公开(公告)号：US20180338727A1

公开(公告)日：2018-11-29

申请号：US15869207

申请日：2018-01-12

Applicant: Tata Consultancy Services Limited

Inventor： Shalini MUKHOPADHYAY ,  Nasimuddin AHMED ,  Avik GHOSE ,  Arijit SINHARAY ,  Dibyanshu JAISWAL ,  Arijit CHOWDHURY ,  Ramu Reddy VEMPADA ,  Tapas CHAKRAVARTY ,  Arpan PAL

IPC: A61B5/00 ,  A61B5/024

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.

公开(公告)号：US20240068934A1

公开(公告)日：2024-02-29

申请号：US18355266

申请日：2023-07-19

Applicant: Tata Consultancy Services Limited

Inventor： Subhasri CHATTERJEE ,  Abhijit GOREY ,  Arijit SINHARAY ,  Chirabrata BHAUMIK ,  Tapas CHAKRAVARTY ,  Supriya GAIN ,  Arpan PAL

IPC: G01N21/17 ,  G01N33/28

CPC classification number: G01N21/1702 ,  G01N33/2888 ,  G01N2201/06113

Abstract: The disclosure relates generally to methods and systems for monitoring lubricant oil condition using a photoacoustic modelling. Conventional techniques in the art for checking the condition of the lubricant oil is laboratory based and thus time consuming, error prone and not efficient. The present disclosure discloses a photoacoustic simulation model which is developed utilizing a photonic model such as a Monte Carlo method-based optical simulation integrated with a finite element model such as a k-wave toolbox-based acoustic measurement. The photoacoustic simulation model of the present disclosure is used to obtain a photoacoustic signal of the lubricant oil sample and a set of statistical features are determined from the obtained photoacoustic signal. The determined set of statistical features are then used as a training data to develop a machine learning (ML) model which is used to classify a type of contamination of the test lubricating oil.

公开(公告)号：US20210157887A1

公开(公告)日：2021-05-27

申请号：US17044299

申请日：2019-02-18

Applicant: TATA CONSULTANCY SERVICES LIMITED

Inventor： Dibyendu ROY ,  Arijit CHOWDHURY ,  Arijit SINHARAY ,  Avik GHOSE

IPC: G06F21/32 ,  G06F21/31 ,  G06N20/10

Abstract: 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.

公开(公告)号：US20190323882A1

公开(公告)日：2019-10-24

申请号：US16248646

申请日：2019-01-15

Applicant: Tata Consultancy Services Limited

Inventor： Arijit SINHARAY ,  Raj RAKSHIT ,  Dibyendu ROY ,  Tapas CHAKRAVARTY ,  Balamuralidhar PURUSHOTHAMAN

IPC: G01H9/00 ,  G01S13/50 ,  G01S15/50 ,  G01S17/50 ,  G01N29/46

Abstract: This disclosure relates generally to methods and systems for unobtrusive and automated detection of frequencies of spatially located distinct parts of a machine. Location of vibration and detection of vibration frequency of each vibrating part in a machine is critical for routine monitoring and fault detection in the machine. Current solutions use either high frames per second (fps) industrial grade camera or stroboscopes tuned at one particular frequency. Manual stroboscopes require manual intervention for objects moving at different speeds with high convergence time. Point-lasers need prior knowledge of exact location of faults. Also Point-by-point scanning of a large machine body is time consuming. In the present disclosure, a movement detector such as RADAR enables detecting all vibration frequencies that also serve to reduce the search space of a stroboscope configured to start strobing at each detected vibration frequency to enable mapping of each vibration frequency to a corresponding vibrating part.

公开(公告)号：US20210243260A1

公开(公告)日：2021-08-05

申请号：US17136436

申请日：2020-12-29

Applicant: Tata Consultancy Services Limited

Inventor： Chirabrata BHAUMIK ,  Rajat DAS ,  Arpan PAL ,  Tapas CHAKRAVARTY ,  Raj RAKSHIT ,  Avik GHOSE ,  Amit SWAIN ,  Arijit SINHARAY

IPC: H04L29/08 ,  G16Y30/00 ,  G06F16/25

Abstract: Any sensing system is faced with triangle of dilemma between accuracy, latency and energy. High energy and high latency sensing systems are often very accurate but less useful. Embodiments herein provide a method and system for edge based sensor controlling in the IoT network for event monitoring. The system disclosed herein applies a hierarchical sensor selection process and adaptively chooses sensors among multiple sensors deployed in the IoT network. Further, on-the-fly changes operation modes of the sensors to automatically produce the best possible inference from the selected sensor data, in time, power and latency at the edge. Further, sensors of the system include a waveform and diversity control mechanism that enables controlling of an excitation signal of the sensor.

公开(公告)号：US20180256029A1

公开(公告)日：2018-09-13

申请号：US15760709

申请日：2016-09-26

Applicant: Tata Consultancy Services Limited

Inventor： Parijat Dilip DESHPANDE ,  Arijit SINHARAY ,  Ranjan DASGUPTA ,  Arpan PAL

IPC: A61B5/00 ,  G16H10/60 ,  G16H70/60 ,  G06F17/30 ,  A61B5/145 ,  A61B34/32 ,  A61B5/0205

CPC classification number: A61B5/0022 ,  A61B5/002 ,  A61B5/0075 ,  A61B5/0077 ,  A61B5/0205 ,  A61B5/021 ,  A61B5/02405 ,  A61B5/0402 ,  A61B5/0816 ,  A61B5/14532 ,  A61B5/14542 ,  A61B5/6835 ,  A61B5/6898 ,  A61B5/7264 ,  A61B5/7275 ,  A61B34/32 ,  G06F16/951 ,  G06Q10/10 ,  G06Q50/22 ,  G16H10/60 ,  G16H40/67 ,  G16H50/20 ,  G16H70/60

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.

