• The Korean Journal of Applied Statistics
• /
• v.28 no.1
• /
• pp.9-21
• /
• 2015

The support vector machine has been successfully applied to various classification areas due to its flexibility and a high level of classification accuracy. However, when analyzing imbalanced data with uneven class sizes, the classification accuracy of SVM may drop significantly in predicting minority class because the SVM classifiers are undesirably biased toward the majority class. The weighted $L_2$-norm SVM was developed for the analysis of imbalanced data; however, it cannot identify irrelevant input variables due to the characteristics of the ridge penalty. Therefore, we propose the weighted $L_1$-norm SVM, which uses lasso penalty to select important input variables and weights to differentiate the misclassification of data points between classes. We demonstrate the satisfactory performance of the proposed method through simulation studies and a real data analysis.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.10
• /
• pp.139-145
• /
• 1996

The machining accuracy and performance is largely influenced by the static, dynamic and thermal characteristics of spindle systems in machine tools, because the spindle system is a intermedium for cutting force from tool and machine powef from motor. Large cutting force and power are transmitted by bearing with a point or line contact. So, the spindle system is the static and dynamic weakest point in machine structure. For improvement of static stiffness of spindle system can be changed design parameters, such as diameter of spindle, stiffness of bearing and bearing span. But for dynamic stiffness, the change of the design parameters are not useful. In this paper, the combined bearing arrangement is suggested for high damping spindle system. The combined bearing arrangement is composed of tandem double back to back arrangement type ball bearins and a high damping hydrostatic bearing. The variation of static deflection and amplitude in first natural frequency is evaluated with the location of hydrostatic bearing between front and rear ball bearing. The optimized location of hydrostatic bearing for high static and dynamic stiffness is determined rapidly and exactly using the mode shape and transfer function of spindle. The calculation of damping effect on vibration by unbalance of grinding wheel and pulley in optimized spindle system is carried out to verify the validity of the combined bearing arrangement. Finally, the simulation of grinding process show that the surface roughness of workpiece with high damping spindle system is 60% better than with ball bearing spindle system.

• Journal of information and communication convergence engineering
• /
• v.14 no.4
• /
• pp.258-267
• /
• 2016

Three-dimensional integrated circuits (3D ICs) experience die-to-die variations in addition to the already challenging within-die variations. This adds an additional design complexity and makes variation estimation and full-chip optimization even more challenging. In this paper, we show that the industry standard on-chip variation (AOCV) tables cannot be applied directly to 3D paths that are spanning multiple dies. We develop a new machine learning-based model and methodology for an accurate variation estimation of logic paths in 3D designs. Our model makes use of key parameters extracted from existing GDSII 3D IC design and sign-off simulation database. Thus, it requires no runtime overhead when compared to AOCV analysis while achieving an average accuracy of 90% in variation evaluation. By using our model in a full-chip variation-aware 3D IC physical design flow, we obtain up to 16% improvement in critical path delay under variations, which is verified with detailed Monte Carlo simulations.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.829-835
• /
• 2012

When the input features are generated by factors in a classification problem, it is more meaningful to identify important factors, rather than individual features. The $F_{\infty}$-norm support vector machine(SVM) has been developed to perform automatic factor selection in classification. However, the $F_{\infty}$-norm SVM may suffer from estimation inefficiency and model selection inconsistency because it applies the same amount of shrinkage to each factor without assessing its relative importance. To overcome such a limitation, we propose the adaptive $F_{\infty}$-norm ($AF_{\infty}$-norm) SVM, which penalizes the empirical hinge loss by the sum of the adaptively weighted factor-wise $L_{\infty}$-norm penalty. The $AF_{\infty}$-norm SVM computes the weights by the 2-norm SVM estimator and can be formulated as a linear programming(LP) problem which is similar to the one of the $F_{\infty}$-norm SVM. The simulation studies show that the proposed $AF_{\infty}$-norm SVM improves upon the $F_{\infty}$-norm SVM in terms of classification accuracy and factor selection performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5425-5448
• /
• 2018

Wireless sensor network has been widely used in Internet of Things (IoT) applications to support large and dense networks. As sensor nodes are usually tiny and provided with limited hardware resources, the existing multiple access methods, which involve high computational complexity to preserve the protocol performance, is not available under such a scenario. In this paper, we propose an intelligent Medium Access Control (MAC) protocol selection scheme based on machine learning in wireless sensor networks. We jointly consider the impact of inherent behavior and external environments to deal with the application limitation problem of the single type MAC protocol. This scheme can benefit from the combination of the competitive protocols and non-competitive protocols, and help the network nodes to select the MAC protocol that best suits the current network condition. Extensive simulation results validate our work, and it also proven that the accuracy of the proposed MAC protocol selection strategy is higher than the existing work.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.127-134
• /
• 2022

