• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.607-617
• /
• 2003

This paper offers a practical comparison of efficiency between local likelihood approach and conventional kernel approach in density estimation. The local likelihood estimation procedure maximizes a kernel smoothed log-likelihood function with respect to a polynomial approximation of the log likelihood function. We use two types of data driven bandwidths for each method and compare the mean integrated squares for several densities. Numerical results reveal that local log-linear approach with simple plug-in bandwidth shows better performance comparing to the standard kernel approach in heavy tailed distribution. For normal mixture density cases, standard kernel estimator with the bandwidth in Sheather and Jones(1991) dominates the others in moderately large sample size.

• Smart Structures and Systems
• /
• v.7 no.2
• /
• pp.133-152
• /
• 2011

System identification is a fundamental step towards the application of structural health monitoring and damage detection techniques. On this respect, the development of evolved identification strategies is a priority for obtaining reliable and repeatable baseline modal parameters of an undamaged structure to be adopted as references for future structural health assessments. The paper presents the identification of the modal parameters of the Guangzhou New Television Tower, China, using a data-driven stochastic subspace identification (SSI-data) approach complemented with an appropriate automatic mode selection strategy which proved to be successful in previous literature studies. This well-known approach is based on a clustering technique which is adopted to discriminate structural modes from spurious noise ones. The method is applied to the acceleration measurements made available within the task I of the ANCRiSST benchmark problem, which cover 24 hours of continuous monitoring of the structural response under ambient excitation. These records are then subdivided into a convenient number of data sets and the variability of modal parameter estimates with ambient temperature and mean wind velocity are pointed out. Both 10 minutes and 1 hour long records are considered for this purpose. A comparison with finite element model predictions is finally carried out, using the structural matrices provided within the benchmark, in order to check that all the structural modes contained in the considered frequency interval are effectively identified via SSI-data.

• Advances in Energy Research
• /
• v.6 no.2
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2687-2698
• /
• 2020

Most of the machine learning-based intrusion detection tools developed for Industrial Control Systems (ICS) are trained on network packet captures, and they rely on monitoring network layer traffic alone for intrusion detection. This approach produces weak intrusion detection systems, as ICS cyber-attacks have a real and significant impact on the process variables. A limited number of researchers consider integrating process measurements. However, in complex systems, process variable changes could result from different combinations of abnormal occurrences. This paper examines recent advances in intrusion detection algorithms, their limitations, challenges and the status of their application in critical infrastructures. We also introduce the discussion on the similarities and conflicts observed in the development of machine learning tools and techniques for fault diagnosis and cybersecurity in the protection of complex systems and the need to establish a clear difference between them. As a case study, we discuss special characteristics in nuclear power control systems and the factors that constraint the direct integration of security algorithms. Moreover, we discuss data reliability issues and present references and direct URL to recent open-source data repositories to aid researchers in developing data-driven ICS intrusion detection systems.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.227-235
• /
• 2015

Big data analysis is a means of organizational problem solving. For an effective problem solving, approaches to problem solving should take into account the factors such as characteristics of problem, types and availability of data, data analytic capability, and technical capability. In this article we propose three approaches: logical top-down, data driven bottom-up, and prototyping for overcoming undefined problem circumstances. In particular we look into the relationship of creative problem solving with the bottom-up approach. Based on the organizational data governance and data analytic capability, we also derive strategic issues concerning the sourcing of big data analysis.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.517-527
• /
• 2021

While the two principles of lean manufacturing and time-driven activity-based costing (TDABC) have been established out of multiple incentives and do not follow the same particular targets, there is substantial commonality between them. In these conditions, the supply management of a multi-product system needs a rigorous production model to minimize costs. In this sense, this paper proposes an interactive model with the consideration of optimizing product-mix decisions using both lean development tools and TDABC. This paper proposes a qualitative approach using the case study of the Iraqi state company for battery production. The suggested model decreased manufacturing time and costs, along with some substantial reduction in idle production capacity by 26 percent in 2019, based on the findings of the case study. On the other hand, the proposed model gives two side advantages: an efficient division of costs on goods due to the use of time spent as a cost factor for products and cost savings due to the introduction of the lean manufacturing approach that reduces all additional costs and increases product-mix decisions. Furthermore, the analytical data gathered here suggests that the incorporation of lean management concepts and TDABC has a strong and important influence on product-mix decisions.

