System and method for tracking perspiration and predicting health conditions of a user

Abstract

According to one embodiment of the present disclosure, a method for tracking perspiration and predicting one or more health conditions of a user is disclosed. The method includes receiving PPG signals of the user and obtaining a DC component from a dynamic AC component and a dynamic DC component of the received PPG signals. The method includes determining a current perspiration level of the user and receiving ambient conditions of the environment of the user. The method also includes determining an expected perspiration level based on the received ambient conditions, user temperature associated with the user and predicting the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based-Al model.

Description

DescriptionTitle of Invention :SYSTEM AND METHOD FOR TRACKING PERSPIRATION AND PREDICTING HEALTH CONDITIONS OF A USERTechnical Field

[0001] The present invention generally relates to health monitoring, and more particularly relates to a system and a method for tracking perspiration and predicting one or more health conditions of a user.Background Art

[0002] Sweating is a natural and vital physiological process that plays a crucial role in regulating the body's temperature. This involuntary mechanism ensures that the internal environment within human body remains within a narrow temperature range conducive to optimal bodily functions. When the human body’s internal temperature rises, sweat glands release water to the surface of the skin called sweat. As the sweat evaporates, it cools the human skin and blood beneath the human skin. Further, sweating plays significant roles in the human body, such as thermoregulation, detoxification, skin hydration, immune function, electrolyte balance, and the like. There are multiple types of sweat related health conditions, such as increased sweating, reduced sweating, heat stroke, and heat exhaustion.

[0003] Further, abnormal sweating and perspiration are related to multiple healthcare conditions, such as heat stroke, acute dehydration, hyperhidrosis, and the like. Therefore, sweat monitoring is used for predicting the health conditions of a person. There are multiple conventional solutions which are used for performing sweat monitoring. For example, sweat patches (adhesive patches worn on the skin) are used to collect sweat for analysis. These sweat patches can measure various biomarkers and electrolytes in sweat. Also, the conventional solutions include wearable sweat sensors integrated into fitness bands or smartwatches which can continuously monitor sweat data during physical activity.

[0004] In another example, the conventional solutions include microfluidic devices which use microchannels to collect and analyze tiny sweat samples, enabling real-time measurements Theconventional solutions also include biosensors which use biochemical reactions to detect specific analytes in sweat and provide quantitative data. The sweat monitoring may also be performed by lab-based analysis. In sweat monitoring, the sweat samples collected through various methods can be analyzed in laboratories using advanced equipment. However, the conventional solutions of sweat measurement and analysis involve extra sensors and procedures resulting in high costs. The conventional solutions do not have the ability to learn from user history and adapt to unique user traits. Further, the conventional solutions fail to properly calibrate the sensors for diverse populations. Hence, the conventional solutions fail to achieve accurate and reliable measurements over time and across different users. Some biomarkers present in sweat may have low concentrations, making their detection challenging. Also, the sensitivity of the sensors is also mostly non-linear. Since high sensitivity and specificity of the sensors are essential for accurate results, the conventional solutions fail to deliver accurate and reliable measurements.

[0005] Further, the sweat production varies between individuals, making it challenging to standardize measurements. Moreover, sweat contains a complex mix of analytes. Thus, accurately identifying and quantifying specific biomarkers is difficult in the conventional solutions. Also, the conventional solutions fail to design sensors that are comfortable to wear and seamlessly integrate into clothing or accessories. The sensors are required to be non-intrusive to avoid causing discomfort or skin irritation. Furthermore, the sweat sensors may face signal interference from ambient factors, such as temperature, humidity, and motion, leading to inaccurate readings. Further, analyzing the data collected by these sweat sensors can be challenging as complex data processing techniques are required to extract meaningful insights and actionable information from the data.

[0006] Accordingly, there is a need for a technique to overcome the above-identified problems.Solution to Problem

[0007] 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 nor is it intended for determining the scope of the invention.

[0008] According to one embodiment of the present disclosure, a method for tracking perspiration and predicting one or more health conditions of a user is disclosed. The method includes receiving, via one or more sensors placed on a body of a user, Photoplethysmography (PPG) signals of the user. Further, the method includes obtaining a Direct Current (DC) component from a dynamicAlternating Current (AC) component and a dynamic DC component of the received PPG signals. The method includes determining a current perspiration level of the user based on the obtained DC component and a predefined mapping table. The predefined mapping table corresponds to a lookup table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals. Furthermore, the method includes receiving, via at least one of one or more environment sensors or an external server, ambient conditions of the environment of the user. The method also includes determining an expected perspiration level based on the received ambient conditions, user temperature associated with the user. Further, the method includes predicting the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Artificial Intelligence (Al) model.

