Method and system to determine cardio respiratory fitness of user with interactive solution

Abstract

Embodiments herein provide a method and a system for determining a cardio respiratory fitness of the user with an interactive solution. The solution includes establishing a connection between mobile device and wearable sensor device using short-range communication and receiving and storing Movement Intensity (MI) and a Heart Rate (HR) of user wearing wearable sensor device while performing a physical activity at a predefined place. The mobile device displays dynamic user interface based on MI and HR, which includes user avatar, at least two antagonist characters and performance indicator (PI). The mobile device controls position and movements of the user avatar across the deviation factor spectrum. Also, mobile device increases performance level of the user based on MI and HR and determines the cardio respiratory fitness of the user based on the at least one of HR, the MI and the combinations of HR and MI.

Description

TITLE OF THE INVENTION“METHOD AND SYSTEM TO DETERMINE CARDIO RESPIRATORY FITNESS OF USER WITH INTERACTIVE SOLUTION”The following specification particularly describes the invention and the manner in which it is to be performed: -FIELD OF INVENTION

[0001] The present application is based on and claims priority from an Indian Provisional Application Number 202441049881 filed on 28th June 2024, the disclosure of which is hereby incorporated by reference herein. The proposed embodiments relate to Internet of Things (loT), and more particularly to a method and system to determine cardio respiratory fitness of user with interactive solution.BACKGROUND

[0002] Elevated physical performance is intrinsically linked to the body's ability to effectively utilize oxygen. At the forefront of this capability lies VO2 max, a pivotal measure indicating the pinnacle of an individual’s aerobic capacity. VO2 max represents the maximum amount of oxygen intake that an individual can utilize during intense or maximal physical exertion. This measure remains constant after reaching the maximum quantity of oxygen uptake, regardless of escalating exertion levels over time. Since VO2 max testing measures both muscle endurance and aerobic efficiency simultaneously, it is instrumental in assessing cardiopulmonary health and aerobic fitness.

[0003] Historically, direct measurements of VO2 max obtained through treadmill or ergometer tests are widely regarded for their high accuracy and reliability. These maximal oxygen uptake assessments are fundamental in gauging cardiovascular fitness. However, these conventional methods are labor-intensive and require various specialized equipment, incurring considerable expenses. Further, they must be conducted exclusively within laboratory settings, adhering tostrict protocols. The involvement of qualified professionals is imperative, and the time constraints inherent in the testing process preclude daily administration. Further, these tests pose limitations for individuals with underlying conditions, such as cardiac issues, making them less accessible to a broader population.

[0004] Recent advancements in wearable technology, notably heart rate monitors, have revolutionized the process of VO2 max assessment. However, equivalent or alternate methods that require less demanding infrastructure still necessitate rigorous protocols, typically lasting several minutes to over an hour. Most wearables almost entirely forgo these protocols in favor of simpler measurements, resulting in significant deviations from the actual VO2 max. In such scenarios, the measurement's accuracy heavily relies on protocol adherence, which is prohibitively difficult to achieve. For general users, this can turn the assessment into an arduous experience, as the procedures are primarily designed for measuring athletic performance.

[0005] Therefore, there is a clear need for a protocol that can mimic VO2 max measurement without the use of laboratory equipment and human capital requirements. This is a challenging endeavor, as even surrogate measures must maintain a level of accuracy and reliability. The problem of reduced adherence in simplified protocols can affect the results to the extent that they become unusable for interpretation. Furthermore, it is important for the protocol to be relatively easier than traditional sub-maximal tests to improve accessibility for users who are less physically fit. Addressing these issues is critical to developing a more inclusive and practical method for assessing VO2 max in a broader population.

[0006] Thus, it is desired to address the above-mentioned disadvantages, issues or other shortcomings or at least provide a useful alternative.OBJECT OF INVENTION

[0007] The principal object of the embodiments herein is to provide a system and method to determine the cardio respiratory fitness of the user along with a dynamic user interface for user engagement.

[0008] Another object of the embodiment herein is to determine the cardio respiratory fitness of the user based on the HR, the MI, and the combinations of the HR and the MI.

[0009] Yet another object of the embodiments herein is to provide a system including a wearable sensor device and a mobile device to determine the cardio respiratory fitness of the user based on the HR, the MI, and the combination of the HR and the MI.SUMMARY

[0010] In an aspect, the objects are achieved by providing a method for determining a cardio respiratory fitness of the user with an interactive solution. The method includes establishing a connection between the mobile device and a wearable sensor device using short-range communication. A Movement Intensity (MI) and a Heart Rate (HR) of a user wearing the wearable sensor device are received and stored. These metrics are collected while the user is performing a physical activity in a predefined place. Further, the mobile device displays a dynamic user interface based on the MI and HR of the user. This dynamic user interface includes a user avatar across a deviation factor spectrum, at least two antagonist characters positioned at opposite ends of the deviation factor spectrum, and a performance indicator (PI) indicating the performance level of the user while performing the physical activity. The mobile device controls the position and movements of the user avatar across the deviation factor spectrum based on the MI while the user is engaged in the physical activity in the predefined place. The position and movements of the user avatar are directed towards or away from at least one antagonist character of the at least two antagonist characters, based on the movements of the user. Furthermore, the mobile device increases the performance level of the user based on the HR while the user is engaged in the physical activity in the predefined place. The mobile device determines the cardio respiratory fitness of the user based on at least one of the HR, the MI, and combinations of the HR and the MI.

[0011] In another aspect, the objects are achieved by providing a system for determining the cardio respiratory fitness of the user. The system includes a wearable sensor device worn by the user while performing physical activity at a predefined place. The wearable sensor device is adapted to measure the MI and HR of the user. A mobile device, connected to the wearable sensor device using short- range communication, is also included. The mobile device comprises a display, a data acquisition controller configured to receive and store the MI and HR from the wearable sensor device, and an interactive logic controller connected to the data acquisition controller and the display.

[0012] The interactive logic controller generates a dynamic user interface on the display of the mobile device based on the MI and HR of the user. This dynamic user interface includes a user avatar displayed across a deviation factor spectrum, at least two antagonist characters positioned at opposite ends of the deviation factor spectrum, and a performance indicator (PI) indicating the performance level of the user while performing the physical activity at the predefined place. The interactive logic controller further controls the position and movements of the user avatar across the deviation factor spectrum based on the MI, directing the position and movements of the user avatar towards or away from at least one antagonist character of the at least two antagonist characters. Further, the interactive logic controller increases the performance level of the user based on at least one of HR, MI, or combinations of HR and MI, and determines the cardio respiratory fitness of the user based on HR and MI.

[0013] The aspects of the embodiments will be better understood with the following description and accompanying drawings. The descriptions, indicating preferred embodiments and specific details, are for illustration and not limitation. Many changes and modifications can be made within the scope of the embodiments without departing from their spirit, and all such modifications are included.BRIEF DESCRIPTION OF FIGURES

[0014] These features, aspects, and advantages of the present embodiments are illustrated in the accompanying drawings, where like reference letters indicatecorresponding parts across figures. The embodiments will be better understood from the following description and drawings.

[0015] Fig. 1A illustrates a scenario of the collection of HR and MI data from the user in real-time while the pre-recorded audio helps maintain the jogging cadence according to the prior art.

[0016] Fig. IB illustrates a real-time feedback system implementing iterative and interactive visual feedback to maintain the jogging cadence according to the embodiments as disclosed herein.

[0017] Fig. 2 is a block diagram that illustrates the hardware features associated with the mobile device according to the embodiments as disclosed herein.

[0018] Fig. 3 is a block diagram that illustrates the flow of generation of the interactive visual representation based on the MI and the HR by the interactive logic controller according to the embodiments as disclosed herein.

[0019] Fig. 4 is a block diagram that illustrates a scenario of predicting cardio respiratory fitness from HR and MI according to the embodiments as disclosed herein.

[0020] Fig. 5 illustrates the MI indicator showing the pointer against the range of values that can be denoted according to the embodiments as disclosed herein.

[0021] Fig. 6 illustrates the MI indicator being represented by interactive elements according to the embodiments as disclosed herein.

[0022] Fig. 7 illustrates the interactive visual representing the antagonist characters at fixed positions and the player character moving horizontally based on the actual MI of the user according to the embodiments as disclosed herein.

[0023] Fig. 8A illustrates a man with a wearable chest strap ECG sensor undergoing cardiac assessment via the mobile application while running over the floor according to the embodiments as disclosed herein.

[0024] Fig. 8B illustrates the proximity of Protagonist Character (PC) (a running character) to Antagonist Character (AC) 1 (a lion) due to the user’s failure to keep up with the MI ((5) = -1) according to the embodiments as disclosed herein.

[0025] Fig. 8C illustrates the proximity of the PC to AC2 due to overexertion during jogging ((5) = +1) according to the embodiments as disclosed herein.

[0026] Fig. 8D illustrates the PC’s HR exceeding the safe zone (zone 5) according to the embodiments as disclosed herein.

[0027] Fig. 9A illustrates a man with a wearable sensor device undergoing cardiac assessment via the mobile device according to the embodiments as disclosed herein.

[0028] Fig. 9B illustrates a wearable sensor device according to the embodiments as disclosed herein.

[0029] Fig. 9C illustrates a plot of HR during the Cardiac Health Assessment Test according to the embodiments as disclosed herein.

[0030] Fig. 10 illustrates a representation of a gradual increase in movement load during the exercise with instructions to remain between the upper and lower limits for 30 sec increases in intensity according to the embodiments as disclosed herein.

[0031] Fig. 11 illustrates an expected MI for protocol adherence indicating upper and lower bounds of tolerance within which actual MI should vary when the user jogs as prescribed according to the embodiments as disclosed herein.

[0032] Fig. 12A illustrates the MI patterns measured during assessments taken by a first user from control group A according to the embodiments as disclosed herein.

[0033] Fig. 12B illustrates the MI patterns measured during assessments taken by a second user from control group A according to the embodiments as disclosed herein.

