• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.4
• /
• pp.265-272
• /
• 2019

In this paper, a vision-based deep learning algorithm and image processing method are proposed to detect bolt-loosening in steel connections. To achieve this objective, the following approaches are implemented. First, a bolt-loosening detection method that includes regional convolutional neural network(RCNN)-based deep learning algorithm and Hough line transform(HLT)-based image processing algorithm are designed. The RCNN-based deep learning algorithm is developed to identify and crop bolts in a connection image. The HLT-based image processing algorithm is designed to estimate the bolt angles from the cropped bolt images. Then, the proposed vision-based method is evaluated for verifying bolt-loosening detection in a lab-scale girder connection. The accuracy of the RCNN-based bolt detector and HLT-based bolt angle estimator are examined with respect to various perspective distortions.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.93-104
• /
• 2024

Demand response is a strategy that encourages customers to adjust their consumption patterns at times of peak demand with the aim to improve the reliability of the power grid and minimize expenses. The integration of renewable energy sources into smart grids poses significant challenges due to their intermittent and unpredictable nature. Demand response strategies, coupled with reinforcement learning techniques, have emerged as promising approaches to address these challenges and optimize grid operations where traditional methods fail to meet such kind of complex requirements. This research focuses on investigating the application of reinforcement learning algorithms in demand response for renewable energy integration. The objectives include optimizing demand-side flexibility, improving renewable energy utilization, and enhancing grid stability. The results emphasize the effectiveness of demand response strategies based on reinforcement learning in enhancing grid flexibility and facilitating the integration of renewable energy.

• Korean Journal of Ecology and Environment
• /
• v.56 no.3
• /
• pp.268-279
• /
• 2023

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier's abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

• Journal of Fisheries and Marine Sciences Education
• /
• v.8 no.1
• /
• pp.28-40
• /
• 1996

In the last 20 years, educators have made significant advances in their thinking about how students learn and what it is that teachers ought to teach. They attempted to teach thinking s kills and designed instructional programs to facilitate learning. The purpose of this study was to review metacognitive approaches in reading comprehension instruction, and to provide some practical implications to school teachers. First, this study reviewed the concept of metacognition. Metacognition can be divided by metacognitive knowledge and metacognitive experiences. Metacognitive knowledge consists of knowledge or beliefs about what factors interact to affect the outcome of cognitive enterprises. Metacognitive experiences are executive control of one's own cognitive process, which include planning, monitorning and evaluating. Second, this study attempted to investigate the processes of reading comprehension in the metacognitively based view. Third, this study reviewed three kinds of reading comprehension instruction. In the metacognitive approaches, instruction is viewed as constructive process in which teachers and students mediate and negotiate meaning from the instructional environment. In order to enhance reading comprehension, teachers should use examples, explicit instruction, modeling, and elaboration to provide sufficient scaffolding to students. The scaffolding gradually diminishes as students learn to use and apply the reading strategies on their own. Also, students should be encouraged to attribute successful reading to the use of appropriate strategies.

• Journal of the Korean earth science society
• /
• v.38 no.5
• /
• pp.357-366
• /
• 2017

Urban planning and engineering undergraduate students need to understand the earth physical systems and that how human beings interact with the earth systems to planning and engineering urban area. The eco-friendly or geo-friendly design and planning of an urban area is a critical issue not only for economic benefits but more importantly for the sustainable future of urban life. However, little study has been done dealing with the urban engineering students' understanding of the earth as a system and what pedagogical approach is appropriate to improve their understanding of the earth as a system. This study is to investigate the impact of a purposely designed ESS course on urban engineering students' understanding of the earth as a system and their perceptions about the instructional approaches of the course on their learning competency. This study utilized a mixed-methodology with three main data sources: concept maps, student's perception survey about their learning competency, and course contents. Both the survey and concept maps were analyzed quantitatively as well as qualitatively. The result of this study showed that the urban engineering students' experience of team-based research about the topic they chose based on their own interest had a positive impact on their understanding of the earth as a system and their learning competency. The results of this study suggest that structuring and presenting the earth system contents in the context of engineering students' understanding and their future career be effective not only for the improvement of students' content knowledge but also for the enhancement of their learning competency such as creativity and problem-solving skills in everyday life situation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.171-177
• /
• 2021

Through the rapid developments in machine learning, there have been diverse utilization approaches not only in industrial fields but also in daily life. Implementations of machine learning on financial data, also have been of interest. Herein, we employ machine learning algorithms to store sales data and present future applications for fintech enterprises. We utilize diverse missing data processing methods to handle missing data and apply gradient boosting machine learning algorithms; XGBoost, LightGBM, CatBoost to predict the future revenue of individual stores. As a result, we found that using median imputation onto missing data with the appliance of the xgboost algorithm has the best accuracy. By employing the proposed method, fintech enterprises and customers can attain benefits. Stores can benefit by receiving financial assistance beforehand from fintech companies, while these corporations can benefit by offering financial support to these stores with low risk.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.4 no.4
• /
• pp.159-176
• /
• 2023

