• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.346-353
• /
• 2023

In this paper, we propose an innovative approach that leverages deep learning to find optimal reference points for achieving precise tooth segmentation in three-dimensional tooth point cloud data. A dataset consisting of 350 aligned maxillary and mandibular cloud data was used as input, and both end coordinates of individual teeth were used as correct answers. A two-dimensional image was created by projecting the rendered point cloud data along the Z-axis, where an image of individual teeth was created using an object detection algorithm. The proposed algorithm is designed by adding various modules to the Unet model that allow effective learning of a narrow range, and detects both end points of the tooth using the generated tooth image. In the evaluation using DSC, Euclid distance, and MAE as indicators, we achieved superior performance compared to other Unet-based models. In future research, we will develop an algorithm to find the reference point of the point cloud by back-projecting the reference point detected in the image in three dimensions, and based on this, we will develop an algorithm to divide the teeth individually in the point cloud through image processing techniques.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.39-52
• /
• 2023

Cadastral maps are important official documents that affect property rights and have experienced issues due to over 100 years of usage. The accuracy of these old cadastral maps has decreased due to damage, wear, and the accumulation of errors during the rewriting process. These errors have persisted into the digitalization process, creating difficulties in map management. A nationwide project to revise cadastral and forest maps is underway, but there are technical and legal challenges in making corrections. This study addresses the technical aspects of map maintenance and proposes a method to reduce errors and improve maintenance rates by preceding with boundary adjustments. The results show that by preceding with boundary adjustments, the average distance discrepancy decreases from 22.56cm to 8.12cm, and the maintenance rate increases by more than 10%.

• Journal of Hydrogen and New Energy
• /
• v.35 no.1
• /
• pp.66-74
• /
• 2024

This study addresses the escalating issue of worldwide hydrogen gas accidents, which has seen a significant increase in occurrences. To comprehensively evaluate the risks associated with hydrogen, a two approach was employed in this study. Firstly, a qualitative risk assessment was conducted using the bow-tie method. Secondly, a quantitative consequence analysis was carried out utilizing the areal locations of hazardous atmospheres (ALOHA) model. The study applied this method to two incidents, the hydrogen explosion accident occurred at the Muskingum River power plant in Ohio, USA, 2007 and the hydrogen storage tank explosion accident occurred at the K Technopark water electrolysis system in Korea, 2019. The results of the risk assessments revealed critical issues such as deterioration of gas pipe, human errors in incident response and the omission of important gas cleaning facility. By analyzing the cause of accidents and assessing risks quantitatively, the effective accident response plans are proposed and the effectiveness is evaluated by comparing the effective distance obtained by ALOHA simulation. Notably, the implementation of these measures led to a significant 54.5% reduction in the risk degree of potential explosions compared to the existing risk levels.

• Journal of Industrial Convergence
• /
• v.22 no.1
• /
• pp.55-63
• /
• 2024

This paper discusses the concept and continuously evolving applications of metaverse technology in the field of safety education, and proposes methodologies for employing metaverse technology in safety education. Additionally, it analyzes educational cases using the metaverse to explore specific directions for the advancement of safety education. Therefore, this study aims to propose methodologies for safety education utilizing metaverse technology. Recently, the metaverse has emerged as a new platform in various fields, including education. In particular, safety education using metaverse technology is carried out because it can provide an engaging learning experience by fostering understanding and immersion through interaction, moving away from one-way didactic teaching. This paper proposes a three-stage educational process for safety education using metaverse technology and presents various implementable projects and activity examples for each stage. This approach can contribute to developing practical response skills for various situations, going beyond traditional safety education methods. Future research is expected to deeply explore the long-term effectiveness of this educational methodology and its practical applicability in educational settings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.1042-1058
• /
• 2024

Terahertz (THz) communication is becoming a key technology for future 6G wireless networks because of its ultra-wide band. However, the implementation of THz communication systems confronts formidable challenges, notably beam splitting effects and high computational complexity associated with them. Our primary objective is to design a hybrid precoder that minimizes the Euclidean distance from the fully digital precoder. The analog precoding part adopts the delay-phase alternating minimization (DP-AltMin) algorithm, which divides the analog precoder into phase shifters and time delayers. This effectively addresses the beam splitting effects within THz communication by incorporating time delays. The traditional digital precoding solution, however, needs matrix inversion in THz massive multiple-input multiple-output (MIMO) communication systems, resulting in significant computational complexity and complicating the design of the analog precoder. To address this issue, we exploit the characteristics of THz massive MIMO communication systems and construct the digital precoder as a product of scale factors and semi-unitary matrices. We utilize Schatten norm and Hölder's inequality to create semi-unitary matrices after initializing the scale factors depending on the power allocation. Finally, the analog precoder and digital precoder are alternately optimized to obtain the ultimate hybrid precoding scheme. Extensive numerical simulations have demonstrated that our proposed algorithm outperforms existing methods in mitigating the beam splitting issue, improving system performance, and exhibiting lower complexity. Furthermore, our approach exhibits a more favorable alignment with practical application requirements, underlying its practicality and efficiency.

