• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.80-90
• /
• 2001

The aim of this study is to develop the methodology which enables to identify the mechanical properties of element such as stress intensity factor by using the AE parameters. Considering the multivariate and nonlinear properties of AE parameters such as ringdown count, rise time, energy, event duration and peak amplitude from fatigue cracks of machine element the principal component regression(PCR) and artificial neural network(ANN) models for the estimation of stress intensity factor were developed and validated. The AE parameters were found to be very significant to estimate the stress intensity factor. Since the statistical values including correlation coefficients, standard mr of calibration, standard error of prediction and bias were stable, the PCR and ANN models for stress intensity factor were very robust. The performance of ANN model for unknown data of stress intensity factor was better than that of PCR model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.21 no.1
• /
• pp.81-100
• /
• 1996

본 연구에서는 보다 효과적인 기업신용평가를 위하여, 통계적 방법과 인공지능 방법을 결합한 결합모형을 제시햐고자 한다. 이를 위하여 본 연ㄴ구에서는 통계적인 모형중에서 가장 널리 활용되고 있는 MDA (Multivariate Discriminant Analysis) 와 인공지능적인 방법으로서 최근에 널리 사용되고 있는 인공싱경망( neural network)모형을 휴리스틱한 방법으로 결합한다. 이러한 결합모형의 성과를 증명하기 위하여 우리나라의 대표적인 3대 기업신용평가 기관에서 수집한 1043개의 기업신용평가자료를 기초로 실혐을 하고, 그 결과를 기존의 MDA 및 인공신경망 방법에 의한 결과와 비교하였다. 실험결과, 통계적으로도 유의하고, 실무적인 관점에서도 의미가 있는 기업신용펑가 결과를 유도할 수 있었다.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2022

This paper applies an expert independent unsupervised neural network learning-based multivariate time series data analysis model, MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder), and to overcome the limitation, because the MCRED is based on Auto-encoder model, that train data must not to be contaminated, by using learning data sampling technique, called Subset Sampling Validation. By using the vibration data of power plant equipment that has been labeled, the classification performance of MSCRED is evaluated with the Anomaly Score in many cases, 1) the abnormal data is mixed with the training data 2) when the abnormal data is removed from the training data in case 1. Through this, this paper presents an expert-independent anomaly diagnosis framework that is strong against error data, and presents a concise and accurate solution in various fields of multivariate time series data.

• Geomechanics and Engineering
• /
• v.35 no.2
• /
• pp.121-133
• /
• 2023

The demand for cement and limestone crushed materials has increased many folds due to the tremendous increase in construction activities in Pakistan during the past few decades. The number of cement production industries has increased correspondingly, and so the rock-blasting operations at the limestone quarry sites. However, the safety procedures warranted at these sites for the blast-induced ground vibrations (BIGV) have not been adequately developed and/or implemented. Proper prediction and monitoring of BIGV are necessary to ensure the safety of structures in the vicinity of these quarry sites. In this paper, an attempt has been made to predict BIGV using artificial neural network (ANN) at three selected limestone quarries of Pakistan. The ANN has been developed in Python using Keras with sequential model and dense layers. The hyper parameters and neurons in each of the activation layers has been optimized using randomized and grid search method. The input parameters for the model include distance, a maximum charge per delay (MCPD), depth of hole, burden, spacing, and number of blast holes, whereas, peak particle velocity (PPV) is taken as the only output parameter. A total of 110 blast vibrations datasets were recorded from three different limestone quarries. The dataset has been divided into 85% for neural network training, and 15% for testing of the network. A five-layer ANN is trained with Rectified Linear Unit (ReLU) activation function, Adam optimization algorithm with a learning rate of 0.001, and batch size of 32 with the topology of 6-32-32-256-1. The blast datasets were utilized to compare the performance of ANN, multivariate regression analysis (MVRA), and empirical predictors. The performance was evaluated using the coefficient of determination (R²), mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), and root mean squared error (RMSE)for predicted and measured PPV. To determine the relative influence of each parameter on the PPV, sensitivity analyses were performed for all input parameters. The analyses reveal that ANN performs superior than MVRA and other empirical predictors, andthat83% PPV is affected by distance and MCPD while hole depth, number of blast holes, burden and spacing contribute for the remaining 17%. This research provides valuable insights into improving safety measures and ensuring the structural integrity of buildings near limestone quarry sites.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.631-637
• /
• 2010

