• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.149-149
• /
• 2022

Accurate quantitative evaluation of baseflow contribution to streamflow is imperative to address seasonal drought vulnerability, flood occurrence and groundwater management concerns for efficient and sustainable water resources management in watersheds. Several baseflow separation algorithms using recursive filters, graphical method and tracer or chemical balance have been developed but resulting baseflow outputs always show wide variations, thereby making it hard to determine best separation technique. Therefore, the current global shift towards implementation of artificial intelligence (AI) in water resources is employed to compare the performance of deep learning models with conventional hydrograph separation techniques to quantify baseflow contribution to streamflow of Piney River watershed, Tennessee from 2001-2021. Streamflow values are obtained from the USGS station 03602500 and modeled to generate values of Baseflow Index (BI) using Web-based Hydrograph Analysis (WHAT) model. Annual and seasonal baseflow outputs from the traditional separation techniques are compared with results of Long Short Term Memory (LSTM) and simple Gated Recurrent Unit (GRU) models. The GRU model gave optimal BFI values during the four seasons with average NSE = 0.98, KGE = 0.97, r = 0.89 and future baseflow volumes are predicted. AI offers easier and more accurate approach to groundwater management and surface runoff modeling to create effective water policy frameworks for disaster management.

• 한국환경과학회지
• /
• 제32권9호
• /
• pp.627-634
• /
• 2023

Tire wear particles(TWPs), regarded as a microplastic, is generated in significant quantities each year and exist in various spaces and have a negative impact on the surrounding environment. Particularly, roadside environments fall within the direct influence of TWPs, necessitating proactive investigation for contamination management and response. Therefore, this study aimed to investigate the soil acidity and electrical conductivity(EC) and TWPs in the roadside soil of six sites based on traffic volume. The analysis revealed that the soil in all sites exhibited subacidity, and there were no significant differences in EC. Microscopic and FT-IR analysis revealed the presence of microscopic particles in soil samples that exhibited common visual characteristics of TWPs. In the road with the highest traffic volume, 48,300 TWPs were detected per unit area. Furthermore, a proportional relationship between traffic volume and TWPs particles was established. However, influences other than traffic volume on TWPs particle count within the soil were observed. Therefore, for the management of TWPs contaminated roadside soil, a proactive response is necessary in areas with high traffic volumes. However, in order to effectively address the factors contributing to the generation and dispersion of TWPs, further research is required with a multidimensional approach.

• 식품보건융합연구
• /
• 제9권6호
• /
• pp.21-26
• /
• 2023

Purpose: This study aims to explore how the modern foodservice industry reflects consumers' rapidly changing taste preferences and health consciousness. In particular, it looks at how companies such as Yakult Korea are expanding their business to meet diverse consumer demands and how traditional and exotic tastes are driving the growth of the sauce market. Research methods: this study was conducted through market analysis, consumer behavior research and case studies. Sales data, consumer purchasing patterns and product development strategy case studies of sauce products in domestic and global markets were investigated to analyze the impact of taste and health harmony and storytelling on brand value. Conclusion: The foodservice industry is meeting consumer expectations for health and taste harmony by developing innovative products that satisfy the senses and adopting marketing strategies through strong storytelling. The success of exotic sauce products in particular reflects consumers' desire for diversity. Implications: the findings suggest that the foodservice industry must continue to innovate to meet consumers' health and taste expectations. They also reveal that product storytelling plays an important role in enhancing brand value. This requires a strategic approach to long-term brand growth and market differentiation. Companies need to reflect these changes in consumer buying behavior.

• 식품보건융합연구
• /
• 제10권1호
• /
• pp.1-6
• /
• 2024

Purpose: The research aims to address the intricacies of AI and Big Data application within the food industry. This study explores the strategic implementation of AI and Big Data in the food industry. The study seeks to understand how these technologies can be employed to bolster consumer engagement and contribute to market expansion, while considering ethical implications. Research Method: This research employs a comprehensive approach, analyzing current trends, case studies, and existing academic literature. It focuses on the application of AI and Big Data in areas such as supply chain management, consumer behavior analysis, and personalized marketing strategies. Results: The study finds that AI and Big Data significantly enhance market analytics, consumer personalization, and market trend prediction. It highlights the potential of these technologies in creating more efficient supply chains, improving consumer satisfaction through personalization, and providing valuable market insights. Conclusion and Implications: The paper offers actionable insights and recommendations for the effective implementation of AI and Big Data strategies in the food industry. It emphasizes the need for ethical considerations, particularly in data privacy and the transparency of AI algorithms. The study also explores future trends, suggesting that AI and Big Data will continue to revolutionize the industry, emphasizing sustainability, efficiency, and consumer-centric practices.

