• Journal of the Korea Safety Management & Science
• /
• v.25 no.4
• /
• pp.141-151
• /
• 2023

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

• Journal of Korean Society for Quality Management
• /
• v.24 no.4
• /
• pp.190-206
• /
• 1996

In case measurements are made on units of production in time order, it is reasonable to expect that the measurement errors will sometimes be first order autocorrelated, and a technique to test such autocorrelation is required to give good control of the productive process. Tool-wear process provide an example for which regression model can sometimes be useful in modeling and controlling the process. For the control of such process, we present a simple method for testing first order autocorrelation in regression errors. The method is based on Bayesian test method via Bayes factor and derived by observing that in general, a Bayes factor can be written as the product of a quantity called the Savage-Dickey density ratio and a correction factor ; both terms are easily estimated from Gibbs sampling technique. Performance of the method is examined by means of Monte Carlo simulation. It is noted that the test not only achieves satisfactory power but eliminates the inconvenience occurred in using the well-known Durbin-Watson test.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.2
• /
• pp.135-139
• /
• 2009

We present a new ensemble learning method that employs the set of region experts, each of which learns to handle a subset of the training data. We split the training data and generate experts for different regions in the feature space. When classifying a data, we apply a weighted voting among the experts that include the data in their region. We used ten datasets to compare the performance of our new ensemble method with that of single classifiers as well as other ensemble methods such as Bagging and Adaboost. We used SMO, Naive Bayes and C4.5 as base learning algorithms. As a result, we found that the performance of our method is comparable to that of Adaboost and Bagging when the base learner is C4.5. In the remaining cases, our method outperformed the benchmark methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.119-125
• /
• 1999

This paper gives an overview of the various approaches to designing statistical pattern recognition scheme based on Bayes discrimination rule and the artificial neural networks for rotating machine condition classification. Concerning to Bayes discrimination rule, this paper contains the linear discrimination rule applied to classification into several multivariate normal distributions with common covariance matrices, the quadratic discrimination rule under different covariance matrices. Also we discribes k-nearest neighbor method to directly estimate a posterior probability of each class. Five features are extracted in time domain vibration signals. Employing these five features, statistical pattern classifier and neural networks have been established to detect defects on rotating machine. Four different cases of rotation machine were observed. The effects of k number and neural networks structures on monitoring performance have also been investigated. For the comparison of diagnosis performance of these two method, their recognition success rates are calculated form the test data. The result of experiment which classifies the rotating machine conditions using each method presents that the neural networks shows the highest recognition rate.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.4
• /
• pp.275-280
• /
• 2015

In this paper, we studied for modified MUSIC algorithm of direction of arrival (DOA)estimation. Modified MUSIC algorithm search optimal covariance matrix using singular value decomposition and Bayes method, and desired signals are estimated by updating weight. In order to estimation of desired signals, we used sub spatial method of MUSIC algorithm. General MUSIC algorithm can estimate a desired signal in case of non-correlation signal. But, general MUSIC algorithm in case of correlation signal can not estimate a desired signals and resolution is decreased. Though simulation in case of correlation signal, we analyze to compare proposed MUSIC algorithm with general MUSIC algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.11-17
• /
• 2017

We proposed malware detection method, which use the feature vector that consist of Opcode(operation code) and Windows API Calls extracted from executable files. And, we implemented our feature vector and measured the performance of it by using Bernoulli Naïve Bayes and K-Nearest Neighbor classifier. In experimental result, when using the K-NN classifier with the proposed method, we obtain 95.21% malware detection accuracy. It was better than existing methods using only either Opcode or Windows API Calls.

• Nuclear Engineering and Technology
• /
• v.46 no.5
• /
• pp.619-632
• /
• 2014

The Best Estimate Plus Uncertainty (BEPU) method has been widely used to evaluate the uncertainty of a best-estimate thermal hydraulic system code against a figure of merit. This uncertainty is typically evaluated based on the physical model's uncertainties determined by expert judgment. This paper introduces the application of data assimilation methodology to determine the uncertainty bands of the physical models, e.g., the mean value and standard deviation of the parameters, based upon the statistical approach rather than expert judgment. Data assimilation suggests a mathematical methodology for the best estimate bias and the uncertainties of the physical models which optimize the system response following the calibration of model parameters and responses. The mathematical approaches include deterministic and probabilistic methods of data assimilation to solve both linear and nonlinear problems with the a posteriori distribution of parameters derived based on Bayes' theorem. The inverse problem was solved analytically to obtain the mean value and standard deviation of the parameters assuming Gaussian distributions for the parameters and responses, and a sampling method was utilized to illustrate the non-Gaussian a posteriori distributions of parameters. SPACE is used to demonstrate the data assimilation method by determining the bias and the uncertainty bands of the physical models employing Bennett's heated tube test data and Becker's post critical heat flux experimental data. Based on the results of the data assimilation process, the major sources of the modeling uncertainties were identified for further model development.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.175-188
• /
• 2015

This study is about estimation methods for the population pharmacokinetic and pharmacodymic model. This is a nonlinear mixed effect model, and it is difficult to find estimates of parameters because of nonlinearity. In this study, we examined theoretical background of various estimation methods provided by NONMEM, which is the most widely used software in the pharmacometrics area. We focused on estimation methods using a stochastic sampling approach - IMP, IMPMAP, SAEM and BAYES. The SAEM method showed the best performance among methods, and IMPMAP and BAYES methods showed slightly less performance than SAEM. The major obstacle to a stochastic sampling approach is the running time to find solution. We propose new approach to find more precise initial values using an ITS method to shorten the running time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.2
• /
• pp.23-32
• /
• 2010

Because ROTA(road traffic authority) analyzes the effects of accident reduction based on the data of 1-year after installation of RLC(red light camera), study of accident reduction effects over year after the installation of RLC is very short. This study deals with the traffic accident reduction during 3 years after the installation of RLC. The objective is to analyze the effects of accident reduction by year using EB method. In pursuing the above, the study uses the 951 accident data occurred at the 20 intersections which RLC are installed. The main results analyzed are as follows. First, the safety performance function (SPF) has been developed by the Poisson regression models which are statistically significant. Second, the results of an Empirical Bayes(EB) analyses showed that the accidents were reduced by the range from 2.73 to 38.75% after 1 year, from 6.85 to 47.36% after 2 year, and from 6.04 to 39.31% after 3 year from the installation of RLC.