• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.3
• /
• pp.145-150
• /
• 2014

In this paper, we propose a novel scheme to improve the performance of a voice activity detection(VAD) which is based on the deep belief networks(DBN) with the likelihood ratio(LR). The proposed algorithm applies the DBN learning method which is trained in order to minimize the probability of detection error instead of the conventional decision rule using geometric mean. Experimental results show that the proposed algorithm yields better results compared to the conventional VAD algorithm in various noise environments.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1199-1209
• /
• 2021

The detection of unexpected loose parts in the primary coolant system in a nuclear power plant remains an extremely important issue. It is essential to develop a methodology for the localization and mass estimation of loose parts owing to the high prediction error of conventional methods. An effective approach is presented for the localization and mass estimation of a loose part using machine-learning and deep-learning algorithms. First, a methodology was developed to estimate both the impact location and the mass of a loose part at the same times in a real structure in which geometric changes exist. Second, an impact database was constructed through a series of impact finite-element analyses (FEAs). Then, impact parameter prediction modes were generated for localization and mass estimation of a simulated metallic loose part using machine-learning algorithms (artificial neural network, Gaussian process, and support vector machine) and a deep-learning algorithm (convolutional neural network). The usefulness of the methodology was validated through blind tests, and the noise effect of the training data was also investigated. The high performance obtained in this study shows that the proposed methodology using an FEA-based database and deep learning is useful for localization and mass estimation of loose parts on site.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.137-142
• /
• 2021

Machine-learning systems have proven their worth in various industries, including healthcare and banking, by assisting in the extraction of valuable inferences. Information in these crucial sectors is traditionally stored in databases distributed across multiple environments, making accessing and extracting data from them a tough job. To this issue, we must add that these data sources contain sensitive information, implying that the data cannot be shared outside of the head. Using cryptographic techniques, Privacy-Preserving Machine Learning (PPML) helps solve this challenge, enabling information discovery while maintaining data privacy. In this paper, we talk about how to keep your data mining private. Because Data mining has a wide variety of uses, including business intelligence, medical diagnostic systems, image processing, web search, and scientific discoveries, and we discuss privacy-preserving in deep learning because deep learning (DL) exhibits exceptional exactitude in picture detection, Speech recognition, and natural language processing recognition as when compared to other fields of machine learning so that it detects the existence of any error that may occur to the data or access to systems and add data by unauthorized persons.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.903-909
• /
• 2018

In this paper, performance analysis of machine vision techniques is presented to improve the convenience and speed of automatic inspection in the industrial field when machine vision is applied to the image not taken in the stationary state, but in the moving state on a conveyer. When the length of cylindrical rods used for automobiles was measured using the edge detection method, the conveying speed increased, and the uncertainty of the boundary between the background and the part image increased, which resulted in a shorter image of the object taken. This paper proposes a linear compensation method to predict the biased errors of the length measurements after examining the pattern of biased and random errors, respectively, with 6 different types of specimens and 7 velocity stages. The length measurement corrected by the linear compensation method had the same accuracy as the stationary state within the speed range of 30 cm/s and could enhance the application capability in automatic inspections.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.105-112
• /
• 2006

In this study, we propose a simple preprocessing method for classification of basal cell carcinoma (BCC), which is one of the most common skin cancer. The preprocessing step consists of data clipping with a half Hanning window and dimension reduction with principal components analysis (PCA). The application of the half Hanning window deemphasizes the peak near $1650cm^{-1}$ and improves classification performance by lowering the false negative ratio. Classification results with various classifiers are presented to show the effectiveness of the proposed method. The classifiers include maximum a posteriori probability (MAP), k-nearest neighbor (KNN), probabilistic neural network (PNN), multilayer perceptron(MLP), support vector machine (SVM) and minimum squared error (MSE) classification. Classification results with KNN involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic BCC detection.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, total misclassification cost is more affected by FNE rather than FPE. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.166-171
• /
• 2013

The method proposed in this paper can improve the performance of the Boosting algorithm in machine learning. The proposed Boundary AdaBoost algorithm can make up for the weak points of Normal binary classifier using threshold boundary concepts. The new proposed boundary can be located near the threshold of the binary classifier. The proposed algorithm improves classification in areas where Normal binary classifier is weak. Thus, the optimal boundary final classifier can decrease error rates classified with more reasonable features. Finally, this paper derives the new algorithm's optimal solution, and it demonstrates how classifier accuracy can be improved using the proposed Boundary AdaBoost in a simulation experiment of pedestrian detection using 10-fold cross validation.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.245-250
• /
• 2002

A successful on-line monitoring system for conventional machining operations has the potential to reduce cost, guarantee consistency of product quality, improve productivity and provide a safer environment for the operator. In fee-shape machining, typical signs of tool problems such as vibration, noise, chip flow characteristics and visual signs are almost unnoticeable without the use of special equipment. These characteristics increase the importance of automatic monitoring in fine-shape machining; however, sensing and interpretation of signals are more complex. In addition, the shafts of the micro-tools break before the typical extensive cutting edge of the tool gets damaged. In this study, the existence of a relationship between the characteristics of the cutting force and tool usage was investigated, and tool breakage detection algorithm was developed and the fellowing results are obtained. In data analysis, didn't use a relative error compare which mainly used in established experiment and investigated tool breakage detection algorithm in time domain which can detect AE and cutting force signals more effective and accurate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2424-2441
• /
• 2012

In this paper, we propose a fake iris detection method that combines the optical and textural features of the human eye. To extract the optical features, we used dual Purkinje images that were generated on the anterior cornea and the posterior lens surfaces based on an analytic model of the human eye's optical structure. To extract the textural features, we measured the amount of change in a given iris pattern (based on wavelet decomposition) with regard to the direction of illumination. This method performs the following two procedures over previous researches. First, in order to obtain the optical and textural features simultaneously, we used five illuminators. Second, in order to improve fake iris detection performance, we used a SVM (Support Vector Machine) to combine the optical and textural features. Through combining the features, problems of single feature based previous works could be solved. Experimental results showed that the EER (Equal Error Rate) was 0.133%.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.127-134
• /
• 2021

In this study, an anomaly detection (AD) algorithm was implemented to detect the failure of a marine air compressor. A lab-scale experiment was designed to produce fault datasets (time-series electric current measurements) for 10 failure modes of the air compressor. The results demonstrated that the temporal pattern of the datasets showed periodicity with a different period, depending on the failure mode. An AD model with a convolutional autoencoder was developed and trained based on a normal operation dataset. The reconstruction error was used as the threshold for AD. The reconstruction error was noted to be dependent on the AD model and hyperparameter tuning. The AD model was applied to the synthetic dataset, which comprised both normal and abnormal conditions of the air compressor for validation. The AD model exhibited good detection performance on anomalies showing periodicity but poor performance on anomalies resulting from subtle load changes in the motor.