• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.803-813
• /
• 2021

Coastal erosion has been a threat to coastal communities and emerged as an urgent problem. Among the coastal communities that are under perceived threat, Cotonou located in Benin, West Africa, is considered as one of the most dangerous area due to its high vulnerability. To address this problem, in 2013, the Benin authorities established seven groynes at east of Cotonou port, and two additional intermediate groynes have recently been integrated in April 2018. However, there is no quantitative analysis of groynes so far, so it is hard to know how effective they have been. To analyze effectiveness, we used optical satellite images from different time periods, especially 2004 and 2020, and then compared changes in length, width and area of shoreline in Cotonou. The study area is divided into two sectors based on the location of Cotonou port. The difference of two areas is that Sector 2 has groynes installed while Sector 1 hasn't. As result of this study, shoreline in Sector 1 showed accretion by recovering 1.20 km² of area. In contrast, 3.67 km² of Sector 2 disappeared due to coastal erosion, although it has groynes. This may imply that groynes helped to lessen the rate of average erosion, however, still could not perfectly stop the coastal erosion in the area. Therefore, for the next step, we assume it is recommended to study how to maximize effectiveness of groynes.

• Journal of Korean Society of Rural Planning
• /
• v.28 no.2
• /
• pp.87-96
• /
• 2022

As part of strengthening energy security and responding to climate change, the government has promoted various renewable energy measures to increase the development of renewable energy facilities. As a result, small-scale solar installations in rural areas have increased rapidly. The number of complaints from local residents is increasing. Therefore, in this study, deep learning technology is applied to high-resolution aerial images on the internet to detect solar power plants installed in rural areas to determine whether or not solar power plants are installed. Specifically, I examined the solar facility detector generated by training the YOLO(You Only Look Once) v2 object detector and looked at its usability. As a result, about 800 pieces of training data showed a high object detection rate of 93%. By constructing such an object detection model, it is expected that it can be utilized for land use monitoring in rural areas, and it can be utilized as a spatial data construction plan for rural areas using technology for detecting small-scale agricultural facilities.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1158-1164
• /
• 2022

In this study, the emotional reaction process and the cognitive reaction process were divided into the process of building trust in order to form a continuous use intention in the process of using the mobile simple payment system. We examined the process by which various external factors generate continuous use intentions, that is, behavioral responses through the process of each reaction. External factors were divided into social factors, systemic factors, and social factors. Among them, system factors were social norms and images, and systemic factors were simplicity and accessibility. And the social factors consisted of security and compatibility. And the emotional response was set as pleasure and emotional trust, the cognitive response was cognitive trust, and the final dependent variable was set as continuous use intention. A survey was conducted for model analysis, and the analysis results were derived using PLS.

• Journal of Information Science Theory and Practice
• /
• v.11 no.1
• /
• pp.14-30
• /
• 2023

The purpose of this study is to compare research trends in the information and communication technology (ICT) field between North and South Korea and analyze the differences by using data mining. Frequency analysis, clustering, and network analysis were performed using keywords from seven South Korean and two North Korean ICT academic journals published for five years (2015-2019). In the case of South Korea (S. Korea), the frequency of research on image processing and wireless communication was high at 16.7% and 16.3%, respectively. North Korea (N. Korea) had a high frequency of research, in the order of 18.2% for image processing, 16.9% for computer/Internet applications/security, and 16.4% for industrial technology. N. Korea's natural language processing (NLP) sector was 11.9%, far higher than S. Korea's 0.7 percent. Student education is a unique subject that is not clustered in S. Korea. In order to promote exchanges between the two Koreas in the ICT field, the following specific policies are proposed. Joint research will be easily possible in the image processing sector, with the highest research rate in both Koreas. Technical cooperation of medical images is required. If S. Korea's high-quality image source is provided free of charge to N. Korea, research materials can be enriched. In the field of NLP, it calls for proposing exchanges such as holding a Korean language information conference, developing a Korean computer operating system. The field of student education encourages support for remote education contents and management know-how, as well as joint research on student remote evaluation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.139-141
• /
• 2022

As interest in digital video media and intelligent systems increases rapidly, technologies using video information are being combined and used in various fields such as security and artificial intelligence. Impulse noise generated during digital image processing degrades the image quality of the image and reduces the reliability of information, so it is necessary to remove it through a filter. There are SMF, AWMF, and MDBUTMF as well-known antecedent methods, but they all have limitations in achieving seamless filtering in environments with large loss of information on valid pixels due to problems with the algorithm itself. Therefore, this paper designs a median filter algorithm that applies weights reflecting the reliability of the information by searching for the nearest effective pixels present within the mask. For performance evaluation, this algorithm and the preceding algorithm were compared and analyzed using PSNR and enlarged images.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.1089-1095
• /
• 2023

Windows are essential and important architectural elements for the organization of architectural spaces, and they give character to the space and have a great impact on the reaction of users. Virtual windows are installed to activate architectural spaces such as underground spaces where windows cannot be installed, and to provide a sense of psychological security to users in hospital clinics, etc. In this study, we reviewed the literature and collected and analyzed the precedents of virtual windows to discuss the factors necessary to improve the realism of virtual windows. The factors that affect the realism of virtual windows are further grouped into five categories: 1. Use of reproduced images or videos for views, 2. Representation of temporality, 3. Responsiveness to changes in the observer's perspective, 4. Realistic reproduction of sunlight, and 5. Provision of non-visual sensory elements. Virtual windows are not just a replacement for traditional windows, but a way to realize a virtual environment using digital media, and it is necessary to expand the discussion to the realization of the virtual environment and the relationship with architectural elements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.77-89
• /
• 2024

This paper presents an unmanned store management system that can provide inventory management and theft prevention for displayed products using a small camera that can monitor the shelves of sold products in small and medium-sized stores. This system is a service solution that integrates object recognition, real-time communication, security management, access management, and mobile authentication. The proposed system uses a custom YOLOv5-x model to recognize objects on the display, measure quantities in real time, and support real-time data communication with servers through Raspberry Pie. In addition, the number of objects in the database and the object recognition results are compared to detect suspected theft situations and provide burial images at the time of theft. The proposed unmanned store solution is expected to improve the efficiency of small and medium-sized unmanned store operations and contribute to responding to theft.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.