• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1589-1605
• /
• 2022

Phase unwrapping is an essential procedure for interferometric synthetic aperture radar techniques. Accordingly, a lot of phase unwrapping methods have been developed. Deep-learning-based unwrapping methods have recently been proposed. In this paper, we reviewed state-of-the-art deep-learning-based unwrapping approaches in terms of 1) the approaches to predicting unwrapped phases, 2) deep learning model structures for phase unwrapping, and 3) training data generation. The research trend of the approaches to predicting unwrapped phases was introduced by categorizing wrap count segmentation, phase jump classification, phase regression, and deep-learning-assisted method. We introduced the case studies of deep learning model structure for phase unwrapping, and model structure optimization to relate the overall phase information. In addition, we summarized the research trend of the training data generation approaches in the views of phase gradient and noise in the main. And the future direction in deep-learning-based phase unwrapping was presented. It is expected that this paper is used as guideline for exploring future direction of deep-learning-based phase unwrapping research in Korea.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.315-321
• /
• 2023

Long-span bridges are flexible structures with low natural frequencies and damping ratios, making them susceptible to vibrational serviceability problems. However, the current design guideline of South Korea assumes a uniform threshold of wind speed or vibrational amplitude to assess the occurrence of harmful vibrations, potentially overlooking the complex vibrational patterns observed in long-span bridges. In this study, we propose a pointwise vortex-induced vibration (VIV) detection method using a deep-learning-based signalsegmentation model. Departing from conventional supervised methods of data acquisition and manual labeling, we synthesize training data by generating sinusoidal waves with an envelope to accurately represent VIV. A Fourier synchrosqueezed transform is leveraged to extract time-frequency features, which serve as input data for training a bidirectional long short-term memory model. The effectiveness of the model trained on synthetic VIV data is demonstrated through a comparison with its counterpart trained on manually labeled real datasets from an actual cable-supported bridge.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.9
• /
• pp.794-806
• /
• 2017

It is essential to protect the national space assets and space environment safely as a space development country from the continuously increasing space debris. And Active Debris Removal(ADR) is the most active way to solve this problem. In this paper, we studied the Artificial Neural Network(ANN) for a stable recognition model of vision-based space debris tracking system. We obtained the simulated image of the space environment by the KARICAT which is the ground-based space debris clearing satellite testbed developed by the Korea Aerospace Research Institute, and created the vector which encodes structure and color-based features of each object after image segmentation by depth discontinuity. The Feature Vector consists of 3D surface area, principle vector of point cloud, 2D shape and color information. We designed artificial neural network model based on the separated Feature Vector. In order to improve the performance of the artificial neural network, the model is divided according to the categories of the input feature vectors, and the ensemble technique is applied to each model. As a result, we confirmed the performance improvement of recognition model by ensemble technique.

• Journal of Information Processing Systems
• /
• v.9 no.2
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.6
• /
• pp.725-736
• /
• 2013

This study segments information users according to depth and variety of use diffusion in order to differentiate between the influence of fashion information spread and diffusions from each segmented group. Data were collected from a fashion community to perform a social network analysis that used UCINET 6.0. Members completed the survey materials and the network materials were utilized in the analysis to test the hypothesis. The segmented groups of information users determined the study results according to use diffusion and the variables that affect them. The variables affecting information diffusion outcomes indicate different significant influence factors on each segmented market. Information variety and complexity represents elevated information reproductions and verbal acceptances from information diffusion outcomes.

• Journal of the Korean Society of Costume
• /
• v.58 no.3
• /
• pp.34-48
• /
• 2008

Modern fashion market is being developed by emotional values rather than rational idea of customers. Experiential marketing is an effective marketing strategy for fashion marketplace because customers tend to consider fashion shopping as an enjoyable experience. Among the fashion markets, the fashion stores for middle.old aged women that have various points of contacts could be appropriate place where emotional and relational marketing strategies would be applied to. The effects of the procedure "emotional and relational experience$\rightarrow$commitments$\rightarrow$long-term relationship orientation" that fashion customers are experiencing, by forming a path model, two types of experiential effects from emotion and relation were examined. It was found that fashion emotional and relational experiences were important factors because these factors affected a long-term relationship orientation. The findings of the study provide marketing strategy that enables to promote a consistent relationship between fashion stores and customers. Furthermore, this study will contribute to the criteria for segmentation of middle and old aged women's fashion market who have own desire for fashion emotional and relational experience.

• Culinary science and hospitality research
• /
• v.23 no.1
• /
• pp.58-65
• /
• 2017

This study performed to test the effect of food neophobia on the formulated model on the relationships among perceived service attributes(food, employee, and physical attributes), brand trust, satisfaction and behavioral intention as perceived by franchise snack bar consumers. Total 299 respondents were used for statistical analysis and SPSS 21.0 and AMOS 21.0 program were employed. The findings of current study verified that food attribute among perceived service attributes has positively influence on brand trust and satisfaction, and the employee attribute has only effect on the brand trust. Additionally, the brand trust was critical predictor of satisfaction, but it was not significant antecedent of behavioral intention in context of franchise snack bar restaurant. Furthermore, this study found the moderating effect according to level of food neophobia on the designed hypothesizes, so it has been identified the importance of people's propensity about food neophobia can significantly effect on brand trust and satisfaction in franchise snack bar restaurant. These findings will contribute to provide meaningful suggestion to develop marketing strategic in franchise snack bar business as well as provide the theoretical evidence in the new segmentation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.559-562
• /
• 2003

A motion-based background subtraction method without geometric computation is proposed, allowing that the camera is moving parallel to the ground plane with uniform velocity. The proposed method subtracts the background region from a given image by evaluating the difference between calculated and model Hows. This approach is insensitive to small errors of calculated optical flows. Furthermore, in order to tackle the significant errors, a strategy for incorporating a set of optical flows calculated over different frame intervals is presented. An experiment with two real image sequences, in which a static box or a moving toy car appears, to evaluate the performance in terms of accuracy under varying thresholds using a receiver operating characteristic (ROC) curve. The ROC curves show, in the best case, the figure-ground segmentation is done at 17.8 ％ in false positive fraction (FPF) and 71.3％ in true positive fraction (TPF) for the static-object scene and also at 14.8％ in FPF and 72.4％ In TPF for the moving-object scene, regardless if the calculated optical flows contain significant errors of calculation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2737-2753
• /
• 2013

In this study, we propose a novel salient object detection strategy based on regional contrast and relative spatial compactness. Our algorithm consists of four basic steps. First, we learn color names offline using the probabilistic latent semantic analysis (PLSA) model to find the mapping between basic color names and pixel values. The color names can be used for image segmentation and region description. Second, image pixels are assigned to special color names according to their values, forming different color clusters. The saliency measure for every cluster is evaluated by its spatial compactness relative to other clusters rather than by the intra variance of the cluster alone. Third, every cluster is divided into local regions that are described with color name descriptors. The regional contrast is evaluated by computing the color distance between different regions in the entire image. Last, the final saliency map is constructed by incorporating the color cluster's spatial compactness measure and the corresponding regional contrast. Experiments show that our algorithm outperforms several existing salient object detection methods with higher precision and better recall rates when evaluated using public datasets.