• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.373-379
• /
• 2019

In this study, image-based flock monitoring and density evaluation were conducted for broiler chicks welfare. Image data were captured by using a mono camera and region of broiler chicks in the image was detected using converting to HSV color model, thresholding, and clustering with filtering. The results show that region detection was performed with 5% relative error and 0.81 IoU on average. The detected region was corrected to the actual region by projection into ground using coordinate transformation between camera and real-world. The flock density of broiler chicks was estimated using the corrected actual region, and it was observed with an average of 80%. The developed algorithm can be applied to the broiler chicks house through enhancing accuracy of region detection and low-cost system configuration.

• The Journal of the Korea Contents Association
• /
• v.19 no.9
• /
• pp.242-253
• /
• 2019

There has been a large literature on bank liquidity risk since the 2008 global financial crisis because liquidity risk was at the heart of the crisis. However, there is no study that investigates whether the level of investor protection influences liquidity risk-taking behavior of banks. Therefore, this study aims to explore the relationship between investor protection and liquidity risk as well as to provide policy implications. Using a panel dataset of commercial banks in 21 OECD countries, we found that strong investor protection encourages banks to take lower liquidity risk. Furthermore, this positive role of shareholder protection is more prominent during a crisis, implying that legal protection of investors plays an essential role in bank stability while market discipline is largely ineffective due to extensive government guarantees in turbulent times.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.289-294
• /
• 2019

It easily collects information on purchased goods using IoT(Internet of Things). The collected data is updated directly to the smartphone for verification. The payment information is generated by QR-Code. As a way to implement a system, System was configured with two assumptions: IoT technology using Raspberry-Pi and mobile QR technology. First, RFID tags are attached to the goods instead of barcodes. Second, it has an IoT computer(Raspberry-Pi) built into its shopping cart. This system keeps traditional shopping method of face-to-face payment, but replace time-consuming tarditional barcode tagging method to QR-tagging system for time-efficiency. By debeloping the system of this paper, we maintain pleasures in offline store shopping and it provide convenience due to reduced waiting time for customers and providing prior information about the products.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.220-222
• /
• 2019

Korean automobile industry has been slow down since 2016. The most fundamental solution for solving this problem is to develop competitive parts. There are two important factors for developing competitive parts. The most important is product design technology, and the second most important is production technology. Production technology is important because it requires lowering the production cost except for the material cost and continuously maintaining the quality. In this paper, an intelligent smart inspection system is proposed and designed to inspect automobile parts of company C. At present, the basic and detailed design of this system has been completed and it is in the development progress stage. If the system is successfully developed, it is expected that the quality inspection stage of company C will be automated and the defect rate will be reduced.

• Journal of the Korea Convergence Society
• /
• v.10 no.5
• /
• pp.27-34
• /
• 2019

In this paper, we propose a method to remove the background area by analyzing the pattern of the character area. In the character detection result of the MSER(Maximally Stable External Regions) method which distinguishes a region having a constant contrast background regions were detected. To solve this problem, we use the MSER method in natural images, the background is removed by calculating the change rate by searching the character area and the background area which are not different from the areas where the contrast values are different from each other. However, in the background removed image, using the LBP(Local Binary Patterns) method, the area with uniform values in the image was determined to be a character area and character detection was performed. Experiments were carried out with simple images with backgrounds, images with frontal characters, and images with slanted images. The proposed method has a high detection rate of 1.73% compared with the conventional MSER and MSER + LBP method.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.3049-3067
• /
• 2018

Although there is a growing body of research on organizational commitment profiles based on a person-centered approach, it is not widely applied to the commitment research conducted by Korean organizational scholars yet. Therefore, in this paper, we introduced the concept and analytical methods, such as cluster analysis and latent profile analysis (LPA), of the person-centered approach. In addition, we also performed both cluster analysis and LPA to identify types of organizational commitment profiles of Korean employees based on the combination of affective, continuance and normative commitment on the sample from a range of different fields in South Korea (n = 349). Both analyses extracted two comparable sets of 6 commitment profiles. These six profiles were then contrasted with employee turnover intention. Finally, implications for commitment theory, practices and future research issues were discussed.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.169-175
• /
• 2021

Recently, an ultrasound hologram and its applications have gained attention in the ultrasound research field. However, the determination technique of transmit signal phases, which generate a hologram, has not been significantly advanced from the previous algorithms which are time-consuming iterative methods. Thus, we applied the deep learning technique, which has been previously adopted to generate an optical hologram, to generate an ultrasound hologram. We further examined the Deep learning-based Holographic Ultrasound Generation algorithm (Deep-HUG). We implement the U-Net-based algorithm and examine its generalizability by training on a dataset, which consists of randomly distributed disks, and testing on the alphabets (A-Z). Furthermore, we compare the Deep-HUG with the previous algorithm in terms of computation time, accuracy, and uniformity. It was found that the accuracy and uniformity of the Deep-HUG are somewhat lower than those of the previous algorithm whereas the computation time is 190 times faster than that of the previous algorithm, demonstrating that Deep-HUG has potential as a useful technique to rapidly generate an ultrasound hologram for various applications.

• Journal of Korean Library and Information Science Society
• /
• v.51 no.4
• /
• pp.121-156
• /
• 2020

Content curation aims to limit the user's experience to the most necessary content; to do this, it is necessary to identify users' information needs. Given that KISTI's Content Curation Center was established in 2018, it had little information about its users. This study intends to investigate what content scientists want to see from KISTI and how they want it curated. It investigated researchers who worked for government-funded research institutes through online surveys and telephone interviews. This study's results helped me review the current practice of KISTI content curation and give some suggestions to improve future practice. They present information on content and content curation services required by researchers; therefore, they can be used as a reference for information agencies (e.g., libraries, data centers) to improve their content curation practices.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.