Proceedings ArticleDOI
Handling Data Imbalance in Predictive Maintenance for Machines using SMOTE-based Oversampling
Reads0
Chats0
TLDR
In this article, a synthesized dataset was used in the predictive maintenance model, that reflects real-time failures encountered in the industries. But the class data imbalance hinders the performance of machine learning algorithms and this is handled by evaluating SMOTE-based oversampling techniques.Abstract:
The identification of failures and defects in industrial machines has proven to be a challenge to gauge their warranty and performance. Depreciation in industrial machines occurs due to several factors, most commonly- tool wear, strain, heat and power failure. In this paper, the development of machine learning algorithms for the prediction of machine failures is done. A synthesized dataset was used in the predictive maintenance model, that reflects real-time failures encountered in the industries. The class data imbalance hinders the performance of machine learning algorithms and this is handled by evaluating SMOTE-based oversampling techniques. By using SMOTE technique, a 7.83 % increase in the AUC score is observed, thereby improving the performance of the Random Forest classifier in distinguishing the instances of non-failure and machine failures.read more
Citations
More filters
Journal ArticleDOI
Industrial Control System Anomaly Detection and Classification Based on Network Traffic
TL;DR: It is shown that integrating the DAE, SMOTE, T-Link, and XGBoost schemes can achieve the highest or extremely high performance in the aspect of ICS anomaly detection and classification based on network traffic.
Journal ArticleDOI
Industrial Control System Anomaly Detection and Classification Based on Network Traffic
TL;DR: In this article , an anomaly detection and classification method for industrial control systems (ICSs) is proposed based on network traffic data of industrial field protocols like Modbus TCP and S7 Communication.
Journal ArticleDOI
Machine learning-based software sensors for machine state monitoring - The role of SMOTE-based data augmentation
TL;DR: In this paper , a method for flexible vibration sensor-based retrofitting of CNC machines is proposed, where the key idea is to use Borderline-Synthetic Minority Oversampling Technique (Borderline-SMOTE) to augment the data set.
Book ChapterDOI
Minimizing False-Rejection Rates in Gas Leak Testing Using an Ensemble Multiclass Classifier for Unbalanced Data
TL;DR: In this paper , a data-driven, equipment agnostic, procedure for leak testing fault classification is proposed, which identifies seven relevant classes for fault diagnosis, and, due to the highly unbalanced nature of these classes (minority class represents only 0.27% of all data), applies a novel unbalanced multiclass classification pipeline based on an ensemble of heterogeneous classifiers.
Proceedings ArticleDOI
Comparison of Ensemble Models as Solutions for Imbalanced Class Classification of Datasets
Yoga Pristyanto,Anggit Ferdita Nugraha,Rifda Faticha Alfa Aziza,Ibnu Hadi Purwanto,Mulia Sulistiyono,Akhmad Dahlan +5 more
TL;DR: In this paper , three different types of ensemble models (XGBoost, Stacking, and Bagging) were examined and contrasted with five distinct unbalanced multiclass datasets, each with a different value for the imbalanced ratio.
References
More filters
Proceedings ArticleDOI
Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results
TL;DR: One of the key findings of this paper is noticing that oversampling performs better than undersampling for different classifiers and obtains higher scores in different evaluation metrics.
Proceedings ArticleDOI
Explainable Artificial Intelligence for Predictive Maintenance Applications
TL;DR: This paper presents and provides a realistic, yet synthetic, predictive maintenance dataset for use in this paper and by the community, and describes an explainable model and an explanatory interface.
Journal ArticleDOI
A Simplified Cohen’s Kappa for Use in Binary Classification Data Annotation Tasks
Juan Wang,Yongyi Yang,Bin Xia +2 more
TL;DR: A simplified, linear relationship for Cohen’s kappa, sensitivity, and specificity is derived by using the 1st-order Taylor approximation and is demonstrated to be an effective measure for annotator assessment when no ground truth is available.
Proceedings ArticleDOI
Addressing Accuracy Paradox Using Enhanched Weighted Performance Metric in Machine Learning
TL;DR: A unique approach utilizing the underlying standard metrics and creating internals 3D evaluation of fitness factors, a part of enhanced machine learning engine engineering for enhanced Weighted Performance Metric.
Proceedings ArticleDOI
Observation Imbalanced Data Text to Predict Users Selling Products on Female Daily with SMOTE, Tomek, and SMOTE-Tomek
TL;DR: Experimental results on this study indicate the usefulness of the using SMOTE or SMOTE-Tomek approach to evaluate the imbalanced data text in Female Daily.
Related Papers (5)
A Generalized Predictive Framework for Data Driven Prognostics and Diagnostics using Machine Logs
Shili Xiang,Dong Huang,Xiaoli Li +2 more