• Archives of Plastic Surgery
• /
• v.51 no.1
• /
• pp.30-35
• /
• 2024

Background Breast aesthetics evaluation often relies on subjective assessments, leading to the need for objective, automated tools. We developed the Seoul Breast Esthetic Scoring Tool (S-BEST), a photometric analysis software that utilizes a DenseNet-264 deep learning model to automatically evaluate breast landmarks and asymmetry indices. Methods S-BEST was trained on a dataset of frontal breast photographs annotated with 30 specific landmarks, divided into an 80-20 training-validation split. The software requires the distances of sternal notch to nipple or nipple-to-nipple as input and performs image preprocessing steps, including ratio correction and 8-bit normalization. Breast asymmetry indices and centimeter-based measurements are provided as the output. The accuracy of S-BEST was validated using a paired t-test and Bland-Altman plots, comparing its measurements to those obtained from physical examinations of 100 females diagnosed with breast cancer. Results S-BEST demonstrated high accuracy in automatic landmark localization, with most distances showing no statistically significant difference compared with physical measurements. However, the nipple to inframammary fold distance showed a significant bias, with a coefficient of determination ranging from 0.3787 to 0.4234 for the left and right sides, respectively. Conclusion S-BEST provides a fast, reliable, and automated approach for breast aesthetic evaluation based on 2D frontal photographs. While limited by its inability to capture volumetric attributes or multiple viewpoints, it serves as an accessible tool for both clinical and research applications.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.17-31
• /
• 2023

An activity-based model requires detailed population information to model individual travel behavior in a disaggregated manner. The recent innovative approach developed deep generative models with novel regularization terms that improves fidelity and diversity for population synthesis. Since the method relies on measuring the distance between distribution boundaries of the sample data and the generated sample, it is crucial to obtain well-defined continuous representation from the discretized dataset. Therefore, we propose an improved entity embedding models to enhance the performance of the regularization terms, which indirectly supports the synthesis in terms of feasible and diverse populations. Our results show a 28.87% improvement in the F1 score compared to the baseline method.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.31-56
• /
• 2024

Pig farming, a vital industry, necessitates proactive measures for early disease detection and crush symptom monitoring to ensure optimum pig health and safety. This review explores advanced thermal sensing technologies and computer vision-based thermal imaging techniques employed for pig disease and piglet crush symptom monitoring on pig farms. Infrared thermography (IRT) is a non-invasive and efficient technology for measuring pig body temperature, providing advantages such as non-destructive, long-distance, and high-sensitivity measurements. Unlike traditional methods, IRT offers a quick and labor-saving approach to acquiring physiological data impacted by environmental temperature, crucial for understanding pig body physiology and metabolism. IRT aids in early disease detection, respiratory health monitoring, and evaluating vaccination effectiveness. Challenges include body surface emissivity variations affecting measurement accuracy. Thermal imaging and deep learning algorithms are used for pig behavior recognition, with the dorsal plane effective for stress detection. Remote health monitoring through thermal imaging, deep learning, and wearable devices facilitates non-invasive assessment of pig health, minimizing medication use. Integration of advanced sensors, thermal imaging, and deep learning shows potential for disease detection and improvement in pig farming, but challenges and ethical considerations must be addressed for successful implementation. This review summarizes the state-of-the-art technologies used in the pig farming industry, including computer vision algorithms such as object detection, image segmentation, and deep learning techniques. It also discusses the benefits and limitations of IRT technology, providing an overview of the current research field. This study provides valuable insights for researchers and farmers regarding IRT application in pig production, highlighting notable approaches and the latest research findings in this field.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.147-154
• /
• 2024

This study focuses on the path planning algorithm for large-scale autonomous delivery using drones and robots in urban environments. When generating delivery routes in urban environments, it is essential that avoid obstacles such as buildings, parking lots, or any other obstacles that could cause property damage. A commonly used method for obstacle avoidance is the grid-based A* algorithm. However, in large-scale urban environments, it is not feasible to set the resolution of the grid too high. If the grid cells are not sufficiently small during path planning, inefficient paths might be generated when avoiding obstacles, and smaller obstacles might be overlooked. To solve these issues, this study proposes a method that initially creates a low-resolution wide-area grid and then progressively reduces the grid cell size in areas containing registered obstacles to maintain real-time efficiency in generating paths. To implement this, obstacles in the operational area must first be registered on the map. When obstacle information is updated, the cells containing obstacles are processed as a primary subdivision, and cells closer to the obstacles are processed as a secondary subdivision. This approach is validated in a simulation environment and compared with the previous research according to the computing time and the path distance.