• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.679-692
• /
• 2020

We coupled a CFD model to the WRF-Chem model (WRF-CFD model) and investigated the characteristics of flows and carbon monoxide (CO) distributions in a building-congested district. We validated the simulated results against the measured wind speeds, wind directions, and CO concentrations. The WRF-Chem model simulated the winds from southwesterly to southeasterly, overestimating the measured wind speeds. The statistical validation showed that the WRF-CFD model simulated the measured wind speeds more realistically than the WRF-Chem model. The WRF-Chem model significantly underestimated the measured CO concentrations, and the WRF-CFD model improved the CO concentration prediction. Based on the statistical validation results, the WRF-CFD model improved the performance in predicting the CO concentrations by taking complicatedly distributed buildings and mobiles sources of CO into account. At 04 KST on May 22, there was a downdraft around the AQMS, and airflow with a relatively low CO concentration was advected from the upper layer. Resultantly, the CO concentration was lower at the AQMS than the surrounding area. At 15 KST on May 22, there was an updraft around the AQMS. This resulted in a slightly higher CO concentration than the surroundings. The WRF-CFD model transported CO emitted from the mobile sources to the AQMS measurement altitude, well reproducing the measured CO concentration. At 18 KST on May 22, the WRF-CFD model simulated high CO concentrations because of high CO emission, broad updraft area, and an increase in turbulent diffusion cause by wind-shear increase near the ground.

• Journal of Korea Water Resources Association
• /
• v.47 no.4
• /
• pp.371-384
• /
• 2014

This study developed a new algorithm of extreme rainfall extraction based on the Communication, Ocean and Meteorological Satellite (COMS) and the Tropical Rainfall Measurement Mission (TRMM) Satellite image data and evaluated its applicability for the heavy rainfall event in July-2011 in Seoul, South Korea. The power-series-regression-based Z-R relationship was employed for taking into account for empirical relationships between TRMM/PR, TRMM/VIRS, COMS, and Automatic Weather System(AWS) at each elevation. The estimated Z-R relationship ($Z=303R^{0.72}$) agreed well with observation from AWS (correlation coefficient=0.57). The estimated 10-minute rainfall intensities from the COMS satellite using the Z-R relationship generated underestimated rainfall intensities. For a small rainfall event the Z-R relationship tended to overestimated rainfall intensities. However, the overall patterns of estimated rainfall were very comparable with the observed data. The correlation coefficients and the Root Mean Square Error (RMSE) of 10-minute rainfall series from COMS and AWS gave 0.517, and 3.146, respectively. In addition, the averaged error value of the spatial correlation matrix ranged from -0.530 to -0.228, indicating negative correlation. To reduce the error by extreme rainfall estimation using satellite datasets it is required to take into more extreme factors and improve the algorithm through further study. This study showed the potential utility of multi-geostationary satellite data for building up sub-daily rainfall and establishing the real-time flood alert system in ungauged watersheds.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.125-136
• /
• 2024

This study presents an automated Python algorithm for analyzing rainfall characteristics to establish critical rainfall thresholds as part of a landslide early warning system. Rainfall data were sourced from the Korea Meteorological Administration's Automatic Weather System (AWS) and the Korea Forest Service's Automatic Mountain Observation System (AMOS), while landslide data from 2020 to 2023 were gathered via the Life Safety Map. The algorithm involves three main steps: 1) processing rainfall data to correct inconsistencies and fill data gaps, 2) identifying the nearest observation station to each landslide location, and 3) conducting statistical analysis of rainfall characteristics. The analysis utilized power law and nonlinear regression, yielding an average R² of 0.45 for the relationships between rainfall intensity-duration, effective rainfall-duration, antecedent rainfall-duration, and maximum hourly rainfall-duration. The critical thresholds identified were 0.9-1.4 mm/hr for rainfall intensity, 68.5-132.5 mm for effective rainfall, 81.6-151.1 mm for antecedent rainfall, and 17.5-26.5 mm for maximum hourly rainfall. Validation using AUC-ROC analysis showed a low AUC value of 0.5, highlighting the limitations of using rainfall data alone to predict landslides. Additionally, the algorithm's speed performance evaluation revealed a total processing time of 30 minutes, further emphasizing the limitations of relying solely on rainfall data for disaster prediction. However, to mitigate loss of life and property damage due to disasters, it is crucial to establish criteria using quantitative and easily interpretable methods. Thus, the algorithm developed in this study is expected to contribute to reducing damage by providing a quantitative evaluation of critical rainfall thresholds that trigger landslides.

