• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.825-832
• /
• 2014

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require accurate detection of P-QRS-T point, higher computational cost and larger processing time. Even if some methods have the advantage in low complexity, but they generally suffer form low sensitivity. Also, it is difficult to detect PVC accurately because of the various QRS pattern by person's individual difference. Therefore it is necessary to design an efficient algorithm that classifies PVC based on QRS pattern in realtime and decreases computational cost by extracting minimal feature. In this paper, we propose PVC classification based on QRS pattern using QS interval and R wave amplitude. For this purpose, we detected R wave, RR interval, QRS pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through QS interval and R wave amplitude. The performance of R wave detection, PVC classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30 PVC. The achieved scores indicate the average of 99.02% in R wave detection and the rate of 93.72% in PVC classification.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.1
• /
• pp.15-26
• /
• 2003

Ultrasonic inspection methods are widely used for detecting flaws in materials. The signal analysis step plays a crucial part in the data interpretation process. A number of signal processing methods have been proposed to classify ultrasonic flaw signals. One of the more popular methods involves the extraction of an appropriate set of features followed by the use of a neural network for the classification of the signals in the feature space. This paper describes an alternative approach which uses the least mean square (LMS) method and expectation maximization (EM) algorithm with the model based deconvolution which is employed for classifying nondestructive evaluation (NDE) signals from steam generator tubes in a nuclear power plant. The signals due to cracks and deposits are not significantly different. These signals must be discriminated to prevent from happening a huge disaster such as contamination of water or explosion. A model based deconvolution has been described to facilitate comparison of classification results. The method uses the space alternating generalized expectation maximization (SAGE) algorithm In conjunction with the Newton-Raphson method which uses the Hessian parameter resulting in fast convergence to estimate the time of flight and the distance between the tube wall and the ultrasonic sensor Results using these schemes for the classification of ultrasonic signals from cracks and deposits within steam generator tubes are presented and showed a reasonable performances.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.1-11
• /
• 2006

Many research demonstrations and commercial applications have been tried to develop face detection and recognition systems. Human face detection plays an important role in applications such as access control and video surveillance, human computer interface, identity authentication, etc. There are some special problems such as a face connected with background, faces connected via the skin color, and a face divided into several small parts after skin region segmentation in generally. It can be allowed many face detection techniques to solve the first and second problems. However, it is not easy to detect a face divided into several parts of regions for reason of different illumination conditions in the third problem. Therefore, we propose an efficient modified skin segmentation algorithm to solve this problem because the typical region segmentation algorithm can not be used to. Our algorithm detects skin regions over the entire image, and then generates face candidate regions using our skin segmentation algorithm For each face candidate, we implement the procedure of region merging for divided regions in order to make a region using adjacency between homogeneous regions. We utilize various different searching window sizes to detect different size faces and a face detection classifier based on a back-propagation algorithm in order to verify whether the searching window contains a face or not.

• Tunnel and Underground Space
• /
• v.25 no.2
• /
• pp.186-198
• /
• 2015

This paper aims for the ultimate goal to optimize the work place environment through assuring the optimal required ventilation rate based on the analysis of the airflow. The working environment is deteriorated due to a rise in temperature of a coal mine caused by increase of its depth and carriage tunnels. To improve the environment, the ventilation evaluation on J coal mine is carried out and the effect of a length of the tunnel on the temperature to enhance the ventilation efficiency in the subsurface is numerically analyzed. The analysis shows that J coal mine needs $17,831m^3/min$ for in-flow ventilation rate but the total input air flowrate is $16,474m^3/min$, $1,357m^3/min$ of in-flow ventilation rate shortage. The temperatures were predicted on the two developed models of J mine, and VnetPC that is a numerical program for the flowrate prediction. The result of the simulation notices the temperature in the case of developing all 4 areas of -425ML as a first model is predicted 29.30 at the main gangway 9X of C section and in the case of developing 3 areas of -425ML excepting A area as a second model, it is predicted 27.45 Celsius degrees.

