• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Computational Structural Engineering
• /
• v.10 no.4
• /
• pp.303-313
• /
• 1997

Though many techniques for the damage assessment of structures have been studied recently, most of them can be only applied to simple structures. Therefore, practical damage assessment techniques that evaluate the damage location and the damage state for large structures need to be developed. In this study, a damage assessment technique using a neural network is developed, in which the bilevel damage assessment procedure is proposed to evaluate the damage of a large structure from the limited monitoring data. The procedure is as follows ; first, for the rational selection of damage critical members, the members that affect the probability of failure or unusual structural behavior are selected by sensitivity analysis. Secondly, the monitoring points and the number of sensors that are sensitive to the damage severity of the selected members are also selected through the sensitivity analysis with a proposed sensitivity measurement format. The validity and applicability of the developed technique are demonstrated by various examples, and it has been shown that the practical information on the damage state of the selected critical members can be assessed even though the limited monitoring data have been used.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1150-1161
• /
• 2018

Classification is widely used in medical images to categorize patients and non-patients. However, conventional classification requires a complex procedure, including some rigid steps such as pre-processing, segmentation, feature extraction, detection, and classification. In this paper, we propose a novel convolutional neural network (CNN), called LeukemiaNet, to specifically classify two different types of leukemia, including acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), and non-cancerous patients. To extend the limited dataset, a PCA color augmentation process is utilized before images are input into the LeukemiaNet. This augmentation method enhances the accuracy of our proposed CNN architecture from 96.9% to 97.2% for distinguishing ALL, AML, and normal cell images.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2004.03b
• /
• pp.442-449
• /
• 2004

This paper describes a new concept of finite element analysis, which is based on neural network based material models (NNCMs) without invoking any pre-chosen mathematical framework. NNCMs have several advantages over conventional constitutive models (CCMs) and once plugged in a finite element (FE) engine, can be used for FE analysis in a manner similar to CCMs. The paper demonstrates a FE framework in which NNCMs are incorporated and also proposes a strategy for data enhancement by invoking the assumption of isotropy of the material. It is shown through some illustrative examples that this provides a better training environment for a generalized NNCM in which stress and strain components are used as effects and cause. Form this study, it appears that there is a prima facia case for developing NNCMs for materials for which mathematical theories become too complex and a large number of material parameters and constants have to be identified or determined.

• Journal of Korean Society for Quality Management
• /
• v.41 no.2
• /
• pp.249-260
• /
• 2013

Purpose: The main objective of this paper is to propose an RD method by developing a neural network (NN)-based estimation approach in order to provide an alternative aspect of response surface methodology (RSM). Methods: A specific modeling procedure for integrating NN principles into response function estimations is identified in order to estimate functional relationships between input factors and output responses. Finally, a comparative study based on simulation is performed as verification purposes. Results: This simulation study demonstrates that the proposed NN-based RD method provides better optimal solutions than RSM. Conclusion: The proposed NN-based RD approach can be a potential alternative method to utilize many RD problems in competitive manufacturing nowadays.

• Transactions of Materials Processing
• /
• v.29 no.4
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.10 no.2
• /
• pp.102-109
• /
• 2006

In this Paper, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. The system that uses the ANN falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the Separate Learning Algorithm(SLA) of ANN has been proposed by using SVM. This is the method that ANN learns selectively after discriminating the defect position by SVM, then more improved performance estimation can be obtained than using ANN only. The proposed SLA can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.10
• /
• pp.1079-1086
• /
• 2013

Optimal mount position of a front pillar trim considering heat resistant characteristics can be determined by two methods. One is conventional approximate optimization method which uses the statistical design of experiments (DOE) and response surface method (RSM). Generally, approximated optimum results are obtained through the iterative process by a trial and error. The quality of results depends seriously on the factors and levels assigned by a designer. The other is a methodology derived from previous work by the authors, which is called sequential design of experiments (SDOE), to reduce a trial and error procedure and to find an appropriate condition for using artificial neural network (ANN) systematically. An appropriate condition is determined from the iterative process based on the analysis of means. With this new technique and ANN, it is possible to find an optimum design accurately and efficiently.

• Nuclear Engineering and Technology
• /
• v.50 no.7
• /
• pp.1154-1159
• /
• 2018

Precise prediction of the radiation interaction position in scintillators plays an important role in medical and industrial imaging systems. In this research, the incident position of the gamma rays was predicted precisely in a plastic rod scintillator by using attenuation technique and multilayer perceptron (MLP) neural network, for the first time. Also, this procedure was performed using nonlinear regression (NLR) method. The experimental setup is comprised of a plastic rod scintillator (BC400) coupled with two PMTs at two sides, a $^{60}Co$ gamma source and two counters that record count rates. Using two proposed techniques (ANN and NLR), the radiation interaction position was predicted in a plastic rod scintillator with a mean relative error percentage less than 4.6% and 14.6%, respectively. The mean absolute error was measured less than 2.5 and 5.5. The correlation coefficient was calculated 0.998 and 0.984, respectively. Also, the ANN technique was confirmed by leave-one-out (LOO) method with 1% error. These results presented the superiority of the ANN method in comparison with NLR and the other methods. The technique and set up used are simpler and faster than other the previous position sensitive detectors. Thus, the time, cost and shielding and electronics requirements are minimized and optimized.

• Computers and Concrete
• /
• v.13 no.4
• /
• pp.547-567
• /
• 2014

Precast Seismic Structural Systems (PRESSS) provided an iterative procedure for obtaining optimum design of unbonded post-tensioned coupled precast concrete wall systems. Although PRESSS procedure is effective, however, it is lengthy and laborious. The purpose of this research is to employ Artificial Neural Network (ANN) to predict the optimum design parameters for such wall systems while avoiding the demanding iterative process. The developed ANN model is very accurate in predicting the nondimensional optimum design parameters related to post-tensioning reinforcement area, yield force of shear connectors and ratio of moment resisted by shear connectors to the design moment. The Mean Absolute Percent Error (MAPE) for the test data for these design parameters is around %1 and the correlation coefficient is almost equal to 1.0. The developed ANN model is then used to study the effect of different design parameters on wall behavior. It is observed that the design moment and the concrete strength have the most influence on the wall behavior as compared to other parameters. Several design examples were presented to demonstrate the accuracy and effectiveness of the ANN model.