Abstract:
Electrocardiography (ECG) signals contain important markers for Coronary Heart Disease (CHD). State of the art systems and methods rely on clinically available multi-lead ECG for CHD classification which is not cost effective. Moreover the state of the art methods are applied on digital ECG time series data only. Also, discriminative HRV markers are not often present in short ECG recordings necessitating long hours of ECG data to analyze. In accordance with the present disclosure, systems and methods described hereinafter extract ECG time series from ECG images obtained from commercially available low-cost single lead ECG devices through a combination of image and signal processing steps including Histogram analysis, Morphological operation-thinning, Extraction of lines, Extraction of Reference Pulse, Extraction of ECG and interpolating missing data. Further, domain independent statistical features such as self-similarity of raw ECG time series and average Maharaj's distance along with domain specific features are used for classifying CHD.
Abstract:
A method and system for removing corruption in photoplethysmogram (PPG) signals for monitoring cardiac health of patients is provided. The method is performed by extracting photoplethysmogram signals from the patient, detecting and eliminating corruption caused by larger and transient disturbances in the extracted photoplethysmogram signals, segmenting photoplethysmogram signals post detection and elimination of corruption caused by larger and transient disturbances, identifying of inconsistent segments from the segmented photoplethysmogram signals, detecting anomalies from the identified inconsistent segments of the photoplethysmogram signals, analysing the detected anomalies of the photoplethysmogram signals and identifying photoplethysmogram signal segments corrupted by smaller and prolonged disturbances.
Abstract:
In many real-life applications, ample amount of examples from one class are present while examples from other classes are rare for training and learning purposes leading to class imbalance problem and misclassification. Methods and systems of the present disclosure facilitate generation of an extended synthetic rare class super dataset that is further pruned to obtain a synthetic rare class dataset by maximizing similarity and diversity in the synthetic rare class dataset while preserving morphological identity with labeled rare class training dataset. Oversampling methods used in the art result in cloning of datasets and do not provide the needed diversity. The methods of the present disclosure can be applied to classification of noisy phonocardiogram (PCG) signals among other applications.
Abstract:
This disclosure relates generally to biomedical signal processing, and more particularly to method and system for physiological parameter derivation from pulsating signals with reduced error. In this method, pulsating signals are extracted, spurious perturbations in the extracted pulsating signals are removed for smoothening, local minima points in the smoothened pulsating signal are derived, systolic maxima point between two derived local minima are derived, most probable pulse duration and most probable peak-to-peak distance are derived, dicrotic minima is removed while ensuring that every dicrotic minima is preceded by a systolic maxima point and followed by a beat start point of said systolic maxima, diastolic peak is derived while ensuring that every dicrotic maxima is preceded by a diastolic notch followed by next beat start point of that maxima, and physiological parameters are derived from the derived local minima points, systolic maxima points, dicrotic notch and diastolic peak.
Abstract:
Traditionally known classification methods of non-stationary physiological audio signals as noisy and clean involve human intervention, may involve dependency on particular type of classifier and further analyses is carried out on classified clean signals. However, in non-stationary audio signals a major portion may end up being classified as noisy and hence may get rejected which may cause missing of intelligence which could have been derived from lightly noisy audio signals that may be critical. The present disclosure enables automation of classification based on auto-thresholding and statistical isolation wherein noisy signals are further classified as highly noisy and lightly noisy through continuous dynamic learning.
Abstract:
The present invention provides a system and method for aggregating and estimating the bandwidth of the multiple network interfaces. Particularly, the invention provides a cross layer system for bandwidth aggregation based on dynamic analysis of network conditions. Further, the invention provides a system and method of estimation for evaluating bandwidth of multiple physical interfaces.
Abstract:
A system and method for dynamic selection of reliability by data publishing protocol while publishing data, comprising a constrained gateway device (102) being adapted to publish data by using a data publisher and adapted to send and receive acknowledgment messages, one or more subscriber devices (104) communicatively coupled with the constrained gateway device (102) and subscribed to the server (106) and adapted to send and receive acknowledgment messages, and a server (106) communicatively coupled with the constrained gateway device (102) and the one or more subscriber devices (104) and adapted to exchange the acknowledgement messages between the data publisher on the constrained gateway device (102) and the one or more subscriber devices (104) wherein the data publisher running on the constrained gateway device (102) has multiple reliability levels for publishing data and is adapted to dynamically select the reliability level based on available bandwidth and energy.
Abstract:
A system and method for dynamic selection of reliability by data publishing protocol while publishing data, comprising a constrained gateway device (102) being adapted to publish data by using a data publisher and adapted to send and receive acknowledgment messages, one or more subscriber devices (104) communicatively coupled with the constrained gateway device (102) and subscribed to the server (106) and adapted to send and receive acknowledgment messages, and a server (106) communicatively coupled with the constrained gateway device (102) and the one or more subscriber devices (104) and adapted to exchange the acknowledgement messages between the data publisher on the constrained gateway device (102) and the one or more subscriber devices (104) wherein the data publisher running on the constrained gateway device (102) has multiple reliability levels for publishing data and is adapted to dynamically select the reliability level based on available bandwidth and energy.
Abstract:
A system and method for resource utilization in a constrained sensor gateway for transfer of data in terms of the bandwidth and energy available to transfer data. The system includes a processor in communication with the constrained sensor gateway, which includes an application layer protocol and which is in communication with a communication network, and a memory coupled to the processor. The memory includes a network condition detection module configured to detect a network condition of the constrained sensor gateway, and an adaption module configured to determine a reliability score. The application layer protocol of the constrained sensor gateway adapts a reliability level based on the reliability score determined by the adaption module, which enables better utilization of the bandwidth and energy to transfer data. The reliability level may pertain to a reliable mode, or a non-reliable mode of communication for transferring data.