The aim of affective engineering is to develop a new product by translating customer affections into design factors. Affective data have so far been analyzed using a multivariate statistical analysis, but the affective data do not always have linear features assumed under normal distribution. Rough sets model is an effective method for knowledge discovery under uncertainty, imprecision and fuzziness. Rough sets model is to deal with any type of data regardless of their linearity characteristics. Therefore, this study utilizes rough sets model to extract affective knowledge from affective data. Four types of scent alternatives and four types of sounds were designed and the experiment was performed to look into affective differences in subject's preference on air conditioner. Finally, the purpose of this study also is to extract knowledge from affective data using rough sets model and to figure out the relationships between rough sets based affective engineering method and statistical one. The result of a case study shows that the proposed approach can effectively extract affective knowledge from affective data and is able to discover the relationships between customer affections and design factors. This study also shows similar results between rough sets model and statistical method, but it can be made more valuable by comparing fuzzy theory, neural network and multivariate statistical methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.383-388
• /
• 2024

This paper is a study to derive the predicted value of power generation based on the photovoltaic power generation data measured in Jeollanam-do, South Korea. Multivariate variables such as direct current, alternating current, and environmental data were measured in the inverter to measure the amount of power generation, and pre-processing was performed to ensure the stability and reliability of the measured values. Correlation analysis used only data with high correlation with power generation in time series data for prediction using partial autocorrelation function (PACF). Deep learning models were used to measure the amount of power generation to predict the amount of photovoltaic power generation, and the results of correlation analysis of each multivariate variable were used to increase the prediction accuracy. Learning using refined data was more stable than when existing data were used as it was, and the solar power generation prediction algorithm was improved by using only highly correlated variables among multivariate variables by reflecting the correlation analysis results.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.61-81
• /
• 2023

This study presents an ensemble learning based Bayesian model updating approach for structural damage diagnosis. In the developed framework, the structure is initially decomposed into a set of substructures. The autoregressive moving average (ARMAX) model is established first for structural damage localization based structural motion equation. The wavelet packet decomposition is utilized to extract the damage-sensitive node energy in different frequency bands for constructing structural surrogate models. Four methods, including Kriging predictor (KRG), radial basis function neural network (RBFNN), support vector regression (SVR), and multivariate adaptive regression splines (MARS), are selected as candidate structural surrogate models. These models are then resampled by bootstrapping and combined to obtain an ensemble model by probabilistic ensemble. Meanwhile, the maximum entropy principal is adopted to search for new design points for sample space updating, yielding a more robust ensemble model. Through the iterations, a framework of surrogate ensemble learning based model updating with high model construction efficiency and accuracy is proposed. The specificities of the method are discussed and investigated in a case study.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1361-1369
• /
• 2000

For the implementation of 3D Sound Localization system, the binaural filtering by HRTFs is generally employed. But the HRTF filter is of high order and its coefficients for all directions have to be stored, which imposes a rather large memory requirement. To cope with this, research works have centered on obtaining low dimensional HRTF representations without significant loss of information and synthesizing the original HRTF efficiently, by means of feature extraction methods for multivariate dat including PCA. In these researches, conventional linear PCA was applied to the frequency domain HRTF data and using relatively small number of principal components the original HRTFs could be synthesized in approximation. In this paper we applied neural network based nonlinear PCA model (NLPCA) and the nonlinear PLS repression model (NLPLS) for this low dimensional HRTF modeling and analyze the results in comparison with the PCA. The NLPCA that performs projection of data onto the nonlinear surfaces showed the capability of more efficient HRTF feature extraction than linear PCA and the NLPLS regression model that incorporates the direction information in feature extraction yielded more stable results in synthesizing general HRTFs not included in the model training.

• Structural Engineering and Mechanics
• /
• v.31 no.1
• /
• pp.57-74
• /
• 2009

Power signals resulting from spindle and feed motor, present a rich content of physical information, the appropriate analysis of which can lead to the clear identification of the nature of the tool wear. The partial least-squares regression (PLSR) method has been established as the tool wear analysis method for this purpose. Firstly, the results of the application of widely used techniques are given and their limitations of prior methods are delineated. Secondly, the application of PLSR is proposed. The singular value theory is used to noise reduction. According to grey relational degree analysis, sample variable is filtered as part sample variable and all sample variables as independent variables for modelling, and the tool wear is taken as dependent variable, thus PLSR model is built up through adapting to several experimental data of tool wear in different milling process. Finally, the prediction value of tool wear is compare with actual value, in order to test whether the model of the tool wear can adopt to new measuring data on the independent variable. In the new different cutting process, milling tool wear was predicted by the methods of PLSR and MLR (Multivariate Linear Regression) as well as BPNN (BP Neural Network) at the same time. Experimental results show that the methods can meet the needs of the engineering and PLSR is more suitable for monitoring tool wear.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.