FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of invention
ESTIMATING OPTIMIZED CARDIAC PARAMETERS TO GENERATE SYNTHESIZED PHOTOPLETHYSMOGRAM SIGNAL USING CARDIOVASCULAR MODEL
Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description
The following specification particularly describes the invention and the manner in which it is to be performed.2

CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
[001] The present application is a patent of addition of Indian Patent Application No. 201921029536, filed on July 22, 2019, the entire content of which is hereby incorporated herein by way of reference.

5
TECHNICAL FIELD
[002] The disclosure herein generally relates to the field of health monitoring, and, more particularly, to estimating optimized cardiac parameters to generate synthesized Photoplethysmogram (PPG) signal using cardiovascular model. 10

BACKGROUND
[003] Cardiovascular disease have been categorized as a main cause of death worldwide according to World Health Organization. An early diagnosis of such diseases are a major focus of medical and scientific research communities. A 15 vital part in diagnosis of cardiovascular diseases is processing and decoding functional information in cardiac physiological signals like Electrocardiogram (ECG), Photoplethysmogram (PPG) and Phonocardiogram (PCG). The PPG is an unobtrusive method and optically measures a PPG signal based on digital volume pulse from peripheral pulse sites such as a fingertip, an ear lobe and a toe of a 20 subject. The PPG signal provide useful insights related to general conditions of major conduit vessels like aorta and other distal peripheral arteries, by monitoring volumetric fluctuations in a vascular system.
[004] Synthetic or synthesized PPG signals are required for creating a training data to enhance efficacy of machine learning (ML) algorithms that may 25 be used in many early diagnostics scenarios. Though capturing the PPG signal is relatively easy, generating the synthetic PPG signal is a time-consuming manual process and is costly to interpret day-long PPG signal. Conventional methods provides different techniques to generate the synthetic PPG signals, for example, fitting multiple Gaussian waveforms, fitting with the Log-normal bases and 30 stochastic modelling. However, generating an enhanced synthetic PPG signal with
3

better accuracy is always an area of improvement. Also, the Conventional methods that have been utilized for generating the synthetic PPG signals are lacking with interpretability.

SUMMARY 5
[005] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a processor-implemented method for estimating optimized cardiac parameters to generate a synthesized Photoplethysmogram (PPG) signal 10 using a cardiovascular model is provided. The method comprising the steps of: receiving, via one or more hardware processors, a measured PPG signal from a database, wherein the measured PPG signal comprises a plurality of measured PPG cycles, each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate (Th) and a set of measured 15 cardiac parameters, calculating, via the one or more hardware processors, Eigenvalues and associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, using a singular spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique, acquiring, based on the heart rate (Th) of the each measured PPG cycle of the measured PPG signal 20 and a set of initial modelled cardiac parameters, a modelled PPG signal using the cardiovascular model, via the one or more hardware processors, wherein the modelled PPG signal comprises a plurality of modelled PPG cycles, each modelled PPG cycle of the plurality of modelled PPG cycles is indicative of the heart cycle comprising the set of initial modelled cardiac parameters, estimating, 25 via the one or more hardware processors, a set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality of modelled PPG cycles, based on an optimization function ( ( )) using a particle swarm optimization (PSO) technique; and generating the synthesized PPG signal, via the one or more hardware processors, based on the modelled PPG signal and the 30
4

corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles.
[006] In another aspect, a system for estimating optimized cardiac parameters to generate a synthesized Photoplethysmogram (PPG) signal using a cardiovascular model is provided. The system comprising: a memory storing 5 instructions; one or more communication interfaces; a cardiovascular unit stored in the memory, wherein the cardiovascular unit comprises the cardiovascular model; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: receive a measured PPG signal from a 10 database, wherein the measured PPG signal comprises a plurality of measured PPG cycles, each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate (Th) and a set of measured cardiac parameters; calculate Eigenvalues and associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, using a singular 15 spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique; acquire, based on the heart rate (Th) of the each measured PPG cycle of the measured PPG signal and a set of initial modelled cardiac parameters, a modelled PPG signal using the cardiovascular model, wherein the modelled PPG signal comprises a plurality of modelled PPG cycles, each modelled PPG cycle of 20 the plurality of modelled PPG cycles is indicative of the heart cycle comprising the set of initial modelled cardiac parameters; estimate a set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality of modelled PPG cycles, based on an optimization function ( ( )) using a particle swarm optimization (PSO) technique; and generate the synthesized PPG signal, 25 based on the modelled PPG signal and the corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles.
[007] In yet another aspect, there is provided a computer program product comprising a non-transitory computer readable medium having a 30 computer readable program embodied therein, wherein the computer readable
5

program, when executed on a computing device, causes the computing device to: receive a measured PPG signal from a database, wherein the measured PPG signal comprises a plurality of measured PPG cycles, each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate (Th) and a set of measured cardiac parameters; calculate Eigenvalues and 5 associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, using a singular spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique; acquire, based on the heart rate (Th) of the each measured PPG cycle of the measured PPG signal and a set of initial modelled cardiac parameters, a modelled PPG signal using the 10 cardiovascular model, wherein the modelled PPG signal comprises a plurality of modelled PPG cycles, each modelled PPG cycle of the plurality of modelled PPG cycles is indicative of the heart cycle comprising the set of initial modelled cardiac parameters; estimate a set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality of modelled PPG cycles, based on 15 an optimization function ( ( )) using a particle swarm optimization (PSO) technique; and generate the synthesized PPG signal, based on the modelled PPG signal and the corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles.
[008] It is to be understood that both the foregoing general description 20 and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[009] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together 25 with the description, serve to explain the disclosed principles:
[010] FIG.1 is a functional block diagram of a system for estimating optimized cardiac parameters to generate a synthesized Photoplethysmogram (PPG) signal using a cardiovascular model, according to some embodiments of the present disclosure. 30
6

