• ETRI Journal
• /
• v.17 no.1
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.5
• /
• pp.69-74
• /
• 2015

In this paper the patterns of information system is reduced so that control rules can guarantee fast response of queries in database. Generally an information system includes many kinds of necessary and unnecessary attribute. In particular, inconsistent information system is less likely to acquire the accuracy of response. Hence we are interested in the simple and understandable rules that can represent useful patterns by means of rough entropy and Bayesian posterior probability. We propose an algorithm which can reduce control rules to a minimum without inadequate patterns such that the implication between condition attributes and decision attributes is measured through the framework of rough entropy. Subsequently the validation of the proposed algorithm is showed through test information system of new employees appointment.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.531-536
• /
• 2022

In order to efficeintly manage a battery, it is important to accurately estimate and manage the SOH(State of Health) and RUL(Remaining Useful Life) of the batteries. Even if the batteries are of the same type, the characteristics such as facility capacity and voltage are different, and when the battery for the training model and the battery for prediction through the model are different, there is a limit to measuring the accuracy. In this paper, We proposed the entropy index using voltage distribution and discharge time is generalized, and four batteries are defined as a training set and a test set alternately one by one to predict the health status of batteries through linear regression analysis of machine learning. The proposed method showed a high accuracy of more than 95% using the MAPE(Mean Absolute Percentage Error).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.140-142
• /
• 2021

Mobile communication technology after 5th generation requires high speed, hyper-connection, and low latency communication. In order to meet technical requirements for secure hyper-connectivity, low-spec IoT devices that are considered the end of IoT services must also be able to provide the same level of security as high-spec servers. For the purpose of performing these security functions, it is required for cryptographic keys to have the necessary degree of stability in cryptographic algorithms. Cryptographic keys are usually generated from cryptographic random number generators. At this time, good noise sources are needed to generate random numbers, and hardware random number generators such as TRNG are used because it is difficult for the low-spec device environment to obtain sufficient noise sources. In this paper we used the chip which is based on quantum characteristics where the decay of radioactive isotopes is unpredictable, and we presented a variety of methods (TRNG) obtaining an entropy source in the form of binary-bit series. In addition, we conducted the NIST SP 800-90B test for the entropy of output values generated by each TRNG to compare the amount of entropy with each method.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.297-307
• /
• 2006

Most methods for describing the relationship among random variables require specific probability distributions and some assumptions of random variables. The mutual information based on the entropy to measure the dependency among random variables does not need any specific assumptions. And the redundancy which is a analogous version of the mutual information was also proposed. In this paper, the redundancy and mutual information are explored to multi-dimensional categorical data. It is found that the redundancy for categorical data could be expressed as the function of the generalized likelihood ratio statistic under several kinds of independent log-linear models, so that the redundancy could also be used to analyze contingency tables. Whereas the generalized likelihood ratio statistic to test the goodness-of-fit of the log-linear models is sensitive to the sample size, the redundancy for categorical data does not depend on sample size but its cell probabilities itself.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.452-472
• /
• 2019

Most existing wavelet-based multiplicative watermarking methods are affected by geometric attacks to a certain extent. A serious limitation of wavelet-based multiplicative watermarking is its sensitivity to rotation, scaling, and translation. In this study, we propose an image watermarking method by using dual-tree complex wavelet transform with a multi-objective optimization approach. We embed the watermark information into an image region with a high entropy value via a multiplicative strategy. The major contribution of this work is that the trade-off between imperceptibility and robustness is simply solved by using the multi-objective optimization approach, which applies the watermark error probability and an image quality metric to establish a multi-objective optimization function. In this manner, the optimal embedding factor obtained by solving the multi-objective function effectively controls watermark strength. For watermark decoding, we adopt a maximum likelihood decision criterion. Finally, we evaluate the performance of the proposed method by conducting simulations on benchmark test images. Experiment results demonstrate the imperceptibility of the proposed method and its robustness against various attacks, including additive white Gaussian noise, JPEG compression, scaling, rotation, and combined attacks.

• Geomechanics and Engineering
• /
• v.12 no.1
• /
• pp.35-52
• /
• 2017

In order to evaluate the grouting effects of water-rich fault in tunnels systematically, a feasible and scientific method is introduced based on the extension theory. First, eight main influencing factors are chosen as evaluation indexes by analyzing the changes of permeability, mechanical properties and deformation of surrounding rocks. The model of evaluating grouting effects based on the extension theory is established following this. According to four quality grades of grouting effects, normalization of evaluation indexes is carried out, aiming to meet the requirement of extension theory on data format. The index weight is allocated by adopting the entropy method. Finally, the model is applied to the grouting effects evaluation in water-rich fault F4-4 of Qingdao Jiaozhou Bay Subsea Tunnel, China. The evaluation results are in good agreement with the test results on the site, which shows that the evaluation model is feasible in this field, providing a powerful tool for systematically evaluating the grouting effects of water-rich fault in tunnels.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.387-394
• /
• 2013

Data mining is the process of discovering hidden, non-trivial patterns in large amounts of data records in order to be used very effectively for analysis and forecasting. Because hundreds of variables give rise to a high level of redundancy and dimensionality with time complexity, they are more likely to have spurious relationships, and even the weakest relationships will be highly significant by any statistical test. Hence cluster analysis is a main task of data mining and is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups. In this paper system implementation is of great significance, which defines a new definition based on information-theoretic entropy and analyse the analogue behaviors of objects at hand so as to address the measurement of uncertainties in the classification of categorical data. The sources were taken from a survey aimed to identify of job guidance from students in high school pyeongtaek. we show how variable precision information-entropy based rough set can be used to group student in each section. It is proved that the proposed method has the more exact classification than the conventional in attributes more than 10 and that is more effective in job guidance for students.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.61-68
• /
• 2008

This paper presents a spam filter system using co-training with spamminess features and URL features based on the maximum entropy model. Spamminess features are the emphasizing patterns or abnormal patterns in spam messages used by spammers to express their intention and to avoid being filtered by the spam filter system. Since spammers use URLs to give the details and make a change to the URL format not to be filtered by the black list, normal and abnormal URLs can be key features to detect the spam messages. Co-training with spamminess features and URL features uses two different features which are independent each other in training. The filter system can learn information from them independently. Experiment results on TREC spam test collection shows that the proposed approach achieves 9.1% improvement and 6.9% improvement in accuracy compared to the base system and bogo filter system, respectively. The result analysis shows that the proposed spamminess features and URL features are helpful. And an experiment result of the co-training shows that two feature sets are useful since the number of training documents are reduced while the accuracy is closed to the batch learning.

• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.351-362
• /
• 1998

In this paper, a test of fit for Weibull distribution on the estimated Kullback-Leibler information is proposed. The test uses the Vasicek entropy estimates, so to compute it a window size m must first be fried, and then is obtained critical values computed by Monte Carlo simulations. The power of the proposed test under various alternatives is compares with that of ocher famous tests. The use of the test is shown in an illustrative example.