[0034] Fig. 12C illustrates the MI patterns measured during assessments taken by a user using audio guidance from control group B according to the embodiments as disclosed herein.

[0035] Fig. 12D illustrates the MI patterns measured during assessments taken by another user using audio guidance from control group B according to the embodiments as disclosed herein.

[0036] Fig. 13 illustrates Root Mean Square Error (RMSE) distribution across control groups to compare the effect of dynamic user interface for protocol adherence according to the embodiments as disclosed herein.

[0037] Fig. 14 illustrates a comparison of RMSE distributions between different protocols for estimating VO2 max from heart rate data with consideration for potentially simpler alternatives to the CPET according to the embodiments as disclosed herein.

[0038] Fig. 15 is a flow diagram that illustrates the method for determining the cardio respiratory fitness of a user according to the embodiments as disclosed herein.DETAILED DESCRIPTION OF INVENTION

[0039] The embodiments and their features are explained with reference to nonlimiting examples illustrated in the accompanying drawings and detailed in the description. Well-known components and processing techniques are omitted to avoid unnecessary complexity. Embodiments can be combined to form new ones, and "or" is non-exclusive unless stated otherwise. Examples are provided to aid understanding and to enable skilled practitioners to apply the embodiments without limiting their scope.

[0040] Embodiments are described using blocks that perform specific functions. These blocks, referred to as managers, units, modules, or hardware components, are implemented using analog and / or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive and active electronic components, optical components, and hardwired circuits. They may be driven by firmware and software and can be on semiconductor chips or printed circuit boards. Blocks can be implemented with dedicated hardware, processors, or a combination of both, and can be separated or combined without departing from the scope of the method.

[0041] The accompanying drawings aid in understanding technical features, but the embodiments are not limited by these drawings. The method extends to any alterations, equivalents, and substitutes beyond those shown. Terms like "first" and "second" are used for distinction and do not limit the elements.

[0042] Embodiments disclosed herein provide a method and system for an interactive solution to estimate the maximal oxygen uptake (VO2 max) of the user.The proposed solution offers a novel means to provide real-time guidance, helping users adhere to an assessment protocol intended to estimate a surrogate metric for VO2 max. To measure cardiorespiratory health, the system processes real-time heart rate and movement data from a body -worn sensor during a short session where the user undergoes physical exertion by jogging in a fixed place. The cadence of jogging is increased every 30 seconds until the user can no longer maintain the expected pace. Subsequently, the user relaxes while the drop in heart rate is recorded. By monitoring the profile and pattern of variations in heart rate and movement data, a metric indicating cardiorespiratory health, referred to as cardio respiratory fitness score is estimated.

[0043] The evolution of the wearable technologies market has expanded the use of fitness trackers beyond mere monitoring and tracking applications. These devices, when combined with software-based interactive strategies, enhance user engagement and motivation to stay active. Research has shown the potential of using wearable devices with interactive visuals to elevate the exercising experience, making it immersive and enjoyable. However, the use of serious visuals for a health assessment routine with demanding protocol adherence requirements has not been extensively reported. In an embodiment, interactive visuals, including a dynamic user interface to improve protocol adherence for the assessment of cardio respiratory fitness, are proposed and their implementation validated. The assessment requires participants to exert physically by jogging in a fixed spot in a prescribed manner while their heart rate is monitored to obtain scoring information. By measuring movement intensity through body-worn sensors, an interactive interface provides live feedback to guide users and help them control the exertion as prescribed. The ability of the implemented dynamic user interface strategy to ensure adherence to the prescribed exertion pattern has been validated through a study involving several assessments. Results of the study indicate the effectiveness of serious games in creating user immersion and engagement, which can be leveraged to improve protocol adherence and instill consistency in exercising routines.

[0044] The embodiments describe the design and implementation of an interactive system to help users ensure adherence to a protocol that mimics a submaximal exertion test. The implementation involves a dynamic user interface on a mobile device display, focusing on making the exercise self-serving and engaging. Wearable sensor devices work in combination with the mobile device to provide real-time feedback to users.

[0045] Research in this domain has demonstrated the feasibility of submaximal tests as an alternative to maximal tests, highlighting several advantages. Unlike maximal tests, submaximal tests do not require extensive medical attention. Further, they require minimal training and can provide a realistic estimate of exercise intensity. Although submaximal tests also require equipment such as treadmills or ergometers, they are less resource-intensive compared to maximal tests. Predictive techniques have started to use machine learning (ML) mechanisms and predictor factors such as heart rate (HR) and speed with maximal and submaximal data. Maximal oxygen uptake can be implicitly estimated by integrating ML models with predictive data, saving time and effort and reducing the health risks associated with exercise testing. Several other studies have emphasized the limitations of maximal and submaximal tests, prompting the development of non-exercise tests as a feasible alternative. These tests enable the estimation of VO2 max without the need for physical exertion or specialized equipment. Instead, they use questionnaire variables such as Perceived Functional Ability (PF A) and Physical Activity Rating (PAR) to create predictive equations. This approach offers simplicity and accessibility but depends greatly on truthful self-reporting of one’s activity. Hybrid exercises, designed based on a unique combination of maximal, submaximal, nonexercise tests, or questionnaire data, help achieve high accuracy for the estimation of VO2 max. However, completing several procedures that make up these tests requires considerable effort, which is a key disadvantage.

[0046] A plethora of techniques have been developed to estimate VO2 by monitoring and measuring HR while jogging on a treadmill or ergometer or even by using a step test. However, these approaches are mostly submaximal due to the significant correlation between HR and VO2. The predominant focus of manystudies has been to explore the relationship between HR and oxygen consumption (VO2) with limited attention directed towards estimating VO2 max from HR.

[0047] In prior art, the potential of wearable devices to estimate ventilatory thresholds is investigated from respiratory data. To confirm the accuracy of these estimates, this research utilizes gas analysis as a ground truth method for measuring ventilatory thresholds. Earlier research explored innovative methods to integrate wearable technology with gaming to encourage physical activity. This included an HR-driven game, which demonstrated how visuals boosted user engagement. In existing systems, estimating VO2 max with direct exercise protocols is slow and cumbersome, highlighting the need for more efficient methods. Indirect methods lack reliance on accurate self-reporting for questionnaires, and hybrid tests require significant effort and need to be streamlined and gamified. This study aims to build on the concept outlined in earlier research papers, focusing on the development of a game-based exercise protocol that employs wearable technology. Addressing key challenges, it explores a pilot investigation to use wearables for assessing cardiovascular fitness through a streamlined interactive Cardiac Assessment Protocol designed to estimate VO2 max. The primary objective is to develop a VO2 max estimation method from a protocol that can mimic the exercise test without the need for expensive equipment or specialized personnel. The protocol is intended to be engaging, effective, and time-efficient for cardiovascular assessments.

[0048] Cardio Respiratory Score (CRS) is essential for assessing an individual's cardiorespiratory fitness. CRS is measured through a combination of Heart Rate (HR), Movement Intensity, and VO2 max. Traditional methods to determine CRS necessitate costly equipment, specialized facilities, and maximal physical exertion from participants. Traditionally, these require sophisticated equipment like metabolic carts and direct gas analysis systems to accurately gauge the volume of oxygen an athlete can utilize during peak physical exertion. Estimating VO2 max with direct exercise protocols is slow and cumbersome, highlighting the need for more efficient methods. Indirect methods lack reliance on accurate self-reportingfor questionnaires, and hybrid tests require significant effort and need to be streamlined and dynamic user interface.

[0049] Alternate methods with less demanding infrastructure requirements exist but require rigorous protocols to be followed that typically last for several minutes to over an hour. In such scenarios, the measurement has a greater reliance on protocol adherence that is prohibitively difficult to achieve. Furthermore, conducting the assessment for general users could turn out to be an arduous experience since the procedures are primarily designed for the measurement of athletic performance. Hence, it is imperative to design a protocol to mimic VO2 max measurement without the use of any laboratory equipment and human capital requirements, which is a challenging effort. Even if the computed metrics are intended to serve only as a surrogate measure, the sheer problem of reduced adherence can affect the results to an extent that they are unusable for interpretation. It is also important for the protocol to be relatively easier than a traditional sub- maximal test to improve accessibility for users who are less fit physically.

[0050] The proposed system for CRS estimation represents a novel approach to overcoming these limitations. By integrating real-time data from a wearable sensor device with interactive visuals, this system transforms the CRS estimation process into an engaging and accessible experience. This novel methodology not only democratizes access to vital health metrics but also addresses key challenges in traditional CRS assessment techniques, including the need for specialized equipment, the risk of bias in subjective estimation methods, and the physical and psychological barriers to maximal exercise testing.

[0051] The present disclosure describes a dynamic user interface-based cardiac assessment protocol designed to simulate an exercise protocol using a wearable sensor device integrated with an electrocardiogram (ECG) sensor and an accelerometer for the estimation of VO2 max. A study was conducted which focused on extracting features from both Heart Rate (HR) and acceleration data collected during the Cardiac Assessment Protocol and Cardiopulmonary Exercise Testing (CPET) utilizing the wearable chest strap. The ground truth for VO2 max was derived from CPET. The Machine Learning (ML) model yielded VO2 maxpredictions from HR data collected during CPET with a Root Mean Square Error (RMSE) of 5.37 compared with the ground truth of earlier VO2 max data. Similarly, when VO2 max was estimated from the HR data during the Cardiac Assessment Protocol, the model had an RMSE of 5.82 compared to the ground truth earlier VO2 max data. These results indicated that VO2 max can be reasonably estimated from HR and acceleration data under a simulated incremental dynamic user interfacebased cardiac assessment protocol, providing a potential alternative to traditional exercise testing methods. Notwithstanding this, the proposed method demonstrates promising potential for VO2 max estimation through a less invasive and more accessible approach to cardiovascular fitness assessment.

[0052] The present disclosure explores a pilot investigation utilizing wearables for assessing cardiovascular fitness through a streamlined interactive Cardiac Assessment Protocol designed to estimate V02max. The primary objective is to develop a V02max estimation method from a strategy that can mimic the exercise test without the need for expensive equipment or specialized personnel. This strategy is intended to be engaging, effective, and time-efficient for cardiovascular assessments.