Generally developed for medical testing, electrocardiogram (ECG) recordings seizure the cardiac electrical signals from the surface of the body. ECG study can consequently be a vital first step to support analyze, comprehend, and expect cardiac ailments accountable for 31% of deaths globally. Different tools are used to analyze ECG signals based on computational methods, and explicitly machine learning method. In all abovementioned computational simulations are prevailing tools for cataloging and clustering. This review demonstrates the different effective methods for heart disease based on computational methods for ECG analysis. The accuracy in machine learning and three-dimensional computer simulations, among medical inferences and contributions to medical developments. In the first part the classification and the methods developed to get data and cataloging between standard and abnormal cardiac activity. The second part emphases on patient analysis from entire ECG recordings due to different kind of diseases present. The last part represents the application of wearable devices and interpretation of computer simulated results. Conclusively, the discussion part plans the challenges of ECG investigation and offers a serious valuation of the approaches offered. Different approaches described in this review are a sturdy asset for medicinal encounters and their transformation to the medical world can lead to auspicious developments.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.2 s.179
• /
• pp.65-72
• /
• 2006

Downcoiler is one of the major facilities in hot strip mill operation. The key to good coiling is having good equipment, modem control systems, excellent maintenance and an understanding of coiling process. Therefore, this study aims to develop a program that is useful for calculating machine design parameters and simulating coiling process. In this study, the pinching and coiling mechanism of the downcoiler was thoroughly studied and some of operational factors and their effects on the coiling process were investigated. The software was developed to estimate engineering parameters for coiler component design and to determine optimal setting values for successful coiling operation. In order to check the accuracy and usefulness of the developed software, the simulation of the downcoiler in $\#2$ Hot Strip Mill in Pohang Works was performed. The simulation results suggested that the set-up value for unit tension could be lowered. Test coiling operation by using the lowered set-up value for unit tension resulted in much more successful coiling in the aspect of strip quality and power consumption.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.891-907
• /
• 2023

Compact Advanced Satellite 500-4 (CAS500-4) is scheduled to be launched to collect high spatial resolution data focusing on vegetation applications. To achieve this goal, accurate surface reflectance retrieval through atmospheric correction is crucial. Therefore, a machine learning-based atmospheric correction algorithm was developed to simulate atmospheric correction from a radiative transfer model using Sentinel-2 data that have similarspectral characteristics as CAS500-4. The algorithm was then evaluated mainly for forest areas. Utilizing the atmospheric correction parameters extracted from Sentinel-2 and GEOKOMPSAT-2A (GK-2A), the atmospheric correction algorithm was developed based on Random Forest and Light Gradient Boosting Machine (LGBM). Between the two machine learning techniques, LGBM performed better when considering both accuracy and efficiency. Except for one station, the results had a correlation coefficient of more than 0.91 and well-reflected temporal variations of the Normalized Difference Vegetation Index (i.e., vegetation phenology). GK-2A provides Aerosol Optical Depth (AOD) and water vapor, which are essential parameters for atmospheric correction, but additional processing should be required in the future to mitigate the problem caused by their many missing values. This study provided the basis for the atmospheric correction of CAS500-4 by developing a machine learning-based atmospheric correction simulation algorithm.

• Journal of Power Electronics
• /
• v.16 no.2
• /
• pp.553-563
• /
• 2016

This paper presents a digital hardware implementation of a real-time simulator for a multiphase drive using a field-programmable gate array (FPGA) device. The simulator was developed with a modular and hierarchical design using very high-speed integrated circuit hardware description language (VHDL). Hence, this simulator is flexible and portable. A state-space representation model suitable for FPGA implementations was proposed for a dual three-phase induction machine (DTPIM). The simulator also models a two-level 12-pulse insulated-gate bipolar transistor (IGBT)-based voltage-source converter (VSC), a pulse-width modulation scheme, and a measurement system. Real-time simulation outputs (stator currents and rotor speed) were validated under steady-state and transient conditions using as reference an experimental test bench based on a DTPIM with 15 kW-rated power. The accuracy of the proposed digital hardware implementation was evaluated according to the simulation and experimental results. Finally, statistical performance parameters were provided to analyze the efficiency of the proposed DTPIM hardware implementation method.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.3
• /
• pp.24-37
• /
• 2024

Due to the thin nature of semiconductor packages, even minor thermal loads can cause significant warpage, impacting product reliability through issues like delamination or cracking. The mold curing process, which encloses the package to protect the semiconductor chip, is particularly challenging to predict due to the complex thermal, chemical, and mechanical interactions. This study proposes a cost-effective machine learning model to predict warpage in the mold curing process. We developed methods to characterize the curing degree based on time and temperature and quantify the material's mechanical properties accordingly. A Finite Element Method (FEM) simulation model was created by integrating these properties into ABAQUS UMAT to predict warpage for various design factors. Additionally, a Warpage formula was developed to estimate local warpage based on the package's stacking structure. This formula combines bending theory with thermo-chemical-mechanical properties and was validated through FEM simulation results. The study presents a method to construct a machine learning model for warpage prediction using this formula and proposes a cost-effective approach for building a training dataset by analyzing input variables and design factors. This methodology achieves over 98% prediction accuracy and reduces simulation time by 96.5%.