• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.323-330
• /
• 2023

The development of an analysis model that reflects the microstructure characteristics of polyvinyl alcohol (PVA) fiber-reinforced cementitious composites, which have a highly complex microstructure, enables synergy between efficient material design and real experiments. PVA fiber orientations are an important factor that influences the mechanical behavior of PVA fiber-reinforced cementitious composites. Owing to the difficulty in distinguishing the gray level value obtained from micro-CT images of PVA fibers from adjacent phases, fiber segmentation is time-consuming work. In this study, a micro-CT test with a voxel size of 0.65 ㎛³ was performed to investigate the three-dimensional distribution of fibers. To segment the fibers and generate training data, histogram, morphology, and gradient-based phase-segmentation methods were used. A U-net model was proposed to segment fibers from micro-CT images of PVA fiber-reinforced cementitious composites. Data augmentation was applied to increase the accuracy of the training, using a total of 1024 images as training data. The performance of the model was evaluated using accuracy, precision, recall, and F1 score. The trained model achieved a high fiber segmentation performance and efficiency, and the approach can be applied to other specimens as well.

• International Journal of High-Rise Buildings
• /
• v.12 no.3
• /
• pp.225-234
• /
• 2023

Even at this point in the era of digital transformation, we are still facing many problems in the safety sector that cannot prevent the occurrence or spread of human casualties. When you are in an unexpected emergency, it is often difficult to respond only with human physical ability. Human casualties continue to occur at construction sites, manufacturing plants, and multi-use facilities used by many people in everyday life. If you encounter a situation where normal judgment is impossible in the event of an emergency at a life site where there are still many safety blind spots, it is difficult to cope with the existing manual guidance method. New variable guidance technology, which combines artificial intelligence and digital twin, can make it possible to prevent casualties by processing large amounts of data needed to derive appropriate countermeasures in real time beyond identifying what safety accidents occurred in unexpected crisis situations. When a simple control method that divides and monitors several CCTVs is digitally converted and combined with artificial intelligence and 3D digital twin control technology, intelligence augmentation (IA) effect can be achieved that strengthens the safety decision-making ability required in real time. With the enforcement of the Serious Disaster Enterprise Punishment Act, the importance of distributing a smart location guidance system that urgently solves the decision-making delay that occurs in safety accidents at various industrial sites and strengthens the real-time decision-making ability of field workers and managers is highlighted. The smart location guidance system that combines artificial intelligence and digital twin consists of AIoT HW equipment, wireless communication NW equipment, and intelligent SW platform. The intelligent SW platform consists of Builder that supports digital twin modeling, Watch that meets real-time control based on synchronization between real objects and digital twin models, and Simulator that supports the development and verification of various safety management scenarios using intelligent agents. The smart location guidance system provides on-site monitoring using IoT equipment, CCTV-linked intelligent image analysis, intelligent operating procedures that support workflow modeling to immediately reflect the needs of the site, situational location guidance, and digital twin virtual fencing access control technology. This paper examines the limitations of traditional fixed passive guidance methods, analyzes global technology development trends to overcome them, identifies the digital transformation properties required to switch to intelligent variable smart location guidance methods, explains the characteristics and components of AI-based public facility smart fire safety integrated system (ISFS).

• Journal of the Korean Society of Radiology
• /
• v.81 no.5
• /
• pp.1164-1174
• /
• 2020

Purpose To evaluate a deep learning model to predict recurrence of thyroid tumor using preoperative ultrasonography (US). Materials and Methods We included representative images from 229 US-based patients (male:female = 42:187; mean age, 49.6 years) who had been diagnosed with thyroid cancer on preoperative US and subsequently underwent thyroid surgery. After selecting each representative transverse or longitudinal US image, we created a data set from the resulting database of 898 images after augmentation. The Python 2.7.6 and Keras 2.1.5 framework for neural networks were used for deep learning with a convolutional neural network. We compared the clinical and histological features between patients with and without recurrence. The predictive performance of the deep learning model between groups was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve served as a summary of the prognostic performance of the deep learning model to predict recurrent thyroid cancer. Results Tumor recurrence was noted in 49 (21.4%) among the 229 patients. Tumor size and multifocality varied significantly between the groups with and without recurrence (p < 0.05). The overall mean area under the curve (AUC) value of the deep learning model for prediction of recurrent thyroid cancer was 0.9 ± 0.06. The mean AUC value was 0.87 ± 0.03 in macrocarcinoma and 0.79 ± 0.16 in microcarcinoma. Conclusion A deep learning model for analysis of US images of thyroid cancer showed the possibility of predicting recurrence of thyroid cancer.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.2
• /
• pp.28-35
• /
• 2024

