• Structural Monitoring and Maintenance
• /
• v.5 no.4
• /
• pp.507-519
• /
• 2018

In this paper, damage assessment in wind-turbine towers using vibration-based artificial neural networks (ANNs) is numerically investigated. At first, a vibration-based ANNs algorithm is designed for damage detection in a wind turbine tower. The ANNs architecture consists of an input, an output, and hidden layers. Modal parameters of the wind turbine tower such as mode shapes and frequencies are utilized as the input and the output layer composes of element stiffness indices. Next, the finite element model of a real wind-turbine tower is established as the test structure. The natural frequencies and mode shapes of the test structure are computed under various damage cases of single and multiple damages to generate training patterns. Finally, the ANNs are trained using the generated training patterns and employed to detect damaged elements and severities in the test structure.

• Advances in nano research
• /
• v.13 no.3
• /
• pp.269-284
• /
• 2022

Nanomachines can be pretty helpful in curing diseases. Nanomototors, thanks to their self-propelled feature, are one of the best structures to be utilized as drug delivery devices. These devices have been employed in biomedical application as they can improve the efficiency of drug delivery. In this study stability of a designed nanomotor in the bloodstream is investigated when the physical activities have been done considering the physical activities. Sports training, as well as exercise enhance the bloodstream, and this factor can significantly impact the drug-delivery quality. The mathematical simulation of nanomotor movement in the condition of the sports is done based on the mechanical sciences, and the impact of various essential parameters is discussed in detail.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.230-232
• /
• 2023

Federated Learning (FL) is a technique that excels in training a global model using numerous clients while only sharing the parameters of their local models, which were trained on their private training datasets. As a result, clients can obtain a high-performing deep learning (DL) model without having to disclose their private data. This setup is based on the understanding that all clients share the common goal of developing a global model with high accuracy. However, recent studies indicate that the security of gradient sharing may not be as reliable as previously thought. This paper introduces the latest research on various attacks that threaten the privacy of federated learning.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.557-560
• /
• 2023

In this paper, we introduce a pre-training method leveraging the capabilities of the Vision Transformer (ViT) for disease diagnosis in conventional Fundus images. Recognizing the need for effective representation learning in medical images, our method combines the Vision Transformer with a Masked Autoencoder to generate meaningful and pertinent image augmentations. During pre-training, the Masked Autoencoder produces an altered version of the original image, which serves as a positive pair. The Vision Transformer then employs contrastive learning techniques with this image pair to refine its weight parameters. Our experiments demonstrate that this dual-model approach harnesses the strengths of both the ViT and the Masked Autoencoder, resulting in robust and clinically relevant feature embeddings. Preliminary results suggest significant improvements in diagnostic accuracy, underscoring the potential of our methodology in enhancing automated disease diagnosis in fundus imaging.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.767-778
• /
• 2003

This paper presents a method for generating optimal fuzzy rules using a genetic algorithm. Fuzzy rules are generated from the training data in the first stage. In this stage, fuzzy c-Means clustering method and cluster validity are used to determine the structure and initial parameters of the fuzzy inference system. A cluster validity is used to determine the number of clusters, which can be the number of fuzzy rules. Once the structure is figured out in the first stage, parameters relating the fuzzy rules are optimized in the second stage. Weights and variance parameters are tuned using genetic algorithms. Variance parameters are also managed with left and right for asymmetrical Gaussian membership function. The method ensures convergence toward a global minimum by using genetic algorithms in weight and variance spaces.

• Journal of Magnetics
• /
• v.19 no.4
• /
• pp.315-322
• /
• 2014

In this work, Artificial Neural Network (ANN) was used to model the dynamic behavior of ferromagnetic hysteresis derived from performing the mean-field analysis on the Ising model. The effect of field parameters and system structure (via coordination number) on dynamic critical points was elucidated. The Ising magnetization equation was drawn from mean-field picture where the steady hysteresis loops were extracted, and series of the dynamic critical points for constructing dynamic phase-diagram were depicted. From the dynamic critical points, the field parameters and the coordination number were treated as inputs whereas the dynamic critical temperature was considered as the output of the ANN. The input-output datasets were divided into training, validating and testing datasets. The number of neurons in hidden layer was varied in structuring ANN network with highest accuracy. The network was then used to predict dynamic critical points of the untrained input. The predicted and the targeted outputs were found to match well over an extensive range even for systems with different structures and field parameters. This therefore confirms the ANN capabilities and indicates the ANN ability in modeling the ferromagnetic dynamic hysteresis behavior for establishing the dynamic-phase-diagram.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1248-1250
• /
• 1996

