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 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: Techniques for heart rate estimation are disclosed. In an embodiment, synchronized photoplethysmograph (PPG) and 3-axis acceleration signals are received. Further, the PPG and acceleration signals are partitioned into windows. Furthermore, it is determined whether motion is present in a window of the acceleration signal. Moreover, Fourier transform is performed on the signals to obtain power spectra of the signals in the window when there is motion. Also, it is determined whether a peak of the acceleration signal is present in a range around first highest PPG peak. Further, it is determined whether the peak of the acceleration signal affects heart rate of the user when the peak of the acceleration signal is in the range around the highest PPG peak. The heart rate of the user in the window is then estimated using second highest PPG peak when the peak of the acceleration signal affects heart rate of the user.

Abstract: Traditional electrocardiography (ECG) and photo-plethysmography (PPG) based HR estimation require human skin contact which is not only user uncomfortable, but also infeasible when multiple user monitoring is required or extreme sensitive conditions is a prime concern as in the case of monitoring neonates, sleeping human and skin damaged patients. Temporal signals depicting the motion or color variations in the frames across time, are estimated from a Region of Interest using Eulerian or Lagrangian approaches. However, the Eulerian approach fails under improper illumination, inappropriate camera focus or human factors like skin color. Likewise, Lagrangian approach is highly time-consuming and may fail when few or less discriminatory features are available for tracking. The present disclosure provides a poorness measure that is indicative of when an approach fails and facilitates serial fusion of the two approaches. Switching to an appropriate approach results in accurate heart rate estimation.

Abstract: Systems and methods of the present disclosure enable exchange of semantic knowledge of resource data and task data between heterogeneous resources in a constrained environment wherein cloud infrastructure and cloud based knowledge repository is not available. Ontology based semantic knowledge exchange firstly enables discovery of available resources in real time. New tasks may evolve at runtime and so also resource data associated with the resources may vary over time. Systems and methods of the present disclosure effectively address these dynamic logistics in a constrained environment involving heterogeneous resources. Furthermore, based on the required resource data for each task and the available resources discovered in real time, task allocation can be effectively handled.

Abstract: The present invention provides a method and system for broadcast of additional content such as metadata required for client specific interactive application in an analog domain along with conventional audio, video and PSI or SI data. The present invention enables transmission of encoded audio data or EPG data, timestamp information required for audio video synchronization referred to as metadata by embedding such metadata in the pixels of video pixels and then encoding by the standard video encoder to generate an encoded stream. The encoded stream is decoded using the standard video decoder at the receiving station to generate a Composite Video Blanking and Sync (CVBS) analog video signal. From the CVBS signal, the RGB or YUV pixels of the videos are extracted. Finally a data extractor module retrieves the embedded metadata from the RGB or YUV pixels.

Abstract: A system and method for real time estimation of heart rate (HR) from one or more face videos acquired in non-invasive manner. The system receives face videos and obtains several blocks as ROI consisting of facial skin areas. Subsequently, the temporal fragments are extracted from the blocks and filtered to minimize the noise. In the next stage, several temporal fragments are extracted from the video. The several temporal fragments, corrupted by noise are determined using an image processing range filter and pruned for further processing. The HR of each temporal fragment, referred as local HR is estimated along with its quality. Eventually, a quality based fusion is applied to estimate a global HR corresponding to the received face videos. In addition, the disclosure herein is also applicable for frontal, profile and multiple faces and performs in real-time.

Abstract: A system and method for dynamically establishing an adhoc network amongst plurality of communication devices in a beyond audible frequency range is disclosed. The system comprises a first communication device to transmit a quantity of data to a second communication device. The first communication device comprises of an input capturing module to receive the quantity of data from a broadcaster in a format and converts the quantity of data received into a quantity of modulated data, an identity generating module to generate a temporary identity for a broadcasting user. The second communication device then receives the data broadcasted from the first communication device and determines a probabilistic confidence level of the quantity of modulated data. A transreceiver implemented in the first communication device and second communication device transmits and receives the quantity of data in conjugation with the temporary identity within a predefined proximity of each device.

Abstract: A system is provided for automated monitoring the health of a patient. The system is unifying the approach of multi-sensing, robotic platform and cloud computing to monitor the health of the patient with zero or very minimal human intervention. The plurality of physiological parameters and the pathological values is sensed using the plurality of physiological sensors and the plurality of pathological sensors or using a smart phone of the patient. The body of the patient is scanned using a robotic arm. The data sensed by the sensor is then identifies a set of anomalies and send the set of anomalies to cloud server. A cognitive engine present on the cloud server is then diagnoses a disease using cloud computing and send the report to caregiver and doctor. According to another embodiment, a method is also provided for automated monitoring the health of the person using the above mentioned system.

