Tata Consultancy Services Limited

Avik Ghose

Arpan Pal

Chirabrata Bhaumik

Tapas Chakravarty

Vivek Chandel

Arijit Chowdhury

Balamuralidhar Purushothaman

Nasimuddin Ahmed

Rohan Banerjee

Aniruddha Sinha

Anirban Dutta Choudhury

Jayavardhana Rama Gubbi Lakshminarasimha

Dibyanshu Jaiswal

Sundeep Khandelwal

Priyanka Sinha

Murali Poduval

Arijit Sinharay

Sakyajit Bhattacharya

Tanushyam Chattopadhyay

Sanjay Madhukar Kimbahune

Sujit Shinde

Amit Swain

Brojeshwar Bhowmick

Soma Bandyopadhyay

Prateep Misra

Dibyendu Roy

Kartik Muralidharan

Karan Bhavsar

Vartika Sengar

Arijit Mukherjee

Arijit Ukil

Sunil Kumar Kopparapu

Snehasis Banerjee

Deepak N Swamy

Swarnava Dey

Rajat Kumar Das

Oishee Mazumder

Shalini Mukhopadhyay

Aparna Kanakatte Gurumurthy

Dhaval Satish Jani

Diptesh Das

Karthik Seemakurthy

Vivek Bangalore Sampathkumar

Archan Misra

Swapna Agarwal

Venkatramanan Siva Subrahmanian

Ashish Omprakash Indani

Devraj Goulikar

Shivam Singhal

Sonia Sharma

Srinivasan Jayaraman

Andrew Gigie

Raj Kumar Rakshit

Amit Kumar Agrawal

Ramu Reddy Vempada

Akshaya Ramaswamy

Tanuka Bhattacharjee

Rohit Gupta

Parama Pal

Arindam Pal

Shahnawaz Alam

Dhiman Chattopadhyay

Aishwarya Visvanathan

Harsh Vishwakarma

Pavan Kumar Reddy Kancham

Varsha Sharma

Sourjya Sarkar

Bhaskar Pawar

Santa Maiti

Plaban Kumar Bhowmick

Provat Biswas

Arijit Chowdhary

Divya Manoharlal Bhatia

Avijit Samal

Abhinav Kumar

Aditi Misra

Shalini Arora

Shalini Mukhopadhayay

Oishee Muzumder

Shivani Johari

Jayeeta Saha

Keshaw Dewangan

Aditi Mishra

Bhaumik Chirabrata

Abhinav Jha

Srinivsan Jayaraman

Tapas Chakravar

This disclosure relates generally to methods and systems for automated image segmentation of an anatomical structure such as heart. Most of the techniques in literature are using 2-D or slice by-slice data due to lightweight and need of less data for training. These networks lack 3-D contextual information. Further, the conventional techniques are inaccurate and inefficient in the 3-D image segmentation till the last slice of the image. The present disclosure solves automated 3-D image segmentation of the anatomical structure such as heart, by proposing a new Generative Adversarial Network (GAN) based architecture for the 3-D segmentation, with a patch-based extraction technique and a class-weighted generalized dice loss. The proposed 3-D GAN based architecture is capable of storing the 3-D contextual information for the image segmentation of the anatomical structure, with high accuracy.

Methods and systems for automated image segmentation of anatomical structure

This disclosure relates generally to system and method for ambient intelligence based user interaction. Prior methods for touchless user interaction are sensitive to ambient temperature in a lab environment, susceptible to noise from metallic surfaces and ambient radio waves and are dependent on ambient lighting. Embodiments of the present disclosure provides a multi-modal sensor fusion method which captures touchless gestures from a user or a group of users with their physical context information fused and tagged to these gestures for user interaction. Further pose graphs are generated for user interaction systems using a data association technique and Gaussian mixture model technique. The disclosed method provides a hands-free interface to operate instruments in a smart space, using principles of ambient intelligence.