[0053] A novel solution proposes a dynamic user interface design to improve protocol adherence for the assessment of cardio respiratory fitness, and its implementation is validated. Users are required to exert physically by jogging in a fixed spot in a prescribed manner while their heart rate is monitored to obtain scoring information. By measuring movement intensity through body-worn sensors, an interactive interface provides live feedback to guide users and help them control the exertion as prescribed. The ability of the implemented interactive visual strategy to ensure adherence to the prescribed exertion pattern has been validated through a study involving over 200 assessments. Results of the study indicate the effectiveness of serious games in creating user immersion and engagement, which can be leveraged to improve protocol adherence and instill consistency in exercising routines.

[0054] Due to the difficulties and practical constraints associated with the direct measurement of VO2 max, indirect assessments based on a variety of tests,including exercise, non-exercise, and hybrid tests, have been developed to predict maximal oxygen uptake. In one of the existing systems, the hardware devices used include a wearable chest strap sensor and a metabolic analyzer. The chest strap sensor is used for the estimation of VO2 max. The test was conducted using the existing wearable chest strap device that records HR and acceleration data obtained through single-lead ECG and a 3-axis accelerometer. Real-time acquisition of data from the sensor is achieved through a mobile application. The ground truth VO2 max data is obtained through the Metabolic Analyzer. This device includes integrated sensors for measuring respiratory gas exchange and ventilation, as well as optional sensors for measuring HR, blood oxygen saturation, and other physiological parameters. The Metabolic Analyzer utilizes a galvanic fuel cell and a non-dispersive infrared sensor for analyzing Oxygen (02) and Carbon Dioxide (C02) levels in inhaled and exhaled air, along with a high-performance turbine flow meter for measuring flow rate. Further, it is equipped with wireless communication capabilities, allowing real-time data transmission to a computer or a mobile device for immediate analysis and feedback.

[0055] In an embodiment, the Protagonist Character (PC) and the user avatar are used interchangeably and have the same meaning. Similarly, the terms body -worn sensors and wearable sensor device are used interchangeably and hold the same meaning.

[0056] Referring now to the drawings and more particularly to Figs. 1 through 15, where similar reference characters denote corresponding features consistently throughout the figure, these are shown preferred embodiments.

[0057] Fig. 1A illustrates a scenario involving the collection of heart rate (HR) and movement intensity (MI) data from the user in real-time, while pre-recorded audio helps maintain the jogging cadence according to prior art. This Fig. describes an open-loop solution of the audio-based adherence strategy, wherein simple audio guidance with no interactive visuals assists in synchronizing the user’s steps, thereby helping users with adherence and sustaining the jogging cadence.

[0058] Fig. IB illustrates a real-time feedback system that implements iterative and interactive visual feedback to maintain the jogging cadence according to theembodiments disclosed herein. The feedback is formed by selecting Movement Intensity (MI) as the parameter based on which correctness monitoring and visual feedback are delivered. Physiological measurement and movement information of the body are obtained through an integrated body-worn wearable sensor device containing heart rate and movement sensors, which wirelessly stream data to a mobile device for further processing. The mobile device runs a dynamic user interface where data from body -worn sensors enable user interactivity and control. Notably, the entire system (100) is designed with low latency considerations to ensure responsiveness and suitability for biofeedback-based applications.

[0059] The figure illustrates the proposed solution where a user (110) performs jogging on a floor (109) while wearing the wearable sensor device (300). The proposed system (100), which includes both a wearable sensor device (300) and a mobile device (200), offers great operational flexibility and does not require specific tools like a treadmill to function. This solution provides a dynamic user interface (108) that enhances user engagement and motivation to stay active. The system (100) requires users to exert physically by jogging in a fixed place, such as the floor, while their HR and MI are monitored to determine cardio respiratory fitness and generate an interactive dynamic user interface (108) based on the MI, HR, and their combinations.

[0060] In Fig. IB, the user (110) wearing the wearable sensor device (300) performs physical activity. The wearable sensor device (300) connects to the mobile device (200) over short-range communication (111), which includes but is not limited to Bluetooth, Wi-Fi, and others. The mobile device (200) receives and stores the MI and HR of the user (110) from the wearable sensor device (300) through the short-range communication (111) while performing the physical activity. Based on the MI and HR of the user (110), the mobile device (200) generates a dynamic user interface (108) on its display. This dynamic user interface includes a user avatar (104) displayed across a deviation factor spectrum (106) and antagonist characters 1 (103) and 2 (105) at the ends of the deviation factor spectrum (106). Further, the dynamic user interface (108) includes a Performance Indicator (PI) that indicates the performance level of the user (110) while doing the physical activity on the floor(109). The mobile device (200) controls the position and movements of the user avatar (104) across the deviation spectrum based on the MI and HR, directing the user avatar (104) towards or away from the antagonist characters (103 or 105). The performance level of the user (110) increases based on the MI and HR, and the mobile device (200) may direct the user (110) to adjust the speed of the physical activity to maintain optimal HR and MI. Furthermore, the mobile device (200) determines the cardio respiratory fitness of the user (110) based on the MI and HR.

[0061] In embodiment, the number and arrangement of antagonist characters along with the user avatar are used for illustrative purposes only and can be adjusted as needed to enhance user engagement and the overall experience.

[0062] The wearable sensor device (300) can encompass a diverse range of devices, including but not limited to chest strap heart rate monitors. It includes an Electrocardiogram (ECG) sensor to collect ECG signals from the heart, an elastic strap, a heart rate sensor, a battery, a controller, and a transmitter apparatus. The chest-worn ECG sensor captures the timing of each heartbeat of the user while performing physical activity at the predefined place and measures the HR based on the timing of each heartbeat. The ECG sensors detect the electrical activity of the heart by measuring small voltage changes in the heartbeat, which are used to measure HR and Heart Rate Variability (HRV). Further, the wearable sensor device (300) includes an accelerometer-based motion sensor configured to record body movement data of the user while performing physical activity at the predefined place across three axes at a predetermined sampling rate. It determines a quantitative representation of actual body movement data based on the recorded data and calculates the MI by removing constant acceleration due to gravity. The elastic strap ensures proper electrode contact with the skin for accurate ECG signal detection. The microcontroller filters and amplifies the ECG signal and transmits it to the mobile device (200) through the transmitter apparatus.

[0063] The present invention describes protocols to be followed, ensuring adherence through an assessment protocol, audiovisual adherence strategy, adherence using visual feedback, and gamification for adherence.

[0064] In the Assessment Protocol, the user begins by jogging at a fixed spot with a slow and steady cadence. After a time period, which can be dynamically adjusted based on the user, the user increases the cadence and sustains it for the next stipulated time period. The cadence of the jog is increased proportionally after every uniform time period as a way of leveling up the exertion. The user’s heart rate (HR) is continuously monitored to ensure physical exertion remains within safe limits. As the user levels up the exertion, and when their HR reaches zone 5, the user is directed to stop jogging and relax.

[0065] Empirical calculations, derived from various tests conducted on a closed user group, indicate that it takes at least 15 seconds for a user to perceive a change, make a correction to revert the change, and for the correction to be reflected in the system. To allow users to experiment with and become accustomed to the system, the duration for each level has been set to twice this duration, i.e., 30 seconds. Increasing the duration further extends the exertion period at each level and the overall session duration.

[0066] Adherence using Visual Feedback: The fundamental limitation of an audio-based guidance system is the lack of a closed loop feedback to ensure synchronization and quantify deviation, if any. The quantified metric can then be used to drive the guidance system in prompting the user to make necessary corrections, thereby bringing back the cadence to expected levels. To ensure that these levels thus attained are also sustainable, a low latency feedback system, where users can react faster to the guidance stimulus, is required, the visual indicator in the guidance system is driven by the deviation metric that directly corresponds to protocol adherence. This deviation metric, referred to as Deviation Factor (5) henceforth, is a measure of the difference between the actual MI (Ia) and the expected MI (Ie) for a given level. It is expressed in simple terms as, la — le s = —8 is clipped to have a working range between -1 to +1, where the values -1 and +1 represent the actual pace lagging behind and leading the expected pace by 100%, respectively. A value of 0 represents a perfect synchronization between the actual pace and the expected pace.

[0067] The audiovisual adherence strategy can be integrated with visual feedback guidance to assist in synchronizing steps and sustaining jogging cadence. The novelty of this solution lies in its user-friendly implementation, which ensures adherence to the exertion protocol and improves the reliability of the assessment. The system can be designed in iterative stages by testing and collecting feedback from a closed user group. This process helps optimize content delivery and finetune user experiences for a self-serving solution.

[0068] Based on feedback from field test iterations, it is imperative to have a dynamic user interface for adherence. In addition to a closed-loop system for realtime feedback, an interactive solution exclusively designed to keep users engaged is necessary for protocol adherence. A straightforward approach involves providing interactive visuals to the Movement Intensity (MI) indicator by wrapping it with interactive elements and controlling them with wearable sensor device data.

[0069] Interactive visuals for exercises have emerged as a notable trend in recent years, demonstrating their efficacy in instilling motivation and sustaining user engagement. By introducing dynamic user interface principles into non-game contexts, the once monotonous act of exercising has been transformed into an enjoyable and immersive experience. Such functional dynamic interfaces not only serve as catalysts for heightened motivation to engage in regular exercise routines but also enhance awareness during physical activity and the progress associated with it. Advancements in software development methodologies for gaming and innovative content delivery mechanisms have further propelled this phenomenon, favoring the surge in this trend. Expanding beyond individual engagement, the incorporation of social elements such as leaderboards and communal recognition has proven instrumental in fostering healthy competition among participants.

