• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.411-418
• /
• 2020

In the field of information security, IDS(Intrusion Detection System) is normally classified in two different categories: signature-based IDS and anomaly-based IDS. Many studies in anomaly-based IDS have been conducted that analyze network traffic data generated in cyberspace by machine learning algorithms. In this paper, we studied pre-processing methods to overcome performance degradation problems cashed by rare classes. We experimented classification performance of a Machine Learning algorithm by reconstructing data set based on rare classes and semi rare classes. After reconstructing data into three different sets, wrapper and filter feature selection methods are applied continuously. Each data set is regularized by a quantile scaler. Depp neural network model is used for learning and validation. The evaluation results are compared by true positive values and false negative values. We acquired improved classification performances on all of three data sets.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.

• Science of Emotion and Sensibility
• /
• v.12 no.1
• /
• pp.33-44
• /
• 2009

This study investigates differential impacts of the positive and negative content and the interaction with pacing, as a structural feature, on information processing while watching televised video clips with moderately intensive emotional tone. College participants watched six positive messages and six negative video clips lasting approximately 60 seconds. Heart rate was used to index attention and skin conductance was used to measure arousal. After all of the stimuli were shown, the participants performed the free recall questionnaire. The result demonstrates, first, positivity superiority on attention in which participants' heart rates were slower during positive content compared to during negative content. Secondly, negativity superiority was shown on free recall memory as participants remembered positive content better than did negative content. The result also manifests the interaction of emotional valence and pacing as the effects of pacing were less for the negatively emotional content compared to those for the positively emotional content. It is suggested that future studies should examine further about the differential and independent functions of positive and negative contents on information processing and the potential interaction with formal features.

• Journal of Distribution Science
• /
• v.6 no.1
• /
• pp.99-116
• /
• 2008

This research is focused on the effects of salesperson's evaluation of using the notebook computer. From analysis of the resulting data, using the notebook computer are increased the quality of salesperson's service-justice. Salesperson's distributive-justice affects to positive the customer satisfaction. But procedural justice and interactional justice cannot affect to positive the customer satisfaction. Maybe, I think that the reason will be a feature of insurance goods. And customer satisfaction affects to positive the salesperson's evaluation. But, only using the notebook computer cannot affect to positive the salesperson's evaluation. According to the result, using the notebook computer of salesperson affects to positive the salesperson's evaluation mediate of the service justice and customer satisfaction. There are limitations on generalization due to the results based on only insurance industry, but this study will be a useful exploratory step before designing a future survey.

• Journal of Korean Dental Science
• /
• v.5 no.2
• /
• pp.77-87
• /
• 2012

Purpose: This study examined the scanning electron microscopic feature, protein marker expression and osteoinductive activity of demineralized dentin matrix (DDM) from human for nude mice. Materials and Methods: Twenty healthy nude mice, weighing about 20 g were used for study. DDM from Human was prepared and implanted into the dorsal portion of nude mouse. Before implantation, DDM was examined by scanning electron microscopy (SEM). Nude mice were sacrificed at 2 weeks, 4 weeks and 8 weeks after DDM grafting and evaluated histologically by H-E, MT staining. And also immunohistochemistry analysis (ostecalcin, osteopontin) was performed. Result: Dentinal tubules and collagen fibers were observed by SEM of dentin surface of DDM. The DDM induced bone and cartilage independently in soft tissues. And, the histological findings showed bone forming cells like osteoblasts, fibroblasts at 2, 4 and 8 weeks. On immunohistochemistry analysis, osteocalcin and osteopontin positive bone forming cells were observed. Conclusion: This results showed that the DDM from human has osteoinductive ability and is a good alternative to autogenous bone graft materials.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.2996-3011
• /
• 2017

With rapid growth of web technology and dissemination of smart devices, social networking service(SNS) is widely used. As a result, huge amount of data are generated from SNS such as Twitter, and sentiment analysis of SNS data is very important for various applications and services. In the existing sentiment analysis based on the $Na{\ddot{i}}ve$ Bayes algorithm, a same number of attributes is usually employed to estimate the weight of each class. Moreover, uncountable and meaningless attributes are included. This results in decreased accuracy of sentiment analysis. In this paper two methods are proposed to resolve these issues, which reflect the difference of the number of positive words and negative words in calculating the weights, and eliminate insignificant words in the feature selection step using Multinomial $Na{\ddot{i}}ve$ Bayes(MNB) algorithm. Performance comparison demonstrates that the proposed scheme significantly increases the accuracy compared to the existing Multivariate Bernoulli $Na{\ddot{i}}ve$ Bayes(BNB) algorithm and MNB scheme.

