Method for monitoring the motion data of a user

Abstract

A method (800) and system (100) for monitoring a motion data of a user is disclosed. The method comprises obtaining (832) from one or more sensors, sensor data associated with movement of the user. The method comprises processing the obtained sensor data and extracting (838) one or more mobility parameters. Furthermore, the method comprises extracting (840) surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. The method comprises monitoring the motion data of the user, by implementing a machine learning model for correlating (842) the one or more classified mobility surfaces and the one or more extracted mobility parameters.

Description

Description Title of Invention :METHOD FOR MONITORING THE MOTION DATA OF A USERTechnical Field

[0001] The present invention generally relates to Artificial intelligence (Al) and healthcare, and more particularly relates to and method and system for monitoring motion data of a user and lowering a risk of a user falling, during different mobility periods.Background Art

[0002] Mobility of an individual is defined as an ability of the user to move purposefully anytime throughout a day. Examples of an individual’s mobility include one or more of walking, jogging, running, or any similar action on different surfaces such as flat surfaces, uneven surfaces, slippery surfaces, an elevated surface, or stairs. Walking is something that is simple, enjoyable, and effective mobility exercise that enhances a healthy lifestyle of individuals. However, a lack of balance, coordination, and walking stability creates a panic situation in an individual’s day-to-day environment. Currently, the individual is not aware of their health and safety when they are in motion on different mobility surfaces. Furthermore, due to lack of monitoring of walking stability, for an individual, there is a potential risk involved, when the individual is walking on different surfaces like stairs, even, uneven, slippery, slope etc. The biomechanics of the user’s mobility is very complex and involves extensive analysis of the muscular activity, force, balance, and momentum of the user when in motion.

[0003] Existing techniques for analysis of health of the user, during mobility, are centered around analysing the timing and symmetry of steps during walking to identify potential neurological issues. For example, gait analysis as known in the state of the art, also known as walking or motion analysis, is a comprehensive evaluation of the way an individual stands and walks. However, the gait analysis fails to perform analysis of balance and coordination of a walking pattern of the individual. Some of the existing techniques include the use of smartwatches or a smartphone to monitor the walking pattern of the individual. The limitation of the gait analysis or the gait includes the presence of sensors such as accelerometers or gyroscopes in proximity to the user's limbs or the user's lower body part so that the contact state and force between the foot and the ground can be detected. Also, the gait analysis is limited only to monitoring parameters such as step length, swing time, and stance time.

[0004] The existing techniques include monitoring the walking pattern of the individual and are restricted to only flat surfaces. In addition, the existing smartphone monitors the walking pattern of the user to provide insights to the user, only when smartphone of the user is placed in pocket. For example, the limitations of the existing techniques include the installation of the wearable sensors on the lower body parts of the user such as shank, sacrum, or on user limbs and feet. The existing techniques fail to evaluate the risk of the user falling when the user is running or walking on different surfaces (for example., non-flat surfaces). Moreover, the existing techniques for monitoring health of the user evaluate data only when the wearable device (for example, the smartphone) is present in a lower pocket or lower area of body of the user. Additionally, the existing techniques for monitoring health of the user fail to consider the scenarios and phases, during which both feet of user are touching and not touching the surface of ground. Moreover, the existing solutions use statistical thresholds to evaluate the health of the user during mobility. Accordingly, there is a need for a system and methods that overcome at least some of the above-mentioned limitations.Solution to Problem

[0005] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.

[0006] According to one embodiment of the present disclosure, a method for monitoring motion data of a user is disclosed. The method comprises obtaining from one or more sensors, sensor data associated with movement of the user. The method comprises processing the obtained sensor data and extracting one or more mobility parameters. Further, the method comprises extracting surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. Furthermore, the method comprises monitoring the motion data of the user, by implementing a machine learning model for correlating the one or more classified mobility surfaces and the one or more extracted mobility parameters.

[0007] According to another embodiment of the present disclosure, a system for monitoring motion data of a user is disclosed. The system comprises a memory configured to store a plurality of modules in the form of programmable instructions and a processor communicatively coupled to the memory. The processor is configured to execute the programmable instructions associated with the plurality of modules. The plurality ofmodules comprises an obtaining module configured to obtain sensor data associated with movement of the user from one or more sensors. The plurality of modules comprises a data processing module configured to process the obtained sensor data. The plurality of modules comprises a mobility identification module configured to extract one or more mobility parameters, based on the processed sensor data. The plurality of modules comprises a surface identification module configured to extract surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. The plurality of modules comprises a correlational module configured to determine the motion data of the user, wherein the correlational module is configured to implement a machine learning model configured to correlate the one or more classified mobility surfaces and the one or more extracted mobility parameters.

[0008] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.Brief Description of Drawings

[0009] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0010] FIG. 1 illustrates a block diagram of a system for monitoring a motion data of a user, according to an embodiment of the present disclosure;

[0011] FIG. 2 illustrates a detailed block diagram of the system of FIG. 1 and its modules, according to an embodiment of the present disclosure;

[0012] FIG. 3 further depicts an operational flow of a method associated with the plurality of modules for monitoring the motion data of the user, according to an embodiment of the present disclosure;

[0013] FIG. 4A illustrates an exemplary graphical representation of experimental simulations for processing of sensor data obtained from one or more sensors for determining a position of the one or more sensors, according to an embodiment of the present disclosure;

[0014] FIG. 4B illustrates an exemplary graphical representation of experimental simulations for normalizing the pre-processed sensor data from one or more sensors at distinctive mobility periods to a single motion data for determining a normalized motion data, according to an embodiment of the present disclosure;

[0015] FIG. 5A and FIG. 5B illustrates an exemplary graphical representation showing an identification of a stance phase and a swing phase based on preset thresholds for different stride wavelets, according to an embodiment of the present disclosure;

