• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Asia Marketing Journal
• /
• v.6 no.3
• /
• pp.143-156
• /
• 2004

This case intorduced E-mart's business philosophy and vision, analyzed E-mart's outline of marketing strategy, and discussed its performance and future task. E-mart took the role of market pioneer by developing discount store market in Korea. It's mission was to provide substantial benefits to the customers by selling quality products at the lowest price in the market. For this purpose, E-mart has conducted a slogan of 'everyday low price discount store-E-mart'. Objective of E-mart's brand strategy was to be No. 1 discount store in Korea or to be a representative brand in the discount store market. To achieve this objective, E-mart has conducted various efforts such as construction of national network, realization of the lowest price, formation of the most reliable discount store image, establishment of competitive edge and so on. E-mart settled a new model for discount store in Korea and took the lead in expanding market potential. With these efforts, E-mart has maintained secure position as a leading company in the discount store market.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.5
• /
• pp.21-30
• /
• 2023

Accurate segmentation of the kidney tumor is necessary to identify shape, location and safety margin of tumor in abdominal CT images for surgical planning before renal partial nephrectomy. However, kidney tumor segmentation is challenging task due to the various sizes and locations of the tumor for each patient and signal intensity similarity to surrounding organs such as intestine and spleen. In this paper, we propose a semi-supervised learning-based mean teacher network that utilizes both labeled and unlabeled data using a kidney local guided map including kidney local information to segment small-sized kidney tumors occurring at various locations in the kidney, and analyze the performance according to the kidney tumor size. As a result of the study, the proposed method showed an F1-score of 75.24% by considering local information of the kidney using a kidney local guide map to locate the tumor existing around the kidney. In particular, under-segmentation of small-sized tumors which are difficult to segment was improved, and showed a 13.9%p higher F1-score even though it used a smaller amount of labeled data than nnU-Net.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.69-91
• /
• 2021

Credit Bureaus in Korea commonly use financial transaction information of the past and present time for calculating an individual's credit scores. Compared to other rating factors, the repayment history information accounts for a larger weights on credit scores. Accordingly, despite full redemption of overdue payments, late payment history is reflected negatively for the assessment of credit scores for certain period of the time. An individual with debt delinquency can be classified into two groups; (1) the individuals who have faithfully paid off theirs overdue debts(Normal Repayment), and (2) those who have not and as differences of creditworthiness between these two groups do exist, it needs to grant relatively higher credit scores to the former individuals with normal repayment. This study is designed to analyze the factors of normal repayment of Korean financial debt delinquents based on credit information of personal loan, overdue payments, redemption from Korea Credit Information Services. As a result of the analysis, the number of overdue and the type of personal loan and delinquency were identified as significant variables affecting normal repayment and among applied methodologies, neural network models suggested the highest classification accuracy. The findings of this study are expected to improve the performance of individual credit scoring model by identifying the factors affecting normal repayment of a financial debt delinquent.

• Journal of The Korean Association For Science Education
• /
• v.27 no.1
• /
• pp.93-104
• /
• 2007

The purpose of this study is to investigate brain activity both during the processing of a scientific hypothesis about biological phenomena and mental arithmetic using 3.0T fMRI at the KAIST. For this study, 16 healthy male subjects participated voluntarily. Each subject's functional brain images by performing a scientific hypothesis task and a mental arithmetic task for 684 seconds were measured. After the fMRI measuring, verbal reports were collected to ensure the reliability of brain image data. This data, which were found to be adequate based on the results of analyzing verbal reports, were all included in the statistical analysis. When the data were statistically analyzed using SPM2 software, the scientific hypothesis generating process was found to have independent brain network different from the mental arithmetic process. In the scientific hypothesis process, we can infer that there is the process of encoding semantic derived from the fusiform gyrus through question-situation analysis in the pre-frontal lobe. In the mental arithmetic process, the area combining pre-frontal and parietal lobes plays an important role, and the parietal lobe is considered to be involved in skillfulness. In addition, the scientific hypothesis process was found to be accompanied by scientific emotion. These results enabled the examination of the scientific hypothesis process from the cognitive neuroscience perspective, and may be used as basic materials for developing a learning program for scientific hypothesis generation. In addition, this program can be proposed as a model of scientific brain-based learning.

• Journal of The Korean Association For Science Education
• /
• v.29 no.6
• /
• pp.730-740
• /
• 2009

The purpose of this study was to investigate secondary science teachers' brain activation and functional connectivity during scientific observation on the biological phenomena. Twenty six right-handed healthy science teachers volunteered to be in the present study. To investigate science teachers' brain activities during the tasks, 3.0T fMRI system with block design was used to measure BOLD signals in their brains. The SPM2 software package was applied to analyze the acquired initial image data from the fMRI system. The results have shown that the left inferior frontal gyrus, the bilateral superior parietal lobule, the left inferior parietal lobule, the left precuneus, the left superior occipital gyrus, the right middle occipital gyrus, the right precuneus, the left inferior occipital gyrus and bilateral fusiform gyrus were significantly activated during participants' scientific observation. The network model consisted of eleven nodes (ROIs) and its ten connections. These results suggested the notion that scientific observation needs a connective cooperation among several brain regions associated with observing over just a sensory receiving process.

• Journal of agricultural medicine and community health
• /
• v.49 no.2
• /
• pp.132-145
• /
• 2024

Objectives: This study compares cases of Dalgubeol Health Care Project, 301 Network Project, and 3 for 1 Project based on program logic models to derive measures for promoting integrated healthcare and welfare services centered around medical institutions. Methods: From January to December 2021, information on the implementation systems and performance of each institution was collected. Data sources included prior academic research, project reports, operational guidelines, official press releases, media articles, and written surveys from project managers. A program logic model analysis framework was applied, structuring the information based on four elements: situation, input, activity, and output. Results: All three projects aimed to address the fragmentation of health and welfare services and medical blind spots. Despite similar multidisciplinary team compositions, differences existed in specific fields, recruitment scale, and employment types. Variations in funding sources led to differences in community collaboration, support methods, and future directions. There were discrepancies in the number of beneficiaries and medical treatments, with different results observed when comparing the actual number of people to input manpower and project cost per beneficiary. Conclusions: To design an integrated health and welfare service provision system centered on medical institutions, securing a stable funding mechanism and establishing an appropriate target population and service delivery system are crucial. Additionally, installing a dedicated department within the medical institution to link activities across various sectors, rather than outsourcing, is necessary. Ensuring appropriate recruitment and stable employment systems is needed. A comprehensive provision system offering services from mild to severe cases through public-private cooperation is suggested.