Abstract: A method and system for blood pressure (BP) estimation of a person is provided. The system is estimating pulse transit time (PTT) using the ECG signal and PPG signal of the person. A plurality of features are extracted from the PPG. The plurality of PPG features and the PTT are provided as inputs to an automated feature selection algorithm. This algorithm selects a set of features suitable for BP estimation. The selected features are fed to a classifier to classify the database into low/normal BP range and a high BP range. The correctly classified normal BP data are then used to create a regression model to predict BP from the selected features. The current methodology uses automated feature selection mechanism and also employs a block to reject extreme BP data. Thus the available accuracy in predicting BP is expected to be more than the existing BP estimation methods.

Abstract: A method and system for detection of coronary artery disease (CAD) in a person using a fusion approach has been described. The invention the detection of CAD in the person by capturing of a plurality of physiological signals such as phonocardiogram (PCG), photoplethysmograph (PPG), ECG, galvanic skin response (GSR) etc. from the person. A plurality of features are extracted from the physiological signals. The person is then classified as CAD or normal using the each of the features independently. The classification is done based on supervised machine learning technique. The output of the classification is then fused and used for the detection of the CAD in the person using a predefined criteria.

Abstract: A pulmonary health monitoring system aims at assessing pulmonary health of subjects. Conventional techniques used for pulmonary health monitoring are not convenient to the subjects and needs considerable cooperation from the subjects. But, there is a challenge in utilizing the conventional devices to the subjects not capable of providing considerable cooperation. The present disclosure includes a blow device applicable to all kind of subjects and doesn't need cooperation from the subjects. Further, in the present disclosure, the blow device generates a phase shifted signal corresponding to a breathe signal and the phase shifted signal is further processed to extract a set of physiological features. Further, pulmonary health of a subject is analyzed by processing the set of physiological features based on a ridge regression based machine learning technique.

Abstract: Disclosed is a method and system for identifying a sensor to be deployed in a physical environment. The method may comprise storing sensor data and metadata of the plurality of sensors in a data store. Further, the method may comprise deriving sensor information comprising at least one of thematic information, temporal information, and spatial information. The method may further comprise creating sensor ontology to define a relationship between the sensor data, the metadata, and the sensor information. The sensor ontology may be stored in a knowledge repository of the data store. The method may further comprise receiving and decomposing the search query into at least one of a basic query component and an inferred query component. Finally, the method may comprise executing the basic query component or the inferred query component on the data store and the knowledge repository respectively in order to identify the sensor.

Abstract: A system(s) and method(s) for secure session establishment and secure encrypted exchange of data is disclosed. The system satisfies authentication requirement of general networking/communication systems. It provides an easy integration with systems already using schemes like DTLS-PSK. The system follows a cross layer approach in which session establishment is performed in a lightweight higher layer like the application layer. The system then passes resultant parameters of such session establishment including the session keys to a lower layer. The lower layer like the transport layer is then used by the system to perform channel encryption to allow exchange of encrypted data based on a cross layer approach, over a secure session. As the exchange of data becomes the responsibility of the lower layer like the transport layer, the data is protected from replay attacks since the transport layer record encryption mechanism provides that kind of protection.

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: This disclosure relates generally to physiological monitoring, and more particularly to feature set optimization for classification of physiological signal. In one embodiment, a method for physiological monitoring includes identifying clean physiological signal training set from an input physiological signal based on a Dynamic Time Warping (DTW) of segments associated with the physiological signal. An optimal features set is extracted from a clean physiological signal training set based on a Maximum Consistency and Maximum Dominance (MCMD) property associated with the optimal feature set that strictly optimizes on the objective function, the conditional likelihood maximization over different selection criteria such that diverse properties of different selection parameters are captured and achieves Pareto-optimality. The input physiological signal is classified into normal signal components and abnormal signal components using the optimal features set.

Abstract: A computing platform for intelligent development, deployment and management of vehicle telemetry applications is disclosed herein. Further, the present disclosure provides a method and system that enables provision of Intelligent Transportation Service on the Cloud-based Platform that facilitates creation and deployment of vehicle telemetry applications configured for enabling traffic measurements, traffic shaping, vehicle surveillance and other vehicle related services.

Abstract: An acoustic array system for anomaly detection is provided. The acoustic array system (100) performs a scan (or a progressive scan of frequencies) of a given volume by transmitting one or more signals, and receives one or more reflected signals from objects within the volume. The reflected signals are then amplified and converted to a set of digital signals. Features of the set of digital signals are extracted both in time and frequency domains. The acoustic array system (100) further performs a comparison of these set of digital extracted features with the reflected signals via machine learning techniques. Based on the comparison, the acoustic array system detects one or more anomalies.

Abstract: A method and system has been provided for recommending features for developing an IoT analytics application. The method follows a deep like architecture. It comprises of three distinct layers. First layer is for input signal processing and other two layers are for feature reduction. The time domain, frequency domain and time-frequency domain features are extracted from the input signal. The invention uses multiple feature selection methods so that the union of the recommended features by these feature selection methods is significantly lesser than the initial set of features. The best feature combination is recommended using an exhaustive search.

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.