[0016] FIG. 5C illustrates an exemplary graphical representation depicting classification of the identified stance phase and the identified swing phase for determining a plurality of stride features, according to an embodiment of the present disclosure;

[0017] FIG. 5D to FIG. 5F illustrates the process flow and exemplary graphical representations for determining one or more mobility patterns of the user, according to an embodiment of the present disclosure;

[0018] FIG. 6A and FIG. 6B illustrates a process flow for extracting surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data, according to an embodiment of the present disclosure;

[0019] FIG. 6C illustrates an exemplary graphical representation showing one or more mobility surfaces classified based on frequency domain, time domain, and statistical features and its comparison with preset thresholds, according to an embodiment of the present disclosure;

[0020] FIG. 7A and FIG. 7B illustrates a process flow and exemplary graphical representation for correlating the one or more classified mobility surfaces and the one or more extracted mobility parameters, according to an embodiment of the present disclosure;

[0021] FIG. 7C and FIG. 7D illustrates a process flow and exemplary graphical representation for determining, the motion data of the user for determining a risk of the user falling during different mobility patterns of the user, in accordance with an embodiment of the present disclosure;

[0022] FIG. 7E and FIG. 7F illustrates a graphical representation for evaluation of mobility parameters such as double contact phase and zero contact phase, for providing personalized insights to the user based on the determined motion data for improving the user's health and lowering the risk of the user falling at the time of mobility, in accordance with an embodiment of the present disclosure; and

[0023] FIG. 8 illustrates another exemplary process flow of a method for monitoring motion data of a user during different mobility patterns of the user, according to an embodiment of the present disclosure.

[0024] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.Description of Embodiments

[0025] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the various embodiments and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

[0026] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the invention and are not intended to be restrictive thereof. Reference throughout this specification to “an aspect”, “another aspect” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0027] The terms “comprise”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by “comprises... a” does not, without more constraints,preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

[0028] Reference is made to FIG. 1 which illustrates a detailed block diagram of a system 100, according to an embodiment of the present disclosure. The system 100 may include a plurality of modules 101, a processor 102, an Input / Output (I / O) interface 103, a memory 104, and a transceiver 105. In an exemplary embodiment, the processor 102 may be operatively coupled to each of the I / O interface 103, the plurality of modules 101, the transceiver 105, and the memory 104. In one embodiment, the processor 102 may include a graphical processing unit (GPU) and / or an Artificial Intelligence Engine (AIE). In one embodiment, the processor 102 may include at least one data processor for executing processes in a virtual storage area network. The processor 102 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc. In one embodiment, the processor 102 may include a central processing unit (CPU), a graphics processing unit (GPU), or both. The processor 102 may be one or more general processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now-known or later developed devices for analyzing and processing data. The processor 102 may execute a software program, such as code generated manually (i.e., programmed) to perform the desired operation. The processor 102 may be disposed in communication with one or more input / output (VO) devices via the VO interface 103. In some embodiments, the processor 102 may communicate with the one or more electronic devices 210 using the VO interface 103. The VO interface 103 may employ near field Communication (NFC), Bluetooth, communication code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, or the like, etc. Using the VO interface 103, the system 100 may communicate with one or more VO devices. For example, the input device may be an antenna, microphone, touch screen, touchpad, storage device, transceiver, video device / source, etc. The output devices may be a video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED), plasma, Plasma Display Panel (PDP), Organic light-emitting diode display (OLED) or the like), audio speaker, etc.

[0029] The processor 102 may be disposed in communication with a communication network via a network interface. In an embodiment, the network interface may be the VOinterface 103. The network interface may connect to the communication network to enable connection of the system 100 with the electronic devices comprising an obtaining module 110, 210 and / or outside environment. The network interface may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), transmission control protocol / intemet protocol (TCP / IP), token ring, IEEE 802.1 la / b / g / n / x, etc. The communication network may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, etc. Using the network interface and the communication network, the system 100 may communicate with other devices. In some embodiments, the memory 104 may be communicatively coupled to the processor 102. The memory 104 may be configured to store data and instructions executable by the processor 102. In another embodiment, the memory 104 may be provided via a cloudbased unit. In yet another embodiment, the memory 104 may communicate with the processor 102 via a bus within the system 100. In yet another embodiment, the memory 104 may be located remotely from the processor 102 and may be in communication with the processor 102 via a network. The memory 104 may include but is not limited to, a non- transitory computer-readable storage media, such as various types of volatile and nonvolatile storage media including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, the memory 104 may include a cache or random-access memory for the processor 102. In alternative examples, the memory 104 is separate from the processor 102, such as a cache memory of a processor, the system memory, or other memory. The memory 104 may be an external storage device or database for storing data. The memory 104 may be operable to store instructions executable by the processor 102. The functions, acts, or tasks illustrated in the figures or described may be performed by the programmed processor 102 for executing the instructions stored in the memory 104. The functions, acts, or tasks are independent of the particular type of instruction set, storage media, processor, or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code, and the like, operating alone or in combination. Likewise, processing strategies may include multiprocessing, multitasking, parallel processing, and the like.

[0030] In some embodiments, the plurality of modules 101 may be included within the memory 104. The memory 104 may further include a database to store data. The pluralityof modules 101 may include a set of instructions that may be executed to cause the system 100, in particular, the processor 102 of the system 100, to perform any one or more of the methods / processes disclosed herein. The plurality of modules 101 may be configured to perform the steps of the present disclosure using the data stored in the database. For instance, the plurality of modules 101 may be configured to perform the steps disclosed in FIG. 3 and FIG. 8. In an embodiment, each of the plurality of modules 101 may be a hardware unit that may be outside the memory 104. Further, the memory 104 may include an operating system for performing one or more tasks of the system 100, as performed by a generic operating system.