[011] FIG.2 is an example block diagram illustrating a processor-implemented method for estimating optimized cardiac parameters to generate a synthesized PPG signal using a cardiovascular model, according to some embodiments of the present disclosure.
[012] FIG.3 is an exemplary flow diagram of a processor-implemented 5 method for estimating optimized cardiac parameters to generate a synthesized PPG signal using a cardiovascular model, according to some embodiments of the present disclosure.
[013] FIG.4 is a graph showing evaluation error of a modelled PPG signal at each particle swarm optimization (PSO) iteration, with and without a 10 singular spectrum analysis (SSA) technique, according to some embodiments of the present disclosure.
[014] FIG.5 is a graph showing comparison results of measured PPG signal, and synthesized PPG signal with and without a singular spectrum analysis (SSA) technique along with a PSO technique, in accordance with some 15 embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[015] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference 20 number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed 25 embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following claims.
[016] Synthetic or synthesized Photoplethysmogram (PPG) signals are important for creating training data to enhance efficacy of machine learning (ML) related technologies that may be used in many early diagnostics scenarios. 30 Generation of the synthesized PPG signals include determination of a set of
7

parameters including, for example, a systolic phase gain, a diastolic phase gain, a systolic phase time-delay, a diastolic phase time-delay, a heart cycle, an arterial blood pressure, a left ventricular blood pressure, and a right ventricular blood pressure. Conventional methods provide different techniques to generate the synthesized PPG signals mathematically, for example, fitting multiple Gaussian 5 waveforms, fitting with the Log-normal bases and stochastic modelling. For instance, conventionally, a six-Gaussian model is used to fit and generate the synthesized PPG signal, however efficiency of this model may not be appropriate for daily monitoring of cardiovascular health of a subject. With the Log-normal bases, approximation may not be adjusted to different PPG signals independently 10 thus an accuracy of the synthesized PPG signal may be reduced.
[017] In stochastic modelling, subject specific atlases of the PPG signals are generated along with parameters to provide regeneration of statistically equivalent PPG signals by utilizing shape parameterization and a nonstationary model of PPG signal time evolution. However, this technique generates only 15 subject specific PPG signatures and do not correlate with pathophysiological changes. Further, the discussed conventional methods lack with interpretability. The Applicant has addressed these concerns in Indian patent application no. 201921029536, filed on July 22, 2019.
[018] The applicant discussed about a method and system for pressure 20 autoregulation based synthesizing of PPG signal, in the Indian patent application no. 201921029536. In various embodiments of the Indian patent application no. 201921029536, a hemodynamic cardiovascular model is disclosed. Said hemodynamic cardiovascular model comprises a two chambered heart with contractility function, a plurality of blood vessels with flow dynamics, and a 25 baroreflex control, that is used to generate a modelled PPG signal. A measured PPG signal is received from a ‘physionet MIMIC II’ database. A feature set corresponding to the modelled PPG signal and a feature set corresponding to the measured PPG signal are extracted using the estimation algorithm. Lastly to tune the set of parameters including the systolic phase gain, the diastolic phase gain, 30 the systolic phase time-delay, the diastolic phase time-delay associated with the
8

synthesized PPG signal, a particle-swarm-optimization (PSO) technique is used to minimize an integral-squared-error (ISE) of each element of the feature set.
[019] However, the generation of an enhanced synthesized PPG signals with better accuracy is always an area of improvement. System and method of the present disclosure estimates a set of optimized cardiac parameters to generate a 5 synthesized PPG signal using the cardiovascular model. The generated synthesized PPG signal of the present disclosure is further enhanced with improved accuracy compared to the generated synthesized PPG signal of the disclosure of the Indian patent application no. 201921029536, as will be shown by way of experimental results illustrated and described with reference to FIG.4 and 10 FIG.5. In particular, various embodiments disclosed herein utilized a hemodynamic cardiovascular model to generate the modelled PPG signals, the complete details of which are disclosed in the Indian patent application no. 201921029536.
[020] Referring now to the drawings, and more particularly to FIG.1 15 through FIG.5, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[021] FIG.1 is a functional block diagram of a system for estimating 20 optimized cardiac parameters to generate a synthesized PPG signal using a cardiovascular model, according to some embodiments of the present disclosure. In an embodiment, the system 100 includes or is otherwise in communication with one or more hardware processors 104, communication interface device(s) or input/output (I/O) interface(s) 106, and one or more data storage devices or 25 memory 102 operatively coupled to the one or more hardware processors 104. The one or more hardware processors 104, the memory 102, and the I/O interface(s) 106 may be coupled to a system bus 108 or a similar mechanism.
[022] The I/O interface(s) 106 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and 30 the like. The I/O interface(s) 106 may include a variety of software and hardware
9

interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a plurality of sensor devices, a printer and the like. Further, the I/O interface(s) 106 may enable the system 100 to communicate with other devices, such as web servers and external databases.
[023] The I/O interface(s) 106 can facilitate multiple communications 5 within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface(s) 106 may include one or more ports for connecting a number of computing systems with one another or to another server computer. Further, the I/O 10 interface(s) 106 may include one or more ports for connecting a number of devices to one another or to another server.
[024] The one or more hardware processors 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any 15 devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 are configured to fetch and execute computer-readable instructions stored in the memory 102.
[025] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random 20 access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 102 includes a plurality of modules 102A, a cardiovascular unit 102B, and a repository 102C for storing data processed, 25 received, and generated by one or more of the plurality of modules 102A and the cardiovascular unit 102B. The cardiovascular unit 102B includes the cardiovascular model (not shown in FIG. 1) and other modules (not shown in FIG. 1). The plurality of modules 102A may include routines, programs, objects, components, data structures, and so on, which perform particular tasks or 30 implement particular abstract data types.
10