Corrosion inside electronic packages significantly impacts the system performance and reliability, necessitating non-destructive diagnostic techniques for system health management. This study aims to present a non-destructive method for assessing corrosion in copper interconnects using the Smith chart, a tool that integrates the magnitude and phase of complex impedance for visualization. For the experiment, specimens simulating copper transmission lines were subjected to temperature and humidity cycles according to the MIL-STD-810G standard to induce corrosion. The corrosion level of the specimen was quantitatively assessed and labeled based on color changes in the R channel. S-parameters and Smith charts with progressing corrosion stages showed unique patterns corresponding to five levels of corrosion, confirming the effectiveness of the Smith chart as a tool for corrosion assessment. Furthermore, by employing data augmentation, 4,444 Smith charts representing various corrosion levels were obtained, and artificial intelligence models were trained to output the corrosion stages of copper interconnects based on the input Smith charts. Among image classification-specialized CNN and Transformer models, the ConvNeXt model achieved the highest diagnostic performance with an accuracy of 89.4%. When diagnosing the corrosion using the Smith chart, it is possible to perform a non-destructive evaluation using electronic signals. Additionally, by integrating and visualizing signal magnitude and phase information, it is expected to perform an intuitive and noise-robust diagnosis.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.2
• /
• pp.147-156
• /
• 2024

The sustainable management and enhancement of marine resources are becoming increasingly important issues worldwide. This study was conducted in response to these challenges, focusing on the development and performance comparison of fish detection and classification models as part of a deep learning-based technique for assessing the effectiveness of marine resource enhancement projects initiated by the Korea Fisheries Resources Agency. The aim was to select the optimal model by training various sizes of YOLOv8-Seg models on a fish image dataset and comparing each performance metric. The dataset used for model construction consisted of 36,749 images and label files of 12 different species of fish, with data diversity enhanced through the application of augmentation techniques during training. When training and validating five different YOLOv8-Seg models under identical conditions, the medium-sized YOLOv8m-Seg model showed high learning efficiency and excellent detection and classification performance, with the shortest training time of 13 h and 12 min, an of 0.933, and an inference speed of 9.6 ms. Considering the balance between each performance metric, this was deemed the most efficient model for meeting real-time processing requirements. The use of such real-time fish detection and classification models could enable effective surveys of marine resource enhancement projects, suggesting the need for ongoing performance improvements and further research.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.205-212
• /
• 2024

This study developed a deep learning model that distinguishes the front (with garnish) and the back (without garnish) surface of the dried semi-finished product (dried bukak) for screening operation before transfter the dried bukak to oil heater using robot's vacuum gripper. For deep learning model training and verification, RGB images for the front and back surfaces of 400 dry bukak that treated by data preproccessing were obtained. YOLO-v5 was used as a base structure of deep learning model. The area, surface information labeling, and data augmentation techniques were applied from the acquired image. Parameters including mAP, mIoU, accumulation, recall, decision, and F1-score were selected to evaluate the performance of the developed YOLO-v5 deep learning model-based surface detection model. The mAP and mIoU on the front surface were 0.98 and 0.96, respectively, and on the back surface, they were 1.00 and 0.95, respectively. The results of binary classification for the two front and back classes were average 98.5%, recall 98.3%, decision 98.6%, and F1-score 98.4%. As a result, the developed model can classify the surface information of the dried bukak using RGB images, and it can be used to develop a robot-automated system for the surface detection process of the dried bukak before deep frying.

• Journal of Biomedical Engineering Research
• /
• v.25 no.3
• /
• pp.171-182
• /
• 2004

This study investigates the biomechanical efficacies of vertebroplasty which is used to treat vertebral body fracture with bone cement augmentation for osteoporotic patients using image and finite element analysis. Simulated models were divided into two groups: (a) a vertebral body, (b) a functional spinal unit(FSU). For a vertebral body model, the maximum axial displacement was investigated under axial compression to evaluate the effect of structural integrity. The stiffness of each FE model simulated was normalized by the stiffness of intact model. In the case of FSU model, 3 types of compression fractures were formulated to assess the influence on spinal curvature changes. The FSU models were loaded under compressive pressure to calculate the change of spinal curvature. The results according to the various factors suggest that vertebroplasty has the biomechanical efficacy of the increment of structural reinforcement in a patient who has relatively high level of BMD and a patient with the amount of 15％, PMMA injection of the cancellous bone volume. The spinal curvatures after compression fracture simulation vary from 9$^{\circ}$ to 17$^{\circ}$ of kyphosis compared to that the spinal curvature of normal model was -2.8$^{\circ}$ of lordosis. These spinal curvature changes cause the severe spinal deformity under the same loading. As the degree of compressive fracture increases the spinal deformity also increases. The results indicate that vertebroplasty has the increasing effect of the structural integrity regardless of the amount of PMMA or BMD and the restoration of decreased vertebral body height may be an important factor when the compressive fracture caused the significant height loss of vertebral body.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.3
• /
• pp.24-35
• /
• 2024

