Abstract: This disclosure relates generally to method and system for monitoring human parameters using hierarchical human activity sensing. The method is based on sensing as service (SEAS) model which processes continuous mobility data from multiple sensors on the client edge-device by optimizing the on-device processing pipelines. The method requests a subject to select a human parameter of the human body to be monitored using a master device and capture the plurality of signals by recognizing sensors corresponding to the health parameter. The master device transmits to the server the subject selected human parameter of the human body to be monitored and requesting the server to recommend a hierarchical classifier structure. Further, the human body is monitored based on the on-device hierarchical sensing pipeline by executing a plurality of algorithms. In addition, the system is suitable for remote monitoring and flexible edge cloud arbitration, optimizing costs, infrastructure, and energy.

Abstract: Systems and methods for modelling prediction errors in path-learning of an autonomous learning agent are provided. The traditional systems and methods provide for machine learning techniques, wherein estimation of errors in prediction is reduced with an increase in the number of path-iterations of the autonomous learning agent. Embodiments of the present disclosure provide for a two-stage modelling technique to model the prediction errors in the path-learning of the autonomous learning agent, wherein the two-stage modelling technique comprises extracting a plurality of fitted error values corresponding to a plurality of predicted actions and actual actions by implementing an Autoregressive moving average (ARMA) technique on a set of prediction error values; and estimating, by implementing a linear regression technique on the plurality of fitted error values, a probable deviation of the autonomous learning agent from each of an actual action amongst a plurality of predicted and actual actions.

Abstract: It is important to monitor the cardiac condition of an individual outside the clinic, using wearable physiological sensors. However, existing methods for calculating the cardiac risk score of an individual are primarily based on static information like individual's metadata, lifestyle, family history, clinical assessment, etc. but do not consider the cardiac state in a daily living scenario using wearable-based measurements. Embodiments herein provide a method and a system for determining post-exercise cardiac score in a recovery period using personalized cardiac model. A clinical decision support system (CDSS) is disclosed to predict cardiac recovery score of a subject in post-exercise conditions. The system employs a hybrid approach using a computational cardiac model and wearable data. Further, several personalized cardiac parameters are simulated using a cardiovascular simulation (CVS) platform.

Abstract: State of the art systems and methods attempting to generate synthetic biosignals such as PPG generate patient specific PPG signatures and do not correlate with pathophysiological changes. Embodiments herein provide a method and system for generating synthetic time domain signals to build a classifier. The synthetic signals are generated using statistical explosion. Initially, a parent dataset of actual sample data of class and non-class subjects is identified, and statistical features are extracted. Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class.

Abstract: Improvement in the accuracy of disease diagnosis associated with cardiac abnormalities is an open research area. Appropriate feature selection to capture the underlying signs of a disease is critical in Machine Learning (ML) based approaches. A method and system for, determining cardiac abnormalities using chaos-based classification model from multi-lead ECG signals, is disclosed. The method combines the commonly used chaos parameter with other set of chaos-related statistical parameters like non-linearity, self-similarity, Chebyshev distance and spectral flatness for a holistic approach to the study of cardiac abnormalities. The method disclosed thus attempts to use above ML based measures for disease classification. The set of chaos-related features used herein contribute to improving the accuracy of detection of various cardiac diseases arising due to cardiac abnormalities such as Atrial Fibrillation (AF) and the like.

Abstract: This disclosure relates generally to method and system for estimating smoking episodes from smoke puffs using a wearable device. Since the expense of treating diseases is rising, a digital smoking cessation improves healthcare systems such as cardiovascular issues. To achieve an optimum model given the platform limitations a very compact model is built specifically for the target microcontroller platform. The method of the present disclosure generates an optimum model for deployment on the wearable device using a pretrained deep neural network (DNN). A set of sensor signals are inputted to a convolutional neural network (CNN) smoke detection model to detect smoke puffs. Gesture classifier determines whether the user of the wearable device is engaged/engaging in a smoking session. Further, the method provides users of the wearable device with a cloud estimated smoking behavior analysis based on a set of smoking episodes to generate a set of user risk scores.

