• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1061-1069
• /
• 2021

Recently, the magnitude and frequency of extreme heavy rains and localized heavy rains have increased due to abnormal climate, which caused increased flood damage in river basin. As a result, the nonlinearity of the hydrological system of rivers or basins is increasing, and there is a limitation in that the lead time is insufficient to predict the water level using the existing physical-based hydrological model. This study predicted the water level at Ulsan (Taehwagyo) with a lead time of 0, 1, 2, 3, 6, 12 hours by applying deep learning techniques based on Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and evaluated the prediction accuracy. As a result, DNN model using the sliding window concept showed the highest accuracy with a correlation coefficient of 0.97 and RMSE of 0.82 m. If deep learning-based water level prediction using a DNN model is performed in the future, high prediction accuracy and sufficient lead time can be secured than water level prediction using existing physical-based hydrological models.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.311-323
• /
• 2023

Ever since ancient times, earthquakes have been a major threat to the civil infrastructures and the safety of human beings. The majority of casualties in earthquake disasters are caused by the damaged civil infrastructures but not by the earthquake itself. Therefore, the efficient and accurate post-earthquake assessment of the conditions of structural damage has been an urgent need for human society. Traditional ways for post-earthquake structural assessment rely heavily on field investigation by experienced experts, yet, it is inevitably subjective and inefficient. Structural response data are also applied to assess the damage; however, it requires mounted sensor networks in advance and it is not intuitional. As many types of damaged states of structures are visible, computer vision-based post-earthquake structural assessment has attracted great attention among the engineers and scholars. With the development of image acquisition sensors, computing resources and deep learning algorithms, deep learning-based post-earthquake structural assessment has gradually shown potential in dealing with image acquisition and processing tasks. This paper comprehensively reviews the state-of-the-art studies of deep learning-based post-earthquake structural assessment in recent years. The conventional way of image processing and machine learning-based structural assessment are presented briefly. The workflow of the methodology for computer vision and deep learning-based post-earthquake structural assessment was introduced. Then, applications of assessment for multiple civil infrastructures are presented in detail. Finally, the challenges of current studies are summarized for reference in future works to improve the efficiency, robustness and accuracy in this field.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.17-23
• /
• 2022

Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.7
• /
• pp.512-518
• /
• 2013

A resource allocation algorithm has a high impact on user satisfaction as well as the ability to accommodate and process services in a distributed cloud computing. In other words, service rejections, which occur when datacenters have no enough resources, degrade the user satisfaction level. Therefore, in this paper, we propose a resource allocation algorithm considering the cloud domain's remaining resources to minimize the number of service rejections. The resource allocation rate based on Q-Learning increases when the remaining resources are sufficient to allocate the maximum allocation rate otherwise and avoids the service rejection. To demonstrate, We compare the proposed algorithm with two previous works and show that the proposed algorithm has the smaller number of the service rejections.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.185-198
• /
• 2023

In marine seismic surveys, the inevitable occurrence of trace gaps in the near offset resulting from geometrical differences between sources and receivers adversely affects subsequent seismic data processing and imaging. The absence of data in the near-offset region hinders accurate seismic imaging. Therefore, reconstructing the missing near-offset information is crucial for mitigating the influence of seismic multiples, particularly in the case of offshore surveys where the impact of multiple reflections is relatively more pronounced. Conventionally, various interpolation methods based on the Radon transform have been proposed to address the issue of the nearoffset data gap. However, these methods have several limitations, leading to the recent emergence of deep-learning (DL)-based approaches as alternatives. In this study, we conducted an in-depth analysis of two representative DL-based studies to scrutinize the challenges that future studies on near-offset interpolation must address. Furthermore, through field data experiments, we precisely analyze the limitations encountered when applying previous DL-based trace interpolation techniques to near-offset situations. Consequently, we suggest that near-offset data gaps must be approached by extrapolation rather than interpolation.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.1
• /
• pp.39-60
• /
• 2014

In domestic university libraries, the difference between the knowledge resource collection activities on campus is depending on the size of the university, and their collection is concentrated on some types of digital resources. In recent years, the main universities in developed countries has developed actively in social openness and share activities of their knowledge resources, through the OA-based institutional repository, for the purpose of image improvement and competitiveness as a knowledge production base. This study examined ways to improve the relevant regulations in order to effectively collect and systematically manage the knowledge resources from graduate school, research institutes, center for teaching and learning, e-learning center, museum, press, a variety of campus organizations, so as to enhance the role of the library as the right manager of knowledge resources on campus. To this end, this study, considering the improvement of relevant regulations, investigates the operating situation of the library regulations of 176 universities and suggests necessary improvement methods in order to facilitate the digital legal deposit and expand its scope.

• International Journal of Computer Science & Network Security
• /
• v.24 no.1
• /
• pp.209-214
• /
• 2024

This is an extended research paper focusing on the applications of Machine Learing and Artificial Intelligence in virtual learning environment. The world is moving at a fast pace having the application of Machine Learning (ML) and Artificial Intelligence (AI) in all the major disciplines and the educational sector is also not untouched by its impact especially in an online learning environment. This paper attempts to elaborate on the benefits of ML and AI in E-Learning (EL) in general and explain how King Khalid University (KKU) EL Deanship is making the best of ML and AI in its practices. Also, researchers have focused on the future of ML and AI in any academic program. This research is descriptive in nature; results are based on qualitative analysis done through tools and techniques of EL applied in KKU as an example but the same modus operandi can be implemented by any institution in its EL platform. KKU is using Learning Management Services (LMS) for providing online learning practices and Blackboard (BB) for sharing online learning resources, therefore these tools are considered by the researchers for explaining the results of ML and AI.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.95-100
• /
• 2018

The future society will be identify various problem situations accurately and the ability to solve problems effectively using computing technology become more important. Based on this background, an education of future human resources based on computational thinking as well as a problem-solving ability are important in university education. Therefore, in this paper, we have analyzed the effects of software education to improve computational thinking based on problem-solving learning. We have found that there is a significant difference between the interest of the students and their learning and academic achievements. Therefore, based on the understanding of the learning motivation and method, if the problem-solving learning is conducted in real-life scenarios suitable for the level of the student, it can be possible to induce the interest of the students and improve their computational thinking ability.