Abstract: State of art techniques rely of FPGA based approaches when power efficiency is of concern. However, compared to SNN on Neuromorphic hardware, ANN on FPGA requires higher power and longer design cycles to deploy neural network on hardware accelerators. Embodiments of the present disclosure provide a method and system for energy efficient hierarchical multi-stage SNN architecture for classification and segmentation of high-resolution images. Patch-to-patch-class classification approach is used, where the image is divided into smaller patches, and classified at first stage into multiple labels based on percentage coverage of a parameter of interest, for example, cloud coverage in satellite images. The image portion corresponding to the partially covered patches is divided into further smaller size patches, classified by a binary classifier at second level of classification.

Abstract: Embodiments herein provide a method and system for a non-invasive mechanism providing simultaneous determination of viscosity-temperature variation of a lubricant for predicting machine health using a Photo Acoustic (PA) sensing mechanism, Laser-enabled swept frequency acoustic interferometry (LE-SFAI), wherein the lubricant produces acoustic wave only if it absorbs the laser irradiation, thus overcomes the limitation of ultrasound based SFAI through optical absorption based contrast and proper selection of laser excitation wavelength. A PA signal received from the lubricant is processed by a Vector Network Analyzer (VNA), then converted to time domain to obtain normalized first peak that corresponds to the PA signal generated by the lubricant. A squared rise time of the first peak is indicative of viscosity of the liquid and shift in the first peak is indicative of variation of the viscosity as temperature of the lubricant varies.

Abstract: The disclosure herein generally relates to the field of determination of cardiopulmonary signals for multi-persons, and, more particularly, to determination of cardiopulmonary signals for multi-persons using in-body signals obtained by ultra-wide band (UWB) radar. The disclosed method determines of cardiopulmonary signals for multi-persons using in-body signals, wherein a UWB radar signals/waves reflected from inside a human body is utilized for efficient determination of cardiopulmonary signals. The disclosed method and system utilize the UWB radar signals to identify a number of persons along with several details about the persons that include a girth of the each identified person and the orientation of the identified person towards the one or more UWB radar. Further a chest wall distance, a breathing rate, a heart wall distance and a heart rate are determined for all the identified persons based on the identified girth and the identified orientation along with the UWB radar signals.

Abstract: In sensor data analytics, physics-based models generate high quality data. However, these models consume lot of time as they rely on physical simulations. On the other hand, generative learning takes much less time to generate data, and may be prone to error. Present disclosure provides system and method for generation of synthetic machine data for healthy and abnormal condition using hybrid of physics based and generative model-based approach. Finite Element Analysis (FEA) is used for simulating healthy and faulty parts in machinery with set of parameters and pre-condition(s). Small output data from FEA is fed into a generative model for generating synthesized data by learning data distribution knowledge and representing into latent space. Rule engine is built using statistical features wherein realistic bounds serve as faulty data indicators. Synthesized data which does not satisfies features bounds are discarded. Further, AI-based validation framework is used to analyze quality of synthesized data.

Abstract: This disclosure relates generally to a method and a system for computing using a field programmable gate array (FPGA) neuromorphic architecture. Implementing energy efficient Artificial Intelligence (AI) applications at power constrained environment/devices is challenging due to huge energy consumption during both training and inferencing. The disclosure is a FPGA architecture based neuromorphic computing platform, the basic components include a plurality of neurons and memory. The FPGA neuromorphic architecture is parameterized, parallel and modular, thus enabling improved energy/inference and Latency-Throughput. Based on values of the plurality of features of the data set, the FPGA neuromorphic architecture is generated in a modular and parallel fashion. The output of the disclosed FPGA neuromorphic architecture is the plurality of output spikes from the neuron, which becomes the basis of inference for computing.

Abstract: This disclosure generally relates to the field of structural health monitoring, and, more particularly, to a method and system for evaluating residual life of components made of composite materials. Existing methods require performing computational methods such as Finite Element Analysis (FEA) on the results of Non-Destructive Testing (NDT) every time a component is inspected. This makes the process expensive and time-consuming. Thus, embodiments of present disclosure provide a method wherein NDT is performed using different sensing methods such as ultrasound, ultrasound pulse echo, thermography to determine type of defect, location of defect and depth of defect in a test component which are then fed into a pre-trained machine learning model to predict residual life of the component. Testing time is greatly reduced since the pre-trained machine learning model is trained offline using results of the computational methods.

