• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.827-838
• /
• 2021

The dynamic displacement is considered to be an important indicator of structural safety, and becomes an indispensable part of Structural Health Monitoring (SHM) system for high-speed railway bridges. This paper proposes an indirect strain based dynamic displacement reconstruction methodology for high-speed railway box girders. For the typical box girders under eccentric train load, the plane section assumption and elementary beam theory is no longer applicable due to the bend-torsion coupling effects. The monitored strain was decoupled into bend and torsion induced strain, pre-trained multi-output support vector regression (M-SVR) model was employed for such decoupling process considering the sensor layout cost and reconstruction accuracy. The decoupled strained based displacement could be reconstructed respectively using box girder plate element analysis and mode superposition principle. For the transformation modal matrix has a significant impact on the reconstructed displacement accuracy, the modal order would be optimized using particle swarm algorithm (PSO), aiming to minimize the ill conditioned degree of transformation modal matrix and the displacement reconstruction error. Numerical simulation and dynamic load testing results show that the reconstructed displacement was in good agreement with the simulated or measured results, which verifies the validity and accuracy of the algorithm proposed in this paper.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.6
• /
• pp.120-127
• /
• 1995

A nonlinear empirical state-space model of the Artificial Neural Network(ANN) has been developed. The nonlinear model structure incorporates characteristic, so as to enable identification of the transient response, as well as the steady-state response of a dynamic system. A hybrid feedfoward/feedback neural network, namely a Local Time Delayed Recurrent Multi-layer Perception(RMLP), is the model structure developed in this paper. RMLP is used to identify nonlinear dynamic system in an input/output sense. The feedfoward protion of the network architecture provides with the well-known curve fitting factor, while local recurrent and cross-talk connections provides the dynamics of the system. A dynamic learning algorithm is used to train the proposed network in a supervised manner. The derived dynamic learning algorithm exhibit a computationally desirable characteristic; both network sweep involved in the algorithm are performed forward, enhancing its parallel implementation. RMLP state-space and its associate learning algorithm is demonstrated through a simple examples. The simulation results are very encouraging.

• Structural Engineering and Mechanics
• /
• v.90 no.2
• /
• pp.189-208
• /
• 2024

Artificial intelligence is one of the efficient methods that can be developed to simulate nonlinear behavior and predict the response of building structures. In this regard, an adaptive method based on optimization algorithms is used to train the TSK model of the fuzzy inference system to estimate the seismic behavior of building structures based on analytical data. The optimization algorithm is implemented to determine the parameters of the TSK model based on the minimization of prediction error for the training data set. The adaptive training is designed on the feedback of the results of previous time steps, in which three training cases of 2, 5, and 10 previous time steps were used. The training data is collected from the results of nonlinear time history analysis under 100 ground motion records with different seismic properties. Also, 10 records were used to test the inference system. The performance of the proposed inference system is evaluated on two 3 and 20-story models of nonlinear steel moment frame. The results show that the inference system of the TSK model by combining the optimization method is an efficient computational method for predicting the response of nonlinear structures. Meanwhile, the multi-vers optimization (MVO) algorithm is more accurate in determining the optimal parameters of the TSK model. Also, the accuracy of the results increases significantly with increasing the number of previous steps.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4607-4616
• /
• 2023

We implement machine learning regression models to predict peak pressures of primary and secondary systems, a major safety concern in Loss Of Condenser Vacuum (LOCV) accident. We selected the Multi-dimensional Analysis of Reactor Safety-KINS standard (MARS-KS) code to analyze the LOCV accident, and the reference plant is the Korean Optimized Power Reactor 1000MWe (OPR1000). eXtreme Gradient Boosting (XGBoost) is selected as a machine learning tool. The MARS-KS code is used to generate LOCV accident data and the data is applied to train the machine learning model. Hyperparameter optimization is performed using a simulated annealing. The randomly generated combination of initial conditions within the operating range is put into the input of the XGBoost model to predict the peak pressure. These initial conditions that cause peak pressure with MARS-KS generate the results. After such a process, the error between the predicted value and the code output is calculated. Uncertainty about the machine learning model is also calculated to verify the model accuracy. The machine learning model presented in this paper successfully identifies a combination of initial conditions that produce a more conservative peak pressure than the values calculated with existing methodologies.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.514-523
• /
• 2024