Method and system for ambient intelligence based user interaction

This disclosure relates generally to real time analysis of range of motion (ROM), wherein ROM is a measurement of movement around a specific joint or body part. The existing techniques for ROM fail for measurements made in certain planes and are not very effective for ROM measurements for extremely slow and very fast movements. The disclosed provides a real time analysis of ROM based on computation of range of motion (ROM) of a joint and a set of ROM parameters using a gyroscope. The gyroscope collects data from a subject at pre-defined neutral position of the subject as well as a pre-defined rotation movement of a joint of the subject. The received data is corrected for bias and processed at real time to analyze the ROM by computing range of motion (ROM) of a joint and a set of ROM parameters.

Method and a system for real time analysis of range of motion (ROM)

Ultra Wide Band (UWB) based Real Time Location Systems (RTLS) that are being used for location tracking suffer from environment specific errors that are introduced due to factors such as difference in reflection and propagation. In order to address this challenge, present invention discloses performing error modelling for object localization using Ultra Wide Band (UWB) sensors. The error modelling allows to correct a determined location of an object being tracked, to determine a corrected location. Based on an obtained distance value of a tag node with reference to position of a plurality of anchor nodes, location of an object in a 2-Dimensional space is determined. The determined location is corrected to obtain the corrected location, and in this process the error modelling and related error correction is done.

Method and system of error modelling for object localization using ultra wide band (UWB) sensors

Embodiments herein provide a system and method for screening and monitoring of cardiac diseases by analyzing acquired physiological signals. Unlike state of art approaches that consider only synchronized ECG and PPG signals for cardiac health analysis and do not consider PCG which is a critical signal for CAD analysis, the system synchronously captures physiological signals such as photo plethysmograph (PPG), phonocardiogram (PCG) and electrocardiogram (ECG) from subject(s) and builds an analytical model in the cloud for analyzing heart conditions from the captured physiological signals. The system and method provides a fusion based approach of combining the captured physiological signals such as PPG, PCG and ECG along with other details such as subject clinical information, demography information and so on. The analytical model is pretrained using ECG. PPG and PCG along with metadata associated with the subject such as demography and clinical information.

Method and system for screening and monitoring of cardiac diseases

Non-communicable diseases (NCDs) are the pandemics of modern era and are generating huge impact in the modern society. Conventional methods are inaccurate due to a challenge in handling data from heterogenous sensors. The present disclosure is capable of tracking fitness parameters of a user even with heterogenous sensors. Initially, the system receives a raw data from a plurality of heterogenous sensors associated with the user. The raw data is further transformed into a metadata format associated with the corresponding sensor. The transformed data is temporally aligned based on a time based slotting. An algorithm pipeline corresponding to a disorder to be analyzed is selected from a Directed Acyclic Graph (DAG) based on a sensor metadata and a plurality of algorithm metadata corresponding to a plurality of algorithms stored in an algorithm database and an algorithm pipeline. The corresponding disorder is analyzed using the algorithm pipeline.

Method and system for digital biomarkers platform

Tracking motion using inertial sensors embedded in commercial grade wearables like smartwatches has proved to be a challenging task, especially if real-time tracking is a requirement. Present disclosure provides system and method wherein data from sensors are obtained and scaled. Further, Euler Rodrigues Matrix (ERM) is generated based delta value obtained using sensor data. The scaled sensor data and ERM are used for generating feature vectors. Windowing technique is applied for subsets of feature vectors to obtain label for each window and machine learning model is trained with the label and window. Further, during real-time, sensor data is obtained, and steps of ERM, feature vectors generation, and application of windowing technique are repeated, and coordinates are estimated for each window in real-time based on which trajectories are tracked in real-time for each window.

Systems and methods for real-time tracking of trajectories using motion sensors

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.

