• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.475-480
• /
• 2023

When modeling a sensor system mathematically, we assume that the sensor noise is Gaussian and white to simplify the model. If this assumption fails, the performance of the sensor model-based controller or estimator degrades due to incorrect modeling. In practice, non-Gaussian or non-white noise sources often arise in many digital sensor systems. Additionally, the noise parameters of the sensor model are not known in advance without additional noise statistical information. Moreover, disturbances or high nonlinearities often cause unknown sensor modeling errors. To estimate the uncertain noise and model parameters of a sensor system, this paper proposes an iterative batch calibration method using data-driven machine learning. Our simulation results validate the calibration performance of the proposed approach.

• KIEAE Journal
• /
• v.17 no.5
• /
• pp.77-86
• /
• 2017

Purpose: Because of the growing concern over fossil fuel use and increasing demand for greenhouse gas emission reduction since the 1990s, the building energy analysis field has produced various types of methods, which are being applied more often and broadly than ever. A lot of research products have been actively proposed in the area of the building energy simulation for over 50 years around the world. However, in the last 20 years, there have been only a few research cases where the trend of building energy analysis is examined, estimated or compared. This research aims to investigate a trend of the building energy analysis by focusing on methodology and characteristics of each method. Method: The research papers addressing the building energy analysis are classified into two types of method: engineering analysis and algorithm estimation. Especially, EPG(Energy Performance Gap), which is the limit both for the existing engineering method and the single algorithm-based estimation method, results from comparing data of two different levels- in other words, real time data and simulation data. Result: When one or more ensemble algorithms are used, more accurate estimations of energy consumption and performance are produced, and thereby improving the problem of energy performance gap.

• Molecules and Cells
• /
• v.44 no.11
• /
• pp.843-850
• /
• 2021

The rapid increase in collateral omics and phenotypic data has enabled data-driven studies for the fast discovery of cancer targets and biomarkers. Thus, it is necessary to develop convenient tools for general oncologists and cancer scientists to carry out customized data mining without computational expertise. For this purpose, we developed innovative software that enables user-driven analyses assisted by knowledge-based smart systems. Publicly available data on mutations, gene expression, patient survival, immune score, drug screening and RNAi screening were integrated from the TCGA, GDSC, CCLE, NCI, and DepMap databases. The optimal selection of samples and other filtering options were guided by the smart function of the software for data mining and visualization on Kaplan-Meier plots, box plots and scatter plots of publication quality. We implemented unique algorithms for both data mining and visualization, thus simplifying and accelerating user-driven discovery activities on large multiomics datasets. The present Q-omics software program (v0.95) is available at http://qomics.sookmyung.ac.kr.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.4
• /
• pp.19-30
• /
• 2020

Purpose: The purpose of this study examines the mediating effect of clan leadership in the relationship between hierarchy culture and organizational commitment. Most previous research focused on the relationship between organizational culture and organizational performance or organizational culture and job satisfaction. There are few empirical studies that focus on organizational commitment data because it is difficult to collect in many cases of export-driven small and medium sized enterprises. However, this research measures affective commitment, continuance commitment, and normative commitment differently than previous research, which is mostly focused on the hierarchy culture, clan leadership, and organizational commitment measurements. Research design, data, methodology: Conceptual research model is based on the studies of Cameron and Quinn (2011), and Gungor and Sahin (2018). The model is designed with three constructs such as hierarchy culture, organizational commitment, and clan leadership. The monitor culture and coordinator culture are as proxy for the hierarchy culture. The affective commitment, continuance commitment, and normative commitment are as proxy for the organizational commitment. And also the facilitator leadership and mentor leadership are as proxy for the clan leadership. Based on three hundred cases such as export-driven small and medium sized enterprises (SMEs), this study verify the hypothesis. Hypothesis was analyzed with the structural equation modeling. Results: In case of export-driven small and medium sized enterprises (SMEs), clan leadership acts as a mediator in the relationship between hierarchy culture and organizational commitment. In case of export-driven small and medium sized enterprises (SMEs) with high organizational commitment, clan leadership acts as a mediator in the relationship between hierarchy culture and organizational commitment. In case of export-driven small and medium sized enterprises (SMEs) with low organizational commitment, clan leadership did not act as a mediator in the relationship between hierarchy culture and organizational commitment. Conclusions: By controlling for the mediating effect of clan culture, this study have improved the academic contributions as well as policy and practical implications through empirical study of clan leadership that affect organizational commitment in the fields of hierarchy culture. In addition, this study means that the mediating effects on the variables of clan leadership were examined.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6B
• /
• pp.867-874
• /
• 2010

Since high packet losses occur in multi-hop transmission of wireless sensor networks, reliable data transmission is required. Especially, in case of event-driven data, a loss recovery mechanism should be provided for lost packets. Because retransmission for lost packets is requested to a node that caches the packets, the caching node should maintains all of data for transmission in its buffer. However, nodes of wireless sensor networks have limited resources. Thus, both a loss recovery mechanism and a buffer management technique are provided for reliable data transmission in wireless sensor networks. In this paper, we propose a buffer management technique at a caching position determined by a loss recovery mechanism. The caching position of data is determined according to desirable reliability for the data. In addition, we validate the performance of the proposed method through computer simulations.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.28 no.4
• /
• pp.133-142
• /
• 2023