• Journal of Environmental Science International
• /
• v.31 no.1
• /
• pp.33-42
• /
• 2022

The objective of this study is to determine the appropriate size of the inlet pipe diameter and thereby conduct hydraulic analysis for the Korean water distribution network. To this end, the data tables for equivalent pipe diameters and outflow rates presently employed in Korea were adopted. By incorporating the table of equivalent pipe diameters, it was found that the size of the inlet pipe diameter was overestimated, which can cause shortage of water pressure and malfunctioning or insufficiency of outflow rate in the corresponding adjacent region. However, by conducting hydraulic analysis based on the table of outflow rates, relatively reasonable flow rates were observed. Furthermore, by comparing the real demand-driven analysis (RDDA) approach and demand-driven analysis (DDA) approach toward managing the huge water demand, it was observed that DDA could not effectively respond to real hourly usage conditions, whereas RDDA (which reflects the hourly effects of inlet pipe diameter and storage tanks) demonstrated results similar to that of real water supply.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.141-146
• /
• 2024

Station blackout (SBO) risk is one of the most significant contributors to nuclear power plant risk. In this paper, the sequence probability formulas derived by the convolution approach are compared with those derived by the conventional event tree/fault tree (ET/FT) approach for the SBO situation in which emergency diesel generators fail to start. The comparison identifies what makes the ET/FT approach more conservative and raises the issue regarding the mission time of a turbine-driven auxiliary feedwater pump (TDP), which suggests a possible modeling improvement in the ET/FT approach. Monte Carlo simulations with up-to-date component reliability data validate the convolution approach. The sequence probability of an alternative alternating current diesel generator (AAC DG) failing to start and the TDP failing to operate owing to battery depletion contributes most to the SBO risk. The probability overestimation of the scenario in which the AAC DG fails to run and the TDP fails to operate owing to battery depletion contributes most to the SBO risk overestimation determined by the ET/FT approach. The modification of the TDP mission time renders the sequence probabilities determined by the ET/FT approach more consistent with those determined by the convolution approach.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.210-218
• /
• 2023

The author presents a simple data-driven intraday technical indicator trading approach based on Genetic Programming (GP) for return forecasting in the Bitcoin market. We use five trend-following technical indicators as input to GP for developing trading rules. Using data on daily Bitcoin historical prices from January 2017 to February 2020, our principal results show that the combination of technical analysis indicators and Artificial Intelligence (AI) techniques, primarily GP, is a potential forecasting tool for Bitcoin prices, even outperforming the buy-and-hold strategy. Sensitivity analysis is employed to adjust the number and values of variables, activation functions, and fitness functions of the GP-based system to verify our approach's robustness.

• Nuclear Engineering and Technology
• /
• v.44 no.8
• /
• pp.889-896
• /
• 2012

Recent progress in the computational fluid dynamics methods of two- and multiphase phase flows has already started opening up new exciting possibilities for using complete multidimensional models to simulate boiling systems. Combining this new theoretical and computational approach with novel experimental methods should dramatically improve both our understanding of the physics of boiling and the predictive capabilities of models at various scale levels. However, for the multidimensional modeling framework to become an effective predictive tool, it must be complemented with accurate mechanistic closure laws of local boiling mechanisms. Boiling heat transfer has been studied quite extensively before. However, it turns out that the prevailing approach to the analysis of experimental data for both pool boiling and forced-convection boiling has been associated with formulating correlations which normally included several adjustable coefficients rather than based on first principle models of the underlying physical phenomena. One reason for this has been the tendency (driven by practical applications and industrial needs) to formulate single expressions which encompass a broad range of conditions and fluids. This, in turn, makes it difficult to identify various specific factors which can be independently modeled for different situations. The objective of this paper is to present a mechanistic modeling concept for both pool boiling and forced-convection boiling. The proposed approach is based on theoretical first-principle concepts, and uses a minimal number of coefficients which require calibration against experimental data. The proposed models have been validated against experimental data for water and parametrically tested. Model predictions are shown for a broad range of conditions.