scholarly journals Evaluation of One-Class Classifiers for Fault Detection: Mahalanobis Classifiers and the Mahalanobis–Taguchi System

Processes ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 1450
Author(s):  
Seul-Gi Kim ◽  
Donghyun Park ◽  
Jae-Yoon Jung
Keyword(s):  
Fault Detection ◽  
Binary Classification ◽  
Rotating Machinery ◽  
Industrial Robots ◽  
Sensor Data ◽  
Support Vector ◽  
Imbalanced Classification ◽  
Vibration Data ◽  
Binary Classifiers ◽  
One Class Classification

Today, real-time fault detection and predictive maintenance based on sensor data are actively introduced in various areas such as manufacturing, aircraft, and power system monitoring. Many faults in motors or rotating machinery like industrial robots, aircraft engines, and wind turbines can be diagnosed by analyzing signal data such as vibration and noise. In this study, to detect failures based on vibration data, preprocessing was performed using signal processing techniques such as the Hamming window and the cepstrum transform. After that, 10 statistical condition indicators were extracted to train the machine learning models. Specifically, two types of Mahalanobis distance (MD)-based one-class classification methods, the MD classifier and the Mahalanobis–Taguchi system, were evaluated in detecting the faults of rotating machinery. Their performance for fault detection on rotating machinery was evaluated with different imbalanced ratios of data by comparing with binary classification models, which included classical versions and imbalanced classification versions of support vector machine and random forest algorithms. The experimental results showed the MD-based classifiers became more effective than binary classifiers in cases in which there were much fewer defect data than normal data, which is often common in the real-world industrial field.

scholarly journals Expert guided natural language processing using one-class classification

2015 ◽  
Vol 22 (5) ◽  
pp. 962-966 ◽  
Author(s):  
Erel Joffe ◽  
Emily J Pettigrew ◽  
Jorge R Herskovic ◽  
Charles F Bearden ◽  
Elmer V Bernstam
Keyword(s):  
Breast Cancer ◽  
Language Processing ◽  
Text Processing ◽  
Binary Classification ◽  
Model Performance ◽  
Imbalanced Data ◽  
Superior Performance ◽  
Support Vector ◽  
Free Text ◽  
One Class Classification

Abstract Introduction Automatically identifying specific phenotypes in free-text clinical notes is critically important for the reuse of clinical data. In this study, the authors combine expert-guided feature (text) selection with one-class classification for text processing. Objectives To compare the performance of one-class classification to traditional binary classification; to evaluate the utility of feature selection based on expert-selected salient text (snippets); and to determine the robustness of these models with respects to irrelevant surrounding text. Methods The authors trained one-class support vector machines (1C-SVMs) and two-class SVMs (2C-SVMs) to identify notes discussing breast cancer. Manually annotated visit summary notes (88 positive and 88 negative for breast cancer) were used to compare the performance of models trained on whole notes labeled as positive or negative to models trained on expert-selected text sections (snippets) relevant to breast cancer status. Model performance was evaluated using a 70:30 split for 20 iterations and on a realistic dataset of 10 000 records with a breast cancer prevalence of 1.4%. Results When tested on a balanced experimental dataset, 1C-SVMs trained on snippets had comparable results to 2C-SVMs trained on whole notes (F = 0.92 for both approaches). When evaluated on a realistic imbalanced dataset, 1C-SVMs had a considerably superior performance (F = 0.61 vs. F = 0.17 for the best performing model) attributable mainly to improved precision (p = .88 vs. p = .09 for the best performing model). Conclusions 1C-SVMs trained on expert-selected relevant text sections perform better than 2C-SVMs classifiers trained on either snippets or whole notes when applied to realistically imbalanced data with low prevalence of the positive class.

MINIMAL CLASSIFICATION METHOD WITH ERROR-CORRECTING CODES FOR MULTICLASS RECOGNITION

2005 ◽  
Vol 19 (05) ◽  
pp. 663-680 ◽  
Author(s):  
DAYAN MANOHAR SIVALINGAM ◽  
NARENKUMAR PANDIAN ◽  
JEZEKIEL BEN-ARIE
Keyword(s):  
Binary Classification ◽  
Classification Problem ◽  
Error Correcting Codes ◽  
Classification Method ◽  
Support Vector ◽  
Object Image ◽  
Generalization Error ◽  
Image Library ◽  
Binary Classification Problem ◽  
Binary Classifiers

In this work, we develop an efficient technique to transform a multiclass recognition problem into a minimal binary classification problem using the Minimal Classification Method (MCM). The MCM requires only log 2 N classifications whereas the other methods require much more. For the classification, we use Support Vector Machine (SVM) based binary classifiers since they have superior generalization performance. Unlike the prevalent one-versus-one strategy (the bottom-up one-versus-one strategy is called tournament method) that separates only two classes at each classification, the binary classifiers in our method have to separate two groups of multiple classes. As a result, the probability of generalization error increases. This problem is alleviated by utilizing error correcting codes, which results only in a marginal increase in the required number of classifications. However, in comparison to the tournament method, our method requires only 50% of the classifications and still similar performance can be attained. The proposed solution is tested with the Columbia Object Image Library (COIL). We also test the performance under conditions of noise and occlusion.