Recently, research using deep learning technologies such as artificial intelligence, convolutional neural networks, etc. has been actively conducted in various fields including healthcare, manufacturing, autonomous driving, and security, and is having a significant influence on society. In line with this trend, the present study attempted to apply deep learning to the classification of archaeological artifacts, specifically ancient Korean roof-end tiles. Using 100 images of roof-end tiles from each of the Goguryeo, Baekje, and Silla dynasties, for a total of 300 base images, a dataset was formed and expanded to 1,200 images using data augmentation techniques. After building a model using transfer learning from the pre-trained EfficientNetB0 model and conducting five-fold cross-validation, an average training accuracy of 98.06% and validation accuracy of 97.08% were achieved. Furthermore, when model performance was evaluated with a test dataset of 240 images, it could classify the roof-end tile images from the three dynasties with a minimum accuracy of 91%. In particular, with a learning rate of 0.0001, the model exhibited the highest performance, with accuracy of 92.92%, precision of 92.96%, recall of 92.92%, and F1 score of 92.93%. This optimal result was obtained by preventing overfitting and underfitting issues using various learning rate settings and finding the optimal hyperparameters. The study's findings confirm the potential for applying deep learning technologies to the classification of Korean archaeological materials, which is significant. Additionally, it was confirmed that the existing ImageNet dataset and parameters could be positively applied to the analysis of archaeological data. This approach could lead to the creation of various models for future archaeological database accumulation, the use of artifacts in museums, and classification and organization of artifacts.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.4
• /
• pp.21-35
• /
• 2023

Expectations surrounding generative AI technology and its profound ramifications are sweeping across various industrial domains. Given the anticipated pivotal role of the startup ecosystem in the utilization and advancement of generative AI technology, it is imperative to cultivate a deeper comprehension of the present state and distinctive attributes characterizing venture capital (VC) investments within this domain. The current investigation delves into South Korea's landscape of VC investment deals and prognosticates the projected VC investments by juxtaposing these against the United States, the frontrunner in the generative AI industry and its associated ecosystem. For analytical purposes, a compilation of 286 investment deals originating from 117 U.S. generative AI startups spanning the period from 2008 to 2023, as well as 144 investment deals from 42 South Korean generative AI startups covering the years 2011 to 2023, was amassed to construct new datasets. The outcomes of this endeavor reveal an upward trajectory in the count of VC investment deals within both the U.S. and South Korea during recent years. Predominantly, these deals have been concentrated within the early-stage investment realm. Noteworthy disparities between the two nations have also come to light. Specifically, in the U.S., in contrast to South Korea, the quantum of recent VC deals has escalated, marking an augmentation ranging from 285% to 488% in the corresponding developmental stage. While the interval between disparate investment stages demonstrated a slight elongation in South Korea relative to the U.S., this discrepancy did not achieve statistical significance. Furthermore, the proportion of VC investments channeled into generative AI enterprises, relative to the aggregate number of deals, exhibited a higher quotient in South Korea compared to the U.S. Upon a comprehensive sectoral breakdown of generative AI, it was discerned that within the U.S., 59.2% of total deals were concentrated in the text and model sectors, whereas in South Korea, 61.9% of deals centered around the video, image, and chat sectors. Through forecasting, the anticipated VC investments in South Korea from 2023 to 2029 were derived via four distinct models, culminating in an estimated average requirement of 3.4 trillion Korean won (ranging from at least 2.408 trillion won to a maximum of 5.919 trillion won). This research bears pragmatic significance as it methodically dissects VC investments within the generative AI domain across both the U.S. and South Korea, culminating in the presentation of an estimated VC investment projection for the latter. Furthermore, its academic significance lies in laying the groundwork for prospective scholarly inquiries by dissecting the current landscape of generative AI VC investments, a sphere that has hitherto remained void of rigorous academic investigation supported by empirical data. Additionally, the study introduces two innovative methodologies for the prediction of VC investment sums. Upon broader integration, application, and refinement of these methodologies within diverse academic explorations, they stand poised to enhance the prognosticative capacity pertaining to VC investment costs.