[0070] With the evolution of wearable technology and its expansion into the fitness market, the accessibility of wearable fitness trackers has empowered them to be used for more than mere monitoring and tracking purposes. These devices, when combined with interactive visual strategies, possess significant potential to personalize exercise experiences since their real-time physiological data offers an additional dimension of engagement. Previous research in this domain hasdemonstrated the feasibility of leveraging physiological metrics such as Heart Rate (HR) and Movement Intensity (MI) to interact with and influence visual dynamics. The cumulative effect of this integration, where wearable technology enables users to exert control over interactive elements, is an increase in engagement with an added layer of delight.

[0071] While the effect of increasing engagement has been explored through previous research, the impact of such dynamic user interfaces in a health assessment procedure has not been thoroughly investigated. VO2 max assessment, a procedure to estimate cardiorespiratory health, measures the body's ability to consume oxygen. This test typically requires expensive and elaborate infrastructure, as well as human capital and training for operation.

[0072] Fig 2 is a block diagram that illustrates the hardware features associated with the mobile device (200) according to the embodiments as disclosed herein. The mobile device (200) spans a diverse range of devices but is not limited to laptops, palmtops, desktops, mobile phones, smartphones, Personal Digital Assistants (PDAs), tablets, wearable devices, Internet of Things (loT) devices, virtual reality devices, foldable devices, flexible devices, display devices, and immersive systems. In an embodiment, the mobile device (200) includes a memory (204), a processor (201), an I / O interface (203), a display (202), an interactive logic controller (205), a data acquisition controller (206), and a feedback controller (207).

[0073] The memory (204) stores instructions to be executed by the processor (201). The memory (204) can include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard disks, optical disks, floppy disks, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory (204) may in some examples be considered a non-transitory storage medium. The term non-transitory may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term non- transitory should not be interpreted that the memory (204) is non-movable. In some examples, the memory (204) stores larger amounts of information. In certain examples, a non-transitory storage medium may store data that can over timechange (e.g., in Random Access Memory (RAM) or cache). The memory (204) stores the HR and the MI of the user, interactive dynamic user interface information, Machine Learning (ML) models, and others.

[0074] The processor (201) may include one or a plurality of processors. The one or the plurality of processors may be a general -purpose processor such as a central processing unit (CPU), an application processor (AP), or the like, a graphics- only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an Al-dedicated processor such as a neural processing unit (NPU). The processor (201) may include multiple cores and is configured to execute the instructions stored in the memory (204). The processor (201) fetches the HR and the MI of the user and directs the interactive logic controller (205) to generate the dynamic user interface based on the HR and MI of the user. Further, the processor (201) retrieves instructions from the memory (204) and executes them.

[0075] The I / O interface (203) transmits the information between the memory(204) and external peripheral devices. The peripheral devices are the input-output devices associated with the mobile device (200). The I / O interface (203) receives several pieces of information from a wearable sensor device (300) and the like. The I / O interface (203) ensures that the operating speed of the processor is synchronized with respect to the input and output devices. The I / O interface (203) establishes a connection between different peripheral devices like the interactive logic controller(205), the data acquisition controller (206), the memory (204), and others to generate an interactive visual interface for any scenario-specific action like monitoring the user avatar and replacing the PI on the respective value on the deviation factor spectrum and others.

[0076] In an embodiment, the interactive logic controller (205) of the mobile device (200) is coupled with the processor (201), the I / O interface (203), and the memory (204) for generating an interactive dynamic user interface and determining the cardio respiratory fitness. This coupling allows for efficient data transfer and communication between the components, ensuring that the interactive logic controller (205) can access and process movement data in real-time. The interactivelogic controller (205) is an innovative integrated circuit implemented in the mobile device (200).

[0077] The structure of such an innovative integrated circuit includes a multi - core architecture that enables dynamic user interface generation and cardio respiratory fitness determination. Each core is optimized for specific tasks such as receiving the MI and the HR, generating dynamic user interfaces, adaptive arrangement of user avatars, and others. The innovative integrated circuit for generating dynamic user interfaces is made of a combination of analog and digital components designed to optimize power consumption and performance of the cardio respiratory fitness determination procedure and dynamic user interface generation mechanism. The analog components include a low-noise amplifier and a high-precision analog-to-digital converter to ensure accurate signal processing. The digital components consist of a microcontroller unit (MCU) and a digital signal processor (DSP) that work in tandem to generate the dynamic user interface based on the MI and the HR. The memory (204) includes information on HR and MI for the interactive dynamic user interface.

[0078] Configured to generate the dynamic user interface on the display of the mobile device (200) based on the MI and the HR of the user (110), the interactive logic controller (205) ensures the dynamic user interface (108) includes the user avatar (104) displayed across the deviation factor spectrum (106), at least two antagonist characters (103 and 105) positioned at opposite ends of the deviation factor spectrum (106), and the PI (107) indicating the performance level of the user while doing physical activity at the predefined place. The interactive logic controller (205) controls the position and movements of the user avatar (104) across the deviation factor spectrum (106) based on the MI, where the position and movements of the user avatar (104) are directed towards or away from at least one antagonist character of the at least two antagonist characters. Further, the interactive logic controller (205) increases the performance level of the user based on the HR, the MI, or combinations of the HR and the MI, and determines the cardio respiratory fitness of the user based on the HR and the MI.

[0079] In an embodiment, the mobile device (200) includes the feedback controller (207), which is configured to receive the physiological data of the user from the wearable sensor device (300) while doing physical activity at the predefined place. The physiological data includes, but is not limited to, Blood Pressure (BP), respiratory rate, body temperature, oxygen saturation levels, HR, MI and others. The mobile device (200) generates interactive visual feedback on the display (202) of the user interface by converting the physiological data of the user into interactive visual feedback based on the MI and the HR, thereby enhancing user engagement.

[0080] Further, in an embodiment, the interactive logic controller (205) determines whether the HR of the user exceeds a predefined HR threshold while doing physical activity at the predefined place and terminates or suspends the dynamic user interface when the predefined condition has occurred.

[0081] Controlling the position and movements of the user avatar based on the MI includes visually manipulating the position and movements of the user avatar displayed in the dynamic user interface based on the MI while doing physical activity at the predefined place by mapping the movements and the HR of the user avatar (104) to the deviation factor spectrum (106).

[0082] In an embodiment, the system (100) terminates or suspends the dynamic user interface when the predefined condition has occurred, which includes detecting whether a predefined condition has occurred. The predefined condition includes an interaction level of the user falling below a specified threshold while the user avatar is in proximity to a first antagonist character of the at least two antagonist characters, resulting in a negative deviation factor (d). A physical activity level of the user surpasses a predefined exercise level, causing the user avatar to approach a second antagonist character of the at least two antagonist characters, resulting in a positive deviation factor (d). The predefined condition also includes the condition where the HR exceeds a predefined threshold for a specified duration. Based on the occurrence of the predefined condition, the system (100) terminates or suspends the dynamic user interface when the predefined condition has occurred.

[0083] To determine the cardio respiratory fitness of the user based on the HR and the MI, the system (100) includes determining a linear combination of an Exertion Duration (ED) based on the time from the onset of assessment of the user's performance while doing physical activity until at least one predefined condition has occurred. The system (100) determines recovery beats of the user based on the time required by the user to relax for a predetermined period upon termination or suspension of the physical activity. The system (100) further determines the cardio respiratory fitness of the user (110) based on the linear combination of the ED, a Heart Rate Recovery (HRR), and user information. The ED typically refers to the length of time the user maintains a certain level of physical exertion, whereas the linear combination of Exertion Duration involves combining multiple durations of exertion, each scaled by a constant factor to form a new duration. The HRR measures how quickly the HR returns to its resting level after exercise, typically referring to the difference between the peak HR during exercise and the HR at a specific time after stopping the exercise. The user information refers to the data collected from the user during questionnaires relating to their lifestyles from surveys.

[0084] In an embodiment, the interactive logic controller is configured to detect the commencement of a new stage for the physical activity in the predefined place by the user. Upon the commencement of the new stage, the system (100) reinitializes the position (d=0), of the user avatar in the dynamic user interface. This reinitialization promotes sustainability in the physical activity and enables corrective strategies for protocol adherence in subsequent stages of the physical activity by the user. Furthermore, the system (100) iteratively refines the deviation factor spectrum based on user feedback for optimal user engagement and maintenance pace across different stages of the physical activity. The user feedback refers to physiological movement and other data from the user.

[0085] In an embodiment, antagonist characters serve as visual or interactive penalties. These penalties are activated based on deviations in the Movement Index (MI) of the user from predefined target values for the physical activity.

[0086] The predefined place, in an embodiment, can include but is not limited to the floor and similar surfaces with a regular texture.

[0087] The deviation factor spectrum, in an embodiment, defines a range of movement variations corresponding to variations in the MI. The range of movement variations of the deviation factor spectrum is from 1 to -1.

[0088] At least one component of the interactive logic controller (205) may utilize an AI / ML model. Functions associated with the Al model are executed through the memory (204) and processor (201). The processors manage input data processing based on predefined operating rules or AI / ML models stored in volatile and non-volatile memory. These models are created through training or learning processes.

[0089] Learning involves applying a learning process to multiple data sets to develop a desired operating rule or AI / ML model. This can occur within the device or via a separate server / system. The AI / ML model may include multiple neural network layers, each with weight values and layer operations. Examples of neural networks include Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), Restricted Boltzmann Machines (RBM), Deep Belief Networks (DBN), Bidirectional Recurrent DNN (BRDNN), Generative Adversarial Networks (GAN), and deep Q-networks.

[0090] The learning process trains a target device (e.g., a robot) using various data to enable it to make decisions or predictions. Learning methods include supervised, unsupervised, semi-supervised, and reinforcement learning.

[0091] Fig. 3 is a block diagram illustrating the flow of generation of the interactive visual representation based on the Movement Index (MI) and the Heart Rate (HR) according to the embodiments disclosed herein. The Fig. describes the data flow through the data acquisition controller (206) and the interactive logic controller (205) for generating the dynamic user interface on the display (202) of the mobile device (200) based on the MI and HR of the user.

