• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• 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.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.445-471
• /
• 2023

Long-term safety over millennia is the top priority consideration in the construction of disposal sites. However, ensuring the mechanical stability of deep geological repositories for spent fuel, a.k.a. radwaste, disposal during construction and operation is also crucial for safe operation of the repository. Imposing restrictions or limitations on tunnel support and lining materials such as shotcrete, concrete, grouting, which might compromise the sealing performance of backfill and buffer materials which are essential elements for the long-term safety of disposal sites, presents a highly challenging task for rock engineers and tunnelling experts. In this study, as part of an extensive exploration to aid in the proper selection of disposal sites, the anticipation of constructing a deep geological repository at a depth of 500 meters in an unknown state has been carried out. Through a review of 2D and 3D numerical analyses, the study aimed to explore the range of properties that ensure stability. Preliminary findings identified the potential range of rock properties that secure the stability of central and disposal tunnels, while the stability of the vertical tunnel network was confirmed through 3D analysis, outlining fundamental rock conditions necessary for the construction of disposal sites.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.437-447
• /
• 2023

By actively adopting technologies from the Fourth Industrial Revolution, the port industry is trending toward new types of ports, such as automated and smart ports. However, behind the development of these ports, there is an increasing risk of cyber security incidents and threats within ports and container terminals, including information leakage through cargo handling equipment and ransomware attacks leading to disruptions in terminal operations. Despite the necessity of research to enhance cyber security within ports, there is a lack of such studies in the domestic context. This study focuses on Busan Port, a representative port in South Korea that actively incorporates technology from the Fourth Industrial Revolution, in order to discover variables for improving cyber security in container terminals. The research results categorized factors for enhancing cyber security in Busan Port's container terminals into network construction and policy support, standardization of education and personnel training, and legal and regulatory factors. Subsequently, multiple regression analysis was conducted based on these factors, leading to the identification of detailed factors for securing and enhancing safety, reliability, performance, and satisfaction in Busan Port's container terminals. The significance of this study lies in providing direction for enhancing cyber security in Busan Port's container terminals and addressing the increasing incidents of cyber security attacks within ports and container terminals.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.