• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.87-92
• /
• 2021

Bias, variance, error and learning are important factors for performance in modeling a big data based recommendation system. The recommendation model in this system must reduce complexity while maintaining the explanatory diagram. In addition, the sparsity of the dataset and the prediction of the system are more likely to be inversely proportional to each other. Therefore, a product recommendation model has been proposed through learning the similarity between products by using a factorization method of the sparsity of the dataset. In this paper, the generalization ability of the model is improved by applying the max-norm regularization as an optimization method for the loss function of this model. The solution is to apply a stochastic projection gradient descent method that projects a gradient. The sparser data became, it was confirmed that the propsed regularization method was relatively effective compared to the existing method through lots of experiment.

• Advances in nano research
• /
• v.10 no.1
• /
• pp.15-24
• /
• 2021

Microtubules (MTs) are the main part of the cytoskeleton in living eukaryotic cells. In this article, a mechanical model of MT buckling, considering the modified strain gradient theory, is analytically examined. The MT is assumed as a cylindrical beam and a new single variable trigonometric beam theory is developed in conjunction with a modified strain gradient model. The main benefit of the present formulation is shown in its new kinematic where we found only one unknown as the Euler-Bernoulli beam model, which is even less than the Timoshenko beam model. The governing equations are deduced by considering virtual work principle. The effectiveness of the present method is checked by comparing the obtained results with those reported by other higher shear deformation beam theory involving a higher number of unknowns. It is shown that microstructure-dependent response is more important when material length scale parameters are closer to the outer diameter of MTs. Also, it can be confirmed that influences of shear deformation become more considerable for smaller shear modulus and aspect ratios.

• Steel and Composite Structures
• /
• v.51 no.6
• /
• pp.679-695
• /
• 2024

This paper presents a novel technique that combines machine learning (ML) with moth-flame optimization (MFO) methods to predict the axial compressive strength (ACS) of concrete filled double skin steel tubes (CFDST) columns. The proposed model is trained and tested with a dataset containing 125 tests of the CFDST column subjected to compressive loading. Five ML models, including extreme gradient boosting (XGBoost), gradient tree boosting (GBT), categorical gradient boosting (CAT), support vector machines (SVM), and decision tree (DT) algorithms, are utilized in this work. The MFO algorithm is applied to find optimal hyperparameters of these ML models and to determine the most effective model in predicting the ACS of CFDST columns. Predictive results given by some performance metrics reveal that the MFO-CAT model provides superior accuracy compared to other considered models. The accuracy of the MFO-CAT model is validated by comparing its predictive results with existing design codes and formulae. Moreover, the significance and contribution of each feature in the dataset are examined by employing the SHapley Additive exPlanations (SHAP) method. A comprehensive uncertainty quantification on probabilistic characteristics of the ACS of CFDST columns is conducted for the first time to examine the models' responses to variations of input variables in the stochastic environments. Finally, a web-based application is developed to predict ACS of the CFDST column, enabling rapid practical utilization without requesting any programing or machine learning expertise.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.652-662
• /
• 2023

Identifying highly discriminating genes is a critical step in tumor recognition tasks based on microarray gene expression profile data and machine learning. Gene selection based on tree models has been the subject of several studies. However, these methods are based on a single-tree model, often not robust to ultra-highdimensional microarray datasets, resulting in the loss of useful information and unsatisfactory classification accuracy. Motivated by the limitations of single-tree-based gene selection, in this study, ensemble gene selection methods based on multiple-tree models were studied to improve the classification performance of tumor identification. Specifically, we selected the three most representative tree models: ID3, random forest, and gradient boosting decision tree. Each tree model selects top-n genes from the microarray dataset based on its intrinsic mechanism. Subsequently, three ensemble gene selection methods were investigated, namely multipletree model intersection, multiple-tree module union, and multiple-tree module cross-union, were investigated. Experimental results on five benchmark public microarray gene expression datasets proved that the multiple tree module union is significantly superior to gene selection based on a single tree model and other competitive gene selection methods in classification accuracy.

• Advances in nano research
• /
• v.10 no.3
• /
• pp.271-280
• /
• 2021

The present work deals with an investigation on longitudinal wave propagation in nanobeams made of graphene sheets, for the first time. The nanobeam is modelled via a higher-order shear deformation theory accounts for both higher-order and thickness stretching terms. The general nonlocal strain gradient theory including nonlocality and strain gradient characteristics of size-dependency in order is used to examine the small-scale effects. This model has three-small scale coefficients in which two of them are for nonlocality and one of them applied for gradient effects. Hamilton supposition is applied to obtain the governing motion equation which is solved using a harmonic solution procedure. It is indicated that the longitudinal wave characteristics of the nanobeams are significantly influenced by the nonlocal parameters and strain gradient parameter. It is shown that higher nonlocal parameter is more efficient than lower nonlocal parameter to change longitudinal phase velocities, while the strain gradient parameter is the determining factor for their efficiency on the results.