公开(公告)号：US20160113539A1

公开(公告)日：2016-04-28

申请号：US14627334

申请日：2015-02-20

Applicant: Tata Consultancy Services Limited

Inventor： Arijit SINHARAY ,  Debatri CHATTERJEE ,  Arpan PAL

IPC: A61B5/04 ,  A61B5/00 ,  A61B5/0476

CPC classification number: A61B5/04017 ,  A61B5/0476 ,  A61B5/16 ,  A61B5/7203 ,  A61B5/7253 ,  A61B5/7257 ,  A61B5/7264 ,  A61B5/7267

Abstract: Disclosed is a method and system for determining a cognitive load of a subject from Electroencephalography (EEG) signals. EEG signals are received from EEG channels associated with a left-frontal brain lobe. EEG signals are associated with a subject performing cognitive task. EEG signals are received from a low resolution EEG device. EEG channels comprise four EEG channels associated with the left-frontal brain lobe. EEG signals are preprocessed using a Hilbert-Huang Transform (HHT) filter to remove a noise corresponding to one or more non-cerebral artifacts to generate preprocessed EEG signals. Features comprising Fast Fourier Transform (FFT) based alpha and theta band power are extracted from the preprocessed EEG signals. Feature vector is generated from the features. The feature vector is classified using a Support Vector Machine (SVM) classifier to determine the cognitive load of the subject.

Abstract translation: 公开了一种用于从脑电图（EEG）信号确定受试者的认知负荷的方法和系统。 从与左额脑脑相关的EEG通道接收EEG信号。 EEG信号与执行认知任务的对象相关联。 EEG信号从低分辨率EEG设备接收。 脑电信道包括与左额脑脑相关的四个脑电信道。 使用希尔伯特 - 黄变换（HHT）滤波器对EEG信号进行预处理，以去除与一个或多个非脑神经元相对应的噪声，以产生预处理的脑电信号。 从预处理的EEG信号中提取包括基于快速傅里叶变换（FFT）的α和θ带功率的特征。 特征向量是从特征生成的。 使用支持向量机（SVM）分类器对特征向量进行分类，以确定受试者的认知负荷。

公开(公告)号：US20240053221A1

公开(公告)日：2024-02-15

申请号：US18218815

申请日：2023-07-06

Applicant: Tata Consultancy Services Limited

Inventor： Raj RAKSHIT ,  Arijit SINHARAY ,  Supriya GAIN ,  Arpan PAL ,  Chirabrata BHAUMIK ,  Tapas CHAKRAVARTY

IPC: G01M3/24 ,  G01M3/28

CPC classification number: G01M3/243 ,  G01M3/2815

Abstract: One of the biggest challenges faced by oil and gas companies is to monitor such long pipelines for leak events and generate false leak event alarms during routine pipe maintenance. A data associated with a first sensing unit is processed to obtain an instant timing information (T0) of a leak event in a conduit at a test environment. A data associated with a second sensing unit is processed to obtain a transient signal associated with the leak event at a specific band. An accelerometer data is filtered to obtain a band passed filtered accelerometer signal (Accelbpf). The Accelbpf is truncated in a time domain from the T0 to a duration Td of the leak event to obtain a temporal template signal (Acceltemplate). A leak event of a real-time conduit is dynamically detected at a physical environment based on Acceltemplate when a cross-correlation value is greater than a threshold value (∝).

公开(公告)号：US20210215521A1

公开(公告)日：2021-07-15

申请号：US17112414

申请日：2020-12-04

Applicant: Tata Consultancy Services Limited

Inventor： Arijit SINHARAY ,  Rajat Kumar DAS ,  Anwesha KHASNOBISH ,  Tapas CHAKRAVARTY

IPC: G01F1/86 ,  G01F1/66

Abstract: This disclosure relates to a system and method for measuring average temperature of mixed fluid in an enclosed chamber. Measurement is based on two independent principle as measuring variation in acoustic wave velocity and variation in resistivity that works on a single setup. First principle is based on measuring acoustic wave velocity in a known medium, which is isolated from the surrounding. The system comprises a primary pipe and a secondary pipe, wherein the ends of the pipes reside inside the enclosed chamber. The primary pipe is made out of good conductor of heat and filled with air. Ends of the primary pipe is fitted with a transducers have one transmitter at one end and one receiver at another end. Average temperature of the mixed fluid is measured based on the variations in sound velocity of acoustic wave passed through the primary pipe and resistivity variations of the primary pipe.

公开(公告)号：US20210123828A1

公开(公告)日：2021-04-29

申请号：US17036140

申请日：2020-09-29

Applicant: Tata Consultancy Services Limited

Inventor： Arijit SINHARAY ,  Anwesha KHASNOBISH ,  Raj RAKSHIT

IPC: G01M1/22 ,  G01S7/539

Abstract: This disclosure relates generally to method and system for non-contact ultrasound based vibration detection. Here, non-contact vibration detection plays crucial role in industries for monitoring and analyzing machine vibrations to predict early warnings of the potential failures. The method includes receiving, from a non-contact ultrasonic air transducer a signal reflected from a plurality of vibrating parts of a machine. The non-contact ultrasound obtains vibrational frequencies corresponding to the vibrating part of the machine which are further analyzed to determine an electrical impedance of a piezoelectric element. Further, based on the electrical impedance occurred vibrations are detected in each vibrating part from the plurality of vibrating parts of the machine. The measured impedance signal utilizes continuous sinusoidal excitation which enables narrow band filtering to increase signal to noise ratio. The proposed disclosure provides a low cost simple solution thereby reducing design complexity of the non-contact ultrasonic transducer circuit.