公开(公告)号：US12274536B2

公开(公告)日：2025-04-15

申请号：US16946718

申请日：2020-07-01

Applicant: Tata Consultancy Services Limited

Inventor： Sanjay Madhukar Kimbahune ,  Sujit Raghunath Shinde ,  Arpan Pal ,  Sundeep Khandelwal ,  Tanuka Bhattacharjee ,  Shalini Mukhopadhayay ,  Rohan Banerjee ,  Avik Ghose ,  Tapas Chakravarty

IPC: A61B5/024 ,  A61B5/00 ,  A61B5/339 ,  G06N20/00

Abstract: 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.

公开(公告)号：US11710292B2

公开(公告)日：2023-07-25

申请号：US17518921

申请日：2021-11-04

Applicant: Tata Consultancy Services Limited

Inventor： Swapna Agarwal ,  Sujit Shinde ,  Dibyanshu Jaiswal ,  Avik Ghose ,  Sanjay Kimbahune

IPC: G06V10/25 ,  G06V40/16 ,  G06V10/46 ,  G06V10/75

CPC classification number: G06V10/25 ,  G06V10/462 ,  G06V10/751 ,  G06V40/168

Abstract: Embodiments herein provide a method and system for real time ROI detection in thermal face images based on a heuristic approach. The ROI of the thermal images, once detected, is then further used to detect temperature of a subject corresponding to the ROI. Unlike state of the art techniques, the heuristic approach is computationally less intensive and provides fast and accurate ROI detection even in case of occluded faces in a crowd with a single thermal image having a plurality of subject being scanned. The heuristics applied does not focus on face detection but directly on point of interest detection. Once the point of interest (ROI) is detected, it may be used for plurality of applications such as subject tracking and the like, not limited to subject or object temperature sensing since the method disclosed herein is easily implementable on low power devices.

公开(公告)号：US11707208B2

公开(公告)日：2023-07-25

申请号：US17200973

申请日：2021-03-15

Applicant: Tata Consultancy Services Limited

Inventor： Avik Ghose ,  Nasimuddin Ahmed

IPC: A61B5/11 ,  A61B5/00

CPC classification number: A61B5/1101 ,  A61B5/1126 ,  A61B5/7257

Abstract: Existing wearable device-based approaches to capture a_tremor signal have accuracy limitations due to usage of accelerometer sensor with inherent noisy nature. The method and system disclosed herein taps characteristics of the PPG sensor of being sensitive to the motion artifact, as an advantage, to capture tremor_signals present in the PPG sensor. The method disclosed herein describes an approach to extract tremor_signals of interest from the PPG signal by performing a Singular Spectrum Analysis (SSA) followed by spectrum density estimation. The SSA comprises performing embedding on the acquired PPG signal, performing Principal Component Analysis (PCA) on the embedded signal and reconstructing the rest tremor signal from the significant principal components identified post the PCA. Further, the spectrum density estimation detects a dominant frequency present in the principal components, which is the dominant frequency associated with the rest tremor.

公开(公告)号：US11699522B2

公开(公告)日：2023-07-11

申请号：US16396276

申请日：2019-04-26

Applicant: Tata Consultancy Services Limited

Inventor： Avik Ghose ,  Arijit Chowdhury ,  Sakyajit Bhattacharya ,  Vivek Chandel ,  Arpan Pal ,  Soma Bandyopadhyay

IPC: G06N5/02 ,  G06N5/04 ,  G06K9/62 ,  G06F16/9035 ,  A61B5/00 ,  G16H40/67 ,  G06F16/908 ,  G06N5/022 ,  G06F18/25

CPC classification number: G16H40/67 ,  A61B5/7275 ,  G06F16/908 ,  G06F16/9035 ,  G06F18/251 ,  G06N5/022 ,  G06N5/04

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. Further the unified human behaviour inference can be obtained across multiple domains that include health, retail and transportation.

公开(公告)号：US11571162B2

公开(公告)日：2023-02-07

申请号：US16827812

申请日：2020-03-24

Applicant: Tata Consultancy Services Limited

Inventor： Rohan Banerjee ,  Avik Ghose ,  Sundeep Khandelwal

IPC: G08B23/00 ,  A61B5/361 ,  G16H70/60 ,  G16H50/20 ,  G06N3/04 ,  G06N3/08 ,  A61B5/352 ,  A61B5/366

Abstract: Conventionally, Atrial Fibrillation (AF) has been detected using atrial analyses which is vulnerable to background noise. Again there is a dependency on statistical features which are extracted from R-R intervals of long ECG recordings. The present disclosure addresses AF detection from single lead short ECG recordings of less than one minute wherein automatic detection of P-R and P-Q intervals is difficult, which introduces error in feature computing from the segregated intervals and compromises the performance of the classifier. In the present disclosure, a Recurrent Neural Network (RNN) based architecture comprising two Long Short Term Memory (LSTM) networks is provided for temporal analysis of R-R intervals and P wave regions in an ECG signal respectively. Output sates of the two LSTM networks are merged at a dense layer along with a set of hand-crafted statistical features to create a composite feature set for classification of the AF.