[026] The plurality of modules 102A may include programs or computer-readable instructions or coded instructions that supplement applications or functions performed by the system 100. The plurality of modules 102A may also be used as, signal processor(s), state machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions. 5 Further, the plurality of modules 102A can be used by hardware, by computer-readable instructions executed by the one or more hardware processors 104, or by a combination thereof. In an embodiment, the plurality of modules 102A can include various sub-modules (not shown in FIG.1).
[027] The repository 102C may include a database having a dataset 10 comprising a plurality of measured PPG signals indicative of healthy and unhealthy subjects. In an embodiment, the dataset may include the dataset comprised in a ‘physionet MIMIC II’ database or any such other dataset having the measured PPG signals. Further, the repository 102C amongst other things, may serve as a database for storing the data that is processed, received, or 15 generated as a result of the execution of the plurality of modules 102A and the modules associated with the cardiovascular unit 102B.
[028] Although the repository 102C is shown internal to the system 100, it will be noted that, in alternate embodiments, the repository 102C can also be implemented external to the system 100, where the repository 102C may be stored 20 within an external database (not shown in FIG. 1) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. For example, new data may be added into the external database and/or existing data may be modified and/or non-useful data may be deleted from the external database. In one example, the data may be stored in an external system, 25 such as a Lightweight Directory Access Protocol (LDAP) directory and a Relational Database Management System (RDBMS). In another embodiment, the data stored in the repository 102C may be distributed between the system 100 and the external database. The components and functionalities of the system 100 are described further in detail with reference to FIG.2 and FIG.3. 30
11

[029] Referring collectively to FIG.2 and FIG.3, components and functionalities of the system 100 are described in accordance with an example embodiment of the present disclosure. For example, FIG.2 is an example block diagram 200 illustrating a processor-implemented method 300 for estimating optimized cardiac parameters to generate a synthesized PPG signal using a 5 cardiovascular model 202, according to some embodiments of the present disclosure. FIG.3 is an exemplary flow diagram of a processor-implemented method 300 for estimating optimized cardiac parameters to generate a synthesized PPG signal using a cardiovascular model, for example a cardiovascular module 202 (FIG.2) according to some embodiments of the present disclosure. Although 10 steps of the method 300 including process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes 15 described herein may be performed in any order practical. Further, some steps may be performed simultaneously.
[030] At step 302 of the method 300, the one or more hardware processors 104 of the system 100 are configured to receive a measured PPG signal from a measured PPG signals database 204 (FIG.2) having the plurality of 20 measured PPG signals. In an embodiment, the measured PPG signals database 204 is the ‘physionet MIMIC II’ database. Each of the measured PPG signal includes a plurality of measured PPG cycles. Each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate (Th) and a set of measured cardiac parameters. The heart rate (Th) is 25 determined from a duration of the heart cycle. The set of measured cardiac parameters includes the systolic phase gain, the diastolic phase gain, the systolic phase time-delay, the diastolic phase time-delay, the heart cycle, the arterial blood pressure, the left ventricular blood pressure, and the right ventricular blood pressure. 30
12

[031] At step 304 of the method 300, the one or more hardware processors 104 of the system 100 are configured to calculate Eigenvalues and associated Eigenvectors (for example, Eigenvalues and Eigenvectors marked as 208 in FIG.2) of the each measured PPG cycle of the plurality of measured PPG cycles. In an embodiment, the Eigenvalues and the associated Eigenvectors of the 5 each measured PPG cycle are calculated using a singular spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique. A time-series signal of the corresponding measured PPG cycle is mapped into a sequence of logged vectors using the singular spectrum analysis (SSA) technique, to obtain a trajectory matrix of the corresponding measured PPG cycle. The sequence of 10 logged vectors represent coordinates of the corresponding time-series signal. A sample representation of the trajectory matrix for the time-series signal ( ) ( ) of the corresponding measured PPG cycle is mentioned below:

[ ]
where L is defined as a window length which is large enough to 15 account for information about data variation from the time-series signal ( ). A first column of the trajectory matrix has a length of L data of the actual corresponding time-series signal ( ) such that 10} restricts number of Eigenvalues corresponding to domain components. Let us assume that the Eigenvalues are denoted by and the associated Eigenvectors are denoted by of the each measured PPG cycle of the plurality of measured PPG cycles. 5
[033] At step 306 of the method 300, the one or more hardware processors 104 of the system 100 are configured to acquire a modelled PPG signal using the cardiovascular model 202. The modelled PPG signal includes a plurality of modelled PPG cycles. The cardiovascular model is a hemodynamic cardiovascular model including a two chambered heart unit 202B (FIG.2) 10 connected with a contractility function unit 202A (FIG.2), a plurality of blood vessels with flow dynamics (not shown in FIG.2), and a baroreflex control mechanism (not shown in FIG.2), and a modelled PPG function unit 202C (FIG.2).
[034] In an embodiment, the two chambered heart unit 202B includes a 15 right chamber and a left chamber. The plurality of blood vessels including a pulmonary vessel and a systemic vessel. The right chamber is having a right auricle and a right ventricle. The left chamber includes a left auricle and a left ventricle. The systemic vessel is connected to the right ventricle with a tricuspid valve and systemic vein. The systemic vessel is connected to the left ventricle via 20 aortic valve and systemic artery. The pulmonary vessel is connected to the right auricle via pulmonary valve and pulmonary artery. The pulmonary vessel is connected to the left auricle via mitral valve and pulmonary vein. The pulmonary vessel is connected to the right auricle via pulmonic valve and pulmonary artery. The pulmonary artery and systemic vein carries deoxygenated blood. The 25 systemic artery and pulmonary vein carries oxygenated blood. In an embodiment, the cardiovascular model 202 is simulated using a Simulink platform.
14

