• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• pp.211-216
• /
• 1998

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.1
• /
• pp.35-43
• /
• 2020

Turbidity has various effects on the water quality and ecosystem of a river. High turbidity during floods increases the operation cost of a drinking water supply system. Thus, the management of turbidity is essential for providing safe water to the public. There have been various efforts to estimate turbidity in river systems for proper management and early warning of high turbidity in the water supply process. Advanced data analysis technology using machine learning has been increasingly used in water quality management processes. Artificial neural networks(ANNs) is one of the first algorithms applied, where the overfitting of a model to observed data and vanishing gradient in the backpropagation process limit the wide application of ANNs in practice. In recent years, deep learning, which overcomes the limitations of ANNs, has been applied in water quality management. LSTM(Long-Short Term Memory) is one of novel deep learning algorithms that is widely used in the analysis of time series data. In this study, LSTM is used for the prediction of high turbidity(>30 NTU) in a river from the relationship of turbidity to discharge, which enables early warning of high turbidity in a drinking water supply system. The model showed 0.98, 0.99, 0.98 and 0.99 for precision, recall, F1-score and accuracy respectively, for the prediction of high turbidity in a river with 2 hour frequency data. The sensitivity of the model to the observation intervals of data is also compared with time periods of 2 hour, 8 hour, 1 day and 2 days. The model shows higher precision with shorter observation intervals, which underscores the importance of collecting high frequency data for better management of water resources in the future.

• Journal of Korean Society on Water Environment
• /
• v.27 no.6
• /
• pp.794-803
• /
• 2011

Self Organizing Map (SOM) was applied for pattern classification of hydrological and water quality data measured at Jangseong Reservoir on a monthly basis. The primary objective of the present study is to understand better data characteristics and relationship between the data. For the purpose, two SOMs were configured by a methodologically systematic approach with appropriate methods for data transformation, determination of map size and side lengths of the map. The SOMs constructed at the respective measurement stations for water quality data (JSD1 and JSD2) commonly classified the respective datasets into five clusters by Davies-Bouldin Index (DBI). The trained SOMs were fine-tuned by Ward's method of a hierarchical cluster analysis. On the one hand, the patterns with high values of standardized reference vectors for hydrological variables revealed the high possibility of eutrophication by TN or TP in the reservoir, in general. On the other hand, the clusters with low values of standardized reference vectors for hydrological variables showed the patterns with high COD concentration. In particular, Clsuter1 at JSD1 and Cluster5 at JSD2 represented the worst condition of water quality with high reference vectors for rainfall and storage in the reservoir. Consequently, SOM is applicable to identify the patterns of potential eutrophication in reservoirs according to the better understanding of data characteristics and their relationship.

• Journal of Korean Society for Quality Management
• /
• v.46 no.3
• /
• pp.539-550
• /
• 2018

Purpose: The purpose of this study was to find meaningful patient groups of disease using foreign patients data and analyze implemented test of the patient groups. Methods: The data was collected by foreign patients' EMR data of K university hospital. The author proposed tree-form patients' characteristic diagram through statistical methods that association rule, proportion test, clustering using prescription information and questionnaire information. Results: This study's analysis process was applied high blood data and diabetes data. Analysis showed other characteristic of meaningful patient groups in high blood and diabetes. In high blood, test implementation rate of patient group showed the differences. And in diabetes, test implementation rate of patient group and implemented test list showed differences. Conclusion: The result of this study can play a role as basic data that can be clinical testing standard in preventive aspect. Eventually, 5 dimensions of SERVQUAL will be improved by this study's process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.414-435
• /
• 2017

As network adaptive streaming technology becomes increasingly common, transport protocol also becomes important in guaranteeing the quality of multimedia streaming. At the same time, because of the appearance of high-quality video such as Ultra High Definition (UHD), preventing buffering as well as preserving high quality while deploying a streaming service becomes important. The Internet Engineering Task Force recently published Multipath TCP (MPTCP). MPTCP improves the maximum transmission rate by simultaneously transmitting data over different paths with multiple TCP subflows. However, MPTCP cannot preserve high quality, because the MPTCP subflows slowly increase the transmission rate, and upon detecting a packet loss, drastically halve the transmission rate. In this paper, we propose a new multipath congestion control scheme for high-quality multimedia streaming. The proposed scheme preserves high quality of video by adaptively adjusting the increasing parameter of subflows according to the network status. The proposed scheme also increases network efficiency by providing load balancing and stability, and by supporting fairness with single-flow congestion control schemes.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.211-218
• /
• 2022

