• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.61-71
• /
• 2023

With the development of data-driven decision-making and sophisticated big data processing technique, there is a growing demand for information on how to process data. However, recent studies with data preprocessing mentioned only as a means to achieve a result. Therefore, in this study, we aimed to write in detail about the data processing pipeline, include preprocessing data. In particular, we shares the context and domain knowledge to aid fluent understand of the research.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.55-58
• /
• 2000

To achieve high performance by exploiting instruction level parallelism(ILP) aggressively in superscalar processors, value prediction is used. Value prediction is a technique that breaks data dependences by predicting the outcome of an instruction and executes speculatively it's data dependent instruction based on the predicted outcome. In this paper, the performance of a hybrid value prediction scheme with dynamic classification mechanism is measured and analyzed by using execution-driven simulator for SPECint95 benchmark set.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.2
• /
• pp.23-27
• /
• 2017

We propose an inter-leg collision avoidance method that compensates the disadvantage of the data-driven biped control method. The data-driven biped control technique proposed by Lee et. al [1] sometimes generates the movement that the two legs intersect with each other while walking, which can not be realized in walking of a real person or a biped robot. The proposed method changes the angle of the swing hip so that the swing foot can move inward only after passing the stance foot. This process introduces an additional angle adjustment algorithm to avoid collisions with the stance leg to the original feedback rule of the stance hip. It generates a stable walking simulation without any inter-leg collisions, by adding minimal changes and additional calculations to the existing controller behavior.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.6
• /
• pp.457-464
• /
• 2020

This study aims to recognize customers' real sentiment and then discover the data-driven insights for strategic decision-making in the financial sector of Saudi Arabia. The data was collected from the social media (Facebook and Twitter) from start till October 2018 in financial companies (NCB, Al Rajhi, and Bupa) selected in the Kingdom of Saudi Arabia according to criteria. Then, it was analyzed using a sentiment analysis, one of data mining techniques. All three companies have similar likes and followers as they serve customers as B2B and B2C companies. In addition, for Al Rajhi no negative sentiment was detected in English posts, while it can be seen that Internet penetration of both banks are higher than BUPA, rarely mentioned in few hours. This study helps to predict the overall popularity as well as the perception or real mood of people by identifying the positive and negative feelings or emotions behind customers' social media posts or messages. This research presents meaningful insights in data-driven approaches using a specific data mining technique as a tool for corporate decision-making and forecasting. Understanding what the key issues are from customers' perspective, it becomes possible to develop a better data-based global strategies to create a sustainable competitive advantage.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.6 no.3
• /
• pp.226-233
• /
• 1994

The present paper considers the method to estimate the bottom friction driven by waves and current on rough turbulent flow. Parameter adjusting technique is suggested for the computation of bed shear stress driven by uni-directional flow. and the value of parameter is determined by comparing the computational results against Bijker's laboratory data. For the computation of combined flow bottom shear stress, two methods are presented; one is the modified Bijker approach (BYO Model) and the other is the modified Fredsoe approach (FY Model). both of which are refined by the present writer. Both models are again refined in two aspects, and tested against the Bijker's laboratory data.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.19 no.1
• /
• pp.44-51
• /
• 2023

The RCP is one of the main components in nuclear power plants and plays an important role in circulating coolant to the RCS system. Currently, nuclear plants are monitored using various monitoring systems. However, since they operate independently according to their functional purpose, it is not able to analyze vibration and operation/performance information comprehensively, and thus failure diagnosis accuracy is limited. In addition, these systems do not provide some important information (such as fault type, parts and cause) necessary for emergency actions, but provide only alarm information. To improve these technical problems, this study proposes a diagnosis technique (M/L, Rule-based model, Data-driven model, Narrow band model) and methodology for comprehensive analysis.

• ETRI Journal
• /
• v.45 no.6
• /
• pp.929-938
• /
• 2023

The detection of all the symbols transmitted simultaneously in multiuser systems using limited wireless resources is challenging. Traditional model-based methods show high performance with perfect channel state information (CSI); however, severe performance degradation will occur if perfect CSI cannot be acquired. In contrast, data-driven methods perform slightly worse than model-based methods in terms of symbol error ratio performance in perfect CSI states; however, they are also able to overcome extreme performance degradation in imperfect CSI states. This study proposes a novel deep learning-based method by improving a state-of-the-art data-driven technique called deep soft interference cancellation (DSIC). The enhanced DSIC (EDSIC) method detects multiuser symbols in a fully sequential manner and uses an efficient neural network structure to ensure high performance. Additionally, error-propagation mitigation techniques are used to ensure robustness against channel uncertainty. The EDSIC guarantees a performance that is very close to the optimal performance of the existing model-based methods in perfect CSI environments and the best performance in imperfect CSI environments.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.4
• /
• pp.332-338
• /
• 2022

This study proposes a battery state-of-health estimation method by applying a feature extraction technique. The technique that can improve estimation performance is the process of identifying and extracting meaningful data. To apply a data-driven-based aging state estimation method to batteries, health indicators are used as training data. However, limitations occur in extracting health indicators from charge/discharge cycles. This study proposes a deep-learning-based battery state-of-health estimation method that applies feature extraction techniques to compensate for this problem. According to the performance evaluation result of the proposed method, it has a low estimation error of 0.3887% based on an absolute error evaluation method.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.101-105
• /
• 2018

In this paper, the kernel regression model is applied for the case study of gas turbine abnormal state analysis. In addition to vibration analysis at the remote site, the kernel regression model technique can is useful for analyzing abnormal state of rotor vibration signals of gas turbine in power plant. In monitoring based on data-driven techniques correlated measurements, the fault free training data of shaft vibration obtained during normal operations of gas turbine are used to develop a empirical model based on auto-associative kernel regression. This data-driven model can be used to predict virtual measurements, which are compared with real-time data, generating residuals. Any faults in the system may cause statistically abnormal changes in these residuals and could be detected. As the result, the kernel regression model provides information that can distinguish anomalies such as sensor failure in a shaft vibration signal.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.6
• /
• pp.1255-1260
• /
• 2011

In this paper, we study on the reliability of Very High-rate Power Line Communication (VH-PLC) for Smart Grid, so that the resultant data rate is over 400Mbps at a physical layer. Firstly, reviewing the research trend of the PLC, we discuss the required techniques for supporting the Smart Grid. Considering a pre-specification with the value of several parameters, we investigate a multi-carrier modulation technique to overcome limitations of higher rate transmission under power line channel environments. Then, we propose a system specification of the VH-PLC in the sense of enhancing two features. One is resolving the problem of the co-existence of the deployed high-speed PLC according to the published standardization of KS X 4600-1 in Korea. The other is getting better performance on the grid adopting the diverse element techniques, such as multi-carrier modulation, a subcarrier utilization mode, a variable rate LDPC (Low Density Parity Check) code, and a time and frequency diversity technique. Further, a simulation tool, composed of an Event-Driven simulator and a Time-Driven simulator, is developed for the purpose of verifying the system performance and continuously cross-checking the test bench signal of the proposed VH-PLC system.