[035] In an embodiment, the baroreflex control mechanism is adapted from pulsatile heart and vascular dynamics. The baroreflex control mechanism is implemented using three different controllers to capture the effect of aortic pressure variation, namely, a controller to adjust the total systemic arterial resistance or vascular tone, heart rate and a contractility function controller. The 5 baroreflex control mechanism is associated with a feedback mechanism. The feedback mechanism is divided in three parts: (i) affector part, denoting the baroreceptors, for sensing any change in arterial pressure through change in cross sectional area of carotid sinus region and generates a firing rate. (ii) The central nervous system (CNS), generates sympathetic and parasympathetic nerve 10 activities depending on the firing rate of affector parts and is fed to effector organs. (iii) The effector organs are the target areas controls heart rate, contractility and peripheral resistance to regulate blood pressure across the plurality of blood vessels.
[036] In an embodiment, the ventricles of the cardiovascular model 202 15 are modeled as compliant vessels with dynamic compliance property. During diastole, the compliance increases accommodating larger volume of blood. During systole, the compliance decreases, becoming rigid to contract ejecting blood with higher pressure. Flow equations are given in equations 1 to 6.

( ) ( ) ………………..(1) 20
( ) ( ) ( )……………..(2)
( ) ( ) ( )…………….(3)
…………………………..(4)
…………………………..(5)
…………………………..(6) 25
where, V, C, P and Q represents volume, compliance, pressure and flow through various compartments, subscript SA indicates systemic artery, LV represents left ventricle and RV is right ventricle, Ao is aorta, Mi is a mitral valve, is a tricuspid valve and PV is a pulmonary vein. 15

[037] In an embodiment, the blood pressure control is an integral component of cardiovascular mechanism which operates in a feedback mechanism, regulating pressure, thereby regulating flow, heart rate and vascular tone. The feedback mechanism for controlling blood pressure is performed by utilizing a baroreflex feedback mechanism. The baroreflex controller of the 5 baroreflex control mechanism is sensitive to changes in aortic pressure, sensed through baroreceptors placed mainly at carotid sinus region.
[038] In an embodiment, the measured PPG signal received from the measured PPG signals database 204, is directly fed back to the cardiovascular model 202 so that the contractility function unit 202A may learn the PPG cycle 10 duration of the each measured PPG cycle of the plurality of measured PPG cycles. The modelled PPG function unit 202C of the cardiovascular model 202 generates the modelled PPG signal based on the arterial blood pressure (ABP), the right ventricular pressure (RVP), the systemic ventricular pressure (SVP), heart rate of the each measured PPG cycle, and a set of modelled cardiac parameters of each 15 modelled PPG cycle. Each modelled PPG cycle of the plurality of PPG cycles includes the heart rate as same as that of the heart rate (Th) of the corresponding measured PPG cycle of the plurality of measured PPG cycles, so that total duration of the heart cycle is maintained in the plurality of measured PPG cycles of the measured PPG signal and in the plurality of modelled PPG cycles of the 20 modelled PPG signal.
[039] In an embodiment, the set of modelled cardiac parameters of each modelled PPG cycle includes the corresponding systolic phase gain, the corresponding diastolic phase gain, the corresponding systolic phase time-delay, and the corresponding diastolic phase time-delay. In an embodiment, the modelled 25 cardiac parameters of distinct modelled PPG cycles maybe same or different. A PPG function of the each modelled PPG cycle ( ( )) of the plurality of modelled PPG cycle of the modelled PPG signal generated by the modelled PPG function unit 202C, can be represented according to a relation:

( ) [ ( ) ( )] ( 30 ) ……..(7) 16

where is the corresponding systolic phase gain, is the corresponding diastolic phase gain, is the corresponding systolic phase time-delay, is the corresponding diastolic phase time-delay, is the arterial blood pressure, is the left ventricular blood pressure, and is the right ventricular blood pressure. 5
[040] In an embodiment, the arterial blood pressure , the left ventricular blood pressure and the right ventricular blood pressure are supplied by the two chambered heart unit 202B. However the corresponding systolic phase gain , the corresponding diastolic phase gain , the corresponding systolic phase time-delay , and the corresponding diastolic 10 phase time-delay are to be determined for each modelled PPG cycle in order to obtain the synthesized PPG signal. Hence the cardiovascular model 202 generates the modelled PPG signal based on the set of initial modelled cardiac parameters at first instance. For example: =a1, =a2, =a3, and =a4.
[041] At step 308 of the method 300, the one or more hardware 15 processors 104 of the system 100 are configured to estimate the set of optimized cardiac parameters (for example, cardiac parameters marked as 210 in FIG.2) of the each modelled PPG cycle of the plurality of modelled PPG cycles. In an embodiment, the set of optimized cardiac parameters of the each modelled PPG cycle are estimated by minimizing an optimization function ( ( )) using the 20 particle swarm optimization (PSO) technique, as described below.
[042] Firstly, Eigenvalues and associated Eigenvectors of the each modelled PPG cycle (for example, Eigenvalues and Eigenvectors marked as 206 in FIG.2) are calculated using the singular spectrum analysis (SSA) technique and the singular value decomposition (SVD) technique, as explained at step 304 of the 25 method 300. Herein, the Eigenvalues are denoted by and the associated Eigenvectors are denoted by of the each modelled PPG cycle of the plurality of measured PPG cycles.
[043] Secondly, the optimization function ( ( )) is derived based on a L2-norm between the associated Eigenvectors with respect to the 30
17

