• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.183-183
• /
• 2021

Deep learning methods and their application have become an essential part of prediction and modeling in water-related research areas, including hydrological processes, climate change, etc. It is known that application of deep learning leads to high availability of data sources in hydrology, which shows its usefulness in analysis of precipitation, runoff, groundwater level, evapotranspiration, and so on. However, there is still a limitation on microclimate analysis and prediction with deep learning methods because of deficiency of gauge-based data and shortcomings of existing technologies. In this study, a real-time rainfall prediction model was developed from a sky image data set with convolutional neural networks (CNNs). These daily image data were collected at Chung-Ang University and Korea University. For high accuracy of the proposed model, it considers data classification, image processing, ratio adjustment of no-rain data. Rainfall prediction data were compared with minutely rainfall data at rain gauge stations close to image sensors. It indicates that the proposed model could offer an interpolation of current rainfall observation system and have large potential to fill an observation gap. Information from small-scaled areas leads to advance in accurate weather forecasting and hydrological modeling at a micro scale.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.4 no.4
• /
• pp.25-38
• /
• 2004

Schools have focused so far on a student-oriented education. As the roles of schools, however, have been increasingly emphasized in the information society, community-centered functions are now additionally required. Beyond simply allowing communities to utilize selected facilities, schools can conduct re-education programs for community residents and actively use their facilities for such purposes. As explained above, schools must continuously evolve to meet current needs and demands, such as by offering special classes and utilizing learning facilities in the elementary levels to promote learning in ever-changing societies. This study analyzed the functions of school facilities to communities, as well as the educational functions involved in teaching-learning processes, in light of the advent of a knowledge and information society. Through analysis, the types of information facilities in elementary schools were derived. On the basis of such derived types, systematic and reasonable methods to estimate the scope were suggested.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.4
• /
• pp.279-284
• /
• 2007

Nowadays, due to development of automatic control devices and various sensors, one operator can freely handle several remote plants and processes. Automatic diagnosis and warning systems have been adopted in various fields, in order to prepare an operator's absence for patrolling plants. In this paper, a Bayesian networks based on-line diagnosis system is proposed for a wastewater treatment process. Especially, the suggested system is included learning structure, which can continuosly update conditional probabilities in the networks. To evaluate performance of proposed model, we made a lab-scale five-stage step-feed enhanced biological phosphorous removal process plant and applied on-line diagnosis system to this plant in the summer.

• Journal of The Korean Society of Integrative Medicine
• /
• v.2 no.4
• /
• pp.83-90
• /
• 2014

Purpose : PBL is a teaching method to learn problem-solving process. Present study was to investigate the predictors of academic achievement when PBL is applied to students of physical therapy. Method : We Performed in-depth interviews and analyzed using the qualitative analysis by randomly assigning 5 of twenty four students who attended the class. Result : The results are classified into two categories and six sub-subjects. Based on two system of classification, PBL showed the learning effect through problem-solving methods because students directly participated in these processes. Also, students need to clearly comprehend communication method and decision-making process in order to progress the class smoothly. Conclusion : Therefore, futher studies will be continuously needed on how we apply PBL to various curriculums of physical therapy.

• Journal of Intelligence and Information Systems
• /
• v.3 no.1
• /
• pp.31-45
• /
• 1997

To date, research on data mining has focused primarily on individual techniques to su, pp.rt knowledge discovery. However, the integration of elementary learning techniques offers a promising strategy for challenging a, pp.ications such as forecasting nonlinear processes. This paper explores the utility of an integrated a, pp.oach which utilizes a second-order learning process. The a, pp.oach is compared against individual techniques relating to a neural network, case based reasoning, and induction. In the interest of concreteness, the concepts are presented through a case study involving the prediction of network traffic for video-on-demand.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.1
• /
• pp.36-41
• /
• 2012

We tested a single pendulum simulation and observed the influence of several situation space segmentation types in reinforcement learning processes in order to propose a new adaptive automation for situation space segmentation. Its segmentation is performed by the Contraction Algorithm and the Cell Division Approach. Also, its automation is performed by "entropy," which is defined on action values’ distributions. Simulation results were shown to demonstrate the influence and adaptability of the proposed method.

• Journal of Korean Elementary Science Education
• /
• v.17 no.1
• /
• pp.61-73
• /
• 1998

This research suggests science inquiry play of analogy as a teaming method to help the students in concrete operational stage to develop scientific thinking skills and to understand abstract science conceptions. The research focuses on/considers the characteristics and merits of the science inquiry plays, and the learning method by analogical reasoning. This learning through the science inquiry play of analogy can be considered as a meta-model for scientific thinking skill. The learning has the following processes: 1) Students analogize the abstract science conceptions and facts into play-type activities including the concrete contents such as students themselves, their physical-sensory motions, concrete objects, play methods, and play rules. 2) Students as analogized objects play a role physically and sensuously according to the methods and rules analogized in the play. 3) Students find out the concrete contents included in the science inquiry play of analogy, draw the results, and deduce the new conceptions from the results by reflective thinking and analogical reasoning.

• Journal of The Korean Association For Science Education
• /
• v.5 no.2
• /
• pp.139-145
• /
• 1985

This study was undertaken to analyze the research trends on science education in Korea. In this study the analysis for of trends of researches on science education, nine areas such as historical change of science Education, Processes of science learning science curriculum, science instruction, teaching-learning materials and equipment for science education, valuation on science education, survey on Korean science education, policy and management of science education, and natural science, were chosen for the analysir. All science education. thesis and dissertations in Korea, papers of science education published by the science center of the Seoul National University and the papers of the Journal of the Korean Association of Res Search in science Education were analyzed. The findings of this study are as follows: 1. Seventy percentile of science educational thesis and dissertations are on natural science areas. 2. About 14% of all papers being sampled is in science curriculum research category. There are few research studies on historical changes of science education, and teaching-learning materials and equipments for science education.