Abstract: Conventional systems and methods of classifying heart signals include segmenting them which can fail due to the presence of noise, artifacts and other sounds including third heart sound ‘S3’, fourth heart sound ‘S4’, and murmur. Heart sounds are inherently prone to interfering noise (ambient, speech, etc.) and motion artifact, which can overlap time location and frequency spectra of murmur in heart sound. Embodiments of the present disclosure provide parallel implementation of Deep Neural Networks (DNN) for classifying heart sound signals (HSS) wherein spatial (presence of different frequencies component) filters from Spectrogram feature(s) of the HSS are learnt by a first DNN while time-varying component of the signals from MFCC features of the HSS are learnt by a second DNN for classifying the heart sound signal as one of normal sound signal or murmur sound signal.

Abstract: Monitoring the quality of sleep of an individual is essential for ensuring one's overall well-being. The existing methods for non-apnea sleep arousal detection are manual. A system and method for the non-apnea sleep arousal detection has been provided. The method uses a feature engineering based binary classification approach for distinguishing non-apnea arousal and non-arousal. A training data set is prepared using a plurality of physiological signals. A plurality of features are derived from the training data set. Out of those only a set of features are selected for training a plurality of random forest classifier models. A test sample is then provided to the plurality of random forest classifier models in the instances of fixed duration. This results in generation of prediction probabilities for each instances. The prediction probabilities are then used to predict the probabilities of non-apnea sleep arousal in the test sample.

Abstract: Monitoring the quality of sleep of an individual is essential for ensuring one's overall well-being. The existing methods for non-apnea sleep arousal detection are manual. A system and method for the non-apnea sleep arousal detection has been provided. The method uses a feature engineering based binary classification approach for distinguishing non-apnea arousal and non-arousal. A training data set is prepared using a plurality of physiological signals. A plurality of features are derived from the training data set. Out of those only a set of features are selected for training a plurality of random forest classifier models. A test sample is then provided to the plurality of random forest classifier models in the instances of fixed duration. This results in generation of prediction probabilities for each instances. The prediction probabilities are then used to predict the probabilities of non-apnea sleep arousal in the test sample.

Abstract: This disclosure relates generally to PPG signal quality assessment, and more particularly to, a system and method for sensor agnostic PPG signal quality assessment using morphological analysis. In one embodiment, a method for PPG signal quality assessment includes obtaining a PPG signal captured using a testing device in real-time, and segmenting into a first plurality of PPG signal samples such that length of each of the first plurality of PPG signal samples more than a threshold length. A signal sufficiency check (SSC) is performed for each first PPG signal sample to obtain at least a first set of PPG signal samples complying with the SSC. A set of features is extracted from the first set of PPG signal samples, based on which each PPG signal sample is identified as one of a noisy and clean signal sample using a plurality of Random Forest (RF) models created during the training phase.

Abstract: Conventional systems and methods of classifying heart signals include segmenting them which can fail due to the presence of noise, artifacts and other sounds including third heart sound ‘S3’, fourth heart sound ‘S4’, and murmur. Heart sounds are inherently prone to interfering noise (ambient, speech, etc.) and motion artifact, which can overlap time location and frequency spectra of murmur in heart sound. Embodiments of the present disclosure provide parallel implementation of Deep Neural Networks (DNN) for classifying heart sound signals (HSS) wherein spatial (presence of different frequencies component) filters from Spectrogram feature(s) of the HSS are learnt by a first DNN while time-varying component of the signals from MFCC features of the HSS are learnt by a second DNN for classifying the heart sound signal as one of normal sound signal or murmur sound signal.

Abstract: This disclosure relates generally to PPG signal quality assessment, and more particularly to, a system and method for sensor agnostic PPG signal quality assessment using morphological analysis. In one embodiment, a method for PPG signal quality assessment includes obtaining a PPG signal captured using a testing device in real-time, and segmenting into a first plurality of PPG signal samples such that length of each of the first plurality of PPG signal samples more than a threshold length. A signal sufficiency check (SSC) is performed for each first PPG signal sample to obtain at least a first set of PPG signal samples complying with the SSC. A set of features is extracted from the first set of PPG signal samples, based on which each PPG signal sample is identified as one of a noisy and clean signal sample using a plurality of Random Forest (RF) models created during the training phase.

Abstract: A system and a method for mobile sensing data processing are provided. The method includes, receiving one or more requests from one or more applications installed at a client device to obtain a processed sensing data obtained in response to execution of one or more tasks by the application using a set of sensors. Raw data is extracted from the set of sensors in response to the execution of the tasks. A data stream is configured to include sensor data and a task information associated with the tasks. The client device is connected with the server to transmit the data stream. The server outputs the processed sensing data upon processing the data stream and the task information by using one or more task specific models stored at the server. The processed sensing data is received from the server and provided to the applications.

Abstract: A system and a method for mobile sensing data processing are provided. The method includes, receiving one or more requests from one or more applications installed at a client device to obtain a processed sensing data obtained in response to execution of one or more tasks by the application using a set of sensors. Raw data is extracted from the set of sensors in response to the execution of the tasks. A data stream is configured to include sensor data and a task information associated with the tasks. The client device is connected with the server to transmit the data stream. The server outputs the processed sensing data upon processing the data stream and the task information by using one or more task specific models stored at the server. The processed sensing data is received from the server and provided to the applications.