Eigenvalues of the corresponding measured PPG cycle, and the associated Eigenvectors with respect to the Eigenvalues of the corresponding modelled PPG cycle. The corresponding measured PPG cycle and the corresponding modelled PPG cycle indicate that the optimization function ( ( )) is derived between the first measured PPG cycle of the measured PPG signal and 5 the first modelled PPG cycle of the modelled PPG signal. Similarly, the optimization function ( ( )) is derived between the last measured PPG cycle of the measured PPG signal and the last modelled PPG cycle of the modelled PPG signal.
[044] Lastly, the derived optimization function ( ( )) is minimized 10 using the PSO technique in order to estimate the set of optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles. The PSO technique is initialized to perform a plurality of PSO iterations on the corresponding modelled PPG cycle. In an embodiment, a number of the plurality of PSO iterations is equivalent to a number of the Eigenvalues of the 15 corresponding modelled PPG cycle, or may be pre-defined. Each PSO iteration of the plurality of PSO iterations comprises a set of PSO particle iterations. For example, a number of set of PSO particle iterations may be 20. In an embodiment, a dimension of the PSO particle iteration is four, which indicate that four parameters can be obtained from each PSO particle iteration based on a position 20 and velocity of the particle at the corresponding PSO particle iteration.
[045] In an embodiment, the optimization function ( ( )) with respect to the PSO technique is represented according to a relation:

( ) Σ‖ ‖ ……………………...(8) 25
where refers to the Eigenvalues of the corresponding modelled PPG cycle, refers to the associated Eigenvectors of the corresponding modelled PPG cycle, refers to the Eigenvalues of the 30 18

corresponding measured PPG cycle, refers to the associated Eigenvectors of the corresponding measured PPG cycle, r refers to the number of the plurality of PSO iterations, and Z refers to the number of the set of PSO particle iterations.
[046] Each PSO particle iteration of the set of PSO particle iterations 5 outputs a local value of the optimization function (i.e., local value of the ( )). Hence each PSO iteration comprises a set of local values of the optimization function, corresponding to the set of PSO particle iterations. A PSO particle iteration (amongst the set of PSO particle iterations within the corresponding PSO iteration) having a best local value of the optimization function (i.e., minimum 10 local value of the optimization function) is identified. Accordingly, a set of intermediate cardiac parameters are obtained from the PSO particle iteration having the best local value of the optimization function, within the corresponding PSO iteration. It is understood that the intermediate cardiac parameters obtained within the PSO iteration are the intermediate values of the cardiac 15 parameters , , and . For example, =a100, =a200, =a300, and =a400.
[047] Each current iteration of the plurality of PSO iterations is performed based on a modified modelled PPG signal. In an embodiment, the modified modelled PPG signal is acquired from the modelled PPG function unit 20 202C of the cardiovascular model 202, based on the heart rate (Th) of the corresponding measured PPG cycle and the set of intermediate cardiac parameters obtained from a preceding iteration of the plurality of PSO iterations. At each current PSO iteration except the first PSO iteration, the step 308 of the method 300 is repeated such that a set of best local values of the optimization function 25 associating with the plurality of PSO iterations, are obtained. A global value of the optimization function is identified from the set of best local values of the optimization function associating with the plurality of PSO iterations, i.e., the minimum best local value of the optimization function. The corresponding optimized cardiac parameters are estimated from the PSO iteration having the 30 global value of the optimization function.
19

[048] In the PSO technique, the particle in the each PSO particle iteration is initialized with the position and the velocity. The position comprises two dimensions which mimic the corresponding systolic phase gain and the corresponding systolic phase time-delay . Similarly, the velocity comprises two dimensions which mimic the corresponding diastolic phase gain and the 5 corresponding diastolic phase time-delay . The velocity of each particle is updated at each PSO particle iteration and the position of the each particle is updated by applying with a new velocity to previous position of the particle. The velocity of each particle is updated at each PSO particle iteration according to a relation: 10

( ) ( ) ̂ ( ) ( ) ( ) ( )
where i represents index of the particle, ( ) is the velocity of the particle i at time t, ( ) is the position of the particle i at time t. , , are predefined coefficients, where , and . and are random values regenerated at each velocity update. A value of ̂ ( ) indicates best local value of the optimization function for 15 particle i at time t, and ( ) indicates a global value of the optimization function (the minimum best local value of the optimization function) at time t.
[049] At step 310 of the method 300, the one or more hardware processors 104 of the system 100 are configured to generate the synthesized PPG 20 signal from the modelled PPG function unit 202C of the cardiovascular model 202. In an embodiment, the synthesized PPG signal is generated based on the modelled PPG signal and the corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles.
[050] In accordance with an embodiment of the present disclosure, an 25 objective of the optimization function ( ( )) is to minimize a difference between the measured PPG signal and the modelled PPG signal, so that an optimized modelled PPG signal which is close to the measured PPG signal can be considered as the synthesized PPG signal. The singular spectrum analysis (SSA) based technique has been employed to extract features of the modelled PPG signal 30
20

