Incipient Fault Diagnosis for High-Speed Train Traction Systems via Stacked Generalization

Unified Low-Dimensional Subspace Analysis of Continuous and Binary Variables for Industrial Process Monitoring

Industrial data often consist of continuous variables (CVs) and binary variables (BVs), both of which provide crucial information about process operating conditions. Due to the coupling between industrial systems or equipment, these hybrid variables are usually high-dimensional and highly correlated. However, existing methods generally model hybrid variables directly in the observation space and assume independence between the variables to overcome the curse of dimensionality. Thus, they are ineffective at capturing dependencies among hybrid variables, and the effectiveness of process monitoring will be compromised. To overcome the limitations, this study proposes to seek a unified subspace for hybrid variables using the probabilistic latent variable (LV) model. By introducing a low-dimensional continuous LV, the proposed method can avoid the curse of dimensionality while capturing the dependencies between hybrid variables. Nevertheless, the inference of LV is analytically intractable and thus time-consuming due to the heterogeneity of CVs and BVs. To accelerate offline learning and online inference procedures, this study originally derives an analytical Gaussian distribution to approximate the true posterior distribution of the LV, based on which an efficient expectation-maximization algorithm is developed for parameter estimation. The Gaussian approximation is simultaneously optimized with the latest parameters to achieve a high approximation accuracy. The LV is then estimated by the posterior mean of the Gaussian approximation. By mapping the heterogeneous variables into a unified subspace, the proposed method defines three monitoring statistics, which are physically interpretable and thoroughly evaluate the probability of hybrid variables being normal. The effectiveness of the proposed method in detecting anomalies in CVs and BVs is shown through a numerically simulated case and a real industrial case.

Learning to Imbalanced Open Set Generalize: A Meta-Learning Framework for Enhanced Mechanical Diagnosis

To alleviate data distribution under different operating conditions, domain generalization (DG) has been applied in mechanical diagnosis. Still, its effectiveness is limited when unknown fault states appear in the target domain. Consequently, open set DG (OSDG) has emerged to identify unknown classes in unknown domains. However, data collection costs and safety concerns have resulted in a significant class imbalance in OSDG. This imbalance causes the decision boundary to be skewed toward abundant positive classes, ultimately leading to misclassifying unknown states and increasing security risks. Currently, there is a lack of methods to simultaneously address domain shift and class shift in an imbalanced unknown domain. To tackle this issue, this article proposes a multisource domain-class gradient coordination meta-learning (MDGCML) framework, which can learn the generalized boundaries of all tasks by coordinating gradients between interdomains and interclasses. Based on the MDGCML, a joint learning paradigm involving the sharing of parameters between open-set classifiers and closed-set classifiers is constructed to enable quick adaption of the model to unknown domains. The superior performance of the proposed framework has been verified on two datasets.

A machine learning approach to differentiate wide QRS tachycardia: distinguishing ventricular tachycardia from supraventricular tachycardia

BACKGROUND

Differential diagnosis of wide QRS tachycardia (WQCT) has been a challenging issue. Published algorithms to distinguish ventricular tachycardia (VT) and supraventricular tachycardia (SVT) have limited diagnostic capabilities.

METHODS

A total of 278 patients with WQCT from January 2010 to March 2022 were enrolled. The electrophysiological study confirmed SVT in 154 patients and VT in 65 ones. Two hundred nineteen WQCT 12-lead ECGs were randomly divided into development cohort (n = 165) and testing cohort (n = 54) data sets. The development cohort was split into a training group (n = 115) and an internal validation group (n = 50). Forty ECG features extracted from the 219 WQCT ECGs are fed into 9 iteratively trained ML algorithms. This novel ML algorithm was also compared with four published algorithms.

RESULTS

In the development cohort, the Gradient Boosting Machine (GBM) model displayed the maximum area under curve (AUC) (0.91, 95% confidence interval (CI) 0.81-1.00). In the testing cohort, the GBM model had a higher AUC of 0.97 compared to 4 validated ECG algorithms, namely, Brugada (0.68), avR (0.62), RWPTII (0.72), and LLA algorithms (0.70). Accuracy, sensitivity, specificity, negative predictive value, and positive predictive value of the GBM model were 0.94, 0.97, 0.90, 0.94, and 0.95, respectively.

CONCLUSIONS

A GBM ML model contributes to distinguishing SVT from VT based on surface ECG features. In addition, we were able to identify important indicators for distinguishing WQCT.

Machine learning for distinguishing right from left premature ventricular contraction origin using surface electrocardiogram features

BACKGROUND

Precise localization of the site of origin of premature ventricular contractions (PVCs) before ablation can facilitate the planning and execution of the electrophysiological procedure.

OBJECTIVE

The purpose of this study was to develop a predictive model that can be used to differentiate PVCs between the left ventricular outflow tract and right ventricular outflow tract (RVOT) using surface electrocardiogram characteristics.

METHODS

A total of 851 patients undergoing radiofrequency ablation of premature ventricular beats from January 2015 to March 2022 were enrolled. Ninety-two patients were excluded. The other 759 patients were enrolled into the development (n = 605), external validation (n = 104), or prospective cohort (n = 50). The development cohort consisted of the training group (n = 423) and the internal validation group (n = 182). Machine learning algorithms were used to construct predictive models for the origin of PVCs using body surface electrocardiogram features.