• BMB Reports
• /
• 제57권5호
• /
• pp.250-255
• /
• 2024

Due to their stem-like characteristics and immunosuppressive properties, Mesenchymal stem cells (MSCs) offer remarkable potential in regenerative medicine. Much effort has been devoted to enhancing the efficacy of MSC therapy by enhancing MSC migration. In this study, we identified deubiquitinase BRCA1-associated protein 1 (BAP1) as an inhibitor of MSC migration. Using deubiquitinase siRNA library screening based on an in vitro wound healing assay, we found that silencing BAP1 significantly augmented MSC migration. Conversely, BAP1 overexpression reduced the migration and invasion capabilities of MSCs. BAP1 depletion in MSCs upregulates ERK phosphorylation, thereby increasing the expression of the migration factor, osteopontin. Further examination revealed that BAP1 interacts with phosphorylated ERK1/2, deubiquitinating their ubiquitins, and thus attenuating the ERK signaling pathway. Overall, our study highlights the critical role of BAP1 in regulating MSC migration through its deubiquitinase activity, and suggests a novel approach to improve the therapeutic potential of MSCs in regenerative medicine.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• International Journal of Advanced Culture Technology
• /
• 제12권2호
• /
• pp.205-214
• /
• 2024

This paper delves into the application of Gestalt psychology principles in logo design. It analyzes how these principles refine design elements to bolster the efficiency and impact of visual communication. Drawing from Gestalt psychology perspectives, the theoretical foundations and application methods of logo design simplification strategies are discussed. Through the analysis of Gestalt psychology effects in various types and styles of logo designs, this study compares the applicability and differences of logo design simplification strategies under different cultural and social contexts. Furthermore, it evaluates their role and value in enhancing the innovativeness and communicative impact of logo designs. The findings suggest that strategies informed by Gestalt psychology significantly improve the organization rules within logo designs, such as the relationship between figure and ground, proximity, similarity, and continuity. Thereby they enhance perceptual clarity, cognitive load, and aesthetic satisfaction. Moreover, these strategies promote creative thinking and problem-solving abilities in logo design. The results indicate that simplified design methods not only enhance aesthetic appeal but also improve the adaptability and recognizability of logos across different media and environments. This approach aligns with the minimalist and flat design trends of today's information age, meeting the evolving needs and aesthetic preferences of consumers.

• 웰빙융합연구
• /
• 제7권2호
• /
• pp.31-37
• /
• 2024

Purpose: Pop-up stores have emerged in the retail industry in recent years, offering consumers a new shopping experience for a limited time and location, and are used for a variety of purposes, including driving purchase behavior. In particular, they have become an important marketing tool among Gen MZ consumers who are quick to acquire information and sensitive to trends. Therefore, this study aims to analyze the impact of pop-up store characteristics on the purchasing behavior of MZ consumers. Research design, data and methodology: Based on a qualitative research approach, the study analyzed successful pop-up stores in Korea to closely examine how the limited operating period and experience-oriented marketing strategy of pop-up stores affect the perceptual attitudes and purchase decision process of Generation MZ. Results: The results of the case study revealed that selling limited edition items, maximizing customer experience factors, and differentiated concepts are the main factors that positively influence the purchase behavior of Gen MZ consumers. These factors contribute to the enhanced purchasing behavior of Gen MZ, making pop-up stores an effective marketing strategy. Conclusions: Pop-up stores are more than just a sales space, but an important communication channel that can strengthen the emotional connection with Gen MZ and effectively communicate brand values. This study provides useful insights for brands and companies to develop marketing strategies for MZ.

• Nonlinear Functional Analysis and Applications
• /
• 제29권1호
• /
• pp.131-164
• /
• 2024

In this research, we study a modified relaxed Tseng method with a single projection approach for solving common solution to a fixed point problem involving finite family of τ-demimetric operators and a quasi-monotone variational inequalities in real Hilbert spaces with alternating inertial extrapolation steps and adaptive non-monotonic step sizes. Under some appropriate conditions that are imposed on the parameters, the weak and linear convergence results of the proposed iterative scheme are established. Furthermore, we present some numerical examples and application of our proposed methods in comparison with other existing iterative methods. In order to show the practical applicability of our method to real word problems, we show that our algorithm has better restoration efficiency than many well known methods in image restoration problem. Our proposed iterative method generalizes and extends many existing methods in the literature.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.774-776
• /
• 2024

The effective implementation of advanced speech recognition (ASR) systems necessitates the deployment of sophisticated keyword spotting models that are both responsive and resource-efficient. The initial local detection of user interactions is crucial as it allows for the selective transmission of audio data to cloud services, thereby reducing operational costs and mitigating privacy risks associated with continuous data streaming. In this paper, we address these needs and propose utilizing the Whisper-Tiny model with fine-tuning process to specifically recognize keywords from google speech dataset which includes 65000 audio clips of keyword commands. By adapting the model's encoder and appending a lightweight classification head, we ensure that it operates within the limited resource constraints of local devices. The proposed model achieves the notable test accuracy of 92.94%. This architecture demonstrates the efficiency as on-device model with stringent resources leading to enhanced accessibility in everyday speech recognition applications.