[0092] Data from body-worn sensors are transmitted over short-range communication to the mobile device (200), which implements decoding logic to interpret the incoming data. The interactive logic controller (205) also implementsthe processing hardware components necessary for the dynamic user interface. These hardware components include a movement monitoring component and a heart rate monitoring component that compute the Deviation Factor (5) and HR zones, respectively. Data required to drive the interactive dynamic user interface is processed locally to enable real-time feedback with low latency for seamless user interactivity.

[0093] A copy of the acquired data, along with contextual information such as user behavioral events like premature game exiting, game termination, and others, is uploaded to a remote server. This server hosts a cloud application to analyze the physiological data and provide a detailed report for cardio-respiratory assessment. The interactive logic controller (205) receives the acquired data along with contextual information from the remote server, as illustrated at step S302. Further, the interactive logic controller (205) generates the dynamic user interface on the display (202) of the mobile device (200), as illustrated at step S303.

[0094] In an embodiment, the cardiac health assessment is performed through the mobile device with the dynamic user interface design. The method of cardiac health assessment through the mobile device follows the following procedure.

[0095] Initially, the mobile device connects to a wearable sensor device via short-range communication, such as Bluetooth, receiving data that includes heart rate (HR) and Movement Intensity (MI) information from the wearable sensor device. The mobile device then uses decoding logic to interpret the data and contains processing components to control the dynamic user interface.

[0096] These components include a movement monitoring component, which calculates the Deviation Factor (5) to control the MI, and a heart rate (HR) monitoring component, which monitors HR zones.

[0097] The present invention relates to a system and method for predicting V02max from heart rate (HR) and acceleration data using a model training and evaluation apparatus. Fig. 4 is a block diagram illustrating this scenario according to the disclosed embodiments. In the figure, the wearable sensor device (300) transmits the ECG signal and the movement signal to the interactive logic controller (205). The logic controller (205) performs data preprocessing, feature extraction,and MI model selection and training. Further, the interactive logic controller (205) generates a dynamic user interface (108) on the display (202) of the mobile device (200).

[0098] In an embodiment, the data preprocessing is described in detail. This includes processing ground truth data and HR data. The data processing stage for ground truth data is as follows, firstly, timestamps are added to the earlier data and made continuous to facilitate the processing of the datasets. The ground truth data and ECG dataset obtained from the sensor are resampled every second and interpolated to ensure evenly sampled data. The ground truth data is adjusted by incorporating an offset value to align it with the processed HR data. Filtering and denoising operations using a mean filter are performed on each signal.

[0099] To obtain HR, the ECG signals acquired from the sensor undergo a peak detection mechanism to identify the R peaks. Subsequently, the successive differences between consecutive R-R intervals are calculated. These R-R intervals are then refined through outlier removal. The interval data is converted into time series data with a sampling rate of 4 Hz. Finally, artifact-corrected HR is derived from the R-R time series data using the following equation: HR = 60 / ( R-R interval)

[0100] The raw data obtained from the 3 -axis accelerometer in the wearable chest strap sensor is processed to calculate RMS values of acceleration. The RMS data is further processed to remove outliers, specifically to eliminate the maximum sensor values. Subsequently, the time-series RMS acceleration data is sampled at 4 Hz (i.e., 250 ms).

[0101] In an embodiment, the feature extraction is described. The datasets held fundamental demographic details such as gender, weight, height, and Body Mass Index (BMI), providing subject-related information. Key HR metrics like HR max (maximum heart rate) and std. HR (standard deviation of heart rate) were also chosen as features. Another key feature was the average RMS acceleration values derived from the acceleration data, which were instrumental in evaluating the physical stress or movement load during exercise.

[0102] The duration of the exercise period was considered to gauge the individual’s capacity to adhere to the protocol until the maximum Heart Rate Zone(HRZ) was reached, as it serves as a significant parameter for evaluation. Recovery metrics were examined to assess heart recovery after intense exercise. This analysis included tracking the rapid decline in HR after reaching the peak, with a focus on a 60 beats per minute drop as a key measure of cardiac recovery efficiency. Followed by a detailed analysis, the primary HRV features were obtained through frequency domain analysis. This included metrics like Very Low Frequency (VLF) in the 0 to 0.04 Hz range, Low Frequency (LF) in the 0.04 to 0.15 Hz range, and High Frequency (HF) in the 0.15 to 0.4 Hz range, along with the LF / HF ratio. However, when these features were selected as features, the results did not meet the expected criteria, leading to their removal. Ultimately, after thorough review, eleven features were identified as most relevant to the dataset and were retained for further analysis.

[0103] Regression methods are designed to predict continuous numerical outcomes. These methods are well-suited for scenarios where the goal is to estimate or predict a numerical value based on input features. In this study, regression models such as Support Vector Regression (SVR) and Random Forest (RF) were employed. Random Forest is a regressor consisting of multiple decision trees working on the same dataset. It classifies the outcome by combining predictions from all the trees to improve accuracy. Since this model does not rely on a single decision tree, the risk of overfitting is significantly reduced compared to other models based on individual trees. Though it required additional computational power, it had high accuracy. SVR supported both linear and non-linear regression, allowing it to handle complex relationships. However, SVR can also be prone to overfitting. Despite this risk, it had been widely used in various ML problems and achieved good results. The regression step can be conducted after feature extraction.

[0104] Fig. 5 illustrates the MI indicator, showing the pointer against the range of values that can be denoted according to the embodiments disclosed herein. The visual indicator, designed as part of the visual system, represents 5 = 0. Positioned at the 0 value, the indicator can move left or right depending on whether the MI is negative or positive.

[0105] This closed-loop assessment system, where MI is measured and used to drive visual feedback for correction, was tested with a closed group of users to understand its effectiveness in ensuring adherence. The solution was capable of keeping the MI within the expected levels, and any deviations were corrected by users with the help of visual feedback. However, during a user feedback session, most participants reported that following an indicator to sustain a rather exerting physical exercise became less engaging overtime. The possibility of users acquiring boredom can result in disengagement, which could eventually influence participants to give up the exercise sooner without reaching the safe threshold limit for exertion as prescribed by the protocol.

[0106] Fig. 6 illustrates the MI indicator being represented by game elements according to the embodiments disclosed herein. The implementation of gamification for adherence in the indicator is depicted, where the moving marker is represented by a Player Character (PC). This player character is driven by the Deviation Factor to reflect the actual MI of the player. Variations in MI directly manipulate the character’s positional attribute, mapping its extremities to the working range of the Deviation Factor, i.e., from -1 to +1. Two Antagonist Characters (AC1 and AC2) are placed at these extremities to penalize movement intensities deviating from the expected values. Transforming the mundane indicator into an interactive game element is expected to foster engagement and motivation.

[0107] It is noted that between the two metrics measured by the body -worn wearable sensor device (300), HR is not directly used to control any game elements since it depends on other physiological parameters, including MI. Further, a user cannot finely control their HR as much as their MI to drive responsive game elements in the user interface. Therefore, the game visual uses only the MI as the primary control input. However, as per the protocol, when a user crosses the safe limit HR threshold, the exertion is stopped, and the gameplay is terminated.

[0108] Fig. 7 illustrates an interactive visual representing antagonist characters at fixed positions and a player character moving horizontally based on the actual mental imagery (MI) of the user, according to the embodiments disclosed herein. In an embodiment, the visualization of the player character (PC) and antagonistcharacters (ACs) is governed by an interactive logic controller. The player character is directly controlled by the user, while the antagonist characters operate independently of user input. The game's theme is intentionally minimal, designed to maintain user engagement without embellishments. This approach ensures a highly functional user interface that prioritizes usability over stylistic elements. Further, a minimal user interface is accessible to a broader range of age groups compared to interfaces with rich and specific styling, thereby enhancing the game's overall accessibility and appeal.

[0109] All characters in the game are part of an endless running scenario. The player character, represented by a sprinting human, is chased by a lion (AC1) and a lioness in a moving truck (AC2). It should be noted that the choice of game characters is subjective to the theme of the game. As mentioned earlier, the position of the PC is manipulated to move towards AC1 or AC2 to visually indicate the user's mental imagery.

[0110] Fig. 7 illustrates the interactive visual characters with annotations representing the direction of player character movement for variations in MI. A Health Indicator (HI) is also shown as an auxiliary indicator for player health. Exhausting the HI results in the termination of the game. The HI holds a value of 100% at the beginning of the game and reduces its value by 10% when any of the following termination conditions are met: The user, not being able to keep up with the MI, ends up in close proximity to AC1, i.e., 5= -1. The user, when overdoing the jogging exercise consistently, ends up in close proximity to AC2, i.e., 5 = +1. The HR zone of the user breaches the safe zone limit and stays above it for over 10 seconds.

[0111] Termination conditions are periodically checked at 1-second intervals throughout the duration of the game. If these conditions are met, the value denoted by HI drops by 10%. Upon reaching 0%, the game ends. Thus, the HI acts as visual feedback for users, prompting them to adopt corrective measures promptly if they are physically capable of keeping up with the expected MI. Notably, the HI value drops only if the player character is proximal to ACs, i.e., the Deviation Factor (5) is under -0.9 or above +0.9. These tolerance values, iteratively refined through userfeedback and experimentation, enable users to find the optimal pace for a given level and sustain it.

[0112] The position of the PC is reset for every new level to favor users continuing their exercise while helping them adopt corrective measures in the upcoming levels. Established methods to assess cardiac performance through V02max involve monitoring respiratory exchanges under controlled exertion. While the proposed solution aims to calculate only a surrogate measure, it is based on observing aerobic and anaerobic thresholds, the critical factors on which the estimation of V02max depends. The solution, primarily based on heart rate profiling, requires the user to exert until their heart rate enters zone 5. Zones 4 and 5 are indicators of anaerobic energy consumption, and the transition from zone 4 to zone 5 is considered a proxy for increased anaerobic activity, which is used to terminate the assessment.

