• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.269-274
• /
• 2021

In secret communication, steganography is the sending and receiving of secret messages without being recognized by a third party. In the spatial domain method bitwise information is inserted into the virtual bit plane of the decomposed pixel values of the image. That is, the bitwise secret message is sequentially inserted into the least significant bit(LSB) of the image, which is a cover medium. In terms of application, the LSB is simple, but has a drawback that can be easily detected by a third party. If the upper bit plane is used to increase security, the image quality may deteriorate. In this paper, I present a method for concealing Hangul secret messages in image steganography based on the lo-th bit plane and the decomposition of modified pixel intensity values. After decomposing the Hangeul message to be hidden into choseong, jungseong and jongseong, then a shuffling process is applied to increase confidentiality and robustness. PSNR was used to confirm the efficiency of the proposed method. It was confirmed that the proposed technique has a smaller effect in terms of image quality than the method applying BCD and Fibonacci when inserting a secret message in the upper bit plane. When compared with the reference value, it was confirmed that the PSNR value of the proposed method was appropriate.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.1-9
• /
• 2021

In this paper, we propose a training algorithm of support vector machine (SVM) with a sensitive variable. Although machine learning models enable automatic decision making in the real world applications, regulations prohibit sensitive information from being used to protect privacy. In particular, the privacy protection of the legally protected attributes such as race, gender, and disability is compulsory. We present an efficient least square SVM (LSSVM) training algorithm using a fully homomorphic encryption (FHE) to protect a partial sensitive attribute. Our framework posits that data owner has both non-sensitive attributes and a sensitive attribute while machine learning service provider (MLSP) can get non-sensitive attributes and an encrypted sensitive attribute. As a result, data owner can obtain the encrypted model parameters without exposing their sensitive information to MLSP. In the inference phase, both non-sensitive attributes and a sensitive attribute are encrypted, and all computations should be conducted on encrypted domain. Through the experiments on real data, we identify that our proposed method enables to implement privacy-preserving sensitive LSSVM with FHE that has comparable performance with the original LSSVM algorithm. In addition, we demonstrate that the efficient sensitive LSSVM with FHE significantly improves the computational cost with a small degradation of performance.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.184-192
• /
• 2022

Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.457-464
• /
• 2021

The advent of the big data era has enabled the rapid development of deep learning that learns rules by itself from data. In particular, the performance of CNN algorithms has reached the level of self-adjusting the source data itself. However, the existing image processing method only deals with the image data itself, and does not sufficiently consider the heterogeneous environment in which the image is generated. Images generated in a heterogeneous environment may have the same information, but their features may be expressed differently depending on the photographing environment. This means that not only the different environmental information of each image but also the same information are represented by different features, which may degrade the performance of the image analysis model. Therefore, in this paper, we propose a method to improve the performance of the image color constancy model based on Adversarial Learning that uses image data generated in a heterogeneous environment simultaneously. Specifically, the proposed methodology operates with the interaction of the 'Domain Discriminator' that predicts the environment in which the image was taken and the 'Illumination Estimator' that predicts the lighting value. As a result of conducting an experiment on 7,022 images taken in heterogeneous environments to evaluate the performance of the proposed methodology, the proposed methodology showed superior performance in terms of Angular Error compared to the existing methods.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.11
• /
• pp.51-60
• /
• 2021

River scour erodes the soil around the pier, reducing the lateral bearing capacity of the pier and lowering the stability of the structure. In this study, in order to examine the effect of scouring on the stability of the structure, an experiment was performed to measure the natural frequency of the pier according to the excavation of the surrounding ground. Impact vibration test was conducted on the pier with the caisson foundation of the Mangyeonggang Bridge, which is scheduled to be demolished. Accelerometers were attached to the top, center, and bottom of the pier and the acceleration responses were measured by hitting those three points. The experimental results showed that the top hit showed consistent and reasonable results of the acceleration responses according to the hitting position. The measured accelerations were converted to the frequency domain through Fast Fourier Transform (FFT), and then the natural frequency was determined. In addition, to analyze the scour effect on the natural frequency of the pier, the ground around the pier was excavated and the natural frequency change was analyzed. As a result, the natural frequency showed the decreasing tendency according to the excavation depth, but the decrease was small due to the large stiffness of the caisson foundation.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.409-418
• /
• 2022

In this paper, we propose SAAnnot-C3Pap, a semi-automatic annotation method for obtaining ground truth of a player's posture. In order to obtain ground truth about the two-dimensional joint position in the existing music domain, openpose, a two-dimensional posture estimation method, was used or manually labeled. However, automatic annotation methods such as the existing openpose have the disadvantages of showing inaccurate results even though they are fast. Therefore, this paper proposes SAAnnot-C3Pap, a semi-automated annotation method that is a compromise between the two. The proposed approach consists of three main steps: extracting postures using openpose, correcting the parts with errors among the extracted parts using supervisely, and then analyzing the results of openpose and supervisely. Perform the synchronization process. Through the proposed method, it was possible to correct the incorrect 2D joint position detection result that occurred in the openpose, solve the problem of detecting two or more people, and obtain the ground truth in the playing posture. In the experiment, we compare and analyze the results of the semi-automated annotation method openpose and the SAAnnot-C3Pap proposed in this paper. As a result of comparison, the proposed method showed improvement of posture information incorrectly collected through openpose.