[0009] According to another embodiment of the present disclosure, a system for tracking perspiration and predicting one or more health conditions of a user is disclosed. The system includes one or more processors configured to receive, via one or more sensors placed on a body of a user, PPG signals of the user. The one or more processors are also configured to obtain a DC component from a dynamic AC component and a dynamic DC component of the received PPG signals. Further, the one or more processors are configured to determine a current perspiration level of the user based on the obtained DC component and a predefined mapping table. The predefined mapping table corresponds to a look-up table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals. The one or more processors are configured to receive, via at least one of one or more environment sensors or an external server, ambient conditions of the environment of the user. Further, the one or more processors are configured to determine an expected perspiration level based on the received ambient conditions, user temperature associated with the user. The one or more processors are further configured to predict the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Al model.

[0010] 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 are 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

[0011] 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:

[0012] Figure 1 illustrates a block diagram of a system for tracking perspiration and predicting one or more health conditions of a user, according to an embodiment of the present disclosure;

[0013] Figure 2 illustrates a block diagram of a plurality of modules of the system at an electronic device for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure;

[0014] Figure 3A illustrates a flow chart for obtaining a final residual signal from Photoplethysmography (PPG) signals, according to an embodiment of the present disclosure;

[0015] Figure 3B illustrates an exemplary graph showing separation of the PPG signals into multiple components, according to an embodiment of the present disclosure;

[0016] Figure 3C illustrates an exemplary graph of a measured mean body temperature of the user and an estimated mean body temperature, according to an embodiment of the present disclosure;

[0017] Figure 3D illustrates a block diagram for fine tuning a Large Language Model (LLM) for generating one or more recommendations, according to an embodiment of the present disclosure;

[0018] Figure 4 illustrates a block diagram depicting an operation of the system for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure;

[0019] Figures 5A - 5B illustrate pictorial depiction showing the one or more recommendations, according to an embodiment of the present disclosure;

[0020] Figures 6A - 6B illustrate block diagrams depicting use-case scenarios for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure; and

[0021] Figure 7 illustrates an exemplary process flow depicting a method fortracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure.

[0022] Further, skilled artisans will appreciate those 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

[0023] 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.

[0024] 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.

[0025] 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 invention. 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.

[0026] The terms “comprises”, “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.

[0027] Figure 1 illustrates a block diagram of a system 100 for tracking perspiration and predicting one or more health conditions of a user, according to an embodiment of the present disclosure. For example, the one or more health conditions may be dehydration, fever, and the like. In an embodiment of the present disclosure, the system 100 is implemented in an electronic device 102. Examples of the electronic device 102 may include but are not limited to, a smartphone, a laptop, a camera device, a smartwatch, and the like. In an embodiment of the present disclosure, the electronic device 102 may include one or more sensors, one or more temperature sensors, and one or more environment sensors. In another embodiment of the present disclosure, the one or more sensors, the one or more temperature sensors, and the one or more environment sensors are external components and not part of the electronic device 102. For example, the one or more sensors are Photoplethysmography (PPG) sensors. Details on the one or more sensors, the one or more temperature sensors, and the one or more environment sensors are explained in subsequent paragraphs of the invention.

[0028] The system 100 may include one or more processors / controllers 104, an Input / Output (VO) interface 106, a plurality of modules 108, and a memory 110.

[0029] In an exemplary embodiment, the one or more processors / controllers 104 may be operatively coupled to each of the respective VO interface 106, the plurality of modules 108, and the memory 110. In one embodiment, the one or more processors / controllers 104 may include at least one data processor for executing processes in a Virtual Storage Area Network. The one or more processors / controllers 104 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 one or more processors / controllers 104 may include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or both. The one or more processors / controllers 104 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 one or more processors / controllers 104 may execute a software program, such as code generated manually (i.e., programmed) to perform the desired operation. In an embodiment of the present disclosure, the processors / controllers may be a general-purpose processor, such as the CPU, an Application Processor (AP), or the like, a graphics-only processing unit such as the GPU, a Visual Processing Unit (VPU), and / or an Artificial Intelligence (Al)-dedicated processor, such as a Neural Processing Unit (NPU).

[0030] Further, the one or more processors / controllers 104 control the processing of input data in accordance with a predefined operating rule or machine learning (ML) model stored in the nonvolatile memory and the volatile memory. The predefined operating rule or the ML model is provided through training or learning.

[0031] Here, being provided through learning means that, by applying a learning technique to a plurality of learning data, a predefined operating rule or the ML model of a desired characteristic is made. The learning may be performed in a device itself in which ML according to an embodiment is performed, and / or may be implemented through a separate server / system.

[0032] Furthermore, the ML 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 Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), Generative Adversarial Networks (GANs), and deep Q-networks.

[0033] 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, or reinforcement learning.

[0034] The one or more processors / controllers 104 may be disposed in communication with one or more input / output (I / O) devices via the respective I / O interface 106. The I / O interface 106 may employ 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.

[0035] The one or more processors / controllers 104 may be disposed in communication with a communication network via a network interface. In an embodiment, the network interface may be the I / O interface 106. The network interface may connect to the communication network to enable the connection of the electronic device 102 with other electronic devices. 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, adirect interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, and the like.

