• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Journal of Smart Tourism
• /
• v.3 no.2
• /
• pp.15-21
• /
• 2023

This paper presents a conceptual approach to Smart Tourism Design based on semiotic affordances theory. This conceptual approach repositions smart tourism from a techno-centric perspective that frames a seamless connection between the device and its software, to a more human-centric perspective that favors the user's needs, desires as perceived through the senses. An updated Smart Tourism Design emphasizes the aesthetic dimension of smart tourism that presents the objects of the travel experience as destination specific rather than universal, through representations as digital artifacts. This theory is based on an empirical and objective understanding of representations and how they can be identified as useful in the digital augmentation of travel experiences. Using Peirce's sign systems and Gibson's theory of affordances, smart tourism can transcend a prefabricated device-oriented experience to a closer dynamic and direct interaction between the user and the travel destination. Researchers and developers can use semiotics as a structural approach to recognizing objects as sign-types, and they can use affordances to better identify the immediacy of digital artifacts and purpose-driven by users' spontaneous and immediate motives.

• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.223-245
• /
• 2023

Purpose: This study aim to identify the trends in AI-based PHM technology that can enhance reliability and minimize costs. Furthermore, this research provides valuable guidelines for future studies in various industries Methods: In this study, I collected and selected AI-based PHM studies, established classification criteria, and analyzed research trends based on classified fields and techniques. Results: Analysis of 125 domestic studies revealed a greater emphasis on machinery in both diagnosis and prognosis, with more papers dedicated to diagnosis. various algorithms were employed, including CNN for image diagnosis and frequency analysis for signal data. LSTM was commonly used in prognosis for predicting failures and remaining life. Different industries, data types, and objectives required diverse AI techniques, with GAN used for data augmentation and GA for feature extraction. Conclusion: As studies on AI-based PHM continue to grow, selecting appropriate algorithms for data types and analysis purposes is essential. Thus, analyzing research trends in AI-based PHM is crucial for its rapid development.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

• Journal of Korea Multimedia Society
• /
• v.15 no.3
• /
• pp.323-335
• /
• 2012

In this paper, we propose an AR(augmented reality) system using user's bare hand based on computer vision. It is important for registering a virtual object on the real input image to detect and track correct feature points. The AR systems with markers are stable but they can not register the virtual object on an acquired image when the marker goes out of a range of the camera. There is a tendency to give users inconvenient environment which is limited to control a virtual object. On the other hand, our system detects fingertips as fiducial features using adaptive ellipse fitting method considering the geometric characteristics of hand. It registers the virtual object stably by getting movement of fingertips with determining the shortest distance from a palm center. We verified that the accuracy of fingertip detection over 82.0% and fingertip ordering and tracking have just 1.8% and 2.0% errors for each step. We proved that this system can replace the marker system by tacking a camera projection matrix effectively in the view of stable augmentation of virtual object.

• Archives of Craniofacial Surgery
• /
• v.22 no.2
• /
• pp.85-92
• /
• 2021

Background: Patients with secondary deformities associated with unilateral cleft lip and nose might also suffer from nostril stenosis due to a lack of tissue volume in the nostril on the cleft side. Here, we used full-thickness skin grafts (FTSGs) to reduce nostril stenosis and various methods for skin volume augmentation. We compared the changes in the symmetry of both nostrils before and after surgery. Methods: From February 2016 to January 2020, 34 patients underwent secondary cheiloplasty and open rhinoplasty for secondary deformities of the unilateral cleft lip and nose with nostril stenosis. FTSG was used on the nostril floor, nasal columella, and alar inner lining. The measured nasal profile included the nostril surface, nostril circumference, width of the nostril floor, and distance from the alar-facial groove to the nasal tip. The "overlap area," which was defined as the largest overlapping area when the image of the cleft nostril was flipped to the left and right and overlaid on the image of the normal side nostril, was also calculated. The degree of symmetry was evaluated by dividing the value of the cleft side by that of the normal side of each measured profile and expressed as "ratios." Results: The results of all profile ratios, except for the nostril floor width, became significantly close to 1, which represents full symmetry. The overlap area ratio improved from 62.7% to 77.3%, meaning that the length and width of the nostril as well as the overall shape became similar (p< 0.05). Conclusion: When performing cleft rhinoplasty with nostril stenosis, FTSG is useful to achieve symmetry in the nostril size and shape. Skin grafting is simpler to perform than the other types of local flap, and the results are generally satisfactory.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.19-28
• /
• 2021

Esophagogastroduodenoscopy is a method commonly used for early diagnosis of upper gastrointestinal lesions. However, 10-20 percent of the gastric lesions are reported to be missed, due to human error. And countries including the US, the UK, and Japan, the World Endoscopy Organization (WEO) suggested guidelines about essential gastrointestinal parts to take pictures of so that all gastric lesions are observed. In this paper, we propose deep learning techniques for classification of anatomical sites, aiming for the system that informs practitioners whether they successfully did the gastroscopy without blind spots. The proposed model uses pre-processing modules and data augmentation techniques suitable for gastroscopy images. Not only does the experiment result with a maximum F1 score of 99.6%, but it also shows a error rate of less than 4% based on the actual data. Given the performance results, we found the model to be explainable with the potential to be utilized in the clinical area.

• Journal of Biomedical Engineering Research
• /
• v.43 no.1
• /
• pp.45-51
• /
• 2022

The purpose of this study is to improve the classification accuracy compared to the existing InceptionV3 model by proposing a new model modified with the fully connected hierarchical structure of InceptionV3, which showed excellent performance in medical image classification. The data used for model training were trained after data augmentation on a total of 1026 chest X-ray images of patients diagnosed with normal heart and Cardiomegaly at Kyungpook National University Hospital. As a result of the experiment, the learning classification accuracy and loss of the InceptionV3 model were 99.57% and 1.42, and the accuracy and loss of the proposed model were 99.81% and 0.92. As a result of the classification performance evaluation for precision, recall, and F1 score of Inception V3, the precision of the normal heart was 78%, the recall rate was 100%, and the F1 score was 88. The classification accuracy for Cardiomegaly was 100%, the recall rate was 78%, and the F1 score was 88. On the other hand, in the case of the proposed model, the accuracy for a normal heart was 100%, the recall rate was 92%, and the F1 score was 96. The classification accuracy for Cardiomegaly was 95%, the recall rate was 100%, and the F1 score was 97. If the chest X-ray image for normal heart and Cardiomegaly can be classified using the model proposed based on the study results, better classification will be possible and the reliability of classification performance will gradually increase.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.62-68
• /
• 2022

To prevent the spread of disease in aquaculture, it is a need for a system to predict fish diseases while monitoring the water quality environment and the status of growing fish in real time. The existing research in predicting fish disease were image processing techniques. Recently, there have been more studies on disease prediction methods through deep learning techniques. This paper introduces the research results on how to predict diseases of Paralichthys Olivaceus with deep learning technology in aquaculture. The method enhances the performance of disease detection rates by including data augmentation and pre-processing in camera images collected from aquaculture. In this method, it is expected that early detection of disease fish will prevent fishery disasters such as mass closure of fish in aquaculture and reduce the damage of the spread of diseases to local aquaculture to prevent the decline in sales.