• Structural Engineering and Mechanics
• /
• v.90 no.1
• /
• pp.1-18
• /
• 2024

The present study conducts a thorough analysis of thermal vibrations in functionally graded porous nanocomposite beams within a thermal setting. Investigating the temperature-dependent material properties of these beams, which continuously vary across their thickness in accordance with a power-law function, a finite element approach is developed. This approach utilizes a nonlocal strain gradient theory and accounts for a linear temperature rise. The analysis employs four different patterns of porosity distribution to characterize the functionally graded porous materials. A novel two-variable shear deformation beam nonlocal strain gradient theory, based on trigonometric functions, is introduced to examine the combined effects of nonlocal stress and strain gradient on these beams. The derived governing equations are solved through a 3-nodes beam element. A comprehensive parametric study delves into the influence of structural parameters, such as thicknessratio, beam length, nonlocal scale parameter, and strain gradient parameter. Furthermore, the study explores the impact of thermal effects, porosity distribution forms, and material distribution profiles on the free vibration of temperature-dependent FG nanobeams. The results reveal the substantial influence of these effects on the vibration behavior of functionally graded nanobeams under thermal conditions. This research presents a finite element approach to examine the thermo-mechanical behavior of nonlocal temperature-dependent FG nanobeams, filling the gap where analytical results are unavailable.

• Journal of Korean Society of Transportation
• /
• v.22 no.1 s.72
• /
• pp.43-62
• /
• 2004

Conventionally the estimation method of the origin-destination Matrix has been developed by implementing the expansion of sampled data obtained from roadside interview and household travel survey. In the survey process, the bigger the sample size is, the higher the level of limitation, due to taking time for an error test for a cost and a time. Estimating the O-D matrix from observed traffic count data has been applied as methods of over-coming this limitation, and a gradient model is known as one of the most popular techniques. However, in case of the gradient model, although it may be capable of minimizing the error between the observed and estimated traffic volumes, a prior O-D matrix structure cannot maintained exactly. That is to say, unwanted changes may be occurred. For this reason, this study adopts a conjugate gradient algorithm to take into account two factors: estimation of the O-D matrix from the conjugate gradient algorithm while reflecting the prior O-D matrix structure maintained. This development of the O-D matrix estimation model is to minimize the error between observed and estimated traffic volumes. This study validates the model using the simple network, and then applies it to a large scale network. There are several findings through the tests. First, as the consequence of consistency, it is apparent that the upper level of this model plays a key role by the internal relationship with lower level. Secondly, as the respect of estimation precision, the estimation error is lied within the tolerance interval. Furthermore, the structure of the estimated O-D matrix has not changed too much, and even still has conserved some attributes.

• The Journal of Information Systems
• /
• v.31 no.4
• /
• pp.145-160
• /
• 2022

Purpose The purpose of this study is to develop a virtual try-on deep learning model that can efficiently learn front and back clothes images. It is expected that the application of virtual try-on clothing service in the fashion and textile industry field will be vitalization. Design/methodology/approach The data used in this study used 232,355 clothes and product images. The image data input to the model is divided into 5 categories: original clothing image and wearer image, clothing segmentation, wearer's body Densepose heatmap, wearer's clothing-agnosting. We advanced the HR-VITON model in the way of Mixed-Precison, Gradient Accumulation, and sharing model weights. Findings As a result of this study, we demonstrated that the weight-shared MP-GA HR-VITON model can efficiently learn front and back fashion images. As a result, this proposed model quantitatively improves the quality of the generated image compared to the existing technique, and natural fitting is possible in both front and back images. SSIM was 0.8385 and 0.9204 in CP-VTON and the proposed model, LPIPS 0.2133 and 0.0642, FID 74.5421 and 11.8463, and KID 0.064 and 0.006. Using the deep learning model of this study, it is possible to naturally fit one color clothes, but when there are complex pictures and logos as shown in <Figure 6>, an unnatural pattern occurred in the generated image. If it is advanced based on the transformer, this problem may also be improved.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.29-36
• /
• 2022

In this paper, we propose an efficient agricultural products price prediction model based on dataset which provided in DACON. This model is XGBoost and CatBoost, and as an algorithm of the Gradient Boosting series, the average accuracy and execution time are superior to the existing Logistic Regression and Random Forest. Based on these advantages, we design a machine learning model that predicts prices 1 week, 2 weeks, and 4 weeks from the previous prices of agricultural products. The XGBoost model can derive the best performance by adjusting hyperparameters using the XGBoost Regressor library, which is a regression model. The implemented model is verified using the API provided by DACON, and performance evaluation is performed for each model. Because XGBoost conducts its own overfitting regulation, it derives excellent performance despite a small dataset, but it was found that the performance was lower than LGBM in terms of temporal performance such as learning time and prediction time.

• 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.