[0031] The transceiver 105 may be configured to receive and / or transmit signals to and from the one or more electronic devices 210 A-B. In one embodiment, the database may be configured to store the information as required by the plurality of modules 101 and the processor 102 to perform one or more functions as disclosed in FIG. 3 and FIG. 8. The system 100 may be communicably coupled to an electronic device (210 A-B as shown in FIG 2). The electronic device may be a wearable device or a mobile device. In one example, the electronic device may be a smartwatch 210A and a smartphone 210B. The electronic device may include an obtaining module 110, 210. In an embodiment, the system 100 may be integrated within the electronic device. In an embodiment, the system 100 may be provided in a distributed manner, in that, one or more components of the system 100 may be provided on the electronic device and one or more components of the system 100 may be provided on a remote cloud-based unit. In non-limiting examples, the electronic device 110 may include a mobile device, a smartwatch, a tablet, wearable controllers, and any kind of wearable device.

[0032] The system 100 is configured to monitor motion data of a user. The plurality of modules 101 may include but is not limited to, the obtaining module 110, a data processing module 114, a surface identification module 118, a mobility identification module 112, and a correlational module 116. The plurality of modules 101 may be implemented by way of suitable hardware and / or software applications. In some embodiments, at least one of the plurality of modules 101 may use an Al model. A function associated with Al may be performed through the non-volatile memory, the volatile memory, and the processor 102.

[0033] The processor 102 may include one or a plurality of processors. At this time, one or a 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-dedicatedprocessor such as a neural processing unit (NPU). The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule stored in the non-volatile memory or may employ a suitable artificial intelligence (Al) model executed from a server or a local memory module.

[0034] The Al model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through the calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

[0035] The learning technique is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning techniques include but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, active learning, and reinforcement learning. The processor 102 may perform pre-processing operations on the data to convert it into a form appropriate for use as an input for the artificial intelligence (Al) model. Reasoning prediction is a technique of logical reasoning and predicting by determining information and includes, e.g., knowledge-based reasoning, optimization prediction, preference-based planning, or recommendation. Further, the present disclosure contemplates a computer-readable medium that includes instructions or receives and executes instructions responsive to a propagated signal. Further, the instructions may be transmitted or received over the network via a communication port or interface or using a bus (not shown). The communication port or interface may be a part of the processor 102 or may be a separate component. The communication port may be created in software or may be a physical connection in hardware. The communication port may be configured to connect with a network, external media, the display, or any other components in a system, or combinations thereof. The connection with the network may be a physical connection, such as a wired Ethernet connection, or may be established wirelessly. Likewise, the additional connections with other components of the system 100 may be physical or may be established wirelessly. The network may alternatively be directly connected to a bus. For the sake of brevity, the architecture and standard operations of the memory 104, the processor 102, the transceiver 105, and the I / O interface 103 are not discussed in detail.

[0036] In some embodiments, the word ‘user’, and ‘individual’ used in the description may refer to the person and are synonyms, in this context and may be used interchangeably. Embodiments of the present invention will be described below in detail with reference to the accompanying figures.

[0037] FIG. 2 illustrates a detailed block diagram of the system 100 and its modules 101 in detail. Referring to FIG. 2, the system 200 is configured for monitoring motion data of a user. The system 200 is configured for monitoring motion data of the user, during different mobility patterns of the user on distinct mobility surfaces. In one example, the different mobility patterns of the user include but are not limited to, walking, running, jogging, and similar such actions of movement on distinct mobility surfaces comprising one or more of a flat surface, a non-flat surface, an uneven surface, a staircase, a surface with slope, a slippery surface, a treadmill, a slippery surface with a snow, and combinations thereof. The system 200 is configured to track the stability of the user to improve the user’s health, when in motion with different mobility patterns and on distinct mobility surfaces. The system 200 is configured to lower the risk of the user falling, when the user is in motion with different mobility patterns and on distinct mobility surfaces using one or more electronic devices 210 A-B. For example, the electronic device 210 may include a mobile device, a smartwatch, a tablet, wearable controllers, and any kind of wearable devices.

[0038] Referring to FIG.2, a smartwatch 210A and a smartphone 210B are configured to obtain sensor data associated with the user, when in motion, from one or more sensors. The smartwatch 210A and the smartphone 210B may include the obtaining module 210. The obtaining module 210 is configured to obtain sensor data associated with the user, when in motion. The obtaining module 210 comprises a 3D motion sensor. The 3D motion sensor is configured to measure the motion data of the user, along the X, Y, and Z axes of the one or more sensors during different mobility patterns of the user. For example, the 3D motion sensor (for example., the three-axis accelerometer sensor) may be triggered at the sampling rate of 10 milliseconds resulting in 100 readings in 1 second for analysis from both the smartwatch 210A and the smartphone 210B. The sensor data obtained from the obtaining module 210 is transmitted to the data processing module 214. The data processing module 214 includes a pre-processing unit 214A, a position identification unit 214B, and a normalization unit 214C. The pre-processing unit 214A is configured to pre-process the obtained sensor data from the one or more sensors. In one example, the pre-processing unit 214A is configured to take the accelerometer data as input and filter out any noise, shaking, and acceleration due to gravity (g) impact.

[0039] The position identification unit 214B is configured to identify the position and orientation of the one or more sensors from the pre-processed sensor data based on preset thresholds. In one example, features such as dominant frequency, spectral entropy, standard deviation, root mean square, and zero crossing rate are used to set preset thresholds for the identification of the position of one or more sensors. In one example, the position identification unit 214B is configured to take the pre-processed data to analyze position and orientation of the smart wearable 210A and the smartphone 210B. The position identification unit 214B uses the preprocessed accelerometer sensor data of the smart wearable 210A and the smartphone 21 OB to identify whether the smart wearable 210A is in a moving hand or in a stable hand and the smartphone 21 OB is in hand or in pocket.

