Claims:1. A method for estimating a blood pressure (BP) of a person, the method comprising a processor implemented steps of:

capturing an electrocardiogram (ECG) signal of the person using an ECG sensor (102);
capturing a photoplethysmogram (PPG) signal of the person using a PPG sensor (104), wherein the PPG signal is synchronized with the ECG signal;
preprocessing the ECG signal and PPG signal to remove a plurality of noises;
estimating a pulse transit time (PTT) using the ECG signal and PPG signal;
extracting a plurality of features of the PPG signal;
providing the PTT and the plurality of features to a feature selection module (118);
applying a feature selection algorithm for selecting a set of features, wherein the set of features are selected to maximize the accuracy in classifying a low/normal BP class from a high BP class;
classifying the data corresponding to ECG signal, PPG signal and PTT in to the high BP class and the low/normal BP class based on the selected set of features using a classification module (120); and
performing the regression analysis on the ECG signal, the PPG signal and the PTT corresponding to the low/normal BP class to estimate the blood pressure of the person.

2. The method of claim 1 further includes the step of creating a feature matrix containing PTT and the plurality of PPG features.

3. The method of claim 1, wherein the feature selection algorithm is at least one of a maximum relevance minimum redundancy (mRMR) algorithm, a maximum relevance maximum significance (mRMS) algorithm or a µHEM algorithm.

4. The method of claim 1 wherein the classification module is a support vector machine (SVM) classifier designed using the selected set of features.

5. The method of claim 1, wherein the high BP class is with systolic BP more than or equal to150 mmHg and normal/low BP class is with systolic BP less than 150 mmHg.

6. The method of claim 1, wherein the plurality of features include time domain, frequency domain and heart rate variability (HRV) domain features.

7. The method of claim 1 further include the step of evaluating the accuracy of the estimated BP using Bland Altman plot.

8. A system for estimating a blood pressure (BP) of a person, the system comprising:
an ECG sensor (102) for capturing an electrocardiogram (ECG) signal of the person;
a PPG sensor (104) for capturing a photoplethysmogram (PPG) signal of the person, wherein the PPG signal is synchronized with the ECG signal;
a memory (106); and
a processor (108) in communication with the memory, wherein the processor further comprises:
a preprocessor (110) for preprocessing the ECG signal and PPG signal to remove a plurality of noises,
a pulse transit time estimation module (112) for estimating a pulse transit time (PTT) using the ECG signal and PPG signal,
a feature extraction module (114) for extracting a plurality of features of the PPG signal,
an input module (116) for providing the PTT and the plurality of features to a feature selection module,
a feature selection module (118) for applying a feature selection algorithm for selecting a set of features, wherein the set of features are selected to maximize the accuracy in classifying a low/normal BP class from a high BP class,
a classification module (120) for classifying the ECG signal, PPG signal and PTT in to the high BP class and the low/normal BP class based on the selected set of features, and
a regression analysis module (122) for performing the regression analysis on the ECG signal, the PPG signal and the PTT corresponding to the low/normal BP class to estimate the blood pressure of the person.
, Description:As Attached