公开(公告)号：US20250156689A1

公开(公告)日：2025-05-15

申请号：US18898842

申请日：2024-09-27

Applicant: Tata Consultancy Services Limited

Inventor： Shalini MUKHOPADHYAY ,  Swarnava DEY ,  Avik GHOSE ,  Arijit MUKHERJEE ,  Arpan PAL ,  Ashwin SEKHAR

IPC: G06N3/0464 ,  G06F7/544

Abstract: This disclosure relates generally to time series signal classification, and, more particularly, to a method and system for multiple time series classification on tiny edge devices using lightweight attention. Transformer based techniques, sequential deep neural network and the like are utilized for performing time series signal classification. Also, time series classification techniques suitable for tiny edge devices are limited. The method discloses a lightweight attention network comprising attention condenser modules for time series classification on tiny edge device. The method defines a search space which is being used for performing a neural architecture search space that helps to optimize the lightweight attention network to obtain a final lightweight attention network model with high accuracy, low resource and fast inference.

公开(公告)号：US20240104798A1

公开(公告)日：2024-03-28

申请号：US18460949

申请日：2023-09-05

Applicant: Tata Consultancy Services Limited

Inventor： Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Pavan kumar REDDY KANCHAM ,  Mohana SINGH ,  Arpan PAL ,  Viswanath PAMULAKANTY SUDARSHAN

IPC: G06T11/00 ,  G06T7/00 ,  G06V10/74

CPC classification number: G06T11/005 ,  G06T7/0012 ,  G06V10/761 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Model-based image reconstruction (MBIR) methods using convolutional neural networks (CNNs) as priors have demonstrated superior image quality and robustness compared to conventional methods. Studies have explored MBIR combined with supervised and unsupervised denoising techniques for image reconstruction in magnetic resonance imaging (MRI) and positron emission tomography (PET). Unsupervised methods like the deep image prior (DIP) have shown promising results and are less prone to hallucinations. However, since the noisy image is used as a reference, strategies to prevent overfitting are unclear. Recently, Bayesian DIP (BDIP) networks that model uncertainty tend to prevent overfitting without requiring early stopping. However, BDIP has not been studied with data-fidelity term for image reconstruction. Present disclosure provides systems and method that implement a MBIR framework with a modified BDIP. Specifically, an uncertainty-based penalty is included to the BDIP to improve reconstruction across iterations.

公开(公告)号：US20210401296A1

公开(公告)日：2021-12-30

申请号：US17156395

申请日：2021-01-22

Applicant: Tata Consultancy Services Limited

Inventor： Arijit CHOWDHURY ,  Smriti RANI ,  Anwesha KHASNOBISH ,  Taniya DAS ,  Tapas CHAKRAVARTY ,  Arpan PAL

IPC: A61B5/0205 ,  A61B5/00 ,  A61B5/05

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.

公开(公告)号：US20200284895A1

公开(公告)日：2020-09-10

申请号：US16775592

申请日：2020-01-29

Applicant: Tata Consultancy Services Limited

Inventor： Rajat Kumar DAS ,  Arijit CHOWDHURY ,  Tapas CHAKRAVARTY ,  Arpan PAL

IPC: G01S13/66 ,  G01S13/89 ,  G01S13/58 ,  G01S13/32 ,  G01S7/35

Abstract: This disclosure relates generally to tracking motion of target in indoor environment. The method includes estimating an initial position of the target in a mesh grid form based on radar data captured from radar devices installed in the indoor environment. For a subsequent target movement, a subsequent position of the target is estimated in the mesh grid form based on the initial position and a resultant velocity vector of the target. A number of outlier grid-points is computed with a threshold number, and based on comparison the outlier grid-points are either replaced with interpolated grid-points or the subsequent position of the target is repaired based on a probable position of the target obtained from at least one of a linear regression based analysis of prior positions of the target, prior knowledge of the target velocity and sampling interval, and a trilateration based technique.

公开(公告)号：US20200034690A1

公开(公告)日：2020-01-30

申请号：US16526340

申请日：2019-07-30

Applicant: Tata Consultancy Services Limited

Inventor： Avik GHOSE ,  Arpan PAL ,  Sundeep KHANDELWAL ,  Rohan BANERJEE ,  Sakyajit BHATTACHARYA ,  Soma BANDYOPADHYAY ,  Arijit UKIL ,  Dhaval Satish JANI

IPC: G06N3/04 ,  A61B5/11 ,  A61B5/00

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.

公开(公告)号：US20190278971A1

公开(公告)日：2019-09-12

申请号：US16264786

申请日：2019-02-01

Applicant: Tata Consultancy Services Limited

Inventor： Soma BANDYOPADHYAY ,  Arijit UKIL ,  Chetanya PURI ,  Rituraj SINGH ,  Arpan PAL ,  C A. MURTHY

IPC: G06K9/00 ,  G06K9/62 ,  A61B5/0452

Abstract: The present disclosure addresses the technical problem of information loss while representing a physiological signal in the form of symbols and for recognizing patterns inside the signal. Thus making it difficult to retain or extract any relevant information which can be used to detect anomalies in the signal. A system and method for anomaly detection and discovering pattern in a signal using morphology aware symbolic representation has been provided. The system discovers pattern atoms based on the strictly increasing and strictly decreasing characteristics of the time series physiological signal, and generate symbolic representation in terms of these pattern atoms. Additionally the method possess more generalization capability in terms of granularity. This detects discord/abnormal phenomena with consistency.

