• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.73-80
• /
• 2023

In this paper, a technology to protect important information from access in order to revitalize the cloud service market. A technology is proposed to solve the risk of leakage of important confidential and personal information stored in cloud systems, which is one of the various obstacles to the cloud service market. To protect important information, access control rights to cloud resources are granted to cloud service providers and general users. The system administrator has superuser authority to maintain and manage the system. Client computing services are managed by an external cloud service provider, and information is also stored in an external system. To protect important in-house information within the company, all users, it was designed to provide access authority with users including cloud service providers, only after they are authenticated. It is expected that the confidentiality of cloud computing resources and service reliability achieved through the proposed access control technology will contribute to revitalizing the cloud service market.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.259-266
• /
• 2023

In this paper, we propose an algorithm that can improve the accuracy performance of collaborative filtering using attribute-based opinion mining (ABOM). For the experiment, a total of 1,227 online consumer review data about smartphone apps from domestic smartphone users were used for analysis. After morpheme analysis using the KKMA (Kkokkoma) analyzer and emotional word analysis using KOSAC, attribute extraction is performed using LDA topic modeling, and the topic modeling results for each weighted review are used to add up the ratings of collaborative filtering and the sentiment score. MAE, MAPE, and RMSE, which are statistical model performance evaluations that calculate the average accuracy error, were used. Through experiments, we predicted the accuracy of online customers' app ratings (APP_Score) by combining traditional collaborative filtering among the recommendation algorithms and the attribute-based opinion mining (ABOM) technique, which combines LDA attribute extraction and sentiment analysis. As a result of the analysis, it was found that the prediction accuracy of ratings using attribute-based opinion mining CF was better than that of ratings implementing traditional collaborative filtering.

• Fashion & Textile Research Journal
• /
• v.25 no.5
• /
• pp.560-567
• /
• 2023

This study aims to rediscover the industrial value of a borderless service in the hyper-connected era by producing fashion content at the forefront of the cultural industry as XR content and contributing to developing fashion content for edutech. The research method employed design aesthetic theory, while the empirical proposal utilized scientific knowledge information to build a framework for 3D convergence content. The characteristics of fashion content exhibitions that apply the neumorphism technique are as follows: The first is a virtual space that produces clothing culture by type. Africa, where dyeing and crafts are developed, selects a product-oriented exhibition type; Asia, where weaving and textiles are excellent, selects a random movement type; and Europe, where the evolution of clothing design over time is evident, selects a guided movement type to create a three-dimensional fashion edutech. The goal was to produce content. The second is creative reproducibility, which combines a new fashion design that embraces the aura of the original with a trendy sense. The realistic folk costume style of the original allowed for its implementation in the AR exhibition space using historical traditional style techniques such as weaving and textiles. The third is building organic, modular content. By designing and then saving/editing/arranging the basic VP zone for each style, learners and instructors can freely edit the content for each fashion class topic and create various presentations to ensure that it functions as non-face-to-face edutech content around the world.

• Journal of Industrial Convergence
• /
• v.21 no.9
• /
• pp.49-56
• /
• 2023

ID is used as identifying information and password as user authentication for ID-based authentication. In order to have a secure user authentication, the password is generated as a hash value on the client and sent to the server, where it is compared with the stored information and authentication is performed. However, if even one character is incorrect, the different hash value is generated, authentication will be failed and cannot be performed and various functions cannot be applied to the password. In this study, we generate several hash value including imaginary number of entered password and transmit to server and perform authentcation. we propose a technique can grants the right differentially to give various rights to the user who have many rights by one account. This can defend shoulder surfing attack by imaginary password and provide convenience to users who have various rights by granting right based on password.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.361-369
• /
• 2023

Achieving realistic visual quality while maintaining optimal real-time rendering performance is a major challenge in evolving computer graphics and interactive 3D applications. Normal mapping, as a core technology in 3D, has matured through continuous optimization and iteration. Hybrid normal mapping as a new mapping model has also made significant progress and has been applied in the 3D asset production pipeline. This study comprehensively explores the hybrid normal techniques, analyzing Linear Blending, Overlay Blending, Whiteout Blending, UDN Blending, and Reoriented Normal Mapping, and focuses on how the various hybrid normal techniques can be used to achieve rendering performance and visual fidelity. performance and visual fidelity. Under the consideration of computational efficiency, visual coherence, and adaptability in different 3D production scenes, we design comparative experiments to explore the optimal solutions of the hybrid normal techniques by analyzing and researching the code, the performance of different hybrid normal mapping in the engine, and analyzing and comparing the data. The purpose of the research and summary of the hybrid normal technology is to find out the most suitable choice for the mainstream workflow based on the objective reality. Provide an understanding of the hybrid normal mapping technique, so that practitioners can choose how to apply different hybrid normal techniques to the corresponding projects. The purpose of our research and summary of mixed normal technology is to find the most suitable choice for mainstream workflows based on objective reality. We summarized the hybrid normal mapping technology and experimentally obtained the advantages and disadvantages of different technologies, so that practitioners can choose to apply different hybrid normal mapping technologies to corresponding projects in a reasonable manner.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.369-377
• /
• 2023