[0040] The normalization unit 214C is configured to normalize the pre-processed sensor data at distinctive mobility periods to single motion data for determining the normalized motion data, based on the identified position and orientation of the one or more sensors in the smartwatch 210A and smartphone 210B. In one example, the normalization unit 214C is configured to normalize the pre-processed sensor data using techniques such as biased vector summation, a polygon method, a parallelogram method, and similar techniques. The working of the data processing module 214 and its components and experimental simulations are explained in detail further with reference to FIG. 4A and 4B. The normalized motion data from the data processing module 214 is further processed and analysed concurrently using the mobility identification module 212 and the surface identification module 218.

[0041] The mobility identification module 212 is configured to extract one or more mobility parameters from the normalized motion data, based on the processed sensor data. The mobility identification module 212 is configured to identify a stance phase and a swing phase from the normalized motion data, based on preset thresholds for different stride wavelets. In one example, features such as stance phase, swing phase, micro movement features are used to set preset thresholds for identification of one or more mobility parameters. It is to be noted that, for a normal user some threshold values are predefined for different features. The mobility identification module 212 is configured to identify (referred to as mobility feature extraction 212A) one or more micro-moment parameters comprising one or more of a heel strike, a foot flat, a double contact phase, a zero contact phase, a false step, a walking asymmetry, uneven steps, steps coordination or combination thereof. In one example, the one or more mobility parameters comprise one or more identified micro-moment parameters.

[0042] In one example embodiment, the double contact phase (DCP) is the relative time of a stride wavelet when both feet of the user are in contacting manner with the surface. In one example embodiment, the zero-contact phase (ZCP) is the relative time of a stride wavelet when both feet of the user are in a non-contacting manner with the surface. The plurality of stride features comprises one or more of a loading response, a midstance, a terminal stance, a pre-swing, an initial swing, and a terminal swing, the mobility identification module is configured to classify the identified stance phase and the identified swing phase. The mobility identification module 212 is configured to use the determined stride features to determine the occurrence of the double contact phase and the zero contact phase for the user. The mobility identification module 212 is configured to classify the extracted one or more mobility parameters to determine the one or more mobility patterns of the user. In one embodiment, the mobility pattern detector 212B is configured to classify one or more mobility parameters of the mobility patterns and classify the pattern with respect to certain preset parameters. The working of the mobility identification module 212 and its components with experimental simulations are explained in detail further with reference to FIG. 5A-C.

[0043] The surface identification module 218 is configured to extract surface features 218A associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. In one example, the surface identification module 218 is configured to extract surface features 218A such as statistical features, and temporal features associated with surfaces. The surface detector 218B of the surface identification module 218 is configured to estimate mobility surface characteristics from the extracted surface features for classifying one or more mobility surfaces. In one embodiment, the extracted surface features are correlated with a trained dataset for classifying mobility surfaces such as a flat surface, a non-flat surface, an uneven surface, a staircase, a surface with a slope, a slippery surface, a treadmill, and combinations thereof. The working of the surface identification module 218 and its components with experimental simulations are explained in detail further with reference to FIG. 6 A and 6B.

[0044] The correlational module 216 is configured to determine the motion data of the user. The correlational module 216 is configured to implement a machine learning model to correlate the one or more classified mobility surfaces and the one or more extracted mobility parameters. The correlational module 216 includes a correlation unit 216A configured to correlate the identified mobility patterns with the classified mobility surfaces for dynamically adjusting the one or more extracted mobility parameters. In one example, thecorrelation unit 216A is configured to correlate the identified mobility patterns and the classified mobility surfaces to adjust mobility health evaluation parameter’s preset thresholds. In one example, features such as stance phase, swing phase, and micromovement features are used to set preset thresholds for identification of one or more mobility parameters. It is to be noted that, for a normal user some threshold values are predefined for different features. The correlational module 216 includes an inference unit 216B to derive various insights related to user’ s health, when in motion with different mobility patterns and on distinct mobility surfaces, risk of the user falling, and calculating a mobility score based on the correlation of identified mobility patterns and classified mobility surfaces. The insights are presented and displayed to the user on the electronic device as shown by reference numeral 222. The correlational module 216 is configured to calculate, values associated with one or more mobility parameters based on the periodic occurrence of variations in at least two or more mobility cycles during a mobility period of the user. The correlational module 216 is configured to determine, the motion data of the user, by correlating the calculated values associated with one or more mobility parameters with the estimated mobility surface characteristics and determine a risk of the user falling during different mobility patterns of the user. The working of the correlational module 216 and its components with experimental simulations are explained in detail further with reference to FIG. 7A-B. In some other embodiments, a manner in which a sensor data associated with the user when in motion, is obtained for monitoring motion data of the user is described in further detail below.

[0045] FIG. 3 further depicts an operational flow of a method 300 associated with the plurality of modules 101 for monitoring the motion data of the user. The plurality of modules 101 may be performed in conjunction with the processor 102 and the memory 104. FIG. 3 may be described from the perspective of the processor 102 embedded in any of the wearable devices 210A-B that is configured for executing computer-readable instructions stored in a memory to carry out the functions of the modules (described below and not shown in the figures) of the system 200. In particular, the steps as described in FIG. 3 may be executed for improving the user’s health, when in motion with different mobility patterns and on distinct mobility surfaces. In particular, the steps as described in FIG. 3 may be executed for predicting a risk of the user falling during different mobility patterns of the user and on distinct mobility surfaces. In particular, the steps as described in FIG. 3 may be executed for providing personalized insights to the user based on the determined motion data for improving the user's health and lowering the risk of the user falling at the time of mobility.