[0113] However, there is scope for utilizing ventilatory thresholds VT1 or VT2 as better markers to assess the completion of the game. For a protocol that requires continually increasing MI, the duration for which a user sustains the exertion without being in zone 5 is a critical factor in determining their cardio respiratory fitness. This duration, termed Exertion Duration (ED), is denoted by te and is measured as the duration in seconds from the onset of the assessment until the test is terminated. Using ED, a score quantifying the endurance of the heart to sustain increasing levels of exertion is obtained as follows:

[0114] 0e= (10, ra* 10)

[0115] Where, 0eis the Endurance Score, a is called Effort Factor and empirically estimated to be 1.3, r is the endurance ratio expressed as a ratio of te and the maximum allowed session duration of 12 minutes,

[0116] The ability of the heart to lower its heart rate as soon as the body is subjected to rest is another important indicator of cardiac health. The underlying premise of this phenomenon is that when subjected to maximal exertion followed by relaxation, an efficient heart drops its HR as quickly as possible. The user is required to relax for 60 seconds upon termination of the game and the maximumdrop in the number of heart rate beats in this duration is counted as Recovery Beats, denoted by nr. It is used to compute Recovery Score (0r) as follows: nr— 100r= min (10, - - - )6

[0117] Since the magnitude of heart rate recovery and duration of sustained exertion contribute to the overall cardiac health, the reported score, known as Cardiac Health Score (0C), is expressed as a weighted combination endurance and recovery scores, as per the following equation:0C= (0.7 * 0e) + (0.3 * 0r) where, 0.3 and 0.7 are empirically obtained weights for combining the scores.

[0118] In an embodiment, the game was delivered as part of the app to users who expressed interest trying out the assessment. Male and female individuals aged between 20 and 60 were allowed to participate after obtaining consent for participation. As part of the exclusion criteria, individuals with current or history of cardiac ailments, injuries or recent surgery in the lower limbs, and chronic conditions such as arthritis were not allowed undertake the assessment.

[0119] In an embodiment, the data collection was carried out with two different groups where the first group (referred to as Group A henceforth) took the assessment using audio based guidance and the second group (referred to as Group B henceforth) used the interactive system for assessment. Group A users accounted to a total of 110 assessment sessions whereas Group B contributed to a total of 1000 sessions. However, 110 sessions were randomly sampled from Group B for comparative analysis with Group A.

[0120] The consent to participate in the assessment from each participants was obtained, after thoroughly explaining the protocol and requirements, through a personnel qualified to conduct the assessment. Users wore the chest strap with ECG sensor and stood in front of a vertically mounted phone placed conveniently for them to jog hands free. It was ensured that the chest strap is worn with comfort and access to hydration is available after the exercise. Since the app is designed to be user friendly, no explanation on the game specifics and game play instructions was given. Instead, users went through a short in-app tutorial explaining the characters and displaying instructions on how to control them. In addition, as a precaution, allusers were instructed to stop the test upon feeling tired or physically exhausted to keep up with the game. Users start with a light jog and keep a check on the PC to ensure the cadence is maintained until the game levels up. As the game levels up, the jogging cadence is increased and visual feedback helps in adjusting it to sustain the expected MI levels. Heart rate from the sensor is primarily used to compute heart rate zones, based on which the user is indicated to stop jogging and relax upon termination of the game. Recovery measurement is a crucial part of the assessment and the protocol is particular about the user relaxing after the exertion to capture the drop in heart rate. The assessment is terminated to generate a report after the user has rested for 2 minutes.

[0121] Fig 8A illustrates a man with a wearable sensor device (300) with the ECG sensor, undergoing cardiac assessment via the mobile device (200) while running over the floor, according to the embodiments as disclosed herein.

[0122] Fig. 8B illustrates a man with a wearable sensor device (300) undergoing cardiac assessment via the mobile device (200), according to the embodiments as disclosed herein. The Fig. illustrates the scenario where the user (110) which is represented as the PC (104) is unable to keep up the speed and the user is positioned at -0.9 near the lion (AC1 (103b)).

[0123] Fig. 8C illustrates a wearable sensor device (300), according to the embodiments as disclosed herein. The Fig. represents a scenario where the user (represented by the PC (104)) is performing the physical activity beyond the optimal condition. The PC (104) is placed at 0.9 approaching the AC2 (103b). the interactive visual representation of the user approaching the AC2 (103b) enhances the user engagement.

[0124] Fig. 8D illustrates a plot of HR during the cardiac health assessment test, according to the embodiments as disclosed herein. In the Fig. 8D, a warning sign is illustrated when the user is falling behind the required speed or intensity. This approach enhances the user engagement and motivates the user (110) to perform better.

[0125] The lion (103a) in a moving truck (103b) and a person (104) are represented for illustration purposes only. The interactive visual characters likeAC1, AC2 and the PC may vary based on the design of the dynamic user interface (108).

[0126] The cardiac assessment through the dynamic user interface design follows a specific procedure. A mobile device hosts the dynamic user interface to monitor and guide users through an incremental exercise protocol for cardiac assessment. The dynamic user interface’s minimalist design provides a simple and accessible interface. Players control a running character in an endless chase scenario pursued by autonomous characters: a lion (AC1) (103a) and a lion in a moving truck (AC2) (103b). The player’s position is determined by a Movement Index (MI) ranging from -1 to +1, where -1 indicates the player is falling behind and +1 indicates the player is ahead of the expected pace. An MI of 0 represents perfect synchronization.

[0127] This dynamic user interface (108) follows an incremental protocol where the movement load increases at each level, requiring users to adapt to the MI accordingly. The Deviation Factor (5) measures the gap between the actual MI (subject's current MI) and the expected MI (incremented MI set for each level). This metric is integrated into the visual indicator seen on the dynamic user interface, which is used to guide users and control their exertion levels.

[0128] To support subjects' progression, the player’s position is reset at the start of each new level, allowing them to adjust their pace to maintain a safe exertion level. HR data from sensors is not used to control interactive visual elements, as it is influenced by various physiological factors.

[0129] The Health Indicator (HI) starts at 100% and drops by 10% when one of the termination conditions is met. The termination conditions include the following:

[0130] The PC (104) is too close to the lion (AC1) (103a) when the user cannot keep up with the expected pace, resulting in a low MI ((5) = -0.9).

[0131] The PC (104) gets too close to the lioness in the moving truck (AC2) (103b) when the user is overdoing the exercise and the movement load is higher than required, leading to a high MI ((5) = +0.9).

[0132] The user’s HR exceeds the safe limit (zone 5) for over 10 seconds, resulting in protocol termination. Zone 5 represents high-intensity exercise, indicating a shift towards significant anaerobic energy consumption, which can indicate unsafe stress levels and result in protocol termination.

[0133] These termination conditions are checked every second throughout the process. If any of the conditions are met, the HI drops by 10% If it reaches 0% the process ends which is indicated by an empty health indicator.

[0134] Assessments were performed where the users were equipped with the wearable sensor device (300) consisting of a sensor integrated with a 2-point ECG sensor and a 3-axis accelerometer to monitor HR and MI. They were briefed on the assessment procedure and provided with the mobile device (200) running the dynamic user interface (108) enhanced application, which can be connected to the sensor via Bluetooth.

[0135] The assessment protocol was displayed by the dynamic user interface on the mobile device (200) mounted on a holder, e.g., tripod, enabling hands-free operation. Subjects were guided to follow the instructions on the screen and started jogging in place at a slow and steady cadence. Every 30 seconds, they increased their jogging cadence, gradually intensifying the exertion.

[0136] To ensure safety, the HR was continuously monitored to keep it within acceptable limits. The dynamic user interface (108) used visual and audio cues to help subjects maintain movement intensity (MI) within upper and lower bounds determined by the deviation factor.

[0137] The assessment concluded when subjects could no longer sustain the required MI or when their HR reached zone 5, indicating high exertion.

[0138] After completing the jogging portion, the subjects were asked to sit in a relaxed position for 1.5 minutes to measure the recovery period. This helped their HR to return to a resting state, providing valuable data on HR recovery.

[0139] Fig. 9A illustrates a man with a wearable chest strap ECG sensor undergoing cardiac assessment via the mobile application according to the embodiments disclosed herein. The Fig. depicts a real-life scenario where the user (110) is wearing the wearable sensor device (300) and performing physical activityon the floor (109). Positioned in front of the user (110) using a tripod, the mobile device (200) displays the dynamic user interface (108) based on the MI and HR of the user obtained through the wearable sensor device (300).

[0140] Fig. 9B illustrates a wearable chest strap ECG sensor according to the embodiments disclosed herein. This Fig. shows an example of a wearable sensor device (300) integrated with the ECG sensor and the accelerometer to measure the performance of the user and transmit the HR and MI of the user to the mobile device (102).

[0141] Fig. 9C illustrates a plot of HR during the Cardiac Health Assessment Test according to the embodiments disclosed herein. The Fig. 9C presents the assessment results conducted on users equipped with the wearable sensor device (300). The plot indicates the termination of the assessment when users could no longer sustain the required MI or when their HR reached zone 5, indicating high exertion. After completing the jogging portion, the subjects were asked to sit in a relaxed position for 15 minutes to measure the recovery period. This allowed their HR to return to a resting state, providing valuable data on HR recovery as seen in Fig. 9C.

[0142] Fig. 10 illustrates a representation of the gradual increase in movement load during the exercise, with instructions to remain between the upper and lower limits for 30-second increases in intensity, according to the embodiments disclosed herein. The Fig. also depicts the heart rate (HR) of users undergoing the assessment, which was continuously monitored to keep the HR within acceptable limits.

[0143] Fig. 11 illustrates an expected MI for protocol adherence, indicating upper and lower bounds of tolerance within which the actual MI should vary when the user jogs as prescribed, according to the embodiments disclosed herein. For an ideal assessment, the user is expected to maintain jogging cadence and increase it during "level up," resulting in the MI to vary in a stepped fashion. However, pragmatically, MI is expected to lie within the upper and lower bounds of tolerance.