The conservation of the raccoon dog (Nyctereutes procyonoides) in South Korea requires the protection and preservation of natural habitats while additionally ensuring coexistence with human activities. Applying habitat map modeling techniques provides information regarding the distributional patterns of raccoon dogs and assists in the development of future conservation strategies. The purpose of this study is to generate potential habitat distribution maps for the raccoon dog in South Korea using geospatial technology-based models. These models include the frequency ratio (FR) as a bivariate statistical approach, the group method of data handling (GMDH) as a machine learning algorithm, and convolutional neural network (CNN) and long short-term memory (LSTM) as deep learning algorithms. Moreover, the imperialist competitive algorithm (ICA) is used to fine-tune the hyperparameters of the machine learning and deep learning models. Moreover, there are 14 habitat characteristics used for developing the models: elevation, slope, valley depth, topographic wetness index, terrain roughness index, slope height, surface area, slope length and steepness factor (LS factor), normalized difference vegetation index, normalized difference water index, distance to drainage, distance to roads, drainage density, and morphometric features. The accuracy of prediction is evaluated using the area under the receiver operating characteristic curve. The results indicate comparable performances of all models. However, the CNN demonstrates superior capacity for prediction, achieving accuracies of 76.3% and 75.7% for the training and validation processes, respectively. The maps of potential habitat distribution are generated for five different levels of potentiality: very low, low, moderate, high, and very high.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.31-49
• /
• 2023

With the growth of the food-catering industry, consumer preferences and the number of dine-in restaurants are gradually increasing. Thus, personalized recommendation services are required to select a restaurant suitable for consumer preferences. Previous studies have used questionnaires and star-rating approaches, which do not effectively depict consumer preferences. Online reviews are the most essential sources of information in this regard. However, previous studies have aggregated online reviews into long documents, and traditional machine-learning methods have been applied to these to extract semantic representations; however, such approaches fail to consider the surrounding word or context. Therefore, this study proposes a novel review textual-based restaurant recommendation model (RT-RRM) that uses deep learning to effectively extract consumer preferences from online reviews. The proposed model concatenates consumer-restaurant interactions with the extracted high-level semantic representations and predicts consumer preferences accurately and effectively. Experiments on real-world datasets show that the proposed model exhibits excellent recommendation performance compared with several baseline models.

• East Asian mathematical journal
• /
• v.29 no.2
• /
• pp.109-135
• /
• 2013

The purpose of the study was to investigate the reality of middle school mathematics teachers' subject matter knowledge for teaching mathematical conjecture and justification. Data in the study were collected through interviewing nine Chinese and ten Korean middle school mathematics teachers. The teachers responded to the question that was designed in the form of a scenario that presents a teaching task related to a geometrical topic. The teachers' oral responses were audiotaped and transcribed, and their written notes were collected. The results of the study were compared to the analysis of American and Chinese elementary and secondary teachers' responses to the same task in Ball (1988) and Ma (1999). The findings of the study suggested that teachers' approaches to explaining and demonstrating a mathematical topic were significantly influenced by their knowledge of learners and knowledge of the curriculum they teach. One of the practical implications of the study is that teachers should recognize the advantages of learning the conceptual structure of a mathematical topic. It allows the teachers to have the flexibility to come up with meaningful mathematical approaches to teaching the topic, which are comprehensible to the learners whatever the grade levels they teach, rather than rule-based algorithms.

• Journal of Korean Elementary Science Education
• /
• v.20 no.2
• /
• pp.187-196
• /
• 2001

Students' journals in science class are supposed to contribute to students' science teaming and to provide plentiful information on students' learning and progress. If interaction could be reinforced in the process of writing journals, the positive effects of the journals are expected to be increased. New approaches in teaching should be supported by school and community. Otherwise, teachers are frequently frustrated and failed to introduce new ways of instruction into science classes. The purposes of the study are to develop interactive journals, and approaches to introduce interactive journals at school level. The status and situation of the school were investigated by survey. Interactive journals were developed by teachers who experienced workshops on developing journals. A model journal was provided as a guidance to teachers. To establish environments for introducing journals in the school, an invited lecture was provided to increase parents' perceptions on journals. A communication system among students, parents, and teachers was established, and educational materials, such as encyclopedia, books, computers, and so on were prepared. For efficient administration of journals, various prizes and events were established. As a result of the study, teachers participated experienced professional development in terms of journals, interactive journals for science class were developed, the environments for the introduction of interactive journals at school level were established, and most students successfully completed science journals.