• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.4
• /
• pp.21-34
• /
• 2023

Federated Learning is divided into synchronous federated learning and asynchronous federated learning. Asynchronous federated learning has a time advantage over synchronous federated learning, but asynchronous federated learning still has some challenges to obtain better performance. In particular, preventing performance degradation in non-IID training datasets, selecting appropriate clients, and managing stale gradient information are important for improving model performance. In this paper, we deal with K-asynchronous federated learning by using non-IID datasets. In addition, unlike traditional method using static K, we proposed an algorithm that adaptively adjusts K and we can reduce the learning time. Additionally, the we show that model performance is improved by using stale gradient handling method. Finally, we use a method of judging model performance to obtain strong model stability. Experiment results show that overall algorithm can obtain advantages of reducing training time, improving model accuracy, and improving model stability.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.6
• /
• pp.95-105
• /
• 2003

A novel reference point detection method is proposed by exploiting tile gradient probabilistic model that captures the curvature information of fingerprint. The detection of reference point is accomplished through searching and locating the points of occurrence of the most evenly distributed gradient in a probabilistic sense. The uniformly distributed gradient texture represents either the core point itself or those of similar points that can be used to establish the rigid reference from which to map the features for recognition. Key benefits are reductions in preprocessing and consistency of locating the same points as the reference points even when processing arch type fingerprints. Moreover, the new feature extraction method is proposed by improving the existing feature extraction using filterbank method. Experimental results indicate the superiority of tile proposed scheme in terms of computational time in feature extraction and verification rate in various noisy environments. In particular, the proposed gradient probabilistic model achieved 49% improvement under ambient noise, 39.2% under brightness noise and 15.7% under a salt and pepper noise environment, respectively, in FAR for the arch type fingerprints. Moreover, a reduction of 0.07sec in reference point detection time of the GPM is shown possible compared to using the leading the poincare index method and a reduction of 0.06sec in code extraction time of the new filterbank mettled is shown possible compared to using the leading the existing filterbank method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.9
• /
• pp.1041-1050
• /
• 2011

An elasto-plastic finite element method using the theory of strain gradient plasticity is proposed to evaluate the size dependency of structural plasticity that occurs when the configuration size decreases to micron scale. For this method, we suggest a low-order plane and three-dimensional displacement-based elements, eliminating the need for a high order, many degrees of freedom, a mixed element, or super elements, which have been considered necessary in previous researches. The proposed method can be performed in the framework of nonlinear incremental analysis in which plastic strains are calculated and averaged at nodes. These strains are then interpolated and differentiated for gradient calculation. We adopted a strain-gradient-hardening constitutive equation from the Taylor dislocation model, which requires the plastic strain gradient. The developed finite elements are tested numerically on the basis of typical size-effect problems such as micro-bending, micro-torsion, and micro-voids. With respect to the strain gradient plasticity, i.e., the size effects, the results obtained by using the proposed method, which are simple in their calculation, are in good agreement with the experimental results cited in previously published papers.

• 한국신재생에너지학회:학술대회논문집
• /
• 2005.06a
• /
• pp.701-704
• /
• 2005

Aquifer Thermal Energy Storage (ATES) can be a cost-effective and renewable geothermal energy source, depending on site-specific and thermohydraulic conditions. To design an effective ATES system having influenced by groundwater movement, understanding of thermo hydraulic processes is necessary. The heat transfer phenomena for an aquifer heat storage are simulated using FEFLOW with the scenario of heat pump operation with pumping and waste water reinjection in a two layered confined aquifer model. Temperature distribution of the aquifer model is generated, and hydraulic heads and temperature variations are monitored at the both wells during 365 days. The average groundwater velocities are determined with two hydraulic gradient sets according to boundary conditions, and the effect of groundwater flow are shown at the generated thermal distributions of three different depth slices. The generated temperature contour lines at the hydraulic gradient of 0.00 1 are shaped circular, and the center is moved less than 5m to the groundwater flow direction in 365 days simulation period. However at the hydraulic gradient of 0.01, the contour center of the temperature are moved to the end of boundary at each slice and the largest movement is at bottom slice. By the analysis of thermal interference data between two wells the efficiency of the heat pump system model is validated, and the variation of heads is monitored at injection, pumping and no operation mode.

