Atrial fibrillation (AF) is a frequently encountered cardiac arrhythmia characterized by rapid and irregular atrial activity, which increases the risk of strokes, heart failure and other heart-related complications. The mechanisms of AF are complicated. Although various mechanisms were proposed in previous research, the precise mechanisms of AF are not clear yet and the optimal therapy for AF patients are still under debated. A higher success rate of AF treatments requires a deeper understanding of the problem of AF and potentially a better screening of the patients. In order to study AF, instead of using human body surface ECGs, we use the epicardial electrograms (EGMs) obtained directly from the epicardial sites of the human atria during open heart surgery. This data is measured using a high-resolution mapping array and exhibits irregular properties during AF. Although different studies have analyzed electrograms in time and frequency domain, there remain many open questions that require alternative and novel tools to investigate AF. Experience in signal processing suggests that incorporating the spatial dimension into the time-frequency analysis on the multi-electrode electrograms may provide improved insights on the atrial activity. However, the electrophysiologcial models for describing spatial propagation are relatively complex and non-linear such that conventional signal processing methods are less suitable for a joint space, time, and frequency domain analysis. It is also difficult to use very detailed electrophysiologcial models to extract tissue parameters related to AF from the high-dimensional data. In this dissertation, we wish to propose a radically different approach to study and analyze the EGMs from a higher abstraction level and from different perspectives to get more understanding of the characteristics of AF. We also aim to develop a simplified electrophysiological model that can capture the spatial structure of the data and propose an efficient method to estimate the tissue parameters, which are helpful to analyze the electropathology of the tissue, e.g., cell activation time or conductivity. In the first part of this study, we put forward a graph-time spectral analysis framework to analyze EGMs during normal heart rhythm and AF with a higher-level model. To capture the frequency content along both time domain and graph domain, we propose the joint graph and short-time Fourier transform, which allows us to evaluate the temporal and spatial variation of EGMs and capture the interaction between space and time. The spectral analysis of the EGMs helps us to recognize atrial fibrillation impact on the atrial activity and identify the differences between the atrial activity and the ventricular activity. We find that the difference in graph smoothness between the atrial and ventricular activities enables us to better extract the atrial activity from the noisy measurements. The second part of this study is to find a simplified but accurate enough electrophysiological model for the high dimensional EGMs and to make more efficient use of the data to detect the arrythmogenic substrate that causes abnormalities in atrial tissue. In this dissertation, we develop the cross power spectral density matrix (CPSDM) model of the multi-electrode EGMs and make use of an effective method called confirmatory factor analysis (CFA) to jointly estimate the model parameters. The conductivity, the activation time, and the anisotropy ratio are useful parameters to determine abnormalities in cardiac tissue and are therefore the target parameters to be estimated. With the reasonable assumptions that the conductivity parameters and the anisotropy parameters are constant across different frequencies and heart beats, and the activation time of cells are constant across different frequencies, we propose simultaneous CFA (SCFA) to jointly estimate these parameters using multiple frequencies and multiple heart beats. The identifiability conditions which need to be satisfied in the CFA problem are used to find the relationship between the desired resolution and the required amount of data. Evaluations on the simulated data and the clinical data demonstrate that the proposed method can localize the conduction blocks in the tissue and reconstruct the clinical EGMs well using the estimated parameters. @en

Depression has become one of the most common mental illnesses in the world. For better prediction and diagnosis, methods of automatic depression recognition based on speech signal are constantly proposed and updated, with a transition from the early traditional methods based on hand-crafted features to the application of architectures of deep learning. This paper systematically and precisely outlines the most prominent and up-to-date research of automatic depression recognition by intelligent speech signal processing so far. Furthermore, methods for acoustic feature extraction, algorithms for classification and regression, as well as end to end deep models are investigated and analysed. Finally, general trends are summarised and key unresolved issues are identified to be considered in future studies of automatic speech depression recognition.@en

Mathematical models of the electrophysiology of cardiac tissue play an important role when studying heart rhythm disorders like atrial fibrillation. Model parameters such as conductivity, activation time, and anisotropy ratio are useful parameters to determine the arrhythmogenic substrate that causes abnormalities in the atrial tissue. Existing methods often estimate the model parameters separately and assume some of the parameters to be known as a priori knowledge. In this work, we propose an efficient method to jointly estimate the parameters of interest from the cross power spectral density matrix (CPSDM) model of the electrograms. By applying confirmatory factor analysis (CFA) to the CPSDMs of multi-electrode electrograms, we can make use of the spatial information of the data and analyze the relationship between the desired resolution and the required amount of data. With the reasonable assumptions that the conductivity parameters and the anisotropy parameters are constant across different frequencies and heart beats, we estimate these parameters using multiple frequencies and multiple heart beats simultaneously to easier satisfy the identifiability conditions in the CFA problem. Results on the simulated data show that using multiple heart beats decreases the estimation errors of the conductivity and the estimated activation time parameters. The experimental results on clinical data show that using multiple heart beats for parameter estimation can reduce the reconstruction errors of the clinical electrograms, which further demonstrates the robustness of the proposed method.@en