[0036] In some embodiments, the memory 110 may be communicatively coupled to the one or more processors / controllers 104. The memory 110 may be configured to store data, and instructions executable by the one or more processors / controllers 104. The memory 110 may include but is not limited to, a non-transitory computer-readable storage media, such as various types of volatile and non-volatile storage media including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable readonly memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, the memory 110 may include a cache or random-access memory for the one or more processors / controllers 104. In alternative examples, the memory 110 is a part of the one or more processors / controllers 104, such as a cache memory of a processor, the system memory, or other memory. In some embodiments, the memory 110 may be an external storage device or database for storing data. The memory 110 may be operable to store instructions executable by the one or more processors / controllers 104. The functions, acts, or tasks illustrated in the figures or described may be performed by the programmed processor / controller for executing the instructions stored in the memory 110. 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.

[0037] In some embodiments, the plurality of modules 108 may be included within the memory 110. The memory 110 may further include a database 112 to store data. The plurality of modules 108 may include a set of instructions that may be executed to cause the system 100 to perform any one or more of the methods / processes disclosed herein. The plurality of modules 108 may be configured to perform the steps of the present disclosure using the data stored in the database 112 for tracking perspiration and predicting the one or more health conditions of the user, as discussed herein. In an embodiment, each of the plurality of modules 108 may be a hardware unit that may be outside the memory 110. Further, the memory 110 may include an operating system 114 for performing one or more tasks of the system 100, as performed by a generic operating system in the communications domain. In one embodiment, the database 112 may be configured to store the information as required by the plurality of modules 108 and the one or more processors / controllers 104 for tracking perspiration and predicting the one or more health conditions of the user.

[0038] In an embodiment of the present disclosure, at least one of the plurality of modules 108 may be implemented through the ML model. A function associated with the ML may be performed through the non-volatile memory, the volatile memory, and the one or more processors / controllers 104.

[0039] In an embodiment, the I / O interface 106 may enable input and output to and from the system 100 using suitable devices such as, but not limited to, a display, a keyboard, a mouse, a touch screen, a microphone, a speaker, and so forth.

[0040] Further, the present invention also 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 one or more processors / controllers 104 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 the electronic device 102, 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 electronic device 102 may be physical or may be established wirelessly. The network may alternatively be directly connected to the bus. For the sake of brevity, the architecture, and standard operations of the operating system 114, the memory 110, the database 112, the one or more processors / controllers 104, and the I / O interface 106 are not discussed in detail.

[0041] Figure 2 illustrates a block diagram of the plurality of modules 108 of the system 100 at the electronic device 102 for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure. In an embodiment of the present disclosure, the plurality of modules 108 may include but is not limited to, a receiving module 202, an obtaining module 204, a determining module 206, a predicting module 208, an outputting module 210, and a generating module 212. The plurality of modules 108 may be implemented by way of suitable hardware and / or software applications.

[0042] The receiving module 202 may be configured to receive, via the one or more sensors placed on the body of the user, Photoplethysmography (PPG) signals of the user. In an embodiment of the present disclosure, the PPG signals refer to the data obtained from a photoplethysmogram.Further, the photoplethysmogram is a non-invasive optical measurement technique used to detect blood volume changes in the microvascular bed of tissue.

[0043] Further, the obtaining module 204 may be configured to obtain a Direct Current (DC) component from a dynamic Alternating Current (AC) component and a dynamic DC component of the received PPG signals. In an embodiment of the present disclosure, the obtained DC component corresponds to an ultra-low frequency borderline static DC component.

[0044] Furthermore, the determining module 206 may be configured to determine a current perspiration level of the user based on the obtained DC component and a predefined mapping table. In an embodiment of the present disclosure, the predefined mapping table corresponds to a lookup table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals. In determining the current perspiration level of the user, the determining module 206 may be configured to calculate a mean amplitude and a standard deviation of the DC component of the received PPG signals. Further, the determining module 206 may be configured to obtain a one sigma lower bound of the DC component based on the calculated mean amplitude and the standard deviation. The determining module 206 may be configured to determine the current perspiration level of the user based on the obtained one sigma lower bound, the mean amplitude, the standard deviation, and the predefined mapping table.

[0045] In an embodiment of the present disclosure, the receiving module 202 may be configured to receive ambient conditions of the environment of the user. The ambient conditions are received via one or more environment sensors, an external server, or a combination thereof. For example, the one or more environment sensors may be temperature sensors, humidity sensors, pressure sensors, light sensors, motion sensors, and the like. In an exemplary embodiment of the present disclosure, the ambient conditions include an ambient temperature, wind speed and direction, humidity, relative humidity, air quality, oxygen level, or any combination thereof. In an embodiment of the present disclosure, the external server corresponds to a remote server that is dedicated to collecting and storing data related to the environmental conditions of a specific location.