• Journal of Korean Society of Transportation
• /
• v.20 no.6
• /
• pp.59-68
• /
• 2002

AADT(Annual Average Daily Traffic) can be obtained by using short-term counted traffic data rather than using traffic data collected for 365 days. The process is a very important in estimating AADT using short-term traffic count data. Therefore, There have been many studies about estimating AADT. In this Paper, we tried to improve the process of the AADT estimation based on the former AADT estimation researches. Firstly, we found the factor showing differences among groups. To do so, we examined hourly variables(divided to total hours, weekday hours. Saturday hours, Sunday hours, weekday and Sunday hours, and weekday and Saturday hours) every time changing the number of groups. After all, we selected the hourly variables of Sunday and weekday as the factor showing differences among groups. Secondly, we classified 200 locations into 10 groups through cluster analysis using only monthly variables. The nile of deciding the number of groups is maximizing deviation among hourly variables of each group. Thirdly, we classified 200 locations which had been used in the second step into the 10 groups by applying statistical techniques such as Discriminant analysis and Neural network. This step is for testing the rate of distinguish between the right group including each location and a wrong one. In conclusion, the result of this study's method was closer to real AADT value than that of the former method. and this study significantly contributes to improve the method of AADT estimation.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.25 no.1
• /
• pp.27-35
• /
• 2005

Ultrasonic inspection methods are widely used for detecting flaws in materials. The signal analysis step plays a crucial part in the data interpretation process. A number of signal processing methods have been proposed to classify ultrasonic flaw signals. One of the more popular methods involves the extraction of an appropriate set of features followed by the use of a neural network for the classification of the signals in the feature spare. This paper describes an alternative approach which uses the least mean square (LMS) method and exportation maximization (EM) algorithm with the model based deconvolution which is employed for classifying nondestructive evaluation (NDE) signals from steam generator tubes in a nuclear power plant. The signals due to cracks and deposits are not significantly different. These signals must be discriminated to prevent from happening a huge disaster such as contamination of water or explosion. A model based deconvolution has been described to facilitate comparison of classification results. The method uses the space alternating generalized expectation maximiBation (SAGE) algorithm ill conjunction with the Newton-Raphson method which uses the Hessian parameter resulting in fast convergence to estimate the time of flight and the distance between the tube wall and the ultrasonic sensor. Results using these schemes for the classification of ultrasonic signals from cracks and deposits within steam generator tubes are presented and showed a reasonable performances.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.10
• /
• pp.4910-4918
• /
• 2013

This study aims to design a Severity-Adjusted LOS(Length of Stay) Model in order to efficiently manage LOS of AMI(Acute Myocardial Infarction) patients. We designed a Severity-Adjusted LOS Model with using data-mining methods(multiple regression analysis, decision trees, and neural network) which covered 6,074 AMI patients who showed the diagnosis of I21 from 2004-2009 Korean National Hospital Discharge in-depth Injury Survey. A decision tree model was chosen for the final model that produced superior results. This study discovered that the execution of CABG, status at discharge(alive or dead), comorbidity index, etc. were major factors affecting a Sevirity-Adjustment of LOS of AMI patients. The difference between real LOS and adjusted LOS resulted from hospital location and bed size. The efficient management of LOS of AMI patients requires that we need to perform various activities after identifying differentiating factors. These factors can be specified by applying each hospital's data into this newly designed Severity-Adjusted LOS Model.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.11-20
• /
• 2019

Numerous enterprises, organizations and individual users are exposed to large DDoS (Distributed Denial of Service) attacks. DDoS attacks are performed through a BotNet, which is composed of a number of computers infected with a malware, e.g., zombie PCs and a special computer that controls the zombie PCs within a hierarchical chain of a command system. In order to detect a malware, a malware detection software or a vaccine program must identify the malware signature through an in-depth analysis, and these signatures need to be updated in priori. This is time consuming and costly. In this paper, we propose a botnet detection scheme that does not require a periodic signature update using an artificial neural network model. The proposed scheme exploits Word2Vec and accelerated hierarchical density-based clustering. Botnet detection performance of the proposed method was evaluated using the CTU-13 dataset. The experimental result shows that the detection rate is 99.9%, which outperforms the conventional method.