scholarly journals Intelligent Fault Detection, Diagnosis and Health Evaluation for Industrial Robots

Mechanika ◽  
2021 ◽  
Vol 27 (1) ◽  
pp. 70-79
Author(s):  
Huan-Kun HSU ◽  
Hsiang-Yuan TING ◽  
Ming-Bao HUANG ◽  
Han-Pang HUANG
Keyword(s):  
Fault Detection ◽  
Evaluation System ◽  
Industrial Robot ◽  
Principal Component ◽  
Industrial Robots ◽  
Support Vector ◽  
Health Evaluation ◽  
Original Design ◽  
Statistical Process ◽  
The Time Domain

The focus of this study is development of an intelligent fault detection, diagnosis and health evaluation system for real industrial robots. The system uses principal component analysis based statistical process control with Nelson rules for online fault detection. Several suitable Nelson rules are chosen for sensitive detection. When a variation is detected, the system performs a diagnostic operation to acquire features of the time domain and the frequency domain from the motor encoder, motor current sensor and external accelerometer for fault diagnosis with a multi-class support vector machine. Additionally, a fuzzy logic based robot health index generator is proposed for evaluating the health of the robot, and the generator is an original design to reflect the health status of the robot. Finally, several real aging-related faults are implemented on a six-axis industrial robot, DRV90L7A6213N by Delta Electronics, and the proposed system is validated effectively by the experimental results.

scholarly journals A Self-Learning Fault Diagnosis Strategy Based on Multi-Model Fusion

Information ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 116 ◽  
Author(s):  
Tianzhen Wang ◽  
Jingjing Dong ◽  
Tao Xie ◽  
Demba Diallo ◽  
Mohamed Benbouzid
Keyword(s):  
Fault Detection ◽  
Principal Component ◽  
Component Analysis ◽  
Kernel Principal Component Analysis ◽  
Support Vector ◽  
Model Fusion ◽  
Vibration Data ◽  
Kernel Independent Component Analysis ◽  
Domain Description ◽  
Learning Machine

This paper presents an approach to detect and classify the faults in complex systems with small amounts of available data history. The methodology is based on the model fusion for fault detection and classification. Moreover, the database is enriched with additional samples if they are correctly classified. For the fault detection, the kernel principal component analysis (KPCA), kernel independent component analysis (KICA) and support vector domain description (SVDD) were used and combined with a fusion operator. For the classification, extreme learning machine (ELM) was used with different activation functions combined with an average fusion function. The performance of the methodology was evaluated with a set of experimental vibration data collected from a test-to-failure bearing test rig. The results show the effectiveness of the proposed approach compared to conventional methods. The fault detection was achieved with a false alarm rate of 2.29% and a null missing alarm rate. The data is also successfully classified with a rate of 99.17%.

scholarly journals Multi-Class Support Vector Machine via Maximizing Multi-Class Margins

2017 ◽  
Author(s):  
Jie Xu ◽  
Xianglong Liu ◽  
Zhouyuan Huo ◽  
Cheng Deng ◽  
Feiping Nie ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Binary Classification ◽  
Training Data ◽  
Classification Model ◽  
Support Vector ◽  
Frobenius Norm ◽  
Great Success ◽  
Svm Model ◽  
Binary Classifiers ◽  
And Training

Support Vector Machine (SVM) is originally proposed as a binary classification model, and it has already achieved great success in different applications. In reality, it is more often to solve a problem which has more than two classes. So, it is natural to extend SVM to a multi-class classifier. There have been many works proposed to construct a multi-class classifier based on binary SVM, such as one versus all strategy, one versus one strategy and Weston's multi-class SVM. One versus all strategy and one versus one strategy split the multi-class problem to multiple binary classification subproblems, and we need to train multiple binary classifiers. Weston's multi-class SVM is formed by ensuring risk constraints and imposing a specific regularization, like Frobenius norm. It is not derived by maximizing the margin between hyperplane and training data which is the motivation in SVM. In this paper, we propose a multi-class SVM model from the perspective of maximizing margin between training points and hyperplane, and analyze the relation between our model and other related methods. In the experiment, it shows that our model can get better or compared results when comparing with other related methods.

