• International Journal of Contents
• /
• v.15 no.3
• /
• pp.32-38
• /
• 2019

We usually suffer from difficulties in treating or managing Big Data generated from various digital media and/or sensors using traditional mining techniques. Additionally, there are many problems relative to the lack of memory and the burden of the learning curve, etc. in an increasing capacity of large volumes of text when new data are continuously accumulated because we ineffectively analyze total data including data previously analyzed and collected. In this paper, we propose a general-purpose classifier and its structure to solve these problems. We depart from the current feature-reduction methods and introduce a new scheme that only adopts changed elements when new features are partially accumulated in this free-style learning environment. The incremental learning module built from a gradually progressive formation learns only changed parts of data without any re-processing of current accumulations while traditional methods re-learn total data for every adding or changing of data. Additionally, users can freely merge new data with previous data throughout the resource management procedure whenever re-learning is needed. At the end of this paper, we confirm a good performance of this method in data processing based on the Big Data environment throughout an analysis because of its learning efficiency. Also, comparing this algorithm with those of NB and SVM, we can achieve an accuracy of approximately 95% in all three models. We expect that our method will be a viable substitute for high performance and accuracy relative to large computing systems for Big Data analysis using a PC cluster environment.

• Journal of Korea Multimedia Society
• /
• v.10 no.5
• /
• pp.642-651
• /
• 2007

Recently, digital convergence, whose core demand is OSMU (One Sourse Multi Use),has been the main topic in e-learning domain and industry. However, the existing web learning content and the new resource developed toprovide contents to different learning environment must be processed to adapt the new learning settings, which causes the cost and time problem, So in this paper we design and implement a Java based SCORM content transcoding system which can transcode the SCORM-based learning content into MHP-based DiTV content in order to adapt t-learning environment using DiTV, which is closer to our real life. Using this system which has ability of inter-operation, reuse, highly-use, the problem mentioned above can be solved well. Moreover, it is possible for a learner who is not familiar with computer to study using DiTV instead of PC.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.373-379
• /
• 2021

This study intends to test the effects of blended learning and case based learning on learning strategies, critical thinking disposition and academic self-efficacy for undergraduate nursing students. A one group pre-post design was applied to adult nursing of 23 nursing students. Data were collected between March 2 and April 30, 2021. Data were analyzed by using SPSS/WIN 23.0. The results showed that learning strategies(t=-2.43, p=.019) and sub-factor cognitive strategy (t=-2.22, p=.031), meta cognitive strategy(t=-2.59, p=.013) and resource management strategy (z=-2.46, p=.014) were significantly higher than levels before blended learning and case based learning. Critical thinking disposition(t=-1.14, p=.262) and academic self-efficacy(t=-.34, p=.734) were higher than levels before but was no significantly. In conclusion, It was confirmed that blended learning and case based learning is an effective educational program that improves learning strategies of nursing students. In the future, it is necessary to develop a program in which blended learning and case based learning can improve critical thinking disposition and academic self-efficacy, and to verify the effectiveness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3989-4006
• /
• 2020

The intelligent agriculture monitoring is based on the perception and analysis of environmental data, which enables the monitoring of the production environment and the control of environmental regulation equipment. As the scale of the application continues to expand, a large amount of data will be generated from the perception layer and uploaded to the cloud service, which will bring challenges of insufficient bandwidth and processing capacity. A fog-based offline and real-time hybrid data analysis architecture was proposed in this paper, which combines offline and real-time analysis to enable real-time data processing on resource-constrained IoT devices. Furthermore, we propose a data process-ing algorithm based on the incremental principal component analysis, which can achieve data dimensionality reduction and update of principal components. We also introduce the concept of Squared Prediction Error (SPE) value and realize the abnormal detection of data through the combination of SPE value and data fusion algorithm. To ensure the accuracy and effectiveness of the algorithm, we design a regular-SPE hybrid model update strategy, which enables the principal component to be updated on demand when data anomalies are found. In addition, this strategy can significantly reduce resource consumption growth due to the data analysis architectures. Practical datasets-based simulations have confirmed that the proposed algorithm can perform data fusion and exception processing in real-time on resource-constrained devices; Our model update strategy can reduce the overall system resource consumption while ensuring the accuracy of the algorithm.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.502-504
• /
• 2004

With rapidly growing of computer and internet technology, Internet-based tote-operation of robotic systems has created new opportunities in resource sharing, long-distance learning, and remote experimentation. In this paper, remote control system of a mobile robot through the internet has been designed. The internet users can access and command a mobile robot in the real time, receiving the robot's sensor data. The overall system has been tested and its usefulness shown through the experimental results.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.3
• /
• pp.30-40
• /
• 2018

