Multi-Class Disturbance Events Recognition Based on EMD and XGBoost in φ-OTDR

Abstract

A novel pattern recognition method based on Empirical Mode Decomposition (EMD) and extreme gradient boosting (XGBoost) is proposed to recognize the disturbance events in phase sensitive optical time-domain reflectometer (ϕ-OTDR) to reduce nuisance alarm rate (NAR) and improve real-time performance in this paper. Eleven typical eigenvectors are extracted from components obtained by EMD of the disturbance signals and XGBoost is selected as a classifier to identify different type of disturbance signals. Five kinds of disturbance events, including watering, knocking, climbing, pressing and false disturbance event, can be identified, effectively. Experimental results show that NAR is 4.10% and identification time is 0.093 s. The recognition accuracy for the five patterns is 97.96%, 95.90%, 91.10%, 94.84% and 99.69%, respectively. The effectiveness of the proposed method is evaluated by using confusion matrix and decision boundary visualization. Experimental results demonstrate that our proposed pattern recognition method based on XGBoost has better performance in recognition rate and recognition time than other commonly used methods, such as support vector machine (SVM), Gradient Boosting Decision Tree (GBDT), Random Forest (RF) and Adaptive Boosting (Adaboost). INDEX TERMS Phase-sensitive optical time-domain reflectometer (ϕ-OTDR), extreme gradient boosting (XGBoost), nuisance alarm rate (NAR), empirical mode decomposition (EMD), pattern recognition, decision boundary visualization.

Distributed Acoustic Sensor Systems for Vehicle Detection and Classification

“…In line with acoustic signals classification, manual feature extraction techniques were first adopted in DAS event classification. Such techniques include wavelet packet transform [14], [15], spectral substitution [16], Mel-spectrograms [17], and empirical mode decomposition [18]. The classification task is then conducted using conventional classifiers such as support vector machines (SVM such as [14]) and relevant vector machines (e.g., [15]).…”

“…In order to improve the classification results, some works propose to use advanced classifiers instead of conventional classifier. For example, authors in [18] use XGboost, an ensemble algorithm, and authors in [16] and [17] use convolution neural networks (CNN), achieving higher success rate than conventional classifiers. Instead of manual feature extraction, authors in [19] employ a one-dimensional CNN (1D-CNN) directly to the raw signal followed by an SVM-based classifier and outperform previous works.…”

An eXtreme Gradient Boosting Algorithm Combining Artificial Bee Colony Parameters Optimized Technique for Single Sand Body Identification

“…In this experiment, we used a confusion matrix to evaluate the performance of the model. By revealing the relationship between the actual category and the predicted category of the sample data, it obtained four sets of data including true positive examples (TP), false positive examples (FP), true negative examples (TN) and false negative examples (FN) [32]. The distribution of correct and incorrect in each category is shown in Table III.…”

“…( 15) and Eq. ( 16) [32]. TP TPR= TP+FN (15) FP FPR= TN+FP (16) Therefore, the closer the ROC curve is to the upper left corner, the better the model effect.…”

Research on NMR Noise Reduction Method Based on Improved CEEMD

“…In recent years, Huang proposed a new time-frequency analysis method --empirical mode decomposition (EMD). These methods have been widely used in signal noise reduction in various fields [6][7][8][9]. EMD is an adaptive decomposition method.…”