, has significantly impacted design and creative industries. Midjourney continually updates its database and algorithms to enhance user experience, with a focus on character consistency. This paper's examination of the latest V6 version of Midjourney reveals notable advancements in its characteristics and design principles, especially in the realm of character generation. By comparing V6 with its predecessors, this study underscores the significant strides made in ensuring consistent character portrayal across different plots and timelines.Such improvements in AI-driven character consistency are pivotal for storytelling. They ensure coherent and reliable character representation, which is essential for narrative clarity, emotional resonance, and overall effectiveness. This coherence supports a more immersive and engaging storytelling experience, fostering deeper audience connection and enhancing creative expression.The findings of this study encourage further exploration of Midjourney's capabilities for artistic innovation. By leveraging its advanced character consistency, creators can push the boundaries of storytelling, leading to new and exciting developments in the fusion of technology and art.

• Tunnel and Underground Space
• /
• v.25 no.2
• /
• pp.210-219
• /
• 2015

This paper describes a new quantitative process for evaluating the roughness of discontinuity, which is suggested as a qualitative criteria in RMR or Q-system. For this purpose, the Delphi method which is one of the surveying methods was introduced. The selected panels were asked to evaluate the roughness of discontinuities on the Web which was hosted by authors in advance. A total of 3 surveys were performed using JRCs suggested by Barton and Choubey as well as Ai generated by the Monte Carlo simulations. After each survey, the results were provided to all panels for comparing their decisions to others. As surveys proceeded, better consensus and convergence were achieved. With a good agreement of panels on roughness classification, the quantitative criteria for roughness of discontinuity in RMR and Q-system was established in this study.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.267-277
• /
• 2024

This paper explores the use of machine learning in game production to create goal-oriented, realistic animations for skeleton monsters. The purpose of this research is to enhance realism by implementing intelligent movements in monsters within game development. To achieve this, we designed and implemented a learning model for skeleton monsters using reinforcement learning algorithms. During the machine learning process, various reward conditions were established, including the monster's speed, direction, leg movements, and goal contact. The use of configurable joints introduced physical constraints. The experimental method validated performance through seven statistical graphs generated using machine learning methods. The results demonstrated that the developed model allows skeleton monsters to move to their target points efficiently and with natural animation. This paper has implemented a method for creating game monster animations using machine learning, which can be applied in various gaming environments in the future. The year 2024 is expected to bring expanded innovation in the gaming industry. Currently, advancements in technology such as virtual reality, AI, and cloud computing are redefining the sector, providing new experiences and various opportunities. Innovative content optimized for this period is needed to offer new gaming experiences. A high level of interaction and realism, along with the immersion and fun it induces, must be established as the foundation for the environment in which these can be implemented. Recent advancements in AI technology are significantly impacting the gaming industry. By applying many elements necessary for game development, AI can efficiently optimize the game production environment. Through this research, We demonstrate that the application of machine learning to Unity and game engines in game development can contribute to creating more dynamic and realistic game environments. To ensure that VR gaming does not end as a mere craze, we propose new methods in this study to enhance realism and immersion, thereby increasing enjoyment for continuous user engagement.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.209-227
• /
• 2023

The government continues to announce measures to revitalize smart construction technology based on BIM for productivity innovation in the construction industry. In the design phase, the goal is design automation and optimization by converging BIM Data and other advanced technologies. Accordingly, in the basic design of the Namhae Seomyeon-Yeosu Sindeok National Road Construction Project, a domestic undersea tunnel project, BIM-based design was carried out by developing tunnel design automation technology using 3D spatial information according to the tunnel design process. In order to derive the optimal alignment, more than 10,000 alignment cases were generated in 36hr using the generative design technique and a quantitative evaluation of the objective functions defined by the designer was performed. AI-based ground classification and 3D Geo Model were established to evaluate the economic feasibility and stability of the optimal alignment. AI-based ground classification has improved its precision by performing about 30 types of ground classification per borehole, and in the case of the 3D Geo Model, its utilization can be expected in that it can accumulate ground data added during construction. In the case of 3D blasting design, the optimal charge weight was derived in 5 minutes by reviewing all security objects on the project range on Dynamo, and the design result was visualized in 3D space for intuitive and convenient construction management so that it could be used directly during construction.

• Journal of Radiation Protection and Research
• /
• v.44 no.4
• /
• pp.149-155
• /
• 2019

Background: Magnetic resonance (MR) image guided radiation therapy system, enables real time MR guided radiotherapy (RT) without additional radiation exposure to patients during treatment. However, MR image lacks electron density information required for dose calculation. Image fusion algorithm with deformable registration between MR and computed tomography (CT) was developed to solve this issue. However, delivered dose may be different due to volumetric changes during image registration process. In this respect, synthetic CT generated from the MR image would provide more accurate information required for the real time RT. Materials and Methods: We analyzed 1,209 MR images from 16 patients who underwent MR guided RT. Structures were divided into five tissue types, air, lung, fat, soft tissue and bone, according to the Hounsfield unit of deformed CT. Using the deep learning model (U-NET model), synthetic CT images were generated from the MR images acquired during RT. This synthetic CT images were compared to deformed CT generated using the deformable registration. Pixel-to-pixel match was conducted to compare the synthetic and deformed CT images. Results and Discussion: In two test image sets, average pixel match rate per section was more than 70% (67.9 to 80.3% and 60.1 to 79%; synthetic CT pixel/deformed planning CT pixel) and the average pixel match rate in the entire patient image set was 69.8%. Conclusion: The synthetic CT generated from the MR images were comparable to deformed CT, suggesting possible use for real time RT. Deep learning model may further improve match rate of synthetic CT with larger MR imaging data.