[0046] At step 332, the method includes obtaining sensor data, associated with movement of user, from the obtaining module 210 embedded in the smart wearable 210A and the smartphone 210B. In one example, accelerometer data is obtained from the smart wearable 210A and the smartphone 21 OB, for measuring the acceleration of the device along three axes. At step 334, the method includes identifying the position and orientation of the one or more sensors from pre-processed sensor data based on preset thresholds. The accelerometer data obtained at step 332 may be utilized to identify the position and orientation of smart wearable 210A and the smartphone 210B based on the preset thresholds. This step 334 for identifying the position and orientation of the one or more sensors signifies whether the smart wearable 210A is in a moving hand or in a stable hand and whether the smartphone 21 OB is in a hand or in a pocket. The details associated with position identification of the smart wearables 210 A-B are explained in detail with reference to FIG. 4C.

[0047] At step 336, the method includes normalizing the pre-processed sensor data at distinctive mobility periods to the single motion data for determining the normalized motion data, based on the identified position and orientation of the one or more sensors. In one example, the accelerometer data obtained at step 332 may be processed and normalized to a single data for further processing. At step 338, the method includes extracting one or more mobility parameters from the normalized motion data. In one example, this step includes identifying a stance phase and a swing phase from the normalized motion data, based on preset thresholds for different stride wavelets. In one embodiment, this step includes identifying one or more micro-moment parameters comprising one or more of a heel strike, a foot flat, a double contact phase 338A, a zero-contact phase, a false step, a walking asymmetry, uneven steps, steps coordination, or a combination thereof. In another embodiment, this step includes identifying the mobility parameter such as the double contact phase 338A and the zero contact phase 338B. The plurality of stride features comprises one or more of a loading response, a midstance, a terminal stance, a pre-swing, an initial swing, and a terminal swing, the mobility identification module 212 is configured to classify the identified stance phase and the identified swing phase. The mobility identification module 212 is configured to use the determined stride features to determine the occurrence of the double contact phase 338 A and the zero contact phase 338B for the user.

[0048] The mobility identification module 212 is configured to classify the extracted one or more mobility parameters to determine the one or more mobility patterns of the user. In one embodiment, the mobility pattern detector 212B is configured to classify one or more one or more mobility parameters of the mobility patterns and classify the pattern with respect tocertain preset parameters. In one embodiment, the mobility identification module 212 is configured to classify the extracted one or more mobility parameters such as double contact phase (DCP) and the zero contact phase (ZCP) to determine the one or more mobility patterns of the user as shown in Table. 1 below. The mobility parameters DCP and ZCP are evaluated alone or in combination with each other to identify mobility patterns and classify the pattern with respect to certain preset parameters.Table. 1

[0049] The mobility identification module 212 is configured to compute DCP during walking phases and ZCP during running phases on any kind of mobility surfaces using the combination of sensor data obtained from both or any one of the smartwatch 210A and smartphone 21 OB, irrespective of the position of the smartwatch 210A and smartphone 21 OB. Further, the DCP is the time when both feet of the user are in contact with the ground. When the user has high DCP, it is inferred that during walking, the user is not able to take weight on one foot, thus, the user is keeping feet more frequently in touch with the ground which indicates an occurrence of a mobility problem while walking and the user has high risk of falling. Similarly, the ZCP is the time when both feet are not in touch with the ground, so if a user has a high ZCP it is inferred that the user has high running ability because a user can maintain balance while both feet aren't in touch with ground and indicates low risk of falling. Further, both the DCP and ZCP are considered the important mobility parameters for predicting the mobility state of the user and predicting the risk of the user falling. It is to be noted that, the mobility parameters such as DCP and ZCP are changing based on the type of surface identified. As a result, the disclosed method also considers identifying the different types of mobility surfaces for predicting the risk of the user falling on the ground.

[0050] At step 340, the method includes extracting surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. In one embodiment, using the normalized motion data, the mobility surfaces on which the mobility patterns are identified are classified. In one example, the classified mobility surfaces include one or more of a flat surface, a non-flat surface, an uneven surface, a staircase, a surfacewith a slope, a slippery surface, a treadmill, a slippery surface with a snow, and combinations thereof.

[0051] At step 342, the method includes correlating the identified mobility patterns with the classified mobility surfaces for dynamically adjusting the one or more extracted mobility parameters. In one example, the correlation unit 216A is configured to correlate identified mobility patterns and classified mobility surfaces to adjust mobility health evaluation parameters’ preset thresholds.

[0052] At step 344, the method includes providing personalized insights regarding risk of falling, walking stability, balance, coordination, and health associated with user mobility. The correlational module 216 includes an inference unit 216B to derive various insights related to mobility health, risk of user falling, and calculating a mobility score based on the correlation of identified mobility patterns and classified mobility surfaces. The correlational module 216 is configured to calculate, values associated with one or more mobility parameters based on the periodic occurrence of variations in at least two or more mobility cycles during a mobility period of the user. The correlational module 216 is configured to determine, the motion data of the user, by correlating the calculated values associated with one or more mobility parameters with the estimated mobility surface characteristics and determine a risk of the user falling during different mobility patterns of the user. The manner in which each of the plurality of modules 101 and 201 described in FIG.2 and FIG.3 operate are explained in detail below.