generated by the cardiovascular model 202 and the measured PPG signal received from the measured PPG signals database 204 having the measured PPG signals. Finally, the PSO technique is exploited to minimize the error between the extracted features with respect to the features of the measured PPG signal. Hence, the system 100 of the present disclosure generates much enhanced synthesized 5 PPG signal with better accuracy compared the synthesized PPG signal generated from the disclosure of the applicant’s Indian patent application no. 201921029536.
[051] FIG.4 is a graph showing evaluation error of a modelled PPG signal at each PSO iteration, with and without a SSA technique, according to 10 some embodiments of the present disclosure. A curve of the synthesized PPG signal generated from the disclosure of the applicant’s Indian patent application no. 201921029536 is denoted with ‘PSO’ and the curve of the synthesized PPG signal generated from the present disclosure is denoted with ‘SSA-PSO’. It may be observed that an evaluated error between the measured PPG signal and the 15 modelled PPG signal at each PSO iteration of the PSO technique according to the present disclosure is lesser compared to the evaluated error between the measured PPG signal and the modelled PPG signal at each PSO iteration of the PSO technique according to the applicant’s Indian patent application no. 201921029536. 20
[052] FIG.5 is a graph showing comparison results of measured PPG signal, and synthesized PPG signal with and without a SSA technique along with a PSO technique, in accordance with some embodiments of the present disclosure. A curve of the measured PPG signal received from the measured PPG signals database 204 is denoted as ‘Measured PPG’. A curve of the synthesized PPG 25 signal generated from the embodiments of the applicant’s Indian patent application no. 201921029536 is denoted as ‘PSO’ and the curve of the synthesized PPG signal generated from the present embodiments is denoted as ‘SSA-PSO’. It may be observed that the synthesized PPG signal generated from the present disclosure (SSA-PSO) is much closure to the measured PPG signal 30 received from the measured PPG signals database 204 (Measured PPG) compared
21

to the synthesized PPG signal generated from the embodiments of the applicant’s Indian patent application no. 201921029536 (PSO). Hence the synthesized PPG signal generated from the present disclosure (SSA-PSO) is enhanced and accurate compared to the synthesized PPG signal generated from the embodiments of the applicant’s Indian patent application no. 201921029536 (PSO). 5
[053] In order to analyze performance of the present disclosure, a mean and a variance of a peak-to-notch amplitude ratio, a peak time and a notch time are computed for each cycle of the synthesized PPG signal are generated from the embodiments of the present disclosure and the synthesized PPG signal generated from the embodiments of the applicant’s Indian patent application no. 10 201921029536. The mean peak-to-notch amplitude ratio error of the synthesized PPG signal generated based on the embodiments of the present disclosure is 1.4%, whereas the error is around 23% for the synthesized PPG signal generated based on the embodiments of the applicant’s Indian patent application no. 201921029536. Additionally, for the peak time and the notch time, evaluated 15 errors are 0.6% and 0.4% respectively with the embodiments of the present disclosure, whereas the evaluated errors are around 2% and 2.3% respectively for the embodiments of the applicant’s Indian patent application no. 201921029536.
[054] Table.1 shows the performance results of the present disclosure (denoted by ‘SSA-PSO’), the disclosure of the applicant’s Indian patent 20 application no. 201921029536 (denoted by ‘PSO’) and the measured PPG signal received from the measured PPG signals database 204 (denoted by ‘Measured PPG’).

Performance parameters Measured PPG PSO SSA-PSO
Mean Variance Mean Variance Mean Variance
Heart Rate 81 80.16 80.65
Peak vs. Notch Amplitude Ratio 6.22 6.53 8.87 15.66 6.31 9.28
Peak Time
(in min) 4.92e-5 1.4e-6 5.02e-5 3.05e-6 4.95e-5 1.4e-6
Notch Time
(in min) 5.08e-5 1.5e-6 5.2e-5 5.9e-6 5.1e-5 2.7e-6
Table. 1
[055] In order to analyze performance of the present disclosure, PPG features such as an Ejection time compensation ( ), a Elasticity index (EI) and 5 a cardiac ejection elasticity index (EEI) of the measured PPG signal received from the measured PPG signals database 204 are compared to the PPG features of the synthesized PPG signal generated from the embodiments of the present disclosure and the synthesized PPG signal generated from the embodiments of the applicant’s Indian patent application no. 201921029536. For the sake of brevity, a 10 brief portion of the performance results, having the mean and a standard-deviation of the PPG features from the measured PPG signal received from the measured PPG signals database 204 (denoted with “Measured PPG’), the synthesized PPG signal generated from the embodiments of the present disclosure (denoted with ‘SSA-PSO’) and the synthesized PPG signal generated from the embodiments of 15 the applicant’s Indian patent application no. 201921029536 (denoted with ‘PSO’) are provided in the Table 2