[0046] Further, the determining module 206 may be configured to determine an expected perspiration level based on the received ambient conditions and user temperature associated with the user. In an embodiment of the present disclosure, the expected perspiration level is determined by using a Machine Learning (ML) model. In an embodiment of the present disclosure, the user temperature includes a skin temperature, a body temperature of the user, or a combination thereof.In determining the expected perspiration level, the determining module 206 may be configured to determine an apparent temperature based on the received ambient conditions. Furthermore, the determining module 206 may be configured to obtain, via one or more temperature sensors, the user temperature. The determining module 206 may be configured to determine the expected perspiration level based on the determined apparent temperature, the obtained user temperature, and user history using a perspiration determination model. In an embodiment of the present disclosure, the perspiration determination model corresponds to a lookup table, a mathematical regression function, an Artificial Intelligence (Al) regression model, or any combination thereof. In an embodiment of the present disclosure, the user history corresponds to a mapping of historical data related to a perspiration level of the user, the user temperature, an apparent temperature of the environment, or any combination thereof. The details on calculating the apparent temperature and the expected perception level have been elaborated in subsequent paragraphs by using at least with reference to Figure 3 A - 3D.

[0047] Furthermore, the predicting module 208 may be configured to predict the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Al model. In predicting the one or more health conditions of the user, the predicting module 208 may be configured to predict a health condition class of the user by comparing the current perspiration level and the determined expected perspiration level using the health prediction based- Al model. In an embodiment of the present disclosure, the health condition class corresponds to a mapping of dehydration condition and fever condition. Further, the predicting module 208 may be configured to predict the one or more health conditions of the user based on the predicted health condition class. For example, the health condition class may be category of fever and a category of dehydration, such as {mild fever, high dehydration}.

[0048] Further, the outputting module 210 may be configured to generate one or more recommendations for improving the one or more health conditions of the user based on the predicted one or more health conditions. In an embodiment of the present disclosure, the one or more recommendations are generated by using a fine-tuned Large Language Model (LLM). Furthermore, the outputting module 210 may be configured to output the generated one or more recommendations on the electronic device 102 of the user. Examples of the one or more recommendations have been elaborated in subsequent paragraphs by using at least with reference to Figures 5A - 5B.

[0049] In an embodiment of the present disclosure, the generating module 212 may be configured to receive, from the user, one or more queries with respect to the one or more recommendations. In an embodiment of the present disclosure, the one or more queries correspond to follow-up questions related to the one or more recommendations, clarifications related to the one or more recommendations, and change in the predicted one or more health conditions. Further, the generating module 212 may be configured to generate one or more responses with respect to the one or more queries based on the user history, the user behavior, past conversations related to health conditions of the user, and the predicted one or more health conditions.

[0050] The details on tracking perspiration and predicting the one or more health conditions of the user have been elaborated in subsequent paragraphs by using at least with reference to Figure 6A - 6D.

[0051] Figure 3A illustrates a flow chart for obtaining a final residual signal from the PPG signals, according to an embodiment of the present disclosure. Further, Figure 3B illustrates an exemplary graph showing separation of the PPG signals into multiple components, according to an embodiment of the present disclosure. Figure 3C illustrates an exemplary graph of a measured mean body temperature of the user and an estimated mean body temperature, according to an embodiment of the present disclosure. Furthermore, Figure 3D illustrates a block diagram for fine tuning the LLM for generating the one or more recommendations, according to an embodiment of the present disclosure. For the sake of brevity, Figures 3 A - 3D are explained together. The details on the obtaining of the PPG signals and measurement of the body temperature are explained with reference to Figure 2.

[0052] As depicted, the input 302 to the process is PPG signal time series x(t). Further, the system 100 identifies / extracts all local maxima and minima of x(t), at step 304. At step 306, the system 100 forms the upper and lower envelope eU(t) and ei(t) by performing cubic spline interpolation of the extrema point obtained from step 304. Further, at step 308, the system 100 computes the mean function of the upper and lower envelop, mi (t) as shown in equation (1): m l (t) = eU(t) + eU(t) / 2. (1)

[0053] At step 310, the system 100 calculates an Intrinsic Mode Function (IMF) dl (t) by subtracting mi(t) from x(t) as shown in equation (2): dl(t) = x(t) nu(t) . (2)

[0054] Further, the system 100 detects if di (t) is a zero-mean function. When the system 100 detects that di (t) is the zero-mean function, then the iteration stops and di (t) is accepted as first IMF i.e., hi (t) = di (t). If di (t) is not a zero-mean function, the system 100 uses dl(t) as the new data and repeats steps 304 - 310.

[0055] At step 312, the system 100 detects if hi (t) is an IMF. If the output of step 312 is yes, the system 100 calculates equation (3), at step 314: r(t) = x(t) - hi(t) . (3)

[0056] In an embodiment of the present disclosure, a stopping criterion is applied to a number of shifting iterations so that IMF component can retain amplitude and frequency modulation. Once the first IMF hi(t) is obtained, remaining IMFs are obtained by applying shifting process to the residual as given in equation (4): n (t) = x(t) - hi(t) . (4)

[0057] At step 316, it is determined if the residue signal is present. If the output of step is 314 is no, then step 304 is performed. Further, if the output of step is 314 is yes, then x(t) is calculated, at step 318. Furthermore, x(t) is calculated by using the equation (5):

[0058] In an embodiment of the present disclosure, the residual signal includes information about the lower frequency components. Further, the shifting process may be continued until the final residue is a constant, a monotonic function or a function with only one maxima and minima from which no IMF can be obtained. At the end of a decomposition process, a noisy signal x (t) can be represented as a sum of IMFs plus a residue signal.