[0053] FIG. 4A illustrates an exemplary graphical representation 400A of experimental simulations for processing of sensor data obtained from one or more sensors, for determining a position of the one or more sensors. The sensor data obtained from the obtaining module 210 is transmitted to the data processing module 214. The pre-processing unit 214A is configured to pre-process the obtained sensor data from the one or more sensors. The accelerometer raw data along the three axis (x,y,z) obtained from the smartwatch 210A and the smartphone 210B is pre-processed. The raw data is further calibrated to remove or filter out any noise, shaking, and acceleration due to gravity(g) impact. The pre-processing unit 214A is configured to consider both the +ve and -ve directions of all the three axes and provide a square root of sum of their squares which gives a magnitude vector representing the length taking into account all axes and its direction. The position identification unit 214B is configured to identify the position and orientation of the smartwatch 210A and the smartphone 210B from the pre-processed sensor data based on preset thresholds. In one example, the sensor data values above the preset thresholds are analyzed. The presetthresholds are shown in Table. 2 below. In one example, the preset thresholds include dominant frequency, spectral entropy, standard deviation, root mean square, and zero crossing rate. Each of the mentioned features (preset thresholds) depicts the status and position of the smartwatch 210A and the smartphone 210B. The term ‘status’ mentioned herein refers to moving data associated with the smartwatch 210A and the smartphone 21 OB. In one example, the position identification unit 214B is configured to take the pre-processed data to analyze position and orientation of smart wearable 210A and the smartphone 21 OB. The position identification unit 214B uses the preprocessed accelerometer sensor data of the smart wearable 210A and the smartphone 21 OB, to identify whether the smart wearable 210A is in a moving hand or in a stable hand and the smartphone 21 OB is in hand or in pocket. The stable data is depicted as 450A, and the moving data is depicted as 450B.Table. 2

[0054] FIG. 4B illustrates an exemplary graphical representation 400B of experimental simulations for normalizing the pre-processed sensor data from one or more sensors at distinctive mobility periods to single motion data for determining the normalized motion data. The pre-processed sensor data includes data obtained from one or more sensors in the smartwatch 210A and smartphone 210B and are shown as 451 A and 45 IB. In one example, the normalization unit 214C is configured to normalize the pre-processed sensor data using techniques such as biased vector summation, etc. The normalization unit 214C is configuredto normalize the pre-processed sensor data using the equation shown by 453. The normalization process is essential to process single data from one or more data sources and biases are required as devices in different positions fail to contribute equally to calculate mobility-related features like double contact phase, and zero contact phase. The manner in which the normalized motion data is processed for extracting one or more mobility parameters and surface features is explained in detail further below.

[0055] FIG. 5A and FIG. 5B illustrates an exemplary graphical representation 500A showing an identification of the stance phase 564 and the swing phase 565 based on preset thresholds for different stride wavelets. As mentioned above, the normalized accelerometer data is taken as input to analyze and extract features related to mobility. The extracted features are referred to as one or more mobility parameters. The normalized motion data may be processed to identify the stance phase 564, the swing phase 565, and one or more micro parameters 566 such as the heel strike, the foot flat, the DCP, and the ZCP. Based on normalized motion data, a stride wavelet is extracted which is shown in the exemplary signal and may differ in various mobility patterns. Referring to table 567, the stance phase 564 and the swing phase 565 are identified based on preset thresholds for different stride patterns.

[0056] FIG. 5C illustrates an exemplary graphical representation 500B depicting classification of the identified stance phase 564 and the identified swing phase 565 for determining the plurality of stride features 568A-G. The identified stance phase 564 and the identified swing phase 565 may be classified into one or more parameters which can determine the relative time when both feet of the user are either in touch with the ground or not in touch with the ground. The plurality of stride features comprises one or more of a loading response 568A, a midstance 568B, a terminal stance 568C, a pre-swing 568D, an initial swing 568E, a mid-swing 568F, and a terminal swing 568G. The mobility identification module 212 is configured to use the determined stride features 568 A-G to determine the occurrence 569 of the DCP and ZCP for the user. Both DCP and ZCP are important parameters to determine the user’s health, when in motion with different mobility patterns and on distinct mobility surfaces in terms of balance and co-ordination.

[0057] FIG. 5D to FIG. 5F illustrates the process flow and exemplary graphical representations for determining one or more mobility patterns of the user. In particular, FIG. 5D to FIG. 5F depicts the process 575A for the classification of mobility patterns and the respective graphical representations 575B and 575C. The mobility identification module 212 is configured to classify the extracted one or more mobility parameters to determine the one or more mobility patterns of the user. In one embodiment, the mobility pattern detector 212Bis configured to classify one or more mobility parameters of the mobility patterns and classify the pattern with respect to certain preset parameters. The steps for pattern detection include a step 571 of mobility feature engineering for extracting one or more mobility parameters, a step of selection 572 of the mobility parameters, and a step of detecting 573 of the pattern with the trained database 574. The extracted features (one or more mobility parameters) are analyzed to classify various patterns i.e. walking, jogging, running, etc. which may be further processed to examine the user’s health, when in motion with different mobility patterns and distinct mobility surfaces. It can be seen that from the graph 575B, the weak classifier Fl may identify the correct mobility pattern but it may be inaccurate as per various users and hence ‘n’ weak classifiers from ‘n’ features may be combined to classify correct mobility patterns. In one example embodiment, from the selected mobility features one or more mobility patterns such as walkingjogging, and running may be classified using ensemble learning technique i.e. customized adaptive boosting. The multiple weak mobility pattern classifiers may be obtained from selected features of stride wavelet as it may enhance the efficacy. The table 3 and the equation shown below depict exemplary features and its computation for determining the mobility patterns of the user.Table. 3I Input Stride Wavelet is in farm [Acc(x.Weighted Output of Mobility Pattern

[0058] FIG. 6A and FIG. 6B illustrates a process flow for extracting surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. FIG. 6C illustrates an exemplary graphical representation 600B showing one or more mobility surfaces classified based on frequency domain, time domain, and statistical features and its comparison with 600A preset thresholds. In one embodiment, the normalized accelerometer data may be processed to analyze and extract features related to mobility surfaces and identify one or more surfaces in mobility patterns. Any mobility pattern on any surface may have a different stride wavelet pattern. Based on that stride wavelet pattern, various features may be extracted which as a result may identify one or more mobility surfaces. Based on various time domain analysis 675 and frequency domain analysis 676 and statistical feature engineering 677 and its comparison with preset thresholds, various walking surfaces (a slippery surface 679A, a staircase 679B, a treadmill 679C, and an uneven surface 679D) may be identified. The same is depicted in Table 678 and shown with exemplary graphs 678A and 678B.