Pandemic situations such as COVID-19 can occur supply chain crisis. Under the supply chain crisis, delivering farm products from the farm to the city is also very challenging. Therefore it is essential to prepare food sufficiency people who live in a city. We firmly insist on food self-production/consumption systems in each home. However, since it is impossible to grow high-quality crops without expertise knowledge. Therefore expert system is essential to grow high-quality crops in home. To address this problem, we propose a smart kitchen farm as a data-based monitoring system and platform with ICT convergence technology. Our proposed approach 1) collects data and makes judgments based on expert knowledge for home users, 2) increases product quality of the smart kitchen farms by predicting abnormal/normal crops, and 3) controls each personal home cultivation environment through data-based monitoring within the smart central server. We expect people can cultivate high-quality crops in thir kitchens through this system without expert knowledge about cultivation.

• Advances in nano research
• /
• v.14 no.3
• /
• pp.225-234
• /
• 2023

In this study, we aim to use big data resources and statistical analysis to obtain a reliable instruction to reach high-quality and high yield agricultural yields. In this regard, soil type data, raining and temperature data as well as wheat production in each year are collected for a specific region. Using statistical methodology, the acquired data was cleaned to remove incomplete and defective data. Afterwards, using several classification methods in machine learning we tried to distinguish between different factors and their influence on the final crop yields. Comparing the proposed models' prediction using statistical quantities correlation factor and mean squared error between predicted values of the crop yield and actual values the efficacy of machine learning methods is discussed. The results of the analysis show high accuracy of machine learning methods in the prediction of the crop yields. Moreover, it is indicated that the random forest (RF) classification approach provides best results among other classification methods utilized in this study.

• Korean Journal of Child Studies
• /
• v.38 no.2
• /
• pp.149-164
• /
• 2017

Objective: The purpose of the study was to examine the direct effects of parent-adolescent communication and its indirect effects through adolescent friendship quality on happiness among both middle and high school students. Methods: Participants in this study were 1,126 adolescents (667 middle school students and 459 high school students) in Seoul and Gyoung-gi Do. Data were collected through self-report questionnaires for adolescents, which included measures of parent-adolescent communication, friendship quality and happiness. Data were analyzed by t-tests, correlations, and SEM using SPSS 22.0 and Mplus 6.0. Results: For middle school students, father-adolescent communication had direct and indirect effects on happiness. However, mother-adolescent communication did not directly or indirectly affect adolescent happiness. Specifically, only father-adolescent communication had an significant indirect effect through friendship quality on adolescent happiness. For high school students, father-adolescent communication had direct effects on happiness, while mother-adolescent communication had significant indirect effects on adolescent happiness via friendship quality. Conclusion: This study underscores the importance of parent-adolescent communication and friendship quality in predicting adolescent happiness with differences in direct and indirect paths between middle and high school students. These findings emphasize the role of parent-adolescent communication and friendship quality in developing programs to improve the happiness of adolescents.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.333-338
• /
• 2019

Cultural contents are the most important factor in high speed and high quality data communication. High-quality content includes VR and AR technology, and a variety of high-quality content can be streamed over wireless mobile phones via smartphones. In addition, network and wired/wireless communication are inevitably required in an Internet of Things (IoT) environment in which things are connected to a wireless Internet. IoT is used in various network technologies such as 4G, 5G mobile communication, WIFI wireless LAN, Bluetooth and so on. It is a technology that can use the connection between things anytime, anywhere, and can be achieved in a wireless mobile communication environment. Therefore, in this paper, we study data error compensation estimation method which can reduce data error based on mobile communication channel environment analysis so that high quality contents can be serviced even in high speed mobile environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.127-134
• /
• 2021

Recently, acquisition of high quality data has become an important issue as the expansion of the big data industry. In order to acquiring high quality data, accurate evaluation of data quality should be preceded first. The quality of data can be evaluated through meta-information such as statistics on data, and the task to extract such meta-information is called data profiling. Until now, data profiling software has typically been provided as a component or an additional service of traditional data quality or visualization tools. Hence, it was not suitable for utilizing directly in various environments. To address this problem, this paper presents the development result of data profiling software based on a microservice architecture that can be serviced in various environments. The presented data profiler provides an easy-to-use interface that requests of meta-information can be serviced through the restful API. Also, a proposed data profiler is independent of a specific environment, thus can be integrated efficiently with the various big data platforms or data analysis tools.