• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1391-1406
• /
• 2020

A zero-watermarking algorithm in transform domain based on RGB channel and voting strategy is proposed. The registration and identification of ownership have achieved copyright protection for color images. In the ownership registration, discrete wavelet transform (DWT), discrete cosine transform (DCT), and singular value decomposition (SVD) are used comprehensively because they have the characteristics of multi-resolution, energy concentration and stability, which is conducive to improving the robustness of the proposed algorithm. In order to take full advantage of the characteristics of the image, we use three channels of R, G, and B of a color image to construct three master shares, instead of using data from only one channel. Then, in order to improve security, the master share is superimposed with the copyright watermark encrypted by the owner's key to generate an ownership share. When the ownership is authenticated, copyright watermarks are extracted from the three channels of the disputed image. Then using voting decisions, the final copyright information is determined by comparing the extracted three watermarks bit by bit. Experimental results show that the proposed zero watermarking scheme is robust to conventional attacks such as JPEG compression, noise addition, filtering and tampering, and has higher stability in various common color images.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

• ETRI Journal
• /
• v.42 no.6
• /
• pp.859-871
• /
• 2020

A spectrally encapsulated (SE) orthogonal frequency-division multiplexing (OFDM) precoding scheme for wireless short packet transmission, which can suppress the out-of-band emission (OoBE) while maintaining the advantage of the cyclic prefix (CP)-OFDM, is proposed. The SE-OFDM symbol consists of a prefix, an inverse fast Fourier transform (IFFT) symbol, and a suffix generated by the head, center, and tail matrices, respectively. The prefix and suffix play the roles of a guard interval and suppress the OoBE, and the IFFT symbol has the same size as the discrete Fourier transform symbol in the CP-OFDM symbol and serves as an information field. Specifically, as the center matrix generating the IFFT symbol is orthogonal, data and pilot symbols can be allocated to any subcarrier without distinction. Even if the proposed precoder is required to generate OFDM symbols with spectral efficiency in the transmitter, a corresponding decoder is not required in the receiver. The proposed scheme is compared with CP-OFDM in terms of spectrum, OoBE, and bit-error rate.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.21-29
• /
• 2021

With the recent increase in the number of households raising pets, various engineering studies have been underway for pets. The final purpose of this study is to automatically generate situation-sensitive captions that can express implicit intentions based on the behavior and sound of cats by embedding the already mature behavioral detection technology of pets as basic element technology in the video capturing research. As a pilot project to this end, this paper proposes a high-level capturing system using optical-flow, RGB, and sound information of cat videos. That is, the proposed system uses video datasets collected in an actual breeding environment to extract feature vectors from the video and sound, then through hierarchical LSTM encoder and decoder, to identify the cat's behavior and its implicit intentions, and to perform learning to create context-sensitive captions. The performance of the proposed system was verified experimentally by utilizing video data collected in the environment where actual cats are raised.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.169-176
• /
• 2021

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

• Journal of the Korean Society of Visualization
• /
• v.19 no.3
• /
• pp.92-98
• /
• 2021

Large Eddy Simulation (LES) has been popularly applied and used in the last several decades to simulate turbulent boundary layer in the numerical domain. A fully developed turbulent boundary layer has also been applied to predict the complicated wake flow behind bluff bodies. In this study we aimed to generate an artificial turbulent boundary layer, which is based on an exponential correlation function, and generates a series of realistic three-dimensional velocity data in two-dimensional inlet section which are correlated both in space and in time. The results suggest its excellent capability for high Reynolds number flows. To make an effective generation, a hexahedral mesh has been used and Cholesky decomposition was applied to possess suitable turbulent statistics such as the randomness and correlation of turbulent flow. As a result, the flow characteristics in the domain and fluctuating pressure near the wall are very close to those of fully developed turbulent boundary layers.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.41 no.4
• /
• pp.242-249
• /
• 2021

Forage crop management is severely challenged by global warming-induced climate changes representing diverse a/biotic stresses. Thus, screening of valuable genetic resources would be applied to develop stress-tolerant forage crops. We isolated two NAC (NAM, ATAF1, ATAF2, CUC2) transcription factors (ANAC032 and ANAC083) transcriptionally activated by multi-abiotic stresses (salt, drought, and cold stresses) from Arabidopsis by microarray analysis. The NAC family is one of the most prominent transcription factor families in plants and functions in various biological processes. The enhanced expressions of two ANACs by multi-abiotic stresses were validated by quantitative RT-PCR analysis. We also confirmed that both ANACs were localized in the nucleus, suggesting that ANAC032 and ANAC083 act as transcription factors to regulate the expression of downstream target genes. Promoter activities of ANAC032 and ANAC083 through histochemical GUS staining again suggested that various abiotic stresses strongly drive both ANACs expressions. Our data suggest that ANAC032 and ANAC083 would be valuable genetic candidates for breeding multi-abiotic stress-tolerant forage crops via the genetic modification of a single gene.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.2924-2932
• /
• 2022

Motivated by learning from experience and exploiting existing knowledge in civil nuclear operations, we have developed in-house generic Probabilistic Safety Assessment (PSA) models for pressurized and boiling water reactors. The models are computationally light, handy, transparent, user-friendly, and easily adaptable to account for major plant-specific differences. They cover the common internal initiating events, frontline and support systems reliability and dependencies, human-factors, common-cause failures, and account for new factors typically overlooked in many PSAs. For quantification, the models use generic US reliability data, precursor analysis reports, the ETHZ Curated Nuclear Events Database, and experts' opinions. Moreover, uncertainties in the most influential basic events are addressed. The generated results show good agreement with assessments available in the literature with detailed PSAs. We envision the models as an unbiased framework to measure nuclear operational risk with the same "ruler", and hence support inter-plant risk comparisons that are usually not possible due to differences in plant-specific PSA assumptions and scopes. The models can be used for initial risk screening, order-of-magnitude precursor analysis, and other research/pedagogic applications especially when no plant-specific PSAs are available. Finally, we are using the generic models for large-scale precursor analysis that will generate big picture trends, lessons, and insights.

• Journal of Distribution Science
• /
• v.20 no.7
• /
• pp.47-56
• /
• 2022

Purpose: As the need to transition into the distribution of cleaner energy has garnered corporate and scholarly interests, this study aims to track the research trends in sustainable energy supply chains for five years before 2021. Research methodology: This study was conducted by a bibliometric literature review and analysis to map the field's evolution between 2016 and 2020. Out of an initial title search result of 2,484 papers from the Scopus engine, filtering led to 180 documents obtained. The data was exported in excel format (CSV) to VOSviewer software to generate and analyze network visualization of sustainable energy supply chain trends. Results: The results revealed China's the highest publishing country, with 36 research papers. The Journal of Cleaner Production was the top publishing source, with 22 papers per year. These findings showed five clusters formed in the bibliographic coupling of countries. Circular Economy and Green Supply Chain Management represent the current hot topics. Research gaps identified in the field included limited cross-industry testing and modifying sustainable supply chain models. Conclusion: This paper contributes to the sustainability literature on supply chains by providing an overview of trends and research directions for scholars' and practitioners' consideration in future research.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3211-3229
• /
• 2022

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.