[0144] To analyse the effectiveness of the system in ensuring adherence, MI recorded for each assessment session across both control groups is compared withthe ideal pattern to measure the Root Mean Square Error (RMSE), denoted by A, which is expressed as:

[0145] Where, n is the number of data points present for MI in the assessment, represents the actual movement intensity value for the i th data point, I represents the expected movement intensity value corresponding to the

[0146] In an embodiment, the aim of the data collection is to evaluate and measure the effectiveness of the interactive system in ensuring protocol adherence. The analysis was done with an intent to visualize the difference in protocol adherence between the two control groups. To investigate protocol adherence, the independent parameter, movement load was chosen for comparison across all users.

[0147] The MI patterns measured during assessments taken by a first user from control group A are illustrated in Fig. 12A, according to the embodiments disclosed herein. Similarly, Fig. 12B illustrates the MI patterns measured during assessments taken by a second user from control group A. Observations from Fig. 12A and 13B indicate that the actual MI adherence for a user randomly selected from Control Group A deviated significantly from the expected range. This deviation is attributed to users making continuous adjustments to their jogging cadence based on perceived audio after leveling up. In an attempt to find the right cadence, the user (whose data is shown in Fig. 12A) lost track of the audio beats and overexerted for the first 2 minutes. Subsequently, the user attempted to lower the cadence according to the audio beats, settling for a lower cadence and sustaining it despite the increasing tempo in the audio for the next 3 minutes. Beyond 5 minutes of exertion, the user was able to pick up the tempo of the beats, which is manifested as a monotonic increase in MI. However, the user was not able to match the absolute range of expected MI levels, as evidenced by the offset between the actual MI and expected ranges.

[0148] Fig. 12C illustrates the MI patterns measured during assessments taken by a user using audio guidance from control group B, according to the embodimentsdisclosed herein. Further, Fig. 12D illustrates the MI patterns measured during assessments taken by another user using audio guidance from control group B. Samples of MI from Control Group B, shown in Fig. 12C and 12D, demonstrate improved compliance with the expected range of MI. The actual MI fairly lies within the tolerance band, and the variations within the band signify users' attempts to adjust the cadence by taking visual feedback interactively. Regions in these plots where measured MI goes out of the tolerance band and returns within the range portray the role of the Health Indicator, which nudges users to keep up the cadence.

[0149] Fig. 13 illustrates the Root Mean Square Error (RMSE) distribution across control groups to compare the effect of gamification on protocol adherence according to the embodiments disclosed herein. A significant drop in the median RMSE is depicted after the introduction of an interactive feedback system.

[0150] To quantitatively compare the deviation between the two control groups, Group A and Group B, the RMSE is calculated (expressed by A) for every assessment in a given control group. Results are presented as a box and whisker plot. Observations from the distribution indicate that the median RMSE for Control Group B has significantly reduced from that of Control Group A after introducing visual feedback through gamification. The drop in median RMSE, including outliers, affirms the change induced by the feedback system in maintaining the cadence throughout the assessment duration.

[0151] In an embodiment, the ability of an interactive solution to guide users through an assessment protocol is described. The solution was iteratively developed, initially relying on audio-based guidance to help users adhere to the protocol. Although this method of guiding users to exercise works to an extent, the inherent inability to detect violations from the recommendation renders the solution ineffective in helping users sustain the expected behavior. Subsequent iterations reimagined the initial implementation, replacing it with a closed-loop system incorporating interactive visual feedback.

[0152] Given the attention requirements for adherence in an exertion protocol, gamification is expected to provide necessary engagement to help users abide by the protocol. The collective result of gamification and biofeedback is improvedadherence, as demonstrated by results in the validation study. Inclusion of these components in a rather monotonous and uninteresting protocol made the assessment experience enjoyable. This is supported by post-assessment feedback from multiple users stating that the game successfully masked the perception of the passage of time throughout the assessment.

[0153] The validation study demonstrated the potential capabilities of the developed solution in causing psychological immersion, which can be leveraged to help unmotivated users in perfecting or completing workouts. Structured gamification of exercise routines, when implemented and delivered through the discussed solution, could influence such users in cultivating healthy habits and creating consistency.

[0154] Fig. 14 illustrates a comparison of RMSE distributions between different protocols for estimating VO2 max from heart rate data, with consideration for potentially simpler alternatives to the CPET, according to the embodiments as disclosed herein. In an embodiment, the dataset was initially split into a training set and a validation set using k-fold cross-validation. The optimal parameters for each model were determined through five-fold cross-validation within each training set. After identifying the optimal parameters, the model with these parameters was used on the validation set to obtain the final outcome.

[0155] In an embodiment, evaluation metrics is defined wherein Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) are common metrics used for assessing the performance of regression models. Among these metrics, RMSE was chosen for this study because of its sensitivity to significant errors, which are particularly undesirable in this context. The performance of various regression models and different input parameters were evaluated using RMSE.

[0156] In an embodiment, the main objective is to evaluate VO2 max predicted from HR data obtained during CPET and Cardiac Assessment Protocol using ML models. The predicted VO2 max were compared with the ground truth data to assess the performance and validate the data modelling approach. To estimate VO2 max,RF and SVR models were used to predict and evaluate the estimates, as mentioned in the data modelling section.

[0157] Comparison of estimated VO2 max from HR data captured during CPET: The dataset collected using a wearable chest strap with an ECG sensor, recorded data via the mobile application. These datasets were gathered during the CPET procedure, which involved the use of a treadmill. The selected models were applied to estimate VO2 max from this dataset. The RMSE of the predicted V02max for these two models showed notable differences, as presented in Table I. The RF model yielded an RMSE of 5.82, whereas the SVR model yielded an RMSE of 6.88. This indicates that the RF model outperformed the SVR model, suggesting a better fit with lower error rates. However, the overall error rate remained relatively high, indicating that, while predicting VO2 max from HR data is feasible, there’s still some potential for enhancement.Table 1 : performance Metrics for VO2 max estimation between CPET and Cardiac Assessment Protocol

[0158] Comparison of V02max estimated from HR data obtained during Cardiac Health Assessment Test: The dataset collected from the Cardiac Assessment Protocol was used to estimate VO2 max using HR and acceleration data obtained from the sensor. This Table I, reveals a significant difference in the RMSE between the two models used to predict VO2 max. The RF model had an RMSE of 5.37, while the SVR model had an RMSE of 7.18, indicating that the RFmodel generally outperformed the SVR model. Despite this, the error rate was still relatively high.

[0159] The RF model consistently yielded better results than the SVR model. This can be explained by RF’s use of multiple decision trees to create a combined prediction, with each tree capturing different aspects of the data, leading to improved accuracy. The aggregation of these trees results in more robust and reliable predictions, especially when dealing with complex datasets like those with physiological measurements. Further, RF had a natural ability to capture non-linear relationships between the features and the target variable.

[0160] To further quantify the performance of the two experimental methods, RMSE was calculated for each k-fold in the dataset, across all subjects. The results are presented as a box and-whisker plot. It is evident from the distribution that the median RMSE for the HR data collected during the Cardiac Assessment Protocol differed from that of the HR data collected during CPET. The slight increase in median RMSE indicates that the VO2 max estimation from the protocol data is almost adequate for the CPET. Further, the RMSE for both the CPET and Cardiac Assessment Protocol was nearly identical, indicating that enhancing the features to improve one model could inherently benefit the other. Despite yielding relatively high RMSE values, the results obtained demonstrate superior performance compared to many equation-based models, some of which exhibit RMSE values exceeding 5.0. This indicates that, although the RMSE values are high, the model’s predictive accuracy surpasses that of traditional equation-based approaches.

[0161] In an embodiment, a method is given to accurately predict V02max using HR and acceleration data, validated against ground truth value obtained from CPET. Aside from predictive modeling, this study aimed to present a novel gamebased Cardiac Assessment Protocol designed to estimate VO2 max solely from HR and movement data. This approach streamlines the process, providing a timeefficient way to estimate VO2 max without relying on cumbersome protocols, thus improving clinical feasibility and accessibility.

[0162] Given the need for a robust and user-friendly protocol a more streamlined and interactive Cardiac Assessment Protocol was proposed. Todetermine whether V02 max could be predicted from HR data collected during CPET, a model was trained and validated. The accuracy of the proposed protocol has been tested by comparing VO2 max results obtained from HR data during the Cardiac Assessment Protocol with the ground truth VO2 max data from CPET. As per the results, the prediction model has a reasonably high level of accuracy, especially considering the complexity of predicting VO2 max and the variability in the input features. The RMSE results from both the trained models were relatively high and similar. This similarity in value indicates that enhancing the features and refining models could lead to improved outcomes.

[0163] Fig. 15 is a flow diagram illustrating the method for determining a user's cardio respiratory fitness according to the disclosed embodiments. At step SI 601, the mobile device establishes a connection with a wearable sensor device (300) using short-range communication. Subsequently, at step SI 602, the mobile device (200) receives and stores the user's Motion Index (MI) and Heart Rate (HR) from the wearable sensor device (300). Further, the mobile device receives the user's physiological data from the wearable sensor device (300) while the user engages in physical activity at a predefined location.

[0164] At step S1603, the mobile device (200) displays a dynamic user interface based on the user's MI and HR. This dynamic user interface (108) includes a user avatar (108) across a deviation factor spectrum (106), two antagonist characters (103 and 105) positioned at opposite ends of the deviation factor spectrum (106), and a performance indicator (PI) (107) indicating the user's performance level during the physical activity. The mobile device (200) controls the position and movements of the user avatar across the deviation factor spectrum (106) based on the MI while the user (110) performs the physical activity. The position and movements of the user avatar are directed towards or away from at least one of the two antagonist characters. The mobile device (200) increases the user's performance level based on the HR and determines the user's cardio respiratory fitness based on at least one of HR, MI, or their combinations.

[0165] In an embodiment, the mobile device (200) receives the user's physiological data from the wearable sensor device while performing the physicalactivity at the predefined location. It generates interactive visual feedback on the user interface display by converting the physiological data into interactive visual feedback based on the MI and HR, thereby enhancing user engagement.

[0166] In an embodiment, the mobile device (200) determines whether the user's HR exceeds a predefined HR threshold during the physical activity and terminates or suspends the dynamic user interface when a predefined condition occurs. Controlling the position and movements of the user avatar based on the MI involves visually manipulating the user avatar's (104) position and movements displayed in the dynamic user interface. This is achieved by mapping the user avatar's (104) movements to the deviation factor spectrum (106) while performing the physical activity at the predefined location.