公开(公告)号：US11558710B2

公开(公告)日：2023-01-17

申请号：US17178081

申请日：2021-02-17

Applicant: Tata Consultancy Services Limited

Inventor： Vivek Chandel ,  Snehasis Banerjee ,  Avik Ghose

IPC: H04W4/02 ,  H04B17/318 ,  H04Q9/00

Abstract: Conventionally, Received Signal Strength Indicator (RSSI)-based solutions have been extensively devised in the domains of indoor localization and context-aware applications. These solutions are primarily based on a path-loss attenuation model, with customizations on RSSI processing and are usually regression-based. Further, existing solutions for distance and proximity estimation incorporate data features derived only from the RSSI values themselves with additional features like frequency of occurrence of certain RSSI values thus are less accurate. Present disclosure provides systems and methods that implement a classification model that uses RSSI as well as temporal features derived from the received data packets. The model uses data from multiple devices in different environments for training and can execute proximity decisions on the device itself. The method of the present disclosure monitoring proximity between a plurality of devices implements/uses an effective protocol for decision aggregation to suppress false positive proximity events generated and further stabilizes device's response.

公开(公告)号：US11373731B2

公开(公告)日：2022-06-28

申请号：US16179784

申请日：2018-11-02

Applicant: Tata Consultancy Services Limited

Inventor： Vivek Chandel ,  Dhaval Satish Jani ,  Sundeep Khandelwal ,  Shalini Mukhopadhyay ,  Dibyanshu Jaiswal ,  Avik Ghose ,  Arpan Pal ,  Kartik Muralidharan

IPC: G16B40/00 ,  A61B5/0205 ,  A61B5/00 ,  A61B5/024 ,  A61B5/11 ,  G16B50/00

Abstract: This disclosure relates generally to classification of cardiopulmonary fatigue. The method and system provides a longitudinal monitoring platform to classify cardiopulmonary fatigue of a subject using a wearable device worn by the subject. The activities of the subject is continuous monitored by plurality of sensors embedded in a wearable device. The received sensor signals are processed in multiple stages to classify cardiopulmonary fatigue as healthy or unhealthy based on respiratory, heart rate and recovery duration parameters extracted from the received sensor data. Further using the classified cardiopulmonary fatigue level, the C2P also performs longitudinal analysis to detect potential cardiopulmonary disorders.

公开(公告)号：US20220019804A1

公开(公告)日：2022-01-20

申请号：US17197316

申请日：2021-03-10

Applicant: Tata Consultancy Services Limited

Inventor： Jayavardhana Rama Gubbi Lakshminarasimha ,  Akshaya Ramaswamy ,  Balamuralidhar Purushothaman ,  Apama Kanakatte Gurumurthy ,  Avik Ghose

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: State of the art techniques in the domain of video analysis have limitations in terms of capability to capture spatio-temporal representation. This limitation in turn affects interpretation of video data. The disclosure herein generally relates to video analysis, and, more particularly, to a method and system for video analysis to capture spatio-temporal representation for video reconstruction and analysis. The method presents different architecture variations using three main deep network components: 2D convolution units, 3D convolution units and long short-term memory (LSTM) units for video reconstruction and analysis. These variations are trained for learning the spatio-temporal representation of the videos in order to generate a pre-trained video analysis module. By understanding the advantages and disadvantages of different architectural configurations, a novel architecture is designed for video reconstruction. Using transfer learning, the video reconstruction pre-trained model is extended to other video applications such as video object segmentation and surgical video tool segmentation.

公开(公告)号：US10909462B2

公开(公告)日：2021-02-02

申请号：US15160440

申请日：2016-05-20

Applicant: Tata Consultancy Services Limited

Inventor： Avik Ghose ,  Arpan Pal ,  Arindam Pal ,  Tanushyam Chattopadhyay ,  Santa Maiti

IPC: G06F15/18 ,  G06N5/02 ,  G06N20/00 ,  G06Q50/00

Abstract: A multi-dimensional sensor data analysis system and method is provided. The multi-dimensional sensor data analysis system receives indoor and outdoor location, online and physical activity, online and physical proximity and additional a plurality of inputs (specific to a user), for example, surrounding of the subject, physiological parameters of the subject and recent social status of the subject, both online and offline. The multi-dimensional sensor data analysis system processes these inputs along with the knowledge of past behavior and traditional parameters of location, proximity and activity by performing a multi-dimensional sensor data analysis fusion technique, producing one or more outputs, for example, predicting or determining a human behaviour to a given stimuli.

公开(公告)号：US09967715B2

公开(公告)日：2018-05-08

申请号：US15200781

申请日：2016-07-01

Applicant: Tata Consultancy Services Limited

Inventor： Nasimuddin Ahmed ,  Avik Ghose ,  Tapas Chakravarty ,  Arpan Pal

IPC: H04W4/04 ,  H04W4/02 ,  G01S5/02

CPC classification number: H04W4/33 ,  G01S5/0252 ,  H04W4/021 ,  H04W4/043

Abstract: Method(s) and System(s) for determining location of a user device within a premise are described. The method includes identifying multiple zones with physical boundaries within the premise based on parameters associated with geometry of the premise. The premise includes multiple access points distributed across the multiple zones. Thereafter, the method includes collecting a first set of Received Signal Strength Indicator (RSSI) Data that is representative of strength of signals received from each accessible access point, at different locations within the premise. After collecting the first set, the method includes computing a Variable Path Loss Exponent (VPLE) within each zone for each accessible access point for determining location of the user device based on at least one of the first set of RSSI data, a line of sight condition, a non-line of sight condition and distance between each accessible access point from each location.