• Korean Journal of Cognitive Science
• /
• v.8 no.4
• /
• pp.63-75
• /
• 1997

Changes in visual sensitivity were investigated as a function of distance from the locus of attention. While a subject was fixating at a point on a frontal plane, one of the two attention inducing points placed horizontally and symmetrically 4。 apart from it was blinked and a target immediately followed at a location around the blinking dot. The subject's task was to decide and report whether the target was present or abscent. The rate of detection was the highest at the immediate vicinity of the locus of attention and decreased gradually as a function of the distance from it. Results of the experiments support the gradient model of attention-induced changes in visual sensitivity.

• Journal of the Korean Ceramic Society
• /
• v.43 no.11 s.294
• /
• pp.724-727
• /
• 2006

It has long been known that the oxidation kinetics of Zr-based alloys undergoes a crossover from parabolic to cubic in the pretransition period (before breakaway of the oxide scale). This kinetic crossover, however, is not fully understood yet. We have earlier proposed a model for the Zr-oxidation kinetics, in a closed form for the first time, by taking into account a compressive strain energy gradient as a diffusional driving force in addition to a chemical potential gradient of component oxygen across the ZrO$_2$ scale upon Zr [J. Nucl. Mater., 299 (2001) 235]. In this paper, we experimentally reconfirm the validity of the proposed model by using the thermogravimetric data on mass gain of Zr in a plate and wire form, respectively, in air atmosphere at different temperatures in the range of 500$^{\circ}$ to 800$^{\circ}C$, and subsequently report on the numerical values for oxygen chemical diffusivity and strain energy gradient across the oxide scale.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.190-198
• /
• 2023

To enhance customer satisfaction for higher profits, an e-commerce sector can establish a continuous relationship and acquire new customers. Utilize machine-learning models to analyse their customer's behavioural evidence to produce their competitive advantage to the e-commerce platform by helping to improve overall satisfaction. These models will forecast customers who will churn and churn causes. Forecasts are used to build unique business strategies and services offers. This work is intended to develop a machine-learning model that can accurately forecast retainable customers of the entire e-commerce customer data. Developing predictive models classifying different imbalanced data effectively is a major challenge in collected data and machine learning algorithms. Build a machine learning model for solving class imbalance and forecast customers. The satisfaction accuracy is used for this research as evaluation metrics. This paper aims to enable to evaluate the use of different machine learning models utilized to forecast satisfaction. For this research paper are selected three analytical methods come from various classifications of learning. Classifier Selection, the efficiency of various classifiers like Random Forest, Logistic Regression, SVM, and Gradient Boosting Algorithm. Models have been used for a dataset of 8000 records of e-commerce websites and apps. Results indicate the best accuracy in determining satisfaction class with both gradient-boosting algorithm classifications. The results showed maximum accuracy compared to other algorithms, including Gradient Boosting Algorithm, Support Vector Machine Algorithm, Random Forest Algorithm, and logistic regression Algorithm. The best model developed for this paper to forecast satisfaction customers and accuracy achieve 88 %.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Journal of Ecology and Environment
• /
• v.31 no.2
• /
• pp.125-129
• /
• 2008

To predict Daphnia secondary productivity along a trophic gradient indexed as total phosphorus (TP) concentration, we estimated energy transfer efficiencies from food quality for Daphnia such as eicosa-pentaenoic acid (EPA) or docosahexaenoic acid (DHA) content. Eleven flow-through Daphnia magna growth experiments were conducted with seston from 9 lakes, ponds and river waters. Primary productivities were estimated from food supply rates in the flow-through experiments, producing energy transfer efficiencies from seston to D. magna. We found DHA content was the best predictor of energy transfer efficiencies among the essential fatty acids. An asymptotic saturation model explained 79.6% of the variability In energy transfer efficiencies. Based on empirical data in this study and empirical models from literature, we predict that Daphnia productivity would peak in mesotrophic systems by decreasing food quality and Increasing food quantity along trophic gradient.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.413-417
• /
• 2004

Recent experiments have shown the 'size effects' in micro/nano scale. But the classical plasticity theories can not predict these size dependent deformation behaviors because their constitutive models have no characteristic material length scale. The Mechanism - based Strain Gradient(MSG) plasticity is proposed to analyze the non-uniform deformation behavior in micro/nano scale. The MSG plasticity is a multi-scale analysis connecting macro-scale deformation of the Statistically Stored Dislocation(SSD) and Geometrically Necessary Dislocation(GND) to the meso-scale deformation using the strain gradient. In this research we present a study of nano-indentation by the MSG plasticity. Using W. D. Nix and H. Gao s model, the analytic solution(including depth dependence of hardness) is obtained for the nano indentation , and furthermore it validated by the experiments.