[0167] Terminating or suspending the dynamic user interface when a predefined condition occurs includes detecting whether the predefined condition has occurred. The predefined condition may involve the user's interaction level falling below a specified threshold while the user avatar is near a first antagonist character, resulting in a negative deviation factor (d), the user's physical activity level surpassing a predefined exercise level, causing the user avatar to approach a second antagonist character, resulting in a positive deviation factor (d), or the HR exceeding a predefined threshold for a specified duration.

[0168] Determining the user's cardio respiratory fitness based on HR and MI includes calculating a linear combination of Exertion Duration (ED) from the onset of performance assessment until the HR enters a predefined HR zone, a particular movement load, or specific HR characteristics. The mobile device (200) also determines the user's recovery beats based on the time required to relax for a predetermined period after terminating or suspending the physical activity. The cardio respiratory fitness is then determined based on the linear combination of ED, recovery beats, and user feedback.

[0169] Detecting the commencement of a new stage for the physical activity in the predefined location by the user and reinitializing the user avatar's position in the dynamic user interface upon the new stage's commencement promotes sustainability in the physical activity. The mobile device (200) iteratively refinesthe deviation factor spectrum (106) based on user feedback for optimal engagement and pace maintenance across different physical activity stages. The antagonist characters serve as visual or interactive penalties activated based on deviations in the user's MI from predefined target values for the physical activity.

[0170] The description of the specific embodiments provided herein is detailed enough to allow others to modify or adapt them for various applications without deviating from the core concept. Such modifications are intended to be covered within the scope of the disclosed embodiments. The terminology used is for descriptive purposes only and not limiting. Therefore, while preferred embodiments have been described, those skilled in the art will recognize that modifications can be made within the scope of the described embodiments.

Claims

CLAIMSWe claim:

1. A method for determining a cardio respiratory fitness of a user (110), the method comprising: establishing, by a mobile device (200), a connection with a wearable sensor device (300) using a short-range communication; receiving and storing, by the mobile device (200), a movement intensity (MI) and a heart rate (HR) of a user wearing the wearable sensor device (300), wherein the MI and the HR are received while the user is performing a physical activity in a predefined place; displaying, by the mobile device (200), a dynamic user interface (108) based on the MI and HR of the user, wherein the dynamic user interface (108) comprises a user avatar (104) across a deviation factor spectrum (106), at least two antagonist characters positioned at opposite ends of the deviation factor spectrum (106), and a performance indicator (PI) indicating a performance level of the user while performing the physical activity; controlling, by the mobile device (200), position and movements of the user avatar (104) across the deviation factor spectrum (106) based on the MI while the user is doing the physical activity in the predefined place, wherein the position and movements of the user avatar (104) are directed towards or away from at least one antagonist character of the at least two antagonist characters; increasing, by the mobile device (200), the performance level of the user based on the HR, the MI and the combinations of the HR and the MI while the user is doing the physical activity in the predefined place; and determining, by the mobile device (200), the cardio respiratory fitness of the user based on the at least one of HR, the MI and the combinations of the HR and the MI.

2. The method as claimed in claim 1, comprising:receiving, by the mobile device (200), physiological data of the user from the wearable sensor device (300) while performing the physical activity at the predefined place; and generating, by the mobile device (200), an interactive visual feedback on the display of the user interface by converting the physiological data of the user into the interactive visual feedback based on the MI and the HR, thereby enhancing user engagement.

3. The method as claimed in claim 1, comprising: determining, by the mobile device (200), whether the HR of the user exceeds a predefined HR threshold while doing the physical activity at the predefined place; and terminating or suspending, by the mobile device (200), the dynamic user interface (108) when a predefined condition has occurred.

4. The method as claimed in claim 1, wherein controlling the position and movements of the user avatar (104) based on the MI comprises visually manipulating the position and the movements of the user avatar (104) displayed in the dynamic user interface (108) based on the MI while performing the physical activity at the predefined place by mapping the movements of the user avatar (104) to the deviation factor spectrum (106).

5. The method as claimed in claim 3, wherein terminating or suspending, by the mobile device (200), the dynamic user interface (108) when the predefined condition has occurred comprises: detecting whether a predefined condition has occurred, wherein the predefined condition comprises at least one of: an interaction level of the user falls below a specified threshold while the user avatar (104) is in proximity to a first antagonist character of the at least two antagonist characters, resulting in a negative deviation factor (d); a physical activity level of the user surpasses a predefined exercise level, causing the user avatar (104) to approach a second antagonist character of the at least two antagonist characters, resulting in a positive deviation factor (d); and the HR exceeds a predefined threshold for a specified duration; andterminating or suspending, by the mobile device (200), the dynamic user interface (108) when the predefined condition has occurred.

6. The method as claimed in claim 1, wherein determining the cardio respiratory fitness of the user based on the HR and the MI comprises: determining, by the mobile device (200), a linear combination of an Exertion Duration (ED) based on a time from an onset of assessment of performance of the user while performing the physical activity until the HR enters at least one of a predefined HR zone, a particular movement load or a particular HR characteristics; determining, by the mobile device (200), recovery beats of the user based on a time required by the user to relax for a predetermined period upon termination or suspension of the physical activity; and determining, by the mobile device (200), the cardio respiratory fitness of the user based on the at least one of the linear combination of the ED, the recovery beats and user feedback.

7. The method as claimed in claim 1, comprising: detecting, by the mobile device (200), a commencement of a new stage for the physical activity in the predefined place by the user; reinitializing, by the mobile device (200), the position of the user avatar (104) in the dynamic user interface (108) upon the commencement of the new stage to promote sustainability in the physical activity; and iteratively refining, by the mobile device (200), the deviation factor spectrum (106) based on user feedback for optimal user engagement and pace maintenance across different stages of the physical activity.

8. The method as claimed in claim 1, wherein the at least two antagonist characters serve as visual or interactive penalties, and wherein the visual or interactive penalties are activated based on deviations in the MI of the user from predefined target values for the physical activity.

9. A system for determining a cardio respiratory fitness of a user, comprising:a wearable sensor device (300) worn by a user while doing a physical activity on a predefined place, wherein the wearable sensor device (300) is adapted to measure movement intensity (MI) and heart rate (HR) of the user; a mobile device (200) connected to the wearable sensor device (300) using a short-range communication, wherein the mobile device (200) comprises: a display (202); a data acquisition controller (206) configured to receive and store the MI and the HR from the wearable sensor device (300); an interactive logic controller (205), connected to the data acquisition controller (206) and the display (202): generates a dynamic user interface (108) on the display of the mobile device (200) based on the MI and the HR of the user, wherein the dynamic user interface (108) comprises: a) a user avatar (104) displayed across a deviation factor spectrum (106), b) at least two antagonist characters positioned at opposite ends of the deviation factor spectrum (106), and c) a performance indicator (PI) (107) indicating a performance level of the user while doing the physical activity at the predefined place; controls position and movements of the user avatar (104) across the deviation factor spectrum (106) based on the MI, wherein the position and movements of the user avatar (104) being directed towards or away from at least one antagonist character of the at least two antagonist characters, increases the performance level of the user based on the at least one of HR, the MI or the combinations of the HR and the MI, and determines the cardio respiratory fitness of the user based on the HR and the MI.

10. The system as claimed in claim 9, wherein the mobile device (200) comprises a feedback controller (207) configured to:receive physiological data of the user from the wearable sensor device (300) while doing the physical activity at the predefined place; and generate interactive visual feedback on the display of the user interface by converting the physiological data of the user into the interactive visual feedback based on the MI and the HR thereby enhancing the user engagement.

11. The system as claimed in claim 9, wherein the interactive logic controller: determine whether the HR of the user exceeds a predefined HR threshold while doing the physical activity at the predefined place; and terminate or suspend the dynamic user interface (108) when the predefined condition has occurred.

12. The system as claimed in claim 9, wherein to control the position and movements of the user avatar (104) based on the MI comprises visually manipulating the position and the movements of the user avatar (104) displayed in the dynamic user interface (108) based on the MI while doing the physical activity at the predefined place by mapping the at least one of movements and the HR of the user avatar (104) to the deviation factor spectrum (106).

13. The system as claimed in claim 11, wherein to terminate or to suspend the dynamic user interface (108) when the predefined condition has occurred comprises: detect whether a predefined condition has occurred, wherein the predefined condition comprises at least one of: a) an interaction level of the user falls below a specified threshold while the user avatar (104) is in proximity to a first antagonist characters of the at least two antagonist characters, resulting in a negative deviation factor (d), b) a physical activity level of the user surpasses a predefined exercise level, causing the user avatar (104) to approach to a second antagonist characters of the at least two antagonist characters, resulting in a positive deviation factor (d), and c) the HR exceeds a predefined threshold for a specified duration; andterminate or suspend the dynamic user interface (108) when the predefined condition has occurred.

14. The system as claimed in claim 9, wherein to determine the cardio respiratory fitness of the user based on the HR and the MI comprises: determine a linear combination of an Exertion Duration (ED) based on a time from an onset of assessment of performance of the user while doing the physical activity until the at least one predefined condition has occurred; determine recovery beats of the user based on a time required by the user to relax for a predetermined period upon termination or suspension of the physical activity; and determine the cardio respiratory fitness of the user based on the at least one of the linear combination of the ED, a Heart Rate Recovery (HRR) and a user information.

15. The system as claimed in claim 9, wherein the interactive logic controller is configured to: detect a commencement of a new stage for the physical activity in the predefined place by the user; reinitialize the position of the user avatar (104) in the dynamic user interface (108) upon the commencement of the new stage to promote sustainability in the physical activity; enable corrective strategies for protocol adherence in subsequent stages for doing the physical activity by the user; and iteratively refine the deviation factor spectrum (106) based on a user feedback for optimal user engagement and a pace of maintenance across different stages of the physical activity.

Images