Method and system for generating synthetic time domain signals to build a classifier

The disclosure herein relates to methods and systems for generating an end-to-end de-smoking model for removing smoke present in a video. Conventional data-driven based de-smoking approaches are limited mainly due to lack of suitable training data. Further, the conventional data-driven based de-smoking approaches are not end-to-end for removing the smoke present in the video. The de-smoking model of the present disclosure is trained end-to-end with the use of synthesized smoky video frames that are obtained by source aware smoke synthesis approach. The end-to-end de-smoking model localize and remove the smoke present in the video, using dynamic properties of the smoke. Hence the end-to-end de-smoking model simultaneously identifies the regions affected with the smoke and performs the de-smoking with minimal artifacts. localized smoke removal and color restoration of a real-time video.

Methods and systems for generating end-to-end de-smoking model

The disclosure herein relates to methods and systems for localized smoke removal and color restoration of a real-time video. Conventional techniques apply the de-smoking process only on a single image, by finding the regions having the smoke, based on manual air-light estimation. In addition, regaining original colors of de-smoked image is quite challenging. The present disclosure herein solves the technical problems. In the first stage, video frames having the smoky and smoke-free video frames are identified, from the video received in the real-time. In the second stage, an air-light is estimated automatically using a combined feature map. An intermediate de-smoked video frame for each smoky video frame is generated based on the air-light using a de-smoking algorithm. In the third and the last stage, a smoke-free video reference frame is used to compensate for color distortions introduced by the de-smoking algorithm in the second stage.

Methods and systems for localized smoke removal and color restoration of real-time video

The disclosure generally relates to methods and systems for identifying presence of abnormal heart sounds from heart sound signals of a subject being monitored. Conventional Artificial intelligence (AI) based abnormal heart sounds detection models with supervised learning requires a substantial amount of accurate training datasets covering all heart disease types for the training, which is quiet challenging. The present methods and systems solve the problem solves the problem of identifying presence of the abnormal heart sounds using an efficient semi-supervised learning model. The semi-supervised learning model is generated based on probability distribution of spectrographic properties obtained from heart sound signals of healthy subjects. A Kullback-Leibler (KL) divergence between a predefined Gaussian distribution and an encoded probability distribution of the semi-supervised learning model is determined as an anomaly score for identifying the abnormal heart sounds.

Methods and systems for identifying presence of abnormal heart sounds of a subject

This disclosure relates generally to a sensor based wearable fabric design for identifying distortion in movements and quantifying range of motion. Accurate quantification of multi-axial range of motion involved in complex movements of human body parts is challenging. The disclosure discloses a system and method providing a wearable fabric comprising a plurality of honey-comb structure with a plurality of adjacently placed hexagon structures. An optical sensor unit is placed on each side of each hexagon structure comprised in the plurality of honey-comb structures. A deformation of the plurality of sides of hexagon structure is determined to generate signatures of movement patterns of one or more body parts of a subject. Further, a comparison of generated signatures with stored signatures of the movement patterns is performed to determine an error indicative of a distortion in the movement patterns. The system and method accurately quantify range of motion with increased measurement accuracy.

Sensor based wearable fabric design for identifying distortion in movements and quantifying range of motion

This disclosure relates generally to a method and system for online handwritten signature verification providing a simpler low cost system. The method comprises extracting signature data for the subject from a sensor array for the predefined time window at regular predefined time instants. Further, differentiating the matrix row wise and column wise to generate a row difference matrix and a column difference matrix. Further, determining an idle signature time fraction for the extracted signature data of the subject being monitored from the column difference matrix. Further, determining a plurality of signature parameters based on the row difference matrix and the column difference matrix. Further, analyzing the idle signature time fraction and the plurality of signature parameters of the subject being monitored based on a Support Vector Machine (SVM) classifier, wherein the SVM classifier performs online classification of the extracted signature data into one of a matching signature class and a non-matching signature class.

Method and system for handwritten signature verification

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.

Systems and methods for unobtrusive digital health assessment

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. Using an expectation maximization (EM) model, one or more latent variables of each of the cluster-specific transitional matrices are obtained to determine a likelihood of association of the subject to the cluster.

System and method for categorical time-series clustering

Growing community of inventors

Kolkata, India

Avik Ghose