[0059] For example, the obtaining module 204 / or a DC signal separator of the system 100 uses an Empirical Mode Decomposition (EMD) method of signal processing. The EMD is a technique to decompose a given signal into a set of elemental signals called IMFs. The IMFs are simple oscillatory modes with meaningful instantaneous frequencies. The EMD can be used to analyze non-linear and non-stationary signals by separating them into components at different resolutions. In an embodiment of the present disclosure, the EMD facilitates iterative extraction of the highest frequency component from the PPG signal by finding its local maxima and minima and interpolating them with cubic splines to form upper and lower envelopes. The mean of theseenvelopes is then subtracted from the signal to obtain the first IMF. This process is repeated on the residual signal until it becomes a monotonic function or a constant.

[0060] In an embodiment of the present disclosure, the EMD can be formalized as an optimization problem over ordered function vector spaces. The objective is to find the IMFs that minimize the mean square error between the signal and the sum of the IMFs and the residual. This problem can be solved using convex-like optimization and B-splines, which ensure Slater-regularity and strong duality. This also provides a theoretical justification for the null-space-pursuit (NSP) operatorbased signal-separation (OSS) EMD-approach, which uses linear operators to project the signal onto subspaces corresponding to different frequency bands.

[0061] EMD has some limitations, such as mode mixing, end effects, and lack of uniqueness. To overcome these issues, some improved versions of EMD have been proposed, such as ensemble empirical mode decomposition (EEMD) and its complete variant (CEEMDAN). These methods use noise-assisted data analysis to reduce the sensitivity of EMD to local extrema and improve the robustness of the decomposition. However, the end effect is a problem that arises when interpolating between the local extrema of the signal, especially near the boundaries. The interpolation may not accurately capture the true shape of the signal, resulting in spurious oscillations or distortions in the IMFs. To mitigate this problem, the system 100 uses multiple methods, such as extending or mirroring the signal beyond its boundaries, using cubic splines or other smoothing techniques, or applying a window function to attenuate the boundary effects.

[0062] As depicted in Figure 3B, the PPG signal is separated into its components and the DC signal is used for estimating perspiration. Further, numeral 320 represents the PPG signal with AC and DC components. Furthermore, numeral 322 represents the DC signal extracted from the PPG signal.

[0063] In an embodiment of the present disclosure, the system 100 considers the ambient temperature Ta, the wind speed ws, and relative humidity rh to calculate the apparent temperature. Equation (6) defines human thermal comfort, called the 'apparent temperature' (AT). The net radiation absorbed per unit area of body surface Q is taken from a database stored on the electronic device 102.AT = Ta+ 0.348*e - 0.70*ws + 0.70*Q / (ws+10) - 4.25 . . . .(6)

[0064] Where Tais a dry bulb temperature (‘C), e is the water pressure (hPa) humidity, ws is the wind speed (m / s) at an elevation of 10 meters, and Q is the net radiation absorbed per unit area of body surface (W / m2). Further, E is computed using the equation (7):

[0065] Where rh is the relative humidity.

[0066] Further, in calculating the perspiration level of the user, the system 100 calculates the mean amplitude u and standard deviation s of r(t). Since dehydration and heat stroke is the major lifethreatening risk, and it is characterized by less sweating, the system 100 considers one sigma lower bound of r(t), that is u — s. Based on statistics collected from the population for the values of perspiration and the mean amplitude it, the system 100 estimates the current perspiration of the user. For example, uminand umaxbe the closest mean amplitudes in the population statistics to u — s from the lesser and greater side respectively. In another example, the perspiration levels corresponding to uminand umaxare pmtnand pmaxrespectively. Then, the perspiration level is determined by using equation (8):

[0067] In an embodiment of the present disclosure, the apparent temperature (AT) is calculated by using skin temperature (Ts) and Body Temperature (TB). The system 100 calculates the mean body temperature T by using equation (9).T = 0.64 TB+ 0.36 Ts. (9)

[0068] Further, the system 100 estimates the normally expected perspiration from T and AT. In an embodiment of the present disclosure, the system 100 pre-trains a model using an ML regression technique. Use the trained model weights to estimate the normal perspiration. As depicted in Figure 3C, numeral 324 represents the graph of the measured mean body temperature of the user and the estimated mean body temperature.