PPG Features Measured PSO SSA-PSO
Mean SD Mean SD Mean SD
Ejection time compensation 338.23 31.75 328.5 45.92 336.86 33.85
Elasticity index 6.22 6.53 7.18 12.41 6.31 9.28
Cardiac ejection
elasticity index 0.48 0.29 0.57 1.43 0.52
Table. 2 20
[056] It may be observed from the Table 2 that the mean and the standard-deviation of the PPG features of the measured PPG signal received from the measured PPG signals database 204 (denoted with “Measured PPG’) and the synthesized PPG signal generated from the embodiments of the present disclosure 25 (denoted with ‘SSA-PSO’) are much closer compared to the PPG features of the
23

measured PPG signal received from the measured PPG signals database 204 (denoted with “Measured PPG’) and the synthesized PPG signal generated from the embodiments of the disclosure of the applicant’s Indian patent application no. 201921029536.
[057] Even though the embodiments of the present disclosure generates 5 the synthesized PPG signal with plurality of PPG cycles, it is understood that the present disclosure can be applied to single cycle PPG signal. Also in accordance with the present disclosure, the cardiovascular model 202 can generate different PPG templates as per requirement, mainly by changing and tuning the plurality of physiological parameters of the model. The different PPG templates include PPG 10 templetes indicative of healthy subjects and unhealthy subjects. In an example, the unhealthy subject may represent a subject suffering from Atherosclerosis condition, and thus PPG template associated with the unhealthy subject may be indicative of Atherosclerosis condition. Atherosclerosis is a vascular disease resulting in narrowing of blood vessels due to plaque deposition in vascular wall. 15 Hence various kinds of synthesized PPG signals of the healthy subject and the unhealthy subject may be generated and the synthesized PPG data can be utilized for analyzing and diagnosing pertaining to various disease conditions. It will be noted that herein that for the sake of description, the unhealthy subject is considered to be associated with Atherosclerosis condition, however, in various 20 other example scenarios, the unhealthy subject may be associated with other conditions, and the cardiovascular model disclosed herein may be utilized for generating different PPG templates for said conditions.
[058] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope 25 of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims. 30
24

[059] The embodiments of present disclosure herein addresses unresolved problem of generating the plurality of enhanced synthetic PPG signals corresponding to a plurality of health conditions. Further, the disclosed system (for example, the system 100 of FIG. 1) can be utilized to train the Machine Learning model to analyze and diagnose such health conditions based on the PPG 5 signals pertaining to various diseases.
[060] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a 10 server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-15 programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may 20 also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[061] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed 25 by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, 30 apparatus, or device.
25

[062] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been 5 arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. 10 Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It 15 must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[063] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A 20 computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term 25 “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media. 30
26

[064] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.

5 27

We Claim:
1. A processor-implemented method (300) for estimating optimized cardiac parameters to generate a synthesized Photoplethysmogram (PPG) signal using a cardiovascular model, the method (300) comprising the steps of:

receiving, via one or more hardware processors, a measured 5 PPG signal from a database, wherein the measured PPG signal comprises a plurality of measured PPG cycles, each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate (Th) and a set of measured cardiac parameters (302); 10
calculating, via the one or more hardware processors, Eigenvalues and associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, using a singular spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique (304); 15
acquiring, based on the heart rate (Th) of the each measured PPG cycle of the measured PPG signal and a set of initial modelled cardiac parameters, a modelled PPG signal using the cardiovascular model, via the one or more hardware processors, wherein the modelled PPG signal comprises a plurality of modelled PPG cycles, each modelled 20 PPG cycle of the plurality of modelled PPG cycles is indicative of the heart cycle comprising the set of initial modelled cardiac parameters (306);
estimating, via the one or more hardware processors, a set of optimized cardiac parameters corresponding to the each modelled 25 PPG cycle of the plurality of modelled PPG cycles, based on an optimization function ( ( )) using a particle swarm optimization (PSO) technique (308); and
generating the synthesized PPG signal, via the one or more hardware processors, based on the modelled PPG signal and the 30 28

corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled PPG cycles (310).
2. The method of claim 1, wherein estimating the set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality 5 of modelled PPG cycles, comprises:

calculating Eigenvalues and associated Eigenvectors of the corresponding modelled PPG cycle, using the singular spectrum analysis (SSA) technique and the singular value decomposition (SVD) technique; 10
initializing the PSO technique to perform a plurality of PSO iterations on the corresponding modelled PPG cycle, wherein each PSO iteration of the plurality of PSO iterations comprises a set of PSO particle iterations, each PSO particle iteration of the set of PSO particle iterations outputs a local value of the optimization 15 function such that each PSO iteration outputs a set of intermediate cardiac parameters based on the PSO particle iteration having best local value of the optimization function, and wherein each current iteration of the plurality of PSO iterations is performed based on a modified modelled PPG signal acquired based on the heart rate 20 (Th) of the corresponding measured PPG cycle and the set of intermediate cardiac parameters obtained from a preceding iteration of the plurality of PSO iterations, using the cardiovascular model; and
estimating the corresponding optimized cardiac parameters, 25 based on a global value of the optimization function obtained from a set of best local values of the optimization function associating with the plurality of PSO iterations.
3. The method of claim 2, wherein the optimization function ( ( )) is 30 obtained based on a L2-norm between the associated Eigenvectors with respect to the Eigenvalues of the corresponding measured PPG cycle, and
29

the associated Eigenvectors with respect to the Eigenvalues of the corresponding modelled PPG cycle.

4. The method of claim 2, wherein the optimization function ( ( )) with respect to the PSO technique is represented according to a relation: 5