The purpose of this study is to examine the effect of project-based organizational resources on the business performance in the resource-based view (RBV) and dynamic capability one and analyze their relationship through an integrated model. The RBV argues that firms get competitive advantages when they have VRIN characterized resources but dynamic capability view argues that RBV has its limitation under volatility so it enables them to obtain competitive advantages in ever changing environments. This study analyzes data collected from 270 survey questionnaires on the project management related staff at the project-based organization among major companies in Korea. The result demonstrates that two project organizational resources on strategic and executional management with VRIN characteristics are found to bring positive effects on the organizational dynamic capabilities and also the dynamic capabilities such as integration & reconfiguration, organizational learning are verified to bring meaningful positive effects on the business performance. On the other hand, unlike previous studies, ambidexterity has quite a weak effect on the business performance. Therefore, we expect that the resources of the project-based organization with VRIN lead to strengthen the firm's business performance through organizational dynamic capabilities and produce high performance through the integrated model of RBV and dynamic capability one. The study has academic meanings that widely confirm the effects and characteristics of main elements of VRIN project organizational resources on the business performance of competitive advantage through the dynamic capabilities of the organization by the regression on the precedent studies regarding the project management resources and their relationship with the VRIO characteristics. The practical implication is that it is preferentially necessary for the organization to obtain VRIN resources and organizational dynamic capabilities, especially organizational learning to have sustainable competitive advantages.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.4
• /
• pp.489-497
• /
• 2021

Climate change is affecting the evolutionary trajectories of individual species and ecological communities, partly through the creation of new species groups. As population shift geographically and temporally as a result of climate change, reproductive interactions between previously isolated species are inevitable and it could potentially lead to invasion, speciation, or even extinction. Four species of abalone, genus Haliotis are present along the Korean coastline and these species are important for commercial and fisheries resources management. In this study, genetic markers for fisheries resources management were discovered based on genomic information, as part of the management of endemic species in response to climate change. Two thousand one hundred and sixty one single nucleotide polymorphisms (SNPs) were discovered using genotyping-by-sequencing (GBS) method. Forty-one SNPs were selected based on their features for species classification. Machine learning analysis using these SNPs makes it possible to differentiate four Haliotis species and hybrids. In conclusion, the proposed machine learning method has potentials for species classification of the genus Haliotis. Our results will provide valuable data for biodiversity conservation and management of abalone population in Korea.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.577-578
• /
• 2021

Recently, artificial intelligence systems are being used in various fields. The accuracy of the decision algorithm of artificial intelligence is greatly affected by the amount of learning and the accuracy of the learning data. In the case of the amount of learning, a large amount of data is required because it has a decisive effect on the performance of AI. In this paper, we propose a data collection system for constructing a system that analyzes future conditions and changes in infants' conditions based on the body temperature data of infants and toddlers. The proposed system is a system that collects and transmits data, and it is believed that it can minimize the resource consumption of the server system in existing big data analysis and training data construction.

• Environmental and Resource Economics Review
• /
• v.28 no.4
• /
• pp.467-495
• /
• 2019

Uncertainty of renewable energy such as photovoltaic(PV) power is detrimental to the flexibility of the power system. Therefore, precise prediction of PV power generation is important to make the power system stable. The purpose of this study is to forecast PV power generation using meteorological data including particulate matter(PM). In this study, PV power generation is predicted by support vector machine using RBF kernel function based on machine learning. Comparing the forecasting performances by including or excluding PM variable in predictor variables, we find that the forecasting model considering PM is better. Forecasting models considering PM variable show error reduction of 1.43%, 3.60%, and 3.88% in forecasting power generation between 6am~8pm, between 12pm~2pm, and at 1pm, respectively. Especially, the accuracy of the forecasting model including PM variable is increased in daytime when PV power generation is high.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.47-54
• /
• 2023

As understanding sudden climate change and agricultural productivity becomes increasingly important due to global warming, soil moisture prediction is emerging as a key topic in agriculture. Soil moisture has a significant impact on crop growth and health, and proper management and accurate prediction are key factors in improving agricultural productivity and resource management. For this reason, soil moisture prediction is receiving great attention in agricultural and environmental fields. In this paper, we collected and analyzed open field environmental data using a pilot field through random forest, a machine learning algorithm, obtained the correlation between data characteristics and soil moisture, and compared the actual and predicted values of soil moisture. As a result of the comparison, the prediction rate was about 92%. It was confirmed that the accuracy was . If soil moisture prediction is carried out by adding crop growth data variables through future research, key information such as crop growth speed and appropriate irrigation timing according to soil moisture can be accurately controlled to increase crop quality and improve productivity and water management efficiency. It is expected that this will have a positive impact on resource efficiency.