Vivek Nigam

Accessing heart dynamics to estimate durations of heart sounds

Segmentation of the phonocardiogram into its major sound components is the first step in the automated diagnosis of cardiac abnormalities. Almost all of the existing phonocardiogram segmentation algorithms utilize absolute amplitude or frequency characteristics of heart sounds, which vary from one cardiac cycle to the other and across different patients. The objective of this work is to provide an efficient phonocardiogram segmentation technique, under difficult recording situations, by utilizing the underlying complexity of the dynamical system (heart) giving rise to the heart sound. Complexity-based segmentation is invariant to amplitude and frequency variations of the heart sound and yields better time gates for heart sounds.

A dynamic method to estimate the time split between the A2 and P2 components of the S2 heart sound

The time interval between the aortic (A2) and the pulmonary (P2) components of the second heart sound (S2) is an indicator of pulmonary arterial pressure. However, knowledge of the A2 and P2 components of the S2 sound is difficult to obtain due to their temporal overlap and significant spectral similarity. In this work, we aim to extract the A2 and P2 components from the phonocardiogram to estimate the time interval between them. We attain our objective by first isolating the S2 sound from the phonocardiogram by utilizing the mode complexity of the heart. Then, we assume the statistical independence of the A2 and P2 components and extract them from the S2 sound by the application of blind source separation techniques. Once separated, the time interval between the A2 and P2 components is estimated with a time-centroid-based method. Experimental results using simulated data show excellent performance of the proposed algorithm to extract the A2 and the P2 components from the S2 sound and to estimate the time interval between them. Results obtained from real data are also encouraging and show promise for utilizing the proposed method in a clinical setting to non-invasively tract pulmonary hypertension.

Simplicity based gating of heart sounds

Segmentation of the phonocardiogram (PCG) into its major sound components is the first step in automated diagnosis of cardiac abnormalities. Almost all the existing PCG segmentation algorithms are based upon amplitude or frequency characteristics, of the heart sounds, that vary from one cardiac cycle to the other and across different patients. The objective of this work is to provide an efficient PCG segmentation technique, under difficult recording situations, by utilizing the underlying complexity of the dynamical system (heart) giving rise to the heart sound. Complexity based segmentation is invariant to amplitude and frequency variations of the heart sound and yields better time gates for pathological heart sounds.

Compound noise analysis in digital circuits using blind source separation

In the past decade there have been significant efforts to analyze and solve signal integrity issues in pre-nanometer circuits. However, most of these techniques apply to single noise source, and cannot take into account the evolving reality of multiple noise sources interacting with each other. With the scaling of the technology into nanometer regime, maintaining historical rate of performance and signal integrity have become very challenging due to compound noise effects. Noise measurement made at an evaluation node will reflect the cumulative effect of all the active noise sources, while individual and relative severity of various noise sources will determine what types of remedial steps can be adopted, pressing the need for the development of algorithms that study the cumulative noise effects, and analyze the relative contributions of different noise sources. This paper presents a novel method to analyze the characteristics of compound noise effect in very high performance integrated circuits. The algorithm extracts the time characteristics of individual noise sources from the measured voltage in order to study the contribution of each source separately, by applying the technique of blind source separation, which is based on the assumption that the different sources of noise are statistically independent over time. The estimated noise sources can aid in timing and spectral analysis and yield better design techniques

Fuzzy logic based variable step size algorithm for blind delayed source separation

Convergence of blind delayed source separation algorithms, which use constant learning rates, is known to be slow. We propose a fuzzy logic based approach to adaptively select the learning rates, for estimates of delays and cross-weights, in the blind delayed source separation algorithm. We make use of the state of independence of the separated outputs. We also propose a performance index to measure the convergence of the blind delayed source separation algorithm. Simulation results show the improved performance of the proposed algorithm over the conventional delayed source separation algorithm under stationary as well as non-stationary mixing conditions.

Online non-invasive fetal sound analysis

A method is presented to non-invasively separate the fetal phonocardiograms (FPCG) of the fetuses in a multiple fetus pregnancy. The method uses a device like a stethoscope. We assume that the phonocardiograms of the fetuses are statistically independent. Results of simulations are included in the paper.

A Snore Extraction Method from Mixed Sound for a Mobile Snore Recorder

This paper presents a snore recorder that can separate snores from their delayed mixtures. This is useful to study the snore sounds of individuals when these sounds occur in a normal in-home sleeping environment, where two people are sleeping together and both produce sounds. Based on methods for blind source separation, we give a snore separator that solves the blind delayed source separation problem and provide a performance index to monitor its convergence. The separated snores can be analyzed to detect symptoms of sleep apnea prior to polysomnography or as a monitoring device after polysomnography has been performed. Experimental results show good performance of the snore separator.

Compound noise separation in digital circuits using blind source separation

Analysis of individual noise sources in pre-nanometer circuits cannot take into account the evolving reality of multiple noise sources interacting with each other. Noise measurement made at an evaluation node will reflect the cumulative effect of all the active noise sources, while individual and relative severity of various noise sources will determine what types of remedial steps can be taken, pressing the need for development of algorithms that can analyze the contributions of different noise sources when a noise measurement is available. This paper addresses the cocktail-party problem inside integrated circuits with multiple noise sources. It presents a method to extract the time characteristics of individual noise source from the measured compound voltage in order to study the contribution and properties of each source. This extraction is facilitated by application of blind source separation technique, which is based on the assumption of statistical independence of various noise sources over time. The estimated noise sources can aid in performing timing and spectral analysis, and yield better circuit design techniques.

Generalized Blind Delayed Source Separation Model for Online Non-invasive Twin-fetal Sound Separation: A Phantom Study

The fetal phonocardiogram, which is the acoustic recording of mechanical activity of the fetal heart, facilitates the measurement of the instantaneous fetal heart rate, beat-to-beat differences and duration of systolic and diastolic phases. These measures are sensitive indicators of cardiac function, reflecting fetal well-being. This paper provides an algorithm to non-invasively estimate the phonocardiogram of an individual fetus in a multiple fetus pregnancy. A mixture of fetal phonocardiograms is modeled by a generalized pure delayed mixing model. Mutual independence of fetal phonocardiograms is assumed to apply blind source separation based techniques to extract the fetal phonocardiograms from their mixtures. The performance of the algorithm is verified through simulation results and on experimental data obtained from a phantom that is used to simulate a twin pregnancy.

Separation of Individual Noise Sources from Compound Noise Measurements in Digital Circuits

Analysis of individual noise sources in pre-nanometer circuits cannot take into account the evolving reality of multiple noise sources interacting with each other. Noise measurement made at an evaluation node will reflect the cumulative effect of all the active noise sources, while individual and relative severity of various noise sources will determine what types of remedial steps can be taken, pressing the need for development of algorithms that can analyze the contributions of different noise sources when a noise measurement is available. This paper presents a method to extract the time characteristics of individual noise sources from the measured voltage in order to study the contribution of each source separately, by applying the technique of blind source separation, which is based on the assumption that the different sources of noise are statistically independent over time. The estimated noise sources can aid in timing and spectral analysis and yield better design techniques