公开(公告)号：US20170143279A1

公开(公告)日：2017-05-25

申请号：US15356000

申请日：2016-11-18

Applicant: Tata Consultancy Services Limited

Inventor： Srinivasan JAYARAMAN ,  Naveen Kumar THOKALA ,  Balamuralidhar PURUSHOTHAMAN

IPC: A61B5/00 ,  A61B5/024

Abstract: A device and method is provided for the detection of diabetes in a person using pulse palpation signals. The pulse palpation signal is captured from the radial artery of the person using a photo-plethysmograph (PPG) sensor. The PPG signal is then preprocessed by a processor. The preprocessed PPG signal is then analyzed by the processor to detect the peak in the PPG signal. The detected peaks are used to extract a first set of feature parameters. The first of feature parameters are compared with a second set of feature parameters, wherein the second set of feature parameters are extracted from the control group of individuals. Based on the comparison it is detected that the person is one of in normal condition, pre-diabetic condition or a diabetic condition. According to another embodiment, the invention also provides a method to determine the severity index and progression risk of diabetes in the person.

公开(公告)号：US20210011062A1

公开(公告)日：2021-01-14

申请号：US16813794

申请日：2020-03-10

Applicant: Tata Consultancy Services Limited

Inventor： Kriti Kumar ,  Mariswamy Girish CHANDRA ,  Achanna Anil KUMAR ,  Naveen Kumar THOKALA

IPC: G01R21/133 ,  G06N20/00 ,  G06N7/00

Abstract: This disclosure relates generally to method and system for low sampling rate electrical load disaggregation. At low sampling rates, disaggregation of energy load is challenging due to unavailability of events and signatures of the constituent loads. The disclosed energy disaggregation technique receives aggregated load data from a utility meter and sequentially obtains training data for determining disaggregated energy load at low sampling rate. Dictionaries are used to characterize the different loads in terms of power values and time of operation. The obtained dictionary coefficients are treated as graph signals and graph smoothness is used for propagating the coefficients from the training phase to the test phase by formulating an optimization model. The derivation of the optimization model identifies the load of interest and estimate their power consumption based on optimization model constraints. This method achieves accuracy greater than 70% for the loads of interest at low sampling rates.