• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.03a
• /
• pp.24-29
• /
• 1996

The seniconductor, which is precision product, requires many inspection processes. The surface conditions of the semiconductor chip effect on the functions of the semiconductors. The defects of the chip surface is crack or void. Because general inspection method requires many inspection processes, the inspection system which searches immediately and preciselythe defects of the semiconductor chip surface. We propose the inspection method by using the computer vision system. This study presents an image processing algorithm for inspecting the surface defects(crack, void)of the semiconductor test samples. The proposed image processing algorithm aims to reduce inspection time, and to analyze those experienced operator. This paper regards the chip surface as random texture, and deals with the image modeling of randon texture image for searching the surface defects. For texture modeling, we consider the relation of a pixel and neighborhood pixels as noncasul model and extract the statistical characteristics from the radom texture field by using the 2D AR model(Aut oregressive). This paper regards on image as the output of linear system, and considers the fidelity or intelligibility criteria for measuring the quality of an image or the performance of the processing techinque. This study utilizes the variance of prediction error which is computed by substituting the gary level of pixel of another texture field into the two dimensional AR(autoregressive model)model fitted to the texture field, estimate the parameter us-ing the PAA(parameter adaptation algorithm) and design the defect detection filter. Later, we next try to study the defect detection search algorithm.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.237-245
• /
• 2022

The prominence of IoTs (Internet of Things) and exponential advancement of computer networks has resulted in massive essential applications. Recognizing various cyber-attacks or anomalies in networks and establishing effective intrusion recognition systems are becoming increasingly vital to current security. MLTs (Machine Learning Techniques) can be developed for such data-driven intelligent recognition systems. Researchers have employed a TFDNNs (Tensor Flow Deep Neural Networks) and DCNNs (Deep Convolution Neural Networks) to recognize pirated software and malwares efficiently. However, tuning the amount of neurons in multiple layers with activation functions leads to learning error rates, degrading classifier's reliability. HTFDNNs ( Hybrid tensor flow DNNs) and MRNs (Modified Residual Networks) or Resnet CNNs were presented to recognize software piracy and malwares. This study proposes HTFDNNs to identify stolen software starting with plagiarized source codes. This work uses Tokens and weights for filtering noises while focusing on token's for identifying source code thefts. DLTs (Deep learning techniques) are then used to detect plagiarized sources. Data from Google Code Jam is used for finding software piracy. MRNs visualize colour images for identifying harms in networks using IoTs. Malware samples of Maling dataset is used for tests in this work.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.161-171
• /
• 2014

When the Hough transform is applied to identify an instance of a given model, the output is typically a histogram of votes cast by a set of image features into a parameter space. The next step is to threshold the histogram of counts to hypothesize a given match. The question is "What is a reasonable choice of the threshold?" In a standard implementation of the Hough transform, the threshold is selected heuristically, e.g., some fraction of the highest cell count. Setting the threshold too low can give rise to a false alarm of a given shape(Type I error). On the other hand, setting the threshold too high can result in mis-detection of a given shape(Type II error). In this paper, we derive two conditional probability functions of cell counts in the accumulator array of the generalized Hough transform(GHough), that can be used to select a scientific threshold at the peak detection stage of the Ghough.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.5 s.305
• /
• pp.27-34
• /
• 2005

Ventricular fibrillation(VF) is generally caused by chaotic behavior of electrical propagation in heart and may result in sudden cardiac death. In this study, we proposed a ventricular fibrillation detection algorithm based on support vector machine classifier, which could offer benefits to reduce the teaming costs as well as good classification performance. Before the extraction of input features, raw ECG signal was applied to preprocessing procedures, as like wavelet transform based bandpass filtering, R peak detection and segment assignment for feature extraction. We selected input features which of some are related to the rhythm information and of others are related to wavelet coefficients that could describe the morphology of ventricular fibrillation well. Parameters for SVM classifier, C and ${\alpha}$, were chosen as 10 and 1 respectively by trial and error experiments. Each average performance for normal sinus rhythm ventricular tachycardia and VF, was 98.39%, 96.92% and 99.88%. And, when the VF detection performance of SVM classifier was compared to that of multi-layer perceptron and fuzzy inference methods, it showed similar or higher values. Consequently, we could find that the proposed input features and SVM classifier would one of the most useful algorithm for VF detection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of Biomedical Engineering Research
• /
• v.37 no.1
• /
• pp.31-38
• /
• 2016

For the patients with bladder dysfunction, measurement of urine volume inside the bladder is very critical to avoid bladder failure. In measuring urine volume inside a bladder, low-resolution 3D ultrasound images are widely used. However, urine volume estimation from 3D ultrasound images is prone to big errors and inconsistency because of low spatial resolution and low signal-to-noise ratio of ultrasound images. We developed a new robust volume estimation algorithm which is not computationally expensive. We tested the algorithm on a lab-built ultrasound bladder phantom and volunteers. The average error rate of the human bladder volume estimation was 5.9% which was better than the commercial machine.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.8
• /
• pp.108-115
• /
• 2002

In measuring step for reverse engineering of sculptured surfaces, computer vision system is used to simplify the complicated surface by boundary edge detection method that minimizes the measuring error. The measured data by Coordinate measuring machine is clouded data points of surfaces which is segmented surface using image process. In this research, the measured data is approximated as NURBS surfaces by new suggested algorithm. The position and number of control points, selection of parametric values and compensation of weight factors are proposed. Finally, surface model is simulated and improved resulting performance is obtained.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.243-245
• /
• 2005

Condition monitoring is desirable for increasing machinery availability, reducing consequential damage, and improving operational efficiency. In this paper, a model-based method using neural network modeling of induction noter in vibration spectra is proposed for machine fault detection and diagnosis. The short-time Fourier transform (STFT) is used to process the quasi-steady vibration signals to continuous spectra so that the neural network model can be trained with vibration spectra. And the faults are detected from changes in the expectation of vibration spectra modeling error. The effectiveness of the proposed method is demonstrated through experimental results.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.5
• /
• pp.7-12
• /
• 2005

This paper presents several time series methods to analyze the chatter mechanics by using the power spectrum of these algorithms considering the cutting dynamics. In this study, several time series models such as AR(burg, forwardbackward, geometric lattice, instrument variable, least square, Yule Walker), ARX(1s, iv4), ARMAX, ARMA, Box Jenkins, Output Error were modeled and compared with one another. Finally, it was proven that time series modelings are also a desirable and reliable algorithm than the other conventional methods(FFT) for the calculation of the chatter mode in turning operation. Also, the spectrum of times series methods is a little bit more powerful than the FFT fer the detection of a high noisy and weak chatter mode. The radial cutting force Fy has been used for spectrum and chatter stability lobe analysis in this study.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.03a
• /
• pp.119-123
• /
• 1996

The demands for robotic and automatic system are continually increasing in manufacturing fields. There were so many studies to monitor and predict system, but it were mainly relied upon measuring of cutting force, current of motor spindle and using acoustic sensor, etc. In this study digital image of time series sequence was acquired taking advantage of optical technique. Then, mean square error was obtained from it and was available for useful observation data. The parameter was estimated using PAA(parameter adaptation algorithm) from observation data. AR model was selected for system model, fifth order was decided according to parameter estimation. Uncorrelation test was also carried out to verify convergence of parameter. Through the proceedings, we found there was a system stability.