• Journal of Korean Elementary Science Education
• /
• v.41 no.2
• /
• pp.186-198
• /
• 2022

With the science curriculum about to be revised in 2022, this study aimed to guide curriculum revision by addressing suggested approaches to the electromagnetism education in elementary school science curriculum. The core concepts of electromagnetism are "electric field" and "magnetic field" as a medium of force, but the current curriculum does not properly describe the core concepts of electromagnetism. Mechanics and electromagnetism should be linked in elementary schools to form science curriculum based on core concepts to solve this problem. Additionally, the nine aspects of technology extracted in this study offer various educational contexts to match the development of engineering technology based on electromagnetism. However, the current curriculum does not comprise these various contexts and focuses on the limited content of electric circuits using light bulbs. Therefore, it is necessary to expand the scope of the curriculum to better mirror real-life technology. Through the use of more diverse materials and contexts, the scope and level of STS education as well as conceptual learning could be expanded. Finally, in the case of electric circuit learning, various issues such as difficulty in connecting electric circuits and electric field concepts, representativeness of electric circuit, students' learning difficulty, and phenomena-oriented learning should be considered.

• Journal of Service Research and Studies
• /
• v.10 no.4
• /
• pp.57-70
• /
• 2020

Globally, cloud service is a core infrastructure that improves industrial productivity and accelerates innovation through convergence and integration with various industries, and it is expected to continuously expand the market size and spread to all industries. In particular, due to the global pandemic caused by COVID-19, the introduction of cloud services was an opportunity to be recognized as a core infrastructure to cope with the untact era. However, it is still at the preliminary stage for market expansion of cloud service in Korea. This paper aims to empirically analyze how cloud services can be accepted by users by each industry through extended Technology Acceptance Model(TAM), and what factors influence the acceptance and avoidance of cloud services to users. For this purpose, the impact and factors on the acceptance intention of cloud services were analyzed through the hypothesis test through the proposed extended technology acceptance model. The industrial sector selected four industrial sectors of education, finance, manufacturing and health care and derived factors by examining the parameters of TAM, key characteristics of the cloud and other factors. As a result of the empirical analysis, differences were found in the factors that influence the intention to accept cloud services for each of the four industry sectors, which means that there is a difference in perception of the introduction or use of cloud services by industry sector. Eventually it is expected that this study will not only help to understand the intention of using cloud services by industry, but also help cloud service providers expand and provide cloud services to each industry.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.429-440
• /
• 2023

This study explores recent research trends and potential applications of ultrasound optical imaging-based multimodal technology. Ultrasound imaging has been widely utilized in medical diagnostics due to its real-time capability and relative safety. However, the drawback of low resolution in ultrasound imaging has prompted active research on multimodal imaging techniques that combine ultrasound with other imaging modalities to enhance diagnostic accuracy. In particular, ultrasound optical imaging-based multimodal technology enables the utilization of each modality's advantages while compensating for their limitations, offering a means to improve the accuracy of the diagnosis. Various forms of multimodal imaging techniques have been proposed, including the fusion of optical coherence tomography, photoacoustic, fluorescence, fluorescence lifetime, and spectral technology with ultrasound. This study investigates recent research trends in ultrasound optical imaging-based multimodal technology, and its potential applications are demonstrated in the biomedical field. The ultrasound optical imaging-based multimodal technology provides insights into the progress of integrating ultrasound and optical technologies, laying the foundation for novel approaches to enhance diagnostic accuracy in the biomedical domain.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.3
• /
• pp.221-229
• /
• 2023

This research aimed to conduct an empirical assessment of the penetration of chloride and sulfate ions into mortar sections using an anion exchange membrane(AEM) and laser-induced breakdown spectroscopy(LIBS). The study involved a simultaneous ion chromatography(IC) analysis and LIBS analysis performed on mortars immersed in varying concentrations of chloride and sulfate. The findings revealed that at the wavelengths specific to Chloride(837.59nm) and Sulfur(921.30nm), the LIBS intensity achieved using AEM surpassed that obtained with a paper substrate at equivalent penetration concentrations. A robust correlation was confirmed between LIBS intensity and chloride ion concentration. Furthermore, when juxtaposed with IC analysis concentration outcomes at identical depths, the AEM displayed a higher intensity. The research noted an enhancement in LIBS intensity and a diminution in errors within the low-concentration section when deploying AEM. However, for the Sulfur wavelength of 921.3nm, there remains a need to augment the sensitivity of the LIBS signal within the low-concentration section in future studies. The findings underscore the potential of employing AEM and LIBS for precise analysis of chloride and sulfate ion penetration into mortar sections. This strategy can aid in bolstering assessment precision and mitigating errors, particularly in regions with low concentrations. It is recommended to further research and develop methods to amplify the sensitivity of the LIBS signal for sulfur detection in low-concentration sections. In sum, the study accentuates the significance of employing advanced techniques like AEM and LIBS for efficacious and precise analysis in the domain of mortar section assessment.