[0059] FIG. 7A and FIG. 7B illustrates a graphical representation 700A depicting the correlation between the one or more classified mobility surfaces and the one or more extracted mobility parameters. The graphical representation 700A illustrates the identified mobility patterns 780, identified surfaces 782, existing mobility parameter thresholds 784,instructions 786, and co-relational layers 788. In one example, the instructions 786 may be: (1) While walking, 20-40% should be ideal DCP and no time during which none of the feet is in touch with ground. (2) As the surface is uneven, a user might feel difficulty in walking and to reduce the risk of fall user may walk carefully so 35-50% will be the dynamic threshold, (3) On a slippery icy surface, the user may take each step thoughtfully so even time increase much on both feet. (4) While jogging apart from 10-30% DCP, a user should spend at least 4-5% time when both feet are in the air for a healthy jogging. (5) As the surface is uneven, a user may face difficulty jogging on these kinds of surfaces but if still the user wants to jog, then time should be reduced when both feet are in the air to avoid the risk of fall.

[0060] The correlational module 216 is configured to determine the motion data of the user. The correlational module 216 is configured to implement a machine learning model to correlate the one or more classified mobility surfaces and the one or more extracted mobility parameters. The correlational module 216 includes a correlation unit 216A configured to correlate the identified mobility patterns 780 with the classified mobility surfaces 782 for dynamically adjusting the one or more extracted mobility parameters 790. In one example, the correlation unit 216A is configured to correlate identified mobility patterns and classified mobility surfaces to adjust the mobility health evaluation parameter’s preset thresholds 784. The correlational module 216 is configured to determine, the motion data of the user, by correlating the calculated values associated with one or more mobility parameters with the estimated mobility surface characteristics and determine a risk of the user falling during different mobility patterns of the user. In one example, the existing thresholds need to be modified as per the identified surface for any detected mobility pattern at any instance of time. For e.g. a user with a DCP of 45% on a flat surface may have poor health during mobility. The same user with DCP 45% on slippery surfaces may have good health during mobility.

[0061] FIG. 7C and FIG. 7D illustrates a process flow and the simulation observations 700B of the method for determining, the motion data of the user for determining a risk of user falling during different mobility patterns of the user. Each step of the process flow 700B is explained in detail below. At step 791, the method includes identifying mobility health evaluation patterns. The co-related mobility parameters may be compared (step 792) with a trained dataset to identify the health of the user, during mobility and alert the user of any potential risk of fall (step 793) if any, based on the occurrence and repetitiveness of various mobility parameters. The inference unit 716B derives various insights (step 794) related tothe health of the user, during mobility, the risk of the user falling, and calculating a mobility score based on the correlation of identified mobility patterns and classified mobility surfaces. The exemplary N-mapped combinations of pattern and surface are shown in Table 796 (column 1). The table 796 shows the occurrence threshold which may check and maintain conditions for the repetitiveness of parameters. The table 796 shows the parameter threshold which may track the amplitude or value-wise conditions for any parameter threshold.

[0062] FIG. 7E and FIG. 7F illustrates graphical representation 700C for evaluation of mobility parameters DCP and ZCP, for providing personalized insights to the user based on the determined motion data for improving the user health and lowering the risk of the user falling at the time of mobility. In one example, the graph 798 A depicts, for the user to jog on a flat surface, the exemplary values of DCP and ZCP are classified. In another example, the graph 798B depicts, for the user to run on uneven surfaces, the exemplary values of ZCP. Thus, for jogging on a flat surface, DCP and ZCP mobility parameters are classified, and for running on an uneven surface, the mobility parameter ZCP is identified. Referring to FIG. 7FIG. 7E and FIG. 7F, an exemplary scenario 700D for calculation of mobility score based on analysis of different parameters for determining a risk of the user falling during different mobility patterns of the user is depicted. The mobility score is a cumulative score calculated from the analysis of different parameters. In one example, the mobility score may be between the range of 0 to 100, where the health of the user, during different mobility patterns and on any type of surface, is directly proportionate to the mobility score. The risk of the user, falling is inversely proportionate to the mobility score i.e. as the score increases, the risk of falling decreases and vice versa. Depending upon the parameter, if it is continuously increasing or decreasing then the risk of the user falling is increasing and the user should be alerted after certain occurrence. Let’s assume that three evaluation parameters are generated i.e. DCP with 50%, ZCP with 30%, Ground-to-Air ratio as 20% of weightage having mobility exponent as 1.2, 1.8, -1.5 respectively, and values of respective parameters as 40% DCP, 5% ZCP and 0.6 as G-A ratio. For example, the manner in which the mobility score is determined is shown with a formula below.Mobility Score = 48It is to be noted that, the Mobility exponent can be positive, negative, or non integer.

[0063] Thus, the system 100 and the system 200 overcome the limitations, where the user may not be aware of their performance (DCP, ZCP) of a particular activity on a particular surface. The prediction of risk involved for the user falling suddenly while walking is available only for flat surfaces. The smart wearables 210A and smartphone 210B of the system 100 and the system 200 are configured to detect a position of the smartphone 210B, and smart wearable to capture accurate data. The modules 101 of the system 100 and the system 200 are configured for evaluating DCP, and ZCP in any mobility pattern on any surface and calculating the mobility score based on parameters like DCP, ZCP, etc. The modules 101 of the system 100 and the system 200 are configured for providing walking, jogging, and running-related performance insights. The modules 101 of the system 100 and the system 200 are configured to generate personalized suggestions to improve the health of the user during mobility and reduce the risk of falling.