( ) Σ‖ ‖
where refers to the Eigenvalues of the corresponding modelled PPG cycle, refers to the associated Eigenvectors of the 10 corresponding modelled PPG cycle, refers to the Eigenvalues of the corresponding measured PPG cycle, refers to the associated Eigenvectors of the corresponding measured PPG cycle, r refers to a number of the plurality of PSO iterations, and Z refers to a number of the set of PSO particle iterations. 15
5. The method of claim 1, wherein the Eigenvalues and the associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, are calculated by:

mapping a time-series signal of the corresponding measured 20 PPG cycle into a sequence of logged vectors using the singular spectrum analysis (SSA) technique, to obtain a corresponding trajectory matrix, wherein the sequence of logged vectors represent coordinates of the corresponding time-series signal; and
calculating the Eigenvalues and the associated Eigenvectors of 25 the corresponding measured PPG cycle, based on the corresponding trajectory matrix, using the singular value decomposition (SVD) technique.
6. The method of claim 2, wherein the Eigenvalues and the associated 30 Eigenvectors of the corresponding modelled PPG cycle, are calculated by:
30

mapping a time-series signal of the corresponding modelled PPG cycle into a sequence of logged vectors using the singular spectrum analysis (SSA) technique, to obtain a corresponding trajectory matrix, wherein the sequence of logged vectors represent coordinates of the corresponding time-series signal; and 5
calculating the Eigenvalues and the associated Eigenvectors of the corresponding modelled PPG cycle, based on the corresponding trajectory matrix, using the singular value decomposition (SVD) technique.
10
7. The method of claim 2, wherein a number of the plurality of PSO iterations is calculated based on a number of the Eigenvalues of the corresponding modelled PPG cycle.

8. A system (100) for estimating optimized cardiac parameters to generate a 15 synthesized Photoplethysmogram (PPG) signal using a cardiovascular model, the system (100) comprising:

a memory (102) storing instructions;
one or more communication interfaces (106);
a cardiovascular unit (102B) stored in the memory (102), 20 wherein the cardiovascular unit (102B) comprises the cardiovascular model; and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured 25 by the instructions to:
receive a measured PPG signal from a database, wherein the measured PPG signal comprises a plurality of measured PPG cycles, each measured PPG cycle of the plurality of measured PPG cycles is indicative of a heart cycle comprising a heart rate 30 (Th) and a set of measured cardiac parameters; 31

calculate Eigenvalues and associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, using a singular spectrum analysis (SSA) technique and a singular value decomposition (SVD) technique;
acquire, based on the heart rate (Th) of the each measured 5 PPG cycle of the measured PPG signal and a set of initial modelled cardiac parameters, a modelled PPG signal using the cardiovascular model, wherein the modelled PPG signal comprises a plurality of modelled PPG cycles, each modelled PPG cycle of the plurality of modelled PPG cycles is indicative 10 of the heart cycle comprising the set of initial modelled cardiac parameters;
estimate a set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality of modelled PPG cycles, based on an optimization function 15 ( ( )) using a particle swarm optimization (PSO) technique; and
generate the synthesized PPG signal, based on the modelled PPG signal and the corresponding optimized cardiac parameters of the each modelled PPG cycle of the plurality of modelled 20 PPG cycles.
9. The system of claim 8, wherein to estimate the set of optimized cardiac parameters corresponding to the each modelled PPG cycle of the plurality of modelled PPG cycles, the one or more hardware processors (104) are 25 further configured by the instructions to:

calculate Eigenvalues and associated Eigenvectors of the corresponding modelled PPG cycle, using the singular spectrum analysis (SSA) technique and the singular value decomposition (SVD) technique; 30 32

initialize the PSO technique to perform a plurality of PSO iterations on the corresponding modelled PPG cycle, wherein each PSO iteration of the plurality of PSO iterations comprises a set of PSO particle iterations, each PSO particle iteration of the set of PSO particle iterations outputs a local value of the optimization 5 function such that each PSO iteration outputs a set of intermediate cardiac parameters based on the PSO particle iteration having best local value of the optimization function, and wherein each current iteration of the plurality of PSO iterations is performed based on a modified modelled PPG signal acquired based on the heart rate 10 (Th) of the corresponding measured PPG cycle and the set of intermediate cardiac parameters obtained from a preceding iteration of the plurality of PSO iterations, using the cardiovascular model; and
estimate the corresponding optimized cardiac parameters, 15 based on a global value of the optimization function obtained from a set of best local values of the optimization function associating with the plurality of PSO iterations.
10. The system of claim 9, wherein the one or more hardware processors (104) 20 are further configured by the instructions, to obtain the optimization function ( ( )) based on a L2-norm between the associated Eigenvectors with respect to the Eigenvalues of the corresponding measured PPG cycle, and the associated Eigenvectors with respect to the Eigenvalues of the corresponding modelled PPG cycle. 25

11. The system of claim 8, wherein to calculate the Eigenvalues and the associated Eigenvectors of the each measured PPG cycle of the plurality of measured PPG cycles, the one or more hardware processors (104) are further configured by the instructions to: 30

map a time-series signal of the corresponding measured PPG cycle into a sequence of logged vectors using the singular spectrum 33

analysis (SSA) technique, to obtain a corresponding trajectory matrix, wherein the sequence of logged vectors represent coordinates of the corresponding time-series signal; and
calculate the Eigenvalues and the associated Eigenvectors of the corresponding measured PPG cycle, based on the corresponding trajectory 5 matrix, using the singular value decomposition (SVD) technique.
12. The system of claim 9, wherein to calculate the Eigenvalues and the associated Eigenvectors of the corresponding modelled PPG cycle, the one or more hardware processors (104) are further configured by the 10 instructions to:

map a time-series signal of the corresponding modelled PPG cycle into a sequence of logged vectors using the singular spectrum analysis (SSA) technique, to obtain a corresponding trajectory matrix, wherein the sequence of logged vectors represent coordinates of the 15 corresponding time-series signal; and
calculate the Eigenvalues and the associated Eigenvectors of the corresponding modelled PPG cycle, based on the corresponding trajectory matrix, using the singular value decomposition (SVD) technique.

13. The system of claim 9, wherein the one or more hardware processors (104) are further configured by the instructions to calculate a number of the plurality of PSO iterations, based on a number of the Eigenvalues of the corresponding modelled PPG cycle.