RESULTS

In the development cohort, the Random Forest model showed a maximum receiver operating characteristic curve area of 0.96. In the external validation cohort, the Random Forest model surpasses 4 reported algorithms in predicting performance (accuracy 94.23%; sensitivity 97.10%; specificity 88.57%). In the prospective cohort, the Random Forest model showed good performance (accuracy 94.00%; sensitivity 85.71%; specificity 97.22%).

CONCLUSION

Random Forest algorithm has improved the accuracy of distinguishing the origin of PVCs, which surpasses 4 previous standards, and would be used to identify the origin of PVCs before the interventional procedure.

Identification and Validation of Immune Markers in Coronary Heart Disease

Background

Coronary heart disease (CHD) is an ischemic heart disease involving a variety of immune factors. This study was aimed at investigating unique immune and m6A patterns in patients with CHD by gene expression in peripheral blood mononuclear cells (PBMCs) and at identifying novel immune biomarkers.

Methods

The CIBERSORT algorithm and single-sample gene set enrichment analysis (ssGSEA) were applied to assess the population of specific infiltrating immunocytes. Weighted Gene Coexpression Network Analysis (WGCNA) was utilized on immune genes matching CHD. A prediction model based on core immune genes was constructed and verified by a machine learning model. Unsupervised cluster analysis identified various immune patterns in the CHD group according to the abundance of immune cells. Methylation of N6 adenosine- (m6A-) related gene was identified from the literature, and t-distributed stochastic neighbor embedding (t-SNE) analysis was used to determine the rationality of the m6A classification. The association between m6A-related genes and various immune cells was estimated using heat maps.

Results

22/28 immune-associated cells differed between the CHD and normal groups, and a significant difference was detected in the expression of 21 m6A-related genes. The proportion of immune-related cells (activated CD4+ T cells and CD8+ T cells) in the peripheral blood of the CHD group was lower than that of the normal group. The immune genes were divided into four modules, of which the turquoise modules showed a significant association with coronary heart disease. Eight hub immune genes (PDGFRA, GNLY, OSMR, NUDT6, FGFR2, IL2RB, TPM2, and S100A1) can well distinguish the CHD group from the normal group. Two different immune patterns were identified in the CHD group. Interestingly, a significant association was detected between the m6A-related genes and immune cell abundance.

Conclusion

In conclusion, we identified different immune and m6A patterns in CHD. Thus, it could be speculated that the immune system plays a crucial role in CHD, and m6A is correlated with immune genes.

A New Fusion Fault Diagnosis Method for Fiber Optic Gyroscopes

The fiber optic gyroscope (FOG) is a high precision inertial navigation device, and it is necessary to ensure its reliability for effective use. However, the extracted fault features are easily distorted due to the interference of vibrations when the FOG is in operation. In order to minimize the influence of vibrations to the greatest extent, a fusion diagnosis method was proposed in this paper. It extracted features from fault data with Fast Fourier Transform (FFT) and wavelet packet decomposition (WPD), and built a strong diagnostic classifier with a sparse auto encoder (SAE) and a neural network (NN). Then, a fusion neural network model was established based on the diagnostic output probabilities of the two primary classifiers, which improved the diagnostic accuracy and the anti-vibration capability. Then, five fault types of the FOG under random vibration conditions were established. Fault data sets were collected and generated for experimental comparison with other methods. The results showed that the proposed fusion fault diagnosis method could perform effective and robust fault diagnosis for the FOG under vibration conditions with a high diagnostic accuracy.

Prediction for Mitosis-Karyorrhexis Index Status of Pediatric Neuroblastoma via Machine Learning Based 18F-FDG PET/CT Radiomics

Accurate differentiation of intermediate/high mitosis-karyorrhexis index (MKI) from low MKI is vital for the further management of neuroblastoma. The purpose of this research was to investigate the efficacy of ¹⁸F-FDG PET/CT–based radiomics features for the prediction of MKI status of pediatric neuroblastoma via machine learning. A total of 102 pediatric neuroblastoma patients were retrospectively enrolled and divided into training (68 patients) and validation sets (34 patients) in a 2:1 ratio. Clinical characteristics and radiomics features were extracted by XGBoost algorithm and were used to establish radiomics and clinical models for MKI status prediction. A combined model was developed, encompassing clinical characteristics and radiomics features and presented as a radiomics nomogram. The predictive performance of the models was evaluated by AUC and decision curve analysis. The radiomics model yielded AUC of 0.982 (95% CI: 0.916, 0.999) and 0.955 (95% CI: 0.823, 0.997) in the training and validation sets, respectively. The clinical model yielded AUC of 0.746 and 0.670 in the training and validation sets, respectively. The combined model demonstrated AUC of 0.988 (95% CI: 0.924, 1.000) and 0.951 (95% CI: 0.818, 0.996) in the training and validation sets, respectively. The radiomics features could non-invasively predict MKI status of pediatric neuroblastoma with high accuracy.