Non-contact assessment of cardiac physiology using FO-MVSS-based ballistocardiography: a promising approach for heart failure evaluation.

Continuous monitoring of cardiac motions has been expected to provide essential cardiac physiology information on cardiovascular functioning. A fiber-optic micro-vibration sensing system (FO-MVSS) makes it promising. This study aimed to explore the correlation between Ballistocardiography (BCG) waveforms, measured using an FO-MVSS, and myocardial valve activity during the systolic and diastolic phases of the cardiac cycle in participants with normal cardiac function and patients with congestive heart failure (CHF). A high-sensitivity FO-MVSS acquired continuous BCG recordings. The simultaneous recordings of BCG and electrocardiogram (ECG) signals were obtained from 101 participants to examine their correlation. BCG, ECG, and intracavitary pressure signals were collected from 6 patients undergoing cardiac catheter intervention to investigate BCG waveforms and cardiac cycle phases. Tissue Doppler imaging (TDI) measured cardiac time intervals in 51 participants correlated with BCG intervals. The BCG recordings were further validated in 61 CHF patients to assess cardiac parameters by BCG. For heart failure evaluation machine learning was used to analyze BCG-derived cardiac parameters. Significant correlations were observed between cardiac physiology parameters and BCG's parameters. Furthermore, a linear relationship was found betwen IJ amplitude and cardiac output (r = 0.923, R2 = 0.926, p < 0.001). Machine learning techniques, including K-Nearest Neighbors (KNN), Decision Tree Classifier (DTC), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and XGBoost, respectively, demonstrated remarkable performance. They all achieved average accuracy and AUC values exceeding 95% in a five-fold cross-validation approach. We establish an electromagnetic-interference-free and non-contact method for continuous monitoring of the cardiac cycle and myocardial contractility and measure the different phases of the cardiac cycle. It presents a sensitive method for evaluating changes in both cardiac contraction and relaxation in the context of heart failure assessment.

Variational mode decomposition-based abnormal wheel-rail relationship detection in distributed acoustic sensing.

The distributed acoustic sensing system can obtain the vibration signal caused by the vibration of the train. By analyzing these wheel-rail vibration signals, an abnormal wheel-rail relationship identification scheme is proposed. The variational mode decomposition is employed for signal decomposition, thereby obtaining intrinsic mode functions with prominent abnormal fluctuations. The kurtosis value of each intrinsic mode function is calculated, which is compared with the threshold value for the identification of trains with abnormal wheel-rail relationship. And the extreme point of the abnormal intrinsic mode function is used to locate the bogie with an abnormal wheel-rail relationship. Experimental demonstration verifies that the proposed scheme can identify the train and locate the bogie with an abnormal wheel-rail relationship.

Low-Rank and Sparse Matrix Recovery for Hyperspectral Image Reconstruction Using Bayesian Learning.

In order to reduce the amount of hyperspectral imaging (HSI) data transmission required through hyperspectral remote sensing (HRS), we propose a structured low-rank and joint-sparse (L&S) data compression and reconstruction method. The proposed method exploits spatial and spectral correlations in HSI data using sparse Bayesian learning and compressive sensing (CS). By utilizing a simultaneously L&S data model, we employ the information of the principal components and Bayesian learning to reconstruct the hyperspectral images. The simulation results demonstrate that the proposed method is superior to LRMR and SS&LR methods in terms of reconstruction accuracy and computational burden under the same signal-to-noise tatio (SNR) and compression ratio.