[0064] FIG. 8 illustrates another exemplary process flow of a method 800 for monitoring the motion data of a user during different mobility patterns of the user. The method 800 includes a series of operations shown at step 832 through step 842 of Figure 8. The method 800 may be performed by the system 100 and the system 200 in conjunction with the plurality of modules 101, the details of which are explained in conjunction with Figures 1 to 8, and the same are not repeated here for the sake of brevity in the present disclosure. The method 800 begins at step 832. At step 832, the method 800 includes obtaining, from one or more sensors, sensor data associated with movement of the user. At step 854, the method 838 includes processing the obtained sensor data and extracting one or more mobility parameters. At step 840, the method 800 includes extracting surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data. At step 842, the method 800 includes monitoring the motion data of the user, by implementing a machine learning model for correlating the one or more classified mobility surfaces and the one or more extracted mobility parameters. Further, the details regarding the operation of each step (832-842) are described in detail in FIG.3 and hence have not been detailed for the sake of brevity.

[0065] While specific language has been used to describe the present subject matter, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein. The drawings and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively,certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.

Claims

Claims

1. A method (800) for monitoring the motion data of a user, the method (800) comprising: obtaining (832), from one or more sensors, sensor data associated with movement of the user; processing (838) the obtained sensor data and extracting one or more mobility parameters; extracting (840) surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data; and monitoring (842) the motion data of the user, by implementing a machine learning model for correlating the one or more classified mobility surfaces and the one or more extracted mobility parameters.

2. The method (800) as claimed in claim 1, wherein extracting one or more mobility parameters from a normalised motion data comprises the steps of: identifying a stance phase and a swing phase from the normalized motion data, based on preset thresholds for different stride wavelets, and identifying one or more micro-moment parameters comprising one or more of a heel strike, a foot flat, a double contact phase, a zero contact phase, a false step, a walking asymmetry, uneven steps, steps coordination, or a combination thereof.

3. The method (800) as claimed in claim 2, wherein the one or more mobility parameters comprise one or more identified micro-moment parameters comprising one or more of the heel strike, the foot flat, the double contact phase, the zero contact phase, the false step, the walking asymmetry, uneven steps, steps coordination or combination thereof.

4. The method (800) as claimed in claim 3, wherein the double contact phase is the relative time of a stride wavelet when both feet of the user are in contacting manner with the surface, and the zero-contact phase is the relative time of a stride wavelet when both feet of the user are in non-contacting manner with the surface.

5. The method (800) as claimed in claim 2, comprising classifying the identified stance phase and the identified swing phase for determining a plurality of stride features comprising one or more of a loading response, a midstance, a terminal stance, a pre-swing, an initial swing and a terminal swing.

6. The method (800) as claimed in claim 5, comprising determining an occurrence of the double contact phase and the zero contact phase for the user, based on the determined stride features.

7. The method (800) as claimed in claim 3, comprising classifying the extracted one or more mobility parameters for determining one or more mobility patterns of the user.

8. The method (800) as claimed in claim 1, comprising estimating a mobility surface characteristics from the extracted surface features for classifying one or more mobility surfaces.

9. The method (800) as claimed in claim 8, wherein the mobility surfaces comprise one or more of a flat surface, a non-flat surface, an uneven surface, a staircase, a surface with slope, a slippery surface, a treadmill, and combinations thereof.

10. The method (800) as claimed in claim 1, wherein obtaining the sensor data of the user from the one or more sensors comprising a 3D motion sensor, wherein the 3D motion sensor is an accelerometer sensor configured for measuring the sensor data along the X, Y, and Z axes of the one or more sensors during different mobility patterns of the user.

11. The method (800) as claimed in claim 10, wherein processing the obtained sensor data comprises the steps of: pre-processing the obtained sensor data from the one or more sensors; identifying the position and orientation of the one or more sensors from the preprocessed sensor data based on preset thresholds; and normalizing the pre-processed sensor data from one or more sensors at distinctive mobility periods to single motion data for determining the normalized motion data, based on the identified position and orientation of the one or more sensors at distinctive mobility periods.[Claim 121The method (800) as claimed in claim 1, wherein implementing the machine learning model for correlating the one or more classified mobility surfaces and the one or more extracted mobility parameters comprises the steps of: correlating the identified mobility patterns with the classified mobility surfaces for dynamically adjusting the one or more extracted mobility parameters; calculating, values associated with one or more mobility parameters based on periodic occurrence of variations in at least two or more mobility cycles during a mobility period of the user; determining, the motion data of the user, by correlating the calculated values associated with one or more mobility parameters with the estimated mobility surface characteristics; and determining a risk of the user falling during different mobility patterns of the user.

13. The method (800) as claimed in claim 12, comprising providing personalized insights to the user based on the determined motion data for improving the user's health and lowering the risk of the user falling at the time of mobility.

14. A system (100) for monitoring the motion data of a user, the system (100) comprising: a memory (104) configured to store a plurality of modules (101) in the form of programmable instructions;a processor (102) communicatively coupled to the memory (104), the processor (102) being configured to execute the programmable instructions associated with the plurality of modules (101), the plurality of modules (101) comprising: a obtaining module (110) configured to obtain sensor data associated with movement of the user from one or more sensors; a data processing module (114) configured to process the obtained sensor data; a mobility identification module (112) configured to extract one or more mobility parameters, based on the processed sensor data; a surface identification module (118) configured to extract surface features associated with surfaces for classifying one or more mobility surfaces, based on the processed sensor data; and a correlational module (116) configured to determine the motion data of the user, wherein the correlational module (116) is configured to implement a machine learning model configured to correlate the one or more classified mobility surfaces and the one or more extracted mobility parameters.

15. The system (100) as claimed in claim 14, wherein to extract one or more mobility parameters from a normalized motion data, the mobility identification module (112) is configured to: identify a stance phase and a swing phase from the normalized motion data, based on preset thresholds for different stride wavelets, and identify one or more micro-moment parameters comprising one or more of a heel strike, a foot flat, a double contact phase, a zero contact phase, a false step, a walking asymmetry, uneven steps, steps coordination, or a combination thereof.

Images