In the industrial manufacturing sector, quality control is pivotal for minimizing defect rates; inadequate management can result in additional costs and production delays. This study underscores the significance of detecting texture defects in manufactured goods and proposes a more precise defect detection technique. While the DFR(Deep Feature Reconstruction) model adopted an approach based on feature map amalgamation and reconstruction, it had inherent limitations. Consequently, we incorporated a new loss function using statistical methodologies, integrated a skip connection structure, and conducted parameter tuning to overcome constraints. When this enhanced model was applied to the texture category of the MVTec-AD dataset, it recorded a 2.3% higher Defect Segmentation AUC compared to previous methods, and the overall defect detection performance was improved. These findings attest to the significant contribution of the proposed method in defect detection through the reconstruction of feature map combinations.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.197-209
• /
• 2024

This study aimed to analyze recent research trends in Artificial Intelligence (AI) education within South Korea with the overarching objective of exploring the future direction of AI education. For this purpose, an analysis of 697 papers related to AI education published in Research Information Sharing Service (RISS) from 2016 to November 2023 were analyzed using word cloud and Latent Dirichlet Allocation (LDA) topic modeling technique. As a result of the analysis, six major topics were identified: generative AI utilization education, AI ethics education, AI convergence education, teacher perceptions and roles in AI utilization, AI literacy development in university education, and AI-based education and research directions. Based on these findings, I proposed several suggestions, (1) including expanding the use of generative AI in various subjects, (2) establishing ethical guidelines for AI use, (3) evaluating the long-term impact of AI education, (4) enhancing teachers' ability to use AI in higher education, (5) diversifying the curriculum of AI education in universities, (6) analyzing the trend of AI research, and developing an educational platform.

• Science of Emotion and Sensibility
• /
• v.26 no.4
• /
• pp.115-124
• /
• 2023

This study explores the intersection of literary studies and artificial intelligence (AI), focusing on the common theme of human emotions to foster complementary advancements in both fields. By adopting a comparative perspective, the paper investigates emotion as a shared focal point, analyzing various emotion-related concepts from both literary and AI perspectives. Despite the scarcity of research on the fusion of AI and literary studies, this study pioneers an interdisciplinary approach within the humanities, anticipating future developments in AI. It proposes that literary sensibility can contribute to AI by formalizing subjective literary emotions, thereby enhancing AI's understanding of complex human emotions. This paper's methodology involves the terminology-centered extraction of emotions, aiming to blend subjective imagination with objective technology. This fusion is expected to not only deepen AI's comprehension of human complexities but also broaden literary research by rapidly analyzing diverse human data. The study emphasizes the need for a collaborative dialogue between literature and engineering, recognizing each field's limitations while pursuing a convergent enhancement that transcends these boundaries.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.73-80
• /
• 2024

In this paper, we proposes a method to improve the accuracy of predicting the Korea Composite Stock Price Index (KOSPI) by combining topic modeling and Long Short-Term Memory (LSTM) neural networks. In this paper, we use the Latent Dirichlet Allocation (LDA) technique to extract ten major topics related to interest rate increases and decreases from financial news data. The extracted topics, along with historical KOSPI index data, are input into an LSTM model to predict the KOSPI index. The proposed model has the characteristic of predicting the KOSPI index by combining the time series prediction method by inputting the historical KOSPI index into the LSTM model and the topic modeling method by inputting news data. To verify the performance of the proposed model, this paper designs four models (LSTM_K model, LSTM_KNS model, LDA_K model, LDA_KNS model) based on the types of input data for the LSTM and presents the predictive performance of each model. The comparison of prediction performance results shows that the LSTM model (LDA_K model), which uses financial news topic data and historical KOSPI index data as inputs, recorded the lowest RMSE (Root Mean Square Error), demonstrating the best predictive performance.