公开(公告)号：US20180316628A1

公开(公告)日：2018-11-01

申请号：US15901963

申请日：2018-02-22

Applicant: Tata Consultancy Services Limited

Inventor： Sounak DEY ,  Arijit MUKHERJEE ,  Abhijan BHATTACHARYYA ,  Arpan PAL

IPC: H04L12/911 ,  G06F17/27 ,  B25J9/16

CPC classification number: H04L47/82 ,  B25J9/1661 ,  G06F17/2785 ,  G06Q10/06 ,  H04L67/10

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.

公开(公告)号：US20150261963A1

公开(公告)日：2015-09-17

申请号：US14618280

申请日：2015-02-10

Applicant: Tata Consultancy Services Limited

Inventor： Arijit UKIL ,  Soma BANDYOPADHYAY ,  Arpan PAL

IPC: G06F21/60

CPC classification number: G06F21/6245 ,  G01D4/002 ,  H04L2209/04 ,  H04L2209/42 ,  Y02B90/241 ,  Y04S20/32 ,  Y04S40/24

Abstract: A system and method for detecting sensitivity content in time-series data is disclosed. The method comprises receiving the time-series data from a source. The data is received for one or more instances. The method further comprises detecting the sensitivity content in the time-series data. The sensitivity content indicates presence of an anomaly. The detecting comprises determining a kurtosis value corresponding to the time-series data. The detecting further comprises comparing the kurtosis value with a reference value. The detecting further comprises processing the data using a first filtering means or a second filtering means. The first filtering means is used when the data distribution of the time-series data is either of a platykurtic distribution or a mesokurtic distribution. The second filtering means is used when the data distribution of the time-series data is a leptokurtic distribution.

Abstract translation: 公开了一种用于检测时间序列数据中的灵敏度内容的系统和方法。 该方法包括从源接收时间序列数据。 接收到一个或多个实例的数据。 该方法还包括检测时间序列数据中的灵敏度内容。 灵敏度内容表示存在异常。 该检测包括确定对应于时间序列数据的峰度值。 该检测还包括将峰度值与参考值进行比较。 检测还包括使用第一滤波装置或第二滤波装置处理数据。 当时间序列数据的数据分布是板状分布或间质分布时，使用第一过滤装置。 当时间序列数据的数据分布是leptokurtic分布时，使用第二过滤装置。

公开(公告)号：US20240422281A1

公开(公告)日：2024-12-19

申请号：US18740734

申请日：2024-06-12

Applicant: Tata Consultancy Services Limited

Inventor： Gaurab BHATTACHARYA ,  Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Bagya Lakshmi VASUDEVAN ,  Gaurav SHARMA ,  Kuruvilla ABRAHAM ,  Arpan PAL ,  Balamuralidhar PURUSHOTHAMAN ,  Nikhil KILARI

IPC: H04N1/60 ,  G06T7/11 ,  G06T7/90 ,  G06V10/44 ,  G06V10/56 ,  G06V10/762

Abstract: State of the art techniques have challenges for recoloring a product, which includes non-realistic images, incorrect color mapping, structural distortion, color spilling into background, and in handling multi-color, multi-apparel and multi-product scenario images. Embodiments of the present disclosure provide a method and system for recoloring a product using a dual attention (DA) U-Net based on a generative adversarial network (GAN) framework to generate a recolored product with a target color from an input image. The disclosed DAU-Net enables recoloring (i) a single-color in a single-product scenario, (ii) a plurality of colors in a single-product scenario, and (iii) multi-product scenario with a human model. The DAU net uses (i) a product components aware feature (PCAF) extraction to generate feature representations comprising information of the target color with finer details, and (b) a critical feature selection (CFS) mechanism applied on the feature representation, to generate enhanced feature representations.

公开(公告)号：US20240420215A1

公开(公告)日：2024-12-19

申请号：US18666920

申请日：2024-05-17

Applicant: Tata Consultancy Services Limited

Inventor： Vivek Bangalore SAMPATHKUMAR ,  Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Gaurab BHATTACHARYA ,  Bagya Lakshmi VASUDEVAN ,  Arpan PAL ,  Balamuralidhar PURUSHOTHAMAN

IPC: G06Q30/0601

Abstract: Unlike visual similarity, visual compatibility is a complex concept. Existing approaches for outfit compatibility prediction does not focus on methods with personalization. The present disclosure proposes a novel approach to model the user's preference for different styles. The outfit compatibility prediction module is a critical component of an outfit recommendation system. An outfit is said to be compatible if all the items are visually compatible and match the user's preferences. The present disclosure represents the outfit as a graph and uses Graph Neural Network (GNN) with attention mechanism to capture the inter-relationship between the items. A graph read-out layer generates the final outfit embedding. The proposed approach efficiently models the preferences of the users for different styles. Finally, the outfit compatibility score is generated by computing the similarity between the outfit embedding and the user embedding.