• Journal of the Korean Society of Costume
• /
• v.56 no.7 s.106
• /
• pp.148-162
• /
• 2006

The purpose of this study is to examine the concept of convergence which is one of the trendy issues as a new digital paradigm of Integrative thinking in 21st century, to analyze the plastic feature and internal meaning of convergence expressed in fashion design, and to grasp the cultural symbolism through this aesthetic analysis. Because there have been considerable discussions on convergence, centering on industrial product area associated with media, I will proceed my study on the basis of them. For this, the documentary study and practical case study have been executed. This study will be helpful to find a direction of future fashion design trend. Convergence in digital stage can be defined as a phenomenon which different functions of product move towards one direction for greater efficiency, and not only as a technical integration between functions of product, but also an extension of area. Convergence can be classified by their use as (1) convergence for convenient daily life (2) convergence with intelligent scientific technology (3) convergence for entertainment on the basis of sensual experience. The plasticity of convergence designs feature as a open dynamic structure which potentiate transformation and their internal meaning can be inquired such qualities as integrative multiplicity, efficiency, mobility, intelligence. Specially convergence fashion design has protection qualify resulting from wearability on body. Ultimately convergence fashion design as a future digital paradigm can be thought as both eco-friendly design and human-centered design from positive technology-based viewpoint, because it is easy to transform according to our environment, convenient to reserve, and efficient to enhance spatial usibility.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.12
• /
• pp.226-235
• /
• 1998

This study proposes the analysis and evaluation of method of time series of ultrasonic signal using the chaotic feature extraction for ultrasonic pattern recognition. The features are extracted from time series data for analysis of weld defects quantitatively. For this purpose, analysis objectives in this study are fractal dimension, Lyapunov exponent, and strange attractor on hyperspace. The Lyapunov exponent is a measure of rate in which phase space diverges nearby trajectories. Chaotic trajectories have at least one positive Lyapunov exponent, and the fractal dimension appears as a metric space such as the phase space trajectory of a dynamical system. In experiment, fractal(correlation) dimensions and Lyapunov exponents show the mean value of 4.663, and 0.093 relatively in case of learning, while the mean value of 4.926, and 0.090 in case of testing in slag inclusion(weld defects) are shown. Therefore, the proposed chaotic feature extraction can be enhancement of precision rate for ultrasonic pattern recognition in defecting signals of weld zone, such as slag inclusion.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2106-2117
• /
• 2017

An effective statistical feature extraction approach of data sampling of fault in the combined transmission system is presented in this paper. The proposed algorithm leads to high accuracy at minimum cost to predict fault location and fault type classification. This algorithm requires impedance measurement data from one end of the transmission line. Modal decomposition is used to extract positive sequence impedance. Then, the fault signal is decomposed by using discrete wavelet transform. Statistical sampling is used to extract appropriate fault features as benchmark of decomposed signal to train classifier. Support Vector Machine (SVM) is used to illustrate the performance of statistical sampling performance. The overall time of sampling is not exceeding 1 1/4 cycles, taking into account the interval time. The proposed method takes two steps of sampling. The first step takes 3/4 cycle of during-fault and the second step takes 1/4 cycle of post fault impedance. The interval time between the two steps is assumed to be 1/4 cycle. Extensive studies using MATLAB software show accurate fault location estimation and fault type classification of the proposed method. The classifier result is presented and compared with well-established travelling wave methods and the performance of the algorithms are analyzed and discussed.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1088-1094
• /
• 2010

Image authentication algorithms have to discriminate forged contents in the various critical fields of military, medical services, digital documents. They must ensure perceptual invisibility and fragility against malicious attacks. It is desirable that watermarking algorithms support sufficient insertion capacity and blind feature. And, high reliable algorithms that can eliminate false-positive and false-negative errors are needed in the watermark extraction process. In this paper, we control coefficients of high frequency band in a DCT domain and compensate brightness histogram for high reliability. As a result, we found that the proposed algorithm guarantee various requirements such as perceptual invisibility with high PSNR values, fragility, high reliability and blind feature. In addition, experiment results show that the proposed algorithm can be used steganographic applications by sufficient capacity of watermark.