• Asia pacific journal of information systems
• /
• v.21 no.4
• /
• pp.45-62
• /
• 2011

The notion of information systems (IS) continuance has recently emerged as one of the most important research issues in the field of IS. A great deal of research has been conducted thus far on the basis of theories adapted from various disciplines including consumer behaviors and social psychology, in addition to theories regarding information technology (IT) acceptance. This previous body of knowledge provides a robust research framework that can already account for the determination of IS continuance; however, this research points to other, thus-far-unelucidated determinant factors such as habit, which were not included in traditional IT acceptance frameworks, and also re-emphasizes the importance of emotion-related constructs such as satisfaction in addition to conscious intention with rational beliefs such as usefulness. Experiences should also be considered one of the most important factors determining the characteristics of information system (IS) continuance and the features distinct from those determining IS acceptance, because more experienced users may have more opportunities for IS use, which would allow them more frequent use than would be available to less experienced or non-experienced users. Interestingly, experience has dual features that may contradictorily influence IS use. On one hand, attitudes predicated on direct experience have been shown to predict behavior better than attitudes from indirect experience or without experience; as more information is available, direct experience may render IS use a more salient behavior, and may also make IS use more accessible via memory. Therefore, experience may serve to intensify the relationship between IS use and conscious intention with evaluations, On the other hand, experience may culminate in the formation of habits: greater experience may also imply more frequent performance of the behavior, which may lead to the formation of habits, Hence, like experience, users' activation of an IS may be more dependent on habit-that is, unconscious automatic use without deliberation regarding the IS-and less dependent on conscious intentions, Furthermore, experiences can provide basic information necessary for satisfaction with the use of a specific IS, thus spurring the formation of both conscious intentions and unconscious habits, Whereas IT adoption Is a one-time decision, IS continuance may be a series of users' decisions and evaluations based on satisfaction with IS use. Moreover. habits also cannot be formed without satisfaction, even when a behavior is carried out repeatedly. Thus, experiences also play a critical role in satisfaction, as satisfaction is the consequence of direct experiences of actual behaviors. In particular, emotional experiences such as enjoyment can become as influential on IS use as are utilitarian experiences such as usefulness; this is especially true in light of the modern increase in membership-based hedonic systems - including online games, web-based social network services (SNS), blogs, and portals-all of which attempt to provide users with self-fulfilling value. Therefore, in order to understand more clearly the role of experiences in IS continuance, analysis must be conducted under a research framework that includes intentions, habits, and satisfaction, as experience may not only have duration-based moderating effects on the relationship between both intention and habit and the activation of IS use, but may also have content-based positive effects on satisfaction. This is consistent with the basic assumptions regarding the determining factors in IS continuance as suggested by Oritz de Guinea and Markus: consciousness, emotion, and habit. The principal objective of this study was to explore and assess the effects of experiences in IS continuance, with special consideration given to conscious intentions and unconscious habits, as well as satisfaction. IN service of this goal, along with a review of the relevant literature regarding the effects of experiences and habit on continuous IS use, this study suggested a research model that represents the roles of experience: its moderating role in the relationships of IS continuance with both conscious intention and unconscious habit, and its antecedent role in the development of satisfaction. For the validation of this research model. Korean university student users of 'Cyworld', one of the most influential social network services in South Korea, were surveyed, and the data were analyzed via partial least square (PLS) analysis to assess the implications of this study. In result most hypotheses in our research model were statistically supported with the exception of one. Although one hypothesis was not supported, the study's findings provide us with some important implications. First the role of experience in IS continuance differs from its role in IS acceptance. Second, the use of IS was explained by the dynamic balance between habit and intention. Third, the importance of satisfaction was confirmed from the perspective of IS continuance with experience.

• Economic and Environmental Geology
• /
• v.55 no.5
• /
• pp.551-561
• /
• 2022

Geophysical exploration methods are very useful for generating high-resolution images of underground structures, and such methods can be applied to investigation of buried cultural properties and for determining their exact locations. In this study, image feature extraction and image segmentation methods were applied to automatically distinguish the structures of buried relics from the high-resolution ground-penetrating radar (GPR) images obtained at the center of Silla Kingdom, Gyeongju, South Korea. The major purpose for image feature extraction analyses is identifying the circular features from building remains and the linear features from ancient roads and fences. Feature extraction is implemented by applying the Canny edge detection and Hough transform algorithms. We applied the Hough transforms to the edge image resulted from the Canny algorithm in order to determine the locations the target features. However, the Hough transform requires different parameter settings for each survey sector. As for image segmentation, we applied the connected element labeling algorithm and object-based image analysis using Orfeo Toolbox (OTB) in QGIS. The connected components labeled image shows the signals associated with the target buried relics are effectively connected and labeled. However, we often find multiple labels are assigned to a single structure on the given GPR data. Object-based image analysis was conducted by using a Large-Scale Mean-Shift (LSMS) image segmentation. In this analysis, a vector layer containing pixel values for each segmented polygon was estimated first and then used to build a train-validation dataset by assigning the polygons to one class associated with the buried relics and another class for the background field. With the Random Forest Classifier, we find that the polygons on the LSMS image segmentation layer can be successfully classified into the polygons of the buried relics and those of the background. Thus, we propose that these automatic classification methods applied to the GPR images of buried cultural heritage in this study can be useful to obtain consistent analyses results for planning excavation processes.