The objective of camera calibration is to obtain the correlation between camera image coordinate and 3-D real world coordinate. Most calibration methods are based on the camera model which consists of physical parameters of the camera like position, orientation, focal length, etc and in this case camera calibration means the process of computing those parameters. In this research, we suggest a new approach which must be very efficient because the artificial neural network(ANN) model implicitly contains all the physical parameters, some of which are very difficult to be estimated by the existing calibration methods. Implicit camera calibration which means the process of calibrating a camera without explicitly computing its physical parameters can be used for both 3-D measurement and generation of image coordinates. As training each calibration points having different height, we can find the perspective projection point. The point can be used for reconstruction 3-D real world coordinate having arbitrary height and image coordinate of arbitrary 3-D real world coordinate. Experimental comparison of our method with well-known Tsai's 2 stage method is made to verify the effectiveness of the proposed method.

• Journal of Korean Physical Therapy Science
• /
• v.31 no.1
• /
• pp.70-87
• /
• 2024

Background: This study aimed to investigate the effect of Y-balance exercise on spatio-temporal gait parameters in subjects with chronic ankle instability. Design: Randomized Controlled Trial. Method: A study was conducted on 43 people with chronic ankle instability. Subjects performed modified Y-balance exercise 3 times a week for 50 minutes, 4 weeks. Gait parameters were measured using a gait analysis treadmill before exercise, 2 weeks after exercise, and 4 weeks after exercise. A gait analysis treadmill (FDM-T AP1171, Zebris, Germany) was used to measure gait parameters. Mean values were compared using Repeated measured two-way ANOVA. Result:: When comparing the results of three measurements taken before exercise, 2 weeks after exercise, and 4 weeks after exercise, there were significant differences in the qualitative and quantitative aspects of gait in gait variables such as step distance, step time, step ratio, and sway ratio. Conclusions: These results suggest that the Y-balance exercise and various exercises combining balance and proprioception are effective for subjects with chronic ankle instability.

• Computers and Concrete
• /
• v.34 no.4
• /
• pp.477-487
• /
• 2024

The in-situ stresses of concrete are an essential index for assessing the safety performance of concrete structures. Conventional methods for pore pressure release often face challenges in selecting drilling ring parameters, uncontrollable stress release, and unstable detection accuracy. In this paper, the parameters affecting the results of the concrete ring hole stress release method are cross-combined, and finite elements are used to simulate the combined parameters and extract the stress release values to establish a training set. The GridSearchCV function is utilized to determine the optimal hyperparameters. The mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) are used as evaluation indexes to train the gradient boosting decision tree (GBDT) algorithm, and the other three common algorithms are compared. The RMSE of the GBDT algorithm for the test set is 4.499, and the R² of the GBDT algorithm for the test set is 0.962, which is 9.66% higher than the R² of the best-performing comparison algorithm. The model generated by the GBDT algorithm can accurately calculate the concrete in-situ stresses based on the drilling ring parameters and the corresponding stress release values and has a high accuracy and generalization ability.

• Exercise Science
• /
• v.21 no.3
• /
• pp.373-384
• /
• 2012

The effects of inspiratory muscle training in conjunction with aerobic exercise on inspiratory muscle strength, pulmonary function, and maximal oxygen uptake(VO₂max) were examined. Twenty four healthy collegiate men were divided into three groups; respiratory muscle training group(RTG; n=8), running exercise group(REG; n=8), and both respiratory muscle training and running group(BTG; n=8). Their pulmonary function, maximal inspiratory pressures(PImax), and VO₂max were assessed before and after intervention. RTG underwent inspiratory muscle training(IMT) with load set to 50 % of PImax, 30 times per session, twice a day, 4 days a week REG ran on a treadmill at 70-75 % of VO₂max for 30 min a day, 4 days a week. BTG participated both IMT and the running exercise. Participant's anthropometric parameters and pulmonary function were not changed. VO₂max increased by 6.1±3.3 %, 5.9±6.6 %, and 10.0±8.3 % in RTG, REG, and BTG, respectively(p< .05), and PImax also increased by 21.7±14.3 %, 19.7±12.0 %, and 27.0±12.1 % in RTG, REG, and BTG, respectively, but no group differences were found. Based on the study, although statistically insignificant, BTG showed the biggest increase of VO₂max and PImax indicating a possible synergic effect of inspiratory muscle training and aerobic exercise on respiratory responses.