Abstract: Conventional tele-presence robots have their own limitations with respect to task execution, information processing and management. Embodiments of the present disclosure provide a tele-presence robot (TPR) that communicates with a master device associated with a user via an edge device for task execution wherein control command from the master device is parsed for determining instructions set and task type for execution. Based on this determination, the TPR queries for information across storage devices until a response is obtained enough to execute task. The task upon execution is validated with the master device and user. Knowledge acquired, during querying, task execution and validation of the executed task, is dynamically partitioned by the TPR across storage devices namely, on-board memory of the tele-present robot, an edge device, a cloud and a web interface respectively depending upon the task type, operating environment of the tele-presence robot, and other performance affecting parameters.

Abstract: Embodiments herein provide a method and system for continuously validating a user during an established authenticated session using Photoplethysmogram (PPG) and accelerometer data. State of the art approaches are mostly based on feature extraction and ML modelling for PPG based continuous session validation, while a template based approach in the art follows a complicated approach. The method disclosed herein utilizes less computation intensive template based approach to continuously validate the user across the session. The method comprises preprocessing a PPG data or PPG signal acquired from a wearable device worn by the user to identify segments of negligible motion. A first segment, after authentication using conventional authentication mechanism, serves as the initial reference. The chosen segments are then tested one by one with respect to the reference. If the templates in a segment match those of the reference, it is updated as the new reference, else a re-authentication is triggered.

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: Robotic platform for tele-presence applications has gained paramount importance, such as for remote meetings, group discussions, and the like and has sought much attention. There exist some robotic platforms for such tele-presence applications, these lack efficacy in communication and interaction between remote person and avatar robot deployed in another geographic location thus adding network overhead. Embodiments of the present disclosure for edge centric communication protocol for remotely maneuvering tele-presence robot in geographically distributed environment.

Abstract: Conventional hierarchical time-series clustering is highly time consuming process as time-series are characteristically lengthy. Moreover, finding right similarity measure providing best possible hierarchical cluster is critical to derive accurate inferences from the hierarchical clusters. Method and system for Auto Encoded Compact Sequences (AECS) based hierarchical time-series clustering that enables compact latent representation of time-series using an undercomplete multilayered Seq2Seq LSTM auto encoder followed by generating of HCs using multiple similarity measures is disclosed. Further, provided is a mechanism to select the best HC among the multiple HCs on-the-fly, based on an internal clustering performance measure of Modified Hubert statistic ?. Thus, the method provides time efficient and low computational cost approach for hierarchical clustering for both on univariate and multivariate time-series.

Abstract: Unlike state of art eye blink detection techniques that are generalized for usage across individuals affecting accuracy of eye blink prediction from subject to subject, embodiments of the present disclosure provide a method and system for personalized eye blink detection using passive camera-based approach. The method first generates a subject specific annotation data, which is then further processed to derive subject specific personalized blink threshold values. The method disclosed provides three unique approaches to compute the personalized blink threshold values which is one time calibration process. The personalized blink threshold values are then used to generate a binary decision vector (D) while analyzing input test images (video sequences) of the subject of interest. Further, values taken by elements of the decision vector (D) are analyzed for a predefined time period to predict possible eye blinks of the subject.

Abstract: This disclosure relates generally to Millimeter Wave (MMW) frequency antenna scanning system. Conventional approaches available for scanning an antenna beam over a large angular swath with high directivity are unable to address concerns of size and cost involved. The technical problem of providing an MMW frequency antenna scanning system using a single small size antenna capable of scanning as desired at a desired precision is addressed in the present disclosure. The antenna scanning system provided is an electromechanical system that makes the system cost effective. Computer control provides precision control in beam steering from remote. Use of a metasurface and configuration of a radiating patch and a shorting pin in a microstrip antenna addresses the concern with regards to the size of the antenna scanning system.