In this paper, we built a data-driven artificial intelligence model using RNN-LSTM (Recurrent Neural Networks-Long Short-Term Memory) to predict the Lorenz system, and examined the possibility of whether this model can replace chaotic dynamic models. We confirmed that the data-driven model reflects the chaotic nature of the Lorenz system, where a small error in the initial conditions produces fundamentally different results, and the system moves around two stable poles, repeating the transition process, the characteristic of "deterministic non-periodic flow", and simulates the bifurcation phenomenon. We also demonstrated the advantage of adjusting integration time intervals to reduce computational resources in data-driven models. Thus, we anticipate expanding the applicability of data-driven artificial intelligence models through future research on refining data-driven models and data assimilation techniques for data-driven models.

• Informatization Policy
• /
• v.28 no.3
• /
• pp.95-111
• /
• 2021

To achieve a data-driven policy decision-making system, the Ministry of Strategy and Finance has formed a marketing team and is actively building upon it. This system, currently under construction, will enable data-driven financial tasks beyond simple financial administration. The U.S. has already enacted The Foundations for Evidence-Based Policymaking Act in the process of similar pursuits. Since last year, the data-driven system administrative law has been enacted in Korea, and a legal framework has been established for data-driven administrative work. The next-generation budget accounting system to fulfill its role as a data-driven system needs public policy support to operate. Innovation and transformation are needed in various areas such as data management, legal system, and installation of related systems. Accordingly, it is very timely to analyze the financial systems and policies of advanced countries such as the U.S. and U.K., which already have established and operates such a financial system. By benchmarking and applying existing financial information systems to the next-generation budget accounting system, a better system will result. In this study, major developed countries, including the U.S., U.K., France, and Canada were benchmarked and analyzed in terms of the main elements of data governance: public policy, systems, legal framework, promotion system, and service level. It was discovered that the role and direction of the national fiscal policy system that the people favor should be able to respond quickly to the recent difficult economic crisis environment such as the digital transformation trend and COVID-19.

• Korean Journal of Computational Design and Engineering
• /
• v.22 no.1
• /
• pp.80-88
• /
• 2017

Product data analytics (PDA) is a data-driven analysis method that uses product data management (PDM) databases as its operational data. It aims to understand and evaluate product development processes indirectly through the analysis of product data from the PDM databases. To educate and train PDA efficiently, this study proposed an approach that employs courses for both product development and PDA in a class. The participant group for product development provides a PDM database as a result of their product development activities, and the other group for PDA analyses the PDM database and provides analysis result to the product development group who can explain causes of the result. The collaboration between the two groups can enhance the efficiency of the education and training course on PDA. This study also includes an application example of the approach to a graduate class on PDA and discussion of its result.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.1
• /
• pp.44-51
• /
• 2016

Recently, artificial intelligence has reached the level of top information technologies that will have significant influence over many aspects of our future lifestyles. In particular, in the fields of machine learning technologies for classification and decision-making, there have been a lot of research efforts for solving estimation and control problems that appear in the various kinds of portfolio management problems via data-driven approaches. Note that these modern data-driven approaches, which try to find solutions to the problems based on relevant empirical data rather than mathematical analyses, are useful particularly in practical application domains. In this paper, we consider some applications of modern data-driven machine learning methods for portfolio management problems. More precisely, we apply a simplified version of the sparse Gaussian process (GP) classification method for classifying users' sensitivity with respect to financial risk, and then present two portfolio management issues in which the GP application results can be useful. Experimental results show that the GP applications work well in handling simulated data sets.

• Computers and Concrete
• /
• v.15 no.1
• /
• pp.55-71
• /
• 2015

This paper presents a novel harmony search (HS)-based data-driven single input rule modules (SIRMs)-connected fuzzy inference system (FIS) for the prediction of stress in externally prestressed tendon. The proposed method attempts to extract causal relationship of a system from an input-output pairs of data even without knowing the complete physical knowledge of the system. The monotonicity property is then exploited as an additional qualitative information to obtain a meaningful SIRMs-connected FIS model. This method is then validated using results from test data of the literature. Several parameters, such as initial tendon depth to beam ratio; deviators spacing to the initial tendon depth ratio; and distance of a concentrated load from the nearest support to the effective beam span are considered. A computer simulation for estimating the stress increase in externally prestressed tendon, ${\Delta}f_{ps}$, is then reported. The contributions of this paper is two folds; (i) it contributes towards a new monotonicity-preserving data-driven FIS model in fuzzy modeling and (ii) it provides a novel solution for estimating the ${\Delta}f_{ps}$ even without a complete physical knowledge of unbonded tendons.