Abstract: Research work in the literature on imputation of mobility data for missing records of a subject's location trajectory has been specifically revolved around usage of historical data. Thus, performances drop when missing records or imputation mobility data for unknown subject with very little or no historical data has to be predicted. A method and system for training an ensemble classifier for imputation of mobility data of unknown subject based on cohort of the unknown subject is disclosed. The method and system disclosed herein exploits the knowledge that semantic trajectories of different individuals has considerable similarity when individuals belong to the same cohort. This concept is used by the method to predict the behavior of all the individuals in a cohort using ensemble classifier, also referred to as imputation model, trained on the semantic location data of a fraction of total individuals in the cohort with a certain accuracy.

Abstract: Existing systems for behavioural tracking and identification have the disadvantage that they do not analyse data in behavioural aspects. As a result, they lack ability to pre-empt scenarios involving actions that adversely affect user health. The disclosure herein generally relates to behavior prediction, and, more particularly, to a method and system for identifying unhealthy behavior trigger and providing nudges. The system generates a casual inference model, which is a reverse causality model facilitating mapping of context with one or more behaviour of the user. The system further collects and processes real-time data using the casual inference model, to perform behavioral analysis of the user.

Abstract: This disclosure relates generally to methods and systems for unobtrusive digital health assessment of high risk subjects, wherein bio-markers pertaining to a disease are identified automatically using physical activity and physiology monitoring on a continuous basis. Identification of bio-markers in the medical domain is conventionally dependent on insights derived from medical tests which are obtrusive in nature. Systems and methods of the present disclosure integrate physical characteristics, lifestyle habits and prevailing medical conditions with monitored physical activities and physiological measurements to assess health of high risk subjects. Systems and methods of the present disclosure also enable automatic generation of control class and treatment class that may be effectively used for health assessment.

Abstract: This disclosure relates generally to categorical time-series clustering. In an embodiment, the method for categorical time-series clustering for categorical time-series associated with distinct subjects obtained from sensors. Based on the categorical time-series, the subjects are clustered into clusters by using a Markov chain model. Clustering the subjects include assigning each subject to a cluster. The subjects are assigned to the clusters by determining cluster-specific transition matrices based on a transitional probability of the subject's transitioning between states. A semi-distance function is constructed for each cluster-specific transitional matrix between the states at multiple time instances, which us indicative of a conditional probability of movement of the subject between the states at different time instance.

Abstract: This disclosure relates generally to a unified platform for domain adaptable human behaviour inference. The platform provides a unified, low level inference and high level inference of domain adaptable human behaviour inference. The low level inferences include cross-sectional analysis techniques to infer location, activity, physiology. Further the high inference that provide useful and actionable for longitudinal tracking, prediction and anomaly detection is performed based on several longitudinal analysis techniques that include welch analysis, cross-spectrum analysis, Feature of interest (FOI) identification and time-series clustering, autocorrelation-based distance estimation and exponential smoothing, seasonal and non-seasonal models identification, ARIMA modelling, Hidden Markov models, Long short term memory (LSTM) along with low level inference, human meta-data and application domain knowledge.

Abstract: This disclosure relates generally to patient invariant model for freezing of gait detection based on empirical wavelet decomposition. The method receives a motion data from an accelerometer sensor coupled to an ankle of a subject. The motion data is further processed to denoise a plurality of data windows using a peak detection technique to classify into a real motion data window or a noisy data window. Further, a plurality of denoised data windows are generated by processing spectrums associated with each real motion data window and a plurality of empirical modes using an empirical wavelet decomposition technique (EWT). Then, a resultant acceleration is computed, and a plurality of features are extracted from the denoised data window which enables detection of freezing of gait based on a pretrained classifier model into a (i) a positive class, or (ii) a negative class.