[0069] Furthermore, the system 100 pre-trains the model based on the current perspiration level, the normal perspiration level, the skin temperature, and the body temperature using a machine classification technique. In an embodiment of the present disclosure, the system 100 uses the trained model weights to classify the current health condition of the user. In an embodiment of the present disclosure, the class sample space may have fever and dehydration values from the set of{severe, mild, no}. Such a sample space may have nine classes corresponding to 3x3 combinations for fever and dehydration. In another embodiment, greater or lesser classes may be considered.

[0070] Further, the system 100 fine-tunes a Large Language Model (LLM) to give recommendations for various combinations of fever and dehydration conditions by using the database 112 generated from medical journals, articles, and professionals. The system 100 further generates a natural English text describing the health condition by using the health condition class. The generated text is outputted on the electronic device 102.

[0071] As shown in Figure 3D, the system 100 obtains the medical data 326 from the external server, journals, articles, professionals, and the like. At step 328, the system 100 extracts the relevant data / context from the medical data 326, such as body temperature of the user. At step 330, the system 100 splits the relevant data / context into a set of text chunks 332 (text chunk-1, text chunk-2, text chunk-3, text chunk-N). Further, a set of embeddings 334 (embeddings- 1, embeddings -2, embeddings -3, embeddings -N) are generated based on the set of text chunks 332. At step 336, the system 100 creates the semantic index based on the set of embeddings 334. The semantic index is stored in a knowledge base 338.

[0072] Further, the results are ranked in the order of relevance from the highest relevance to the lowest relevance at step 340. The results are then passed to the LLM model 342 to generate and fine tune the response of the LLM model. The fine tuned LLM model 342 generates the one or more recommendations based on the health condition class of the user. Furthermore, the user 344 asks a question related to the one or more recommendations, at step 346. For example, the question may be related to the change in the health condition class after following the one or more recommendations of the system 100. Further, the system 100 at step 348 queries the set of embeddings 334. At step 350, the system 100 performs the semantic search based on the data in the knowledge base 338 for responding to the question.

[0073] Figure 4 illustrates a block diagram depicting an operation of the system 100 for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure. Details on the system 100 for tracking perspiration and predicting the one or more health conditions of the user are explained with reference to Figure 2.

[0074] As depicted in Figure 4, at step 402, the PPG signals are obtained from the one or more sensors 404. Further, at step 406, the system 100 obtains the DC component from the AC component and the DC component of the obtained PPG signals. At step 408, the system 100 determines the current perspiration level of the user based on the obtained DC component and thepredefined mapping table in a population statistics database 410. The current perspiration level of the user is stored in a user history database 412.

[0075] Further, at step 414, the system 100 receives the ambient conditions of environment of the user. At step 416, the system 100 determines the apparent temperature based on the received ambient conditions. At step 418, the system 100 determines the expected perspiration level based on the received ambient conditions, the skin temperature 420, and the body temperature 422. At step 424, the system 100 predicts the health condition class of the user by comparing the current perspiration level and the determined expected perspiration level. Furthermore, the system 100 predicts the one or more health conditions of the user based on the predicted health condition class. At step 426, the system 100 generates the one or more recommendations for improving the one or more health conditions of the user based on the predicted one or more health conditions.

[0076] Figures 5A - 5B illustrate pictorial depiction showing the one or more recommendations, according to an embodiment of the present disclosure. For the sake of brevity, Figures 5A - 5B are explained together. Details on tracking perspiration and predicting the one or more health conditions of the user, as explained with reference to Figure 2.

[0077] As shown in Figure 5A, numeral 502 represents the one or more recommendations generated for the health condition class: {dehydration: mild, fever: severe}. Further, numeral 504 represents the one or more recommendations generated for the health condition class: {dehydration: severe, fever: severe}.

[0078] Further, as shown in Figure 5B, numeral 506 represents the one or more recommendations generated for the health condition class: {dehydration: severe, fever: no}. Further, numeral 508 represents the one or more recommendations generated for the health condition class: {dehydration: no, fever: severe}.

[0079] Figures 6A - 6B illustrate block diagrams depicting use-case scenarios for tracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure. Details on tracking perspiration and predicting the one or more health conditions of the user, as explained with reference to Figure 2.

[0080] Figure 6A shows a use-case scenario of the user feeling extremely hot and has sweat a lot. The user is wearing the electronic device 102 (smartwatch) having the system 100 implemented in the smartwatch. The system 100 extracts the DC signal 602 from the PPG signal and calculates the current perspiration at step 604. For example, the current perspiration may be 30 pL / cm2.Further, at step 606, the system 100 calculates the apparent temperature using the ambient conditions. For example, the apparent temperature may be 35° C. At step 608, the system 100 calculates the normal perspiration based on the skin temperature, the body temperature, the apparent temperature, and the user history. For example, the normal perspiration / current perspiration may be 36 pL / cm2. In an embodiment of the present disclosure, the current perspiration may be stored in the user history 610. Further, at step 612, the system 100 predicts the health condition class of the user i.e., dehydration: mild, fever: no. Further, at step 614, the system 100 generates the one or more recommendations based on the health condition class. For example, the one or more recommendations may be “firstly, please drink plenty of fluids”. The system 100 generates a dehydration alert on the smartwatch for the generated one or more recommendations, at step 616. Further, the user performs one or more actions based on the dehydration alert, such as drinking electrolytes to recover from dehydration.

