• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.148-151
• /
• 2010

분류 기법은 데이터 마이닝 기술 중 가장 잘 알려진 방법으로서, Decision tree, SVM(Support Vector Machine), ANN(Artificial Neural Network) 등 기법을 포함한다. 분류 기법은 이미 알려진 상호 배반적인 몇 개 그룹에 속하는 다변량 관측치로부터 각각의 그룹이 어떤 특징을 가지고 있는지 분류 모델을 만들고, 소속 그룹이 알려지지 않은 새로운 관측치가 어떤 그룹에 분류될 것인가를 결정하는 분석 방법이다. 분류기법을 수행할 때에 기본적으로 특징 공간이 잘 표현되어 있다고 가정한다. 그러나 실제 응용에서는 단일 특징으로 구성된 특징공간이 분명하지 않기 때문에 분류를 잘 수행하지 못하는 문제점이 있다. 본 논문에서는 이 문제에 대한 해결방안으로써 많은 정보를 포함하면서 빈발패턴에 대한 정보의 순실이 없는 닫힌 빈발패턴 기반 분류에 대한 연구를 진행하였다. 본 실험에서는 ${\chi}^2$(Chi-square)과 정보이득(Information Gain) 속성 선택 척도를 사용하여 의미있는 특징 선택을 수행하였다. 그 결과, 이 연구에서 제시한 척도를 사용하여 특징 선택을 수행한 경우, C4.5, SVM 과 같은 분류기법보다 더 향상된 분류 성능을 보였다.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3359-3366
• /
• 2023

In this study, a spiking cortical model (SCM) based n-g discrimination method is proposed. The SCM-based algorithm is compared with three other methods, namely: (i) the pulse-coupled neural network (PCNN), (ii) the charge comparison, and (iii) the zero-crossing. The objective evaluation criteria used for the comparison are the FoM-value and the time consumption of discrimination. Experimental results demonstrated that our proposed method outperforms the other methods significantly with the highest FoM-value. Specifically, the proposed method exhibits a 34.81% improvement compared with the PCNN, a 50.29% improvement compared with the charge comparison, and a 110.02% improvement compared with the zero-crossing. Additionally, the proposed method features the second-fastest discrimination time, where it is 75.67% faster than the PCNN, 70.65% faster than the charge comparison and 38.4% slower than the zero-crossing. Our study also discusses the role and change pattern of each parameter of the SCM to guide the selection process. It concludes that the SCM's outstanding ability to recognize the dynamic information in the pulse signal, improved accuracy when compared to the PCNN, and better computational complexity enables the SCM to exhibit excellent n-γ discrimination performance while consuming less time.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.5
• /
• pp.510-517
• /
• 2001

This paper describes an initial study for the application of eddy current pattern recognition approaches to more realistic flaw characterization in steam generator tubes. For this purpose, finite-element model-based theoretical eddy current testing (ECT) signals are simulated from 5 types of OD flaws with the variation in flaw size parameters and testing frequency. In addition, three kinds of software are developed for the convenience in the application of steps in pattern recognition approaches such as feature extraction feature selection and classification by probabilistic neural networks (PNNs). The cross point of the ECT signals simulated from flaws with non-symmetric cross-sections shows the deviation from the origin of the impedance plane. New features taking advantages of this phenomenon are added to complete the feature set with a total of 18 features. Then, classification with PNNs are performed based on this feature set. The PNN classifiers show high performance for the identification of symmetry in the cross-section of a flaw. However, they show very limited success in the interrogation of the sharpness of flaw tips.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.4
• /
• pp.1419-1429
• /
• 2010

Industry structure and environment of the domestic bank have been changed by an influx of large foreign-banks and advanced financial products when the currency crisis erupted in Korea. In a competitive environment, accurate forecasts of changes and tendencies are essential for the survival and development. Forecast of whether to approve loan applications for customer or not is an important matter because that is related to profit generation and risk management on the bank. Therefore, this paper proposes the method to improve forecast accuracy of loan underwriting. Processes in experiments are as follows. First, we select the predictor variables which affect significantly to the result of loan underwriting by correlation analysis and feature selection technique, and then cluster the customers by the 2-Step clustering technique based on selected variables. Second, we find the most accurate forecasting model for each clustering by applying LR, NN and SVM. Finally, we compare the forecasting accuracy of the proposed method with the forecasting accuracy of existing application way.

• Journal of Sensor Science and Technology
• /
• v.12 no.6
• /
• pp.289-297
• /
• 2003

In this paper, we propose accurate classification method of an EEG signals during a mental tasks. In the experimental task, subjects achieved through the process of responding to visual stimulus, understanding the given problem, controlling hand motions, and select a key. To recognize the subjects' selection time, we analyzed with 4 types feature from the filtered brain waves at frequency bands of $\alpha$, $\beta$, $\theta$, $\gamma$ waves. From the analysed features, we construct specific rules for each subject meta rules including common factors in all subjects. In this system, the architecture of the neural network is a three layered feedforward networks with one hidden layer which implements the error back propagation learning algorithm. Applying the algorithms to 4 subjects show 87% classification success rates. In this paper, the proposed detection method can be a basic technology for brain-computer-interface by combining with discrimination methods.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.590-598
• /
• 2018

Recently, interest in IoT(Internet of Things) technology, which provides Internet services to objects, is increasing. IoT offers a variety of services in home networks, healthcare, and disaster alerts. IoT with LLN(Low Power & Lossy Networks) feature frequently loses sensor node. RPL, the standard routing protocol of IoT, performs global repair when data loss occurs in a sensor node. However, frequent loss of sensor nodes due to lower sensor nodes causes network performance degradation due to frequent full path reset. In this paper, we propose an additional selection method of the storage mode sensor node to solve the network degradation problem due to the frequent path resetting problem even after selecting the storage mode sensor node, and propose a method of equalizing the total path resetting number of each instance.

• Journal of Digital Convergence
• /
• v.14 no.4
• /
• pp.277-283
• /
• 2016

This study proposed new methods to classify normal and epileptic seizure signals from EEG signals using peaks extracted by wavelet transform(WT) and Hilbert transform(HT) based on a neural network with weighted fuzzy membership functions(NEWFM). This study has the following three steps for extracting inputs for NEWFM. In the first step, the WT was used to remove noise from EEG signals. In the second step, the HT was used to extract peaks from the wavelet coefficients. We also selected the peaks bigger than the average of peaks to extract big peaks. In the third step, statistical methods were used to extract 16 features used as inputs for NEWFM from peaks. The proposed methodology shows that accuracy, specificity, and sensitivity are 99.25%, 99.4%, 99% with 16 features, respectively. Improvement in feature selection method in view to enhancing the accuracy is planned as the future work for selecting good features from 16 features.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.