Abstract: The disclosure relates to digital twin of cardiovascular system called as cardiovascular model to generate synthetic Photoplethysmogram (PPG) signal pertaining to disease conditions. The conventional methods are stochastic model capable of generating statistically equivalent PPG signals by utilizing shape parameterization and a nonstationary model of PPG signal time evolution. But these technique generates only patient specific PPG signatures and do not correlate with pathophysiological changes. Further, these techniques like most synthetic data generation techniques lack interpretability. The cardiovascular model of the present disclosure is configured to generate the plurality of synthetic PPG signals corresponding to the plurality of disease conditions. The plurality of synthetic PPG signals can be used to tune Machine Learning algorithms. Further, the plurality of synthetic PPG signals can be utilized to understand, analyze and classify cardiovascular disease progression.

Abstract: Non-invasive methods for accurately classifying Coronary Artery Disease (CAD) is a challenging task. In the present disclosure, a two stage classification is performed. In the first stage of classification, a metadata based rule engine is utilized to classify a subject into one of a confirmed CAD subject, a CAD subject and a non-CAD subject. Here, a set of optimal parameters are selected from a set of metadata associated with the subject based on a difference in frequency of occurrence of the CAD among a disease population and a non-disease population. Further, an optimal threshold associated with each optimal parameter is calculated based on an inflexion based correlation analysis. Further, the CAD subject, classified by the metadata based rule engine is further reclassified in a second stage by utilizing a set of cardiovascular signal into one of the CAD subject and the non-CAD subject.

Abstract: State of the art systems and methods attempting to generate synthetic biosignals such as PPG generate patient specific PPG signatures and do not correlate with pathophysiological changes. Embodiments herein provide a method and system for generating synthetic time domain signals to build a classifier. The synthetic signals are generated using statistical explosion. Initially, a parent dataset of actual sample data of class and non-class subjects is identified, and statistical features are extracted. Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class.

Abstract: According to embodiments illustrated herein, there is provided a system for predicting a health condition of a patient. The system further includes one or more processors configured to separately cluster data points from a set of medical records associated with a first class of patients and a second class of patients. A similarity value of each of the clustered data points with respect to a pre-selected subset of data points that represents landmark points may be determined, using a parameterized similarity measure. One or more classifiers are trained using the determined similarity value of each data point. The trained one or more classifiers are adapted to learn one or more parameters of the parameterized similarity measure during the training. An occurrence of the health condition of the patient may be predicted based on the trained one or more classifiers and one or more medical records of the patient.

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.

Abstract: A method, non-transitory computer readable medium and apparatus for predicting mortality of a current patient are disclosed. For example, the method includes receiving data associated with a plurality of different patients with known mortality outcomes, wherein the data includes a subset of data for each one of a plurality of different measurement timepoints for each one of the plurality of different patients, calculating n number of classifiers, wherein n is equal to a number of the plurality of different measurement timepoints, receiving data associated with the current patient at an i-th measurement timepoint, predicting the current patient has a high mortality risk based on an output of the i-th classifier of the n number of classifiers and transmitting a signal to a health administration server to cause an alarm to be generated in response to the high mortality risk that is predicted.

Abstract: Identification of pulmonary diseases involves accurate auscultation as well as elaborate and expensive pulmonary function tests. Also, there is a dependency on a reference signal from a flowmeter or need for labelled respiratory phases. The present disclosure provides extraction of frequency and time-frequency domain lung sound features such as spectral and spectrogram features respectively that enable classification of healthy and abnormal lung sounds without the dependencies of prior art. Furthermore extraction of wavelet and cepstral features improves accuracy of classification. The lung sound signals are pre-processed prior to feature extraction to eliminate heart sounds and reduce computational requirements while ensuring that information providing adequate discrimination between healthy and abnormal lung sounds is not lost.

Abstract: This disclosure relates generally to categorical time-series clustering. In an embodiment, the method for categorical time-series clustering for categorical time-series associated with distinct subjects obtained from sensors. Based on the categorical time-series, the subjects are clustered into clusters by using a Markov chain model. Clustering the subjects include assigning each subject to a cluster. The subjects are assigned to the clusters by determining cluster-specific transition matrices based on a transitional probability of the subject's transitioning between states. A semi-distance function is constructed for each cluster-specific transitional matrix between the states at multiple time instances, which us indicative of a conditional probability of movement of the subject between the states at different time instance.