[0081] Further, Figure 6B shows a use-case scenario of the user feeling muscle cramps, headache, dizziness, and the like. As explained in steps 604 - 608 of Figure 6A, the system 100 extracts the DC signal 602 from the PPG signal and calculates the current perspiration (20 pL / cm2), the apparent temperature (40 °C), and the normal perspiration (42 pL / cm2). In an embodiment of the present disclosure, the current perspiration may be stored in the user history 610. Further, at step 612, the system 100 predicts the health condition class of the user i.e., dehydration: severe, fever: severe. Further, at step 614, the system 100 generates the one or more recommendations based on the health condition class. For example, the one or more recommendations may be “firstly, please drink plenty of fluids”. The system 100 generates the dehydration alert on the smartwatch for the generated one or more recommendations, at step 616. Further, the user performs the one or more actions based on the dehydration alert, such as taking medicines for fever.

[0082] Figure 7 illustrates an exemplary process flow depicting a method fortracking perspiration and predicting the one or more health conditions of the user, according to an embodiment of the present disclosure. The method 700 may be performed by a system 100 implemented in the electronic device 102, as shown in Figures 1 and 2.

[0083] At step 702, the method 700 includes receiving, via one or more sensors placed on a body of a user, Photoplethysmography (PPG) signals of the user.

[0084] Further, at step 704, the method 700 includes obtaining a Direct Current (DC) component from a dynamic Alternating Current (AC) component and a dynamic DC component of thereceived PPG signals. In an embodiment of the present disclosure, the obtained DC component corresponds to an ultra-low frequency borderline static DC component.

[0085] The method 700 at step 706 further includes determining a current perspiration level of the user based on the obtained DC component and a predefined mapping table. In an embodiment of the present disclosure, the predefined mapping table corresponds to a look-up table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals.

[0086] Further, at step 708, the method 700 includes receiving, via at least one of one or more environment sensors or an external server, ambient conditions of the environment of the user.

[0087] At step 710, the method 700 includes determining an expected perspiration level based on the received ambient conditions and user temperature associated with the user. In an exemplary embodiment of the present disclosure, the ambient conditions include an ambient temperature, wind speed and direction, humidity, relative humidity, air quality, oxygen level, or any combination thereof. In an embodiment of the present disclosure, the user temperature a skin temperature, a body temperature of the user, or a combination thereof.

[0088] At step 712, the method 700 includes predicting the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Artificial Intelligence (Al) model.

[0089] While the above steps shown in Figure 7 are described in a particular sequence, the steps may occur in variations to the sequence in accordance with various embodiments of the present disclosure. Further, the details related to various steps of Figure 7, which are already covered in the description related to Figures 1-6 are not discussed again in detail here for the sake of brevity.

[0090] The present disclosure provides for various technical advancements based on the key features discussed above. The present disclosure uses the fine-tuned LLM model / LLM transformers to generate the one or more recommendations. In an embodiment of the present disclosure, LLM transformers are great in simulating natural human language. The present disclosure allows the user to follow-up questions and clarifications. Further, the system 100 configures the LLM transformers to take conversation history into account. In an embodiment of the present disclosure, the LLM transformers allows the user to converse with it, such that the LLM transformers inform the user about unique circumstances every time. Furthermore, progression of a condition from mild to severe or from severe to mild, after taking action can beanalyzed by the system 100 to generate the one or more recommendations. The LLM transformers can take into account all past and current history of the user while generating the one or more recommendations.

[0091] Further, the LLM transformers enhance the accuracy of the present disclosure as the LLM transformers can learn from historical data and recommendations of the user and improve recommendations over time. Furthermore, the LLM transformers provides personalization to the user because the LLM transformers analyzes user behavior and item attributes to provide highly personalized recommendations. The present disclosure is flexible as the LLM transformers may adapt to changing user preferences and item attributes. Further, the present disclosure is scalable as the LLM transformers can handle large amounts of data and scale to meet the needs of growing user bases.

[0092] Furthermore, the LLM transformers suggest diverse items that users may not have considered otherwise. While generating the one or more recommendations, the LLM transformers may take into account various contextual factors, such as location, time, device, and search history. The present disclosure reduces the need for manual effort and human curation, saving costs and increasing efficiency for generating the one or more recommendations associated with the health condition of the user. The present disclosure provides users with more relevant and accurate recommendations, leading to increased user satisfaction and loyalty.

[0093] The plurality of modules 108 may be implemented by any suitable hardware and / or set of instructions. Further, the sequential flow illustrated in Figure 2 is exemplary in nature and the embodiments may include addition / omission of steps as per the requirement. In some embodiments, the one or more operations performed by the plurality of modules 108 may be performed by the one or more processor / controller 104 based on the requirement.

