This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of twodimensional time-frequency feature maps based on Mel-frequency cepstral coefficients (MFCC). We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time-and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.

The proposed approach is useful in neuroscience studies that investigate the dynamics of underlying brain states.

No abstract

This paper presents a comprehensive study on the analysis of neuromuscular signal activities to recognize eleven facial expressions for Muscle Computer Interfacing applications. A robust denoising protocol comprised of Wavelet transform and Kalman filtering is proposed to enhance the electromyogram (EMG) signal-to-noise ratio and improve classification performance. The effectiveness of eight different time-domain facial EMG features on system performance is examined and compared in order to identify the most discriminative one. Fourteen pattern recognition-based algorithms are employed to classify the extracted features. These classifiers are evaluated in terms of classification accuracy and processing time. Finally, the best methods that obtain almost identical system performance are compared through the Normalized Mutual Information (NMI) criterion and a repeated measure analysis of variance (ANOVA) for a statistical significant test.To clarify the impact of signal denoising, all considered EMG features and classifiers are assessed with and without this stage. Results show that: (1) the proposed denosing step significantly improves the system performance; (2) Root Mean Square is the most discriminative facial EMG feature; (3) discriminant analysis when the parameters are estimated by the Maximum Likelihood algorithm achieves the highest classification accuracy and NMI; however, ANOVA reveals no significant difference among the best methods with almost similar performance.

Objective: This paper considers challenges in developing algorithms for accurate segmentation and classification of heart sound (HS) signals. Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure. The identified boundaries are then utilized for automated classification of pathological HS using the continuous density hidden Markov model (CD-HMM). The MSAR formulated in a state-space form is able to capture simultaneously both the continuous hidden dynamics in HS, and the regime switching in the dynamics using a discrete Markov chain. This overcomes the limitation of HMM which uses a single-layer of discrete states. We introduce three schemes for model estimation: (1.) switching Kalman filter (SKF); (2.) refined SKF; (3.) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results: The proposed methods are evaluated on Physionet/CinC Challenge 2016 database. The SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%. The use of CD-HMM as a classifier and Mel-frequency cepstral coefficients (MFCCs) as features can characterize not only the normal and abnormal morphologies of HS signals but also morphologies considered as unclassifiable (denoted as X-Factor). It gives classification rates with best gross F 1 score of 90.19 (without X-Factor) and 82.7 (with X-Factor) for abnormal beats. Conclusion: The proposed MSAR approach for automatic localization and detection of pathological HS shows a noticeable performance on large HS dataset. Significance: It has potential applications in heart monitoring systems to assist cardiologists for pre-screening of heart pathologies.

No abstract

Recent studies on analyzing dynamic brain connectivity rely on sliding-window analysis or timevarying coefficient models which are unable to capture both smooth and abrupt changes simultaneously. Emerging evidence suggests state-related changes in brain connectivity where dependence structure alternates between a finite number of latent states or regimes. Another challenge is inference of full-brain networks with large number of nodes. We employ a Markov-switching dynamic factor model in which the state-driven time-varying connectivity regimes of high-dimensional fMRI data are characterized by lower-dimensional common latent factors, following a regime-switching process. It enables a reliable, data-adaptive estimation of change-points of connectivity regimes and the massive dependencies associated with each regime. We consider the switching VAR to quantity the dynamic effective connectivity. We propose a three-step estimation procedure: (1) extracting the factors using principal component analysis (PCA) and (2) identifying dynamic connectivity states using the factor-based switching vector autoregressive (VAR) models in a state-space formulation using Kalman filter and expectationmaximization (EM) algorithm, and (3) constructing the high-dimensional connectivity metrics for each state based on subspace estimates. Simulation results show that our proposed estimator outperforms the K-means clustering of time-windowed coefficients, providing more accurate estimation of regime dynamics and connectivity metrics in high-dimensional settings. Applications to analyzing restingstate fMRI data identify dynamic changes in brain states during rest, and reveal distinct directed connectivity patterns and modular organization in resting-state networks across different states.

No abstract