One-Class Fault Detection Using Multi-Layer Elm-Based Auto-Encoder

2020 ◽  
pp. 2150001
Author(s):  
Li Wuke ◽  
Yin Guangluan ◽  
Chen Xiaoxiao
Keyword(s):  
Fault Detection ◽  
Classification Accuracy ◽  
Test Sample ◽  
Reconstruction Error ◽  
Support Vector ◽  
Testing Time ◽  
Decision Threshold ◽  
Learning Machine ◽  
One Class Classification ◽  
And Function

A new approach for one-class fault detection trained only by normal samples has been proposed in this paper. The approach contains multi-anterior-layers for feature extraction and one post-layer for one-class classification. The multi-anterior-layers are based on extreme learning machine-based auto-encoder (ELM-AE). Multi-ELM-AEs are stacked in the front hidden layers to extract abstract features from the raw input. The post-layer is based on the reconstruction error-based ELM-AE (Re-ELM-AE) to act as one-class classifier. As the extension of ELM-AE, the decision threshold and function are given in the Re-ELM-AE, which are utilized to identify whether the test sample is faulty. The efficacy of the presented algorithm is demonstrated on a mathematic example and fault dataset from motor bearing. The method has been compared with shallow learning methods such as one-class support vector machine (OCSVM), the Re-ELM-AE, and one multi-layer neural network named stacked auto-encoder (SAE). The experiment results show that the proposed method outperforms OCSVM and Re-ELM-AE in classification accuracy. Though the classification accuracy of the proposed method and SAE is similar, the training and testing time of the proposed method is much lower than SAE.

scholarly journals A Robust Machine Learning Based Framework for the Automated Detection of ADHD Using Pupillometric Biomarkers and Time Series Analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
William Das ◽  
Shubh Khanna
Keyword(s):  
Machine Learning ◽  
Pupil Size ◽  
Binary Classification ◽  
Approximate Entropy ◽  
Automated Detection ◽  
Support Vector ◽  
Efficient Detection ◽  
Absolute Energy ◽  
Binary Classifiers ◽  
Diagnostic Applications

AbstractAccurate and efficient detection of attention-deficit/hyperactivity disorder (ADHD) is critical to ensure proper treatment for affected individuals. Current clinical examinations, however, are inefficient and prone to misdiagnosis, as they rely on qualitative observations of perceived behavior. We propose a robust machine learning based framework that analyzes pupil-size dynamics as an objective biomarker for the automated detection of ADHD. Our framework integrates a comprehensive pupillometric feature engineering and visualization pipeline with state-of-the-art binary classification algorithms and univariate feature selection. The support vector machine classifier achieved an average 85.6% area under the receiver operating characteristic (AUROC), 77.3% sensitivity, and 75.3% specificity using ten-fold nested cross-validation (CV) on a declassified dataset of 50 patients. 218 of the 783 engineered features, including fourier transform metrics, absolute energy, consecutive quantile changes, approximate entropy, aggregated linear trends, as well as pupil-size dilation velocity, were found to be statistically significant differentiators (p < 0.05), and provide novel behavioral insights into associations between pupil-size dynamics and the presence of ADHD. Despite a limited sample size, the strong AUROC values highlight the robustness of the binary classifiers in detecting ADHD—as such, with additional data, sensitivity and specificity metrics can be substantially augmented. This study is the first to apply machine learning based methods for the detection of ADHD using solely pupillometrics, and highlights its strength as a potential discriminative biomarker, paving the path for the development of novel diagnostic applications to aid in the detection of ADHD using oculometric paradigms and machine learning.

scholarly journals Classification and Automated Interpretation of Spinal Posture Data Using a Pathology-Independent Classifier and Explainable Artificial Intelligence (XAI)

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6323
Author(s):  
Carlo Dindorf ◽  
Jürgen Konradi ◽  
Claudia Wolf ◽  
Bertram Taetz ◽  
Gabriele Bleser ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Back Pain ◽  
Spinal Fusion ◽  
Reference Group ◽  
Binary Classification ◽  
Synthetic Data ◽  
Support Vector ◽  
Spinal Posture ◽  
Explainable Artificial Intelligence ◽  
Binary Classifiers

Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations of the classification decisions. Spinal posture data of healthy subjects and various pathologies (back pain, spinal fusion, osteoarthritis), as well as synthetic data, were used for modeling. A one-class support vector machine was used as a pathology-independent classifier. The outputs were transformed into a probability distribution according to Platt’s method. Interpretation was performed using the explainable artificial intelligence tool Local Interpretable Model-Agnostic Explanations. The results were compared with those obtained by commonly used binary classification approaches. The best classification results were obtained for subjects with a spinal fusion. Subjects with back pain were especially challenging to distinguish from the healthy reference group. The proposed method proved useful for the interpretation of the predictions. No clear inferiority of the proposed approach compared to commonly used binary classifiers was demonstrated. The application of dynamic spinal data seems important for future works. The proposed approach could be useful to provide an objective orientation and to individually adapt and monitor therapy measures pre- and post-operatively.

scholarly journals FAULT DETECTION OF ROTATING MACHINERY FROM BICOHERENCE ANALYSIS OF VIBRATION DATA

2006 ◽  
Vol 39 (13) ◽  
pp. 1348-1353 ◽  
Author(s):  
Enayet B. Halim ◽  
M.A.A. Shoukat Choudhury ◽  
Sirish L. Shah ◽  
Ming J. Zuo
Keyword(s):  
Fault Detection ◽  
Rotating Machinery ◽  
Vibration Data
Sign in / Sign up

Export Citation Format

Share Document