[0094] 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 for tracking perspiration and predicting one or more health conditions of a user, the method comprising: receiving, via one or more sensors placed on a body of a user, Photoplethysmography (PPG) signals of the user; obtaining a Direct Current (DC) component from a dynamic Alternating Current (AC) component and a DC component of the received PPG signals; determining a current perspiration level of the user based on the obtained DC component and a predefined mapping table, wherein the predefined mapping table corresponds to a look-up table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals; receiving , via at least one of one or more environment sensors or an external server, ambient conditions of the environment of the user; determining an expected perspiration level based on the received ambient conditions and user temperature associated with the user; and predicting the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Artificial Intelligence (Al) model.

2. The method as claimed in claim 1, wherein the obtained DC component corresponds to an ultra-low frequency borderline static DC component.

3. The method as claimed in claim 1, wherein the ambient conditions comprise at least one of an ambient temperature, wind speed and direction, humidity, relative humidity, air quality, and oxygen level.

4. The method as claimed in claim 1, wherein the user temperature comprises at least one of a skin temperature and a body temperature of the user.

5. The method as claimed in claim 1, wherein determining the expected perspiration level comprises: determining an apparent temperature based on the received ambient conditions; obtaining, via one or more temperature sensors, the user temperature; and determining the expected perspiration level based on the determined apparent temperature, the obtained user temperature, and user history using a perspiration determination model, wherein the user history corresponds to a mapping of historical data related to at least one of a perspiration level of the user, the user temperature, and an apparent temperature of the environment.

6. The method as claimed in claim 1, wherein predicting the one or more health conditions of the user comprises: predicting a health condition class of the user by comparing the current perspiration level and the determined expected perspiration level using the health prediction based- Al model, wherein the health condition class corresponds to a mapping of dehydration condition and fever condition; and predicting the one or more health conditions of the user based on the predicted health condition class.

7. The method as claimed in claim 1, wherein determining the current perspiration level of the user comprises: calculating a mean amplitude and a standard deviation of the DC component of the received PPG signals; obtaining a one sigma lower bound of the DC component based on the calculated mean amplitude and the standard deviation; and determining the current perspiration level of the user based on the obtained one sigma lower bound, the mean amplitude, the standard deviation, and the predefined mapping table.

8. The method as claimed in claim 1, further comprising:generating one or more recommendations for improving the one or more health conditions of the user based on the predicted one or more health conditions; and outputting the generated one or more recommendations on an electronic device of the user.

9. The method as claimed in claim 8, further comprising: receiving, from the user, one or more queries with respect to the one or more recommendations, wherein the one or more queries correspond to follow-up questions related to the one or more recommendations, clarifications related to the one or more recommendations, and change in the predicted one or more health conditions; and generating one or more responses with respect to the one or more queries based on at least one of user history, user behavior, past conversations related to health conditions of the user, and the predicted one or more health conditions.

10. A system for tracking perspiration and predicting one or more health conditions of a user, the system comprising: a memory; and one or more processors communicably coupled to the memory, the one or more processors are configured to: receive, via one or more sensors placed on a body of a user, Photoplethysmography (PPG) signals of the user; obtain a Direct Current (DC) component from a dynamic Alternating Current (AC) component and a DC component of the received PPG signals; determine a current perspiration level of the user based on the obtained DC component and a predefined mapping table, wherein the predefined mapping table corresponds to a look-up table including the mapping of perspiration levels of multiple persons with corresponding values of DC components of the PPG signals; receive, via at least one of one or more environment sensors or an external server, ambient conditions of the environment of the user;determine an expected perspiration level based on the received ambient conditions and user temperature associated with the user; and predict the one or more health conditions of the user by comparing the current perspiration level and the determined expected perspiration level using a health prediction based- Artificial Intelligence (Al) model.

11. The system as claimed in claim 10, wherein the obtained DC component corresponds to an ultra-low frequency borderline static DC component.

12. The system as claimed in claim 10, wherein the ambient conditions comprise at least one of an ambient temperature, wind speed and direction, humidity, relative humidity, air quality, and oxygen level.

13. The system as claimed in claim 10, wherein the user temperature comprises at least one of a skin temperature and a body temperature of the user.

14. The system as claimed in claim 10, wherein, for determining the expected perspiration level, the one or more processors are configured to: determine an apparent temperature based on the received ambient conditions; obtain, via one or more temperature sensors, the user temperature; and determine the expected perspiration level based on the determined apparent temperature, the obtained user temperature, and user history using a perspiration determination model, wherein the user history corresponds to a mapping of historical data related to at least one of a perspiration level of the user, the user temperature, and an apparent temperature of the environment.

15. The system as claimed in claim 10, wherein for predicting the one or more health conditions of the user, the one or more processors are configured to:predict a health condition class of the user by comparing the current perspiration level and the determined expected perspiration level using the health prediction based- Al model, wherein the health condition class corresponds to a mapping of dehydration condition and fever condition; and predict the one or more health conditions of the user based on the predicted health condition class.

Images