Abstract: This disclosure relates generally to a method and a system for determining quality of PPG signal. The PPG signals are extensively used for deducing health parameters of patients to infer the physiological conditions of heart, blood pressure, breathing patterns of the patients. However, analysis based on PPG signals is extremely challenging and is accurate only on high quality PPG signals. However, the existing techniques for determining quality of PPG signal (that are collected using wearable devices) require huge training or use complicated algorithms and cannot be used for real-time analysis. The disclosed methods and system for PPG quality assessment is based on the frequency domain analysis, wherein heart and respiratory components in the frequency spectrum are used effectively to derive the quality checker metric which is further used to estimate a plurality of optimal thresholds that is used for determining the quality of PPG signals at real-time.

Abstract: This disclosure relates generally to a method and system for classification of cognitive load (CL) using data obtained from wearable sensors. The disclosed method uses a multi-modal based approach using wrist-worn sensors for real time monitoring of CL in real world scenarios and improves the accuracy of detection of CL. A set of distinguishing features are selected from physiological signals received from the wrist-worn sensors. These features are used for training a classification model for classifying the CL of a patient into a no load or a high load. The set of distinguishing features are selected from domain specific features and signal property based generic features of the physiological signals. The disclosed method is used for classification of CL in scenarios such as to check how the cognitive load of a candidate varies during interviews, to assess the participants workload during online meetings and so on.

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: An e-commerce business model has witnessed several cases where packages with faulty goods, returned by buyers, without procured object, rather replaced by different device. This disclosure relates a method to detect whether object under test a desired object. A plurality of back-scattered signals is received from the object under test occluded by packaging with continuous motion on conveyer based on first antenna-radar combination. The plurality of back-scattered signals is processed by applying four-tap difference filter to obtain motion-filtered data matrix. A low pass filter is applied on the motion-filtered data matrix to obtain enveloped motion-filtered data matrix. A sliding constant false alarm rate is applied on the enveloped motion-filtered data matrix to determine detection threshold value. A check is performed to detect whether the object under test is the desired object based on whether intensity of the plurality back-scattered signals exceeds the detection threshold value.

Abstract: Embodiments of the present disclosure provide a method and system for co-operative and cascaded inference on the edge device using an integrated Deep Learning (DL) model for object detection and localization, which comprises a strong classifier trained on largely available datasets and a weak localizer trained on scarcely available datasets, and work in coordination to first detect object (fire) in every input frame using the classifier, and then trigger a localizer only for the frames that are classified as fire frames. The classifier and the localizer of the integrated DL model are jointly trained using Multitask Learning approach. Works in literature hardly address the technical challenge of embedding such integrated DL model to be deployed on edge devices. The method provides an optimal hardware software partitioning approach for components or segments of the integrated DL model which achieves a tradeoff between latency and accuracy in object classification and localization.

Abstract: A method and system for a feature subset-classifier pair for a classification task. The classification task corresponds to automatically classifying data associated with a subject(s) or object(s) of interest into an appropriate class based on a feature subset selected among a plurality of features extracted from the data and a classifier selected from a set of classifier types. The method proposed includes simultaneously determining the feature subset-classifier pair based on a relax-greedy {feature subset, classifier} approach utilizing sub-greedy search process based on a patience function, wherein the feature subset-classifier pair provides an optimal combination for more accurate classification. The automatic joint selection is time efficient solution, effectively speeding up the classification task.

Abstract: A growing need for inferencing to be run on fog devices exists, in order to reduce the upstream network traffic. However, being computationally constrained in nature, executing complex deep inferencing models on such devices has been proved difficult. A system and method for partitioning of deep convolution neural network for execution of computationally constraint devices at a network edge has been provided. The system is configured to use depth wise input partitioning of convolutional operations in deep convolutional neural network (DCNN). The convolution operation is performed based on an input filter depth and number of filters for determining the appropriate parameters for partitioning based on an inference speedup method. The system uses a master-slave network for partitioning the input. The system is configured to address these problems by depth wise partitioning of input which ensures speedup inference of convolution operations by reducing pixel overlaps.