In the Internet of Medical Things, due to the sensitivity of medical information, data typically need to be retained locally. The training model of heart disease data can predict patients' physical health status effectively, thereby providing reliable disease information. It is crucial to make full use of multiple data sources in the Internet of Medical Things applications to improve model accuracy. As network communication speeds and computational capabilities continue to evolve, parties are storing data locally, and using privacy protection technology to exchange data in the communication process to construct models is receiving increasing attention. This shift toward secure and efficient data collaboration is expected to revolutionize computer modeling in the healthcare field by ensuring accuracy and privacy in the analysis of critical medical information. In this paper, we train and test a multiparty decision tree model for the Internet of Medical Things on a heart disease dataset to address the challenges associated with developing a practical and usable model while ensuring the protection of heart disease data. Experimental results demonstrate that the accuracy of our privacy protection method is as high as 93.24%, representing a difference of only 0.3% compared with a conventional plaintext algorithm.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.143-147
• /
• 2024

Image noise classification is a classical problem in the field of image processing, machine learning, deep learning and computer vision. In this paper, image noise classification is performed using deep learning. Keras deep learning library of TensorFlow is used for this purpose. 6900 images images are selected from the Kaggle database for the classification purpose. Dataset for labeled noisy images of multiple type was generated with the help of Matlab from a dataset of non-noisy images. Labeled dataset comprised of Salt & Pepper, Gaussian and Sinusoidal noise. Different training and tests sets were partitioned to train and test the model for image classification. In deep neural networks CNN (Convolutional Neural Network) is used due to its in-depth and hidden patterns and features learning in the images to be classified. This deep learning of features and patterns in images make CNN outperform the other classical methods in many classification problems.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.2
• /
• pp.131-140
• /
• 2022

Installing Continuous Welded Rail (CWR) is one of the economical ways to resolve the challenges of noise, vibration, and the open-deck steel railway bridge impact, and the SSF method using the interlocking sleeper fastener has recently been developed. In this study, the method employed for determining the optimum vertical stiffness of the sleeper pad installed under the bridge sleeper, which is utilized to adjust the rail height and absorb shock when the train passes when the interlocking sleeper fastener is applied, is presented. To determine the optimal vertical stiffness of the sleeper pad, related existing design codes are reviewed, and, running safety, ride comfort, track safety, and bridge vibration according to the change in the vertical stiffness of the sleeper pad are estimated via flexible multi-body dynamic analysis,. The flexible multi-body dynamic analysis is performed using commercial programs ABAQUS and VI-Rail. The numerical analysis is conducted using the bridge model for a 30m-long plate girder bridge, and the response is calculated when passing ITX Saemaeul and KTX vehicles and freight wagon when the vertical stiffness of the sleeper pad is altered from 7.5 kN/mm to 240 kN/mm. The optimum stiffness of the sleeper pad is calculated as 200 kN/mm under the conditions of the track components applied to the numerical analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.11-19
• /
• 2009

A RAM-based Neural Net(RBNN) which has multi-discriminators is more effective than RBNN with a discriminator. Experience Sensitive Cumulative Neural Network and 3-D Neuro System(3DNS) that accumulate the features point improved the performance of BNN, which were enabled to train additional and repeated patterns and extract a generalized pattern. In recognition process of Neural Net with multi-discriminator, the selection of class was decided by the value of MRD which calculates the accumulated sum of each class. But they had a saturation problem of its memory cells caused by learning volume increment. Therefore, the decision of MRD has a low performance because recognition rate is decreased by saturation. In this paper, we propose the method which improve the MRD ability. The method consists of the optimum MRD and the matching ratio prototype to generalized image, the cumulative filter ratio, the gap of prototype response MRD. We experimented the performance using NIST database of NIST without preprocessor, and compared this model with 3DNS. The proposed MRD method has more performance of recognition rate and more stable system for distortion of input pattern than 3DNS.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.121-130
• /
• 2024

As internet and communication technology (ICT) is improved exponentially, types and amount of available data also increase. Even though data analysis including statistics is significant to utilize this large amount of data, there are inevitable limits to process various and complex data in general way. Meanwhile, there are many attempts to apply machine learning (ML) in various fields to solve the problems according to the enhancement in computational performance and increase in demands for autonomous systems. Especially, data processing for the model input and designing the model to solve the objective function are critical to achieve the model performance. Data processing methods according to the type and property have been presented through many studies and the performance of ML highly varies depending on the methods. Nevertheless, there are difficulties in deciding which data processing method for data analysis since the types and characteristics of data have become more diverse. Specifically, multi-variate data processing is essential for solving non-linear problem based on ML. In this paper, we present a multi-variate tabular data processing scheme for ML-aided data analysis by using Titanic dataset from Kaggle including various kinds of data. We present the methods like input variable filtering applying statistical analysis and normalization according to the data property. In addition, we analyze the data structure using visualization. Lastly, we design an ML model and train the model by applying the proposed multi-variate data process. After that, we analyze the passenger's survival prediction performance of the trained model. We expect that the proposed multi-variate data processing and visualization can be extended to various environments for ML based analysis.