Impaired electrical conduction has been shown to play an important role in the development of heart rhythm disorders. Being able to determine the conductivity is important to localize the arrhythmogenic substrate that causes abnormalities in atrial tissue. In this work, we present an algorithm to estimate the conductivity from epicardial electrograms (EGMs) using a high-resolution electrode array. With these arrays, it is possible to measure the propagation of the extracellular potential of the cardiac tissue at multiple positions simultaneously. Given this data, it is in principle possible to estimate the tissue conductivity. However, this is an ill-posed problem due to the large number of unknown parameters in the electrophysiological data model. In this paper, we make use of an effective method called confirmatory factor analysis (CFA), which we apply to the cross correlation matrix of the data to estimate the tissue conductivity. CFA comes with identifiability conditions that need to be satisfied to solve the problem, which is, in this case, estimation of the tissue conductivity. These identifiability conditions can be used to find the relationship between the desired resolution and the required amount of data. Numerical experiments on the simulated data demonstrate that the proposed method can localize the conduction blocks in the tissue and can also estimate the smoother variation in the conductivities. The conductivity values estimated from the clinical data are in line with the values reported in literature and the EGMs reconstructed based on the estimated parameters match well with the clinical EGMs.@en

Estimating tissue conductivity parameters from electrograms (EGMs) could be an important tool for diagnosing and treating heart rhythm disorders such as atrial fibrillation (AF). One of these parameters is the fibre direction, often assumed to be known in conductivity estimation methods. In this paper, a novel method to estimate the fibre direction from EGMs is presented. This method is based on local conduction slowness vectors of a propagating activation wave. These conduction slowness vectors follow an elliptical pattern that depends on the underlying conductivity parameters. The fibre direction and conductivity anisotropy ratio can therefore be estimated by fitting an ellipse to the conduction slowness vectors. Applying the presented method on simulated data shows that it can estimate the fibre direction more accurately than existing methods, and that its performance depends mostly on the range of wavefront directions present in the measurement area. The main advantage of the presented method is that it still functions relatively well in the presence of conduction blocks, as long as the surrounding tissue is approximately homogeneous.@en

Atrial fibrillation is a clinical arrhythmia with multifactorial mechanisms still unresolved. Time-frequency analysis of epicardial electrograms has been investigated to study atrial fibrillation. However, deeper understanding can be achieved by incorporating the spatial dimension. Unfortunately, the physical models describing the spatial relations of atrial fibrillation signals are complex and non-linear; hence, conventional signal processing techniques to study electrograms in the joint space, time, and frequency domain are less suitable. In this study, we wish to put forward a radically different approach to analyze atrial fibrillation with a higher-level model. This approach relies on graph signal processing to represent the spatial relations between epicardial electrograms. To capture the frequency content along both the time and graph domain, we propose the joint graph and short-time Fourier transform. The latter allows us to analyze the spatial variability of the electrogram temporal frequencies. With this technique, we found the spatial variation of the atrial electrograms decreases during atrial fibrillation since the high temporal frequencies of the atrial waves reduce. The proposed analysis further confirms that the ventricular activity is smoother over the atrial area compared with the atrial activity. Besides using the proposed graph-time analysis to conduct a first study on atrial fibrillation, we demonstrate its potential by applying it to the cancellation of ventricular activity from the atrial electrograms. Experimental results on simulated and real data further corroborate our findings in this atrial fibrillation study.@en

Atrial fibrillation (AF) is a common cardiac arrhythmia and its mechanisms are not yet fully understood. Analyzing atrial epicardial electrograms (EGMs) is important to understand the mechanisms underlying AF. However, when measuring the atrial activity (AA), the electrogram is commonly distorted by the far-field ventricular activity (VA). During sinus rhythm, the AA and the VA are separated in time. However, the VA often overlaps with the AA in both time and frequency domain during AF, complicating proper analysis of the AA. Unlike traditional methods, this work explores graph signal processing (GSP) tools for AA extraction in EGMs. Since EGMs are time-varying and non-stationary, we put forward the joint graph and short-time Fourier transform to analyze the graph signal along both time and vertices. It is found that the temporal frequency components of the AA and the VA exhibit different levels of spatial variation over the graph in the joint domain. Subsequently, we exploit these findings to propose a novel algorithm for extracting the AA based on graph smoothness. Experimental results on synthetic and real data show that the smoothness analysis of the EGMs over the atrial area enables us to better extract the AA.@en

Atrial fibrillation (AF) is a common cardiac arrhythmia and its mechanisms are not yet fully understood. Analyzing atrial epicardial electrograms (EGMs) is important to understand the mechanisms underlying AF. However, when measuring the atrial activity (AA), the electrogram is commonly distorted by the far-field ventricular activity (VA). During sinus rhythm, the AA and the VA are separated in time. However, the VA often overlaps with the AA in both time and frequency domain during AF, complicating proper analysis of the AA. Unlike traditional methods, this work explores graph signal processing (GSP) tools for AA extraction in EGMs. Since EGMs are time-varying and non-stationary, we put forward the joint graph and short-time Fourier transform to analyze the graph signal along both time and vertices. It is found that the temporal frequency components of the AA and the VA exhibit different levels of spatial variation over the graph in the joint domain. Subsequently, we exploit these findings to propose a novel algorithm for extracting the AA based on graph smoothness. Experimental results on synthetic and real